OK, the order of packets is a bit off, which makes it harder to analyze. But if you picture packet 1685 between packet 1678 and 1679 it will all make sense. Since the initial part of the 'Write Andx Request' was not seen, the TCP layer on 2.2.2.2 tells 1.1.1.1 that it did not receive part of the.
- Hardware Overview
- A closer look at the T1902 and T1942 headunits
- Serial Communication between headunit and Fortius brakes
- Communication protocols of cable based trainers
- T1902 USB 'legacy' protocol: 6 Bytes OUT, 21 Bytes IN
- Protocol of older wireless ANT Tacx trainers
- Regualar Pages from the device
This is a collection of information from the internet, together with own investigations. Not every information is confirmed.
*** WORK IN PROGRESS ***
There are two major kind of brakes: magnetic (eddy current) brakes and motorbrakes.
To control magnetic brakes, there are two ways: manually with a bowden control cable or electrically. The motorbrakes are always controlled electrically.
A (manual) magnetic brake is controlled by a bowden cable, which changes the distance of magnets to a rotating plate.
For electrical brakes, some kind of device controls the motor force or an (electrical) magnetic field.
The unit can be a stand-alone unit or a (host) computer controlled unit. Sometimes the controller is inside the brake and sometimes the controller is an external headunit connected to the brake by wire or wireless. The cable is always a full connected 6P6C RJ12 (RJ-25) cable. The wireless technology of the TACX brakes are always ANT+. There are two different ANT+ protocols. Older brakes talk a proprietary protocol. The newer brakes talk a portable ANT+ FE-C protocol (fitness equipment control).
'Wheel On' magnetic brakes are
- Basic, Excel and Grand Excel (sometimes called Cycleforce ...)
- i-Magic
- Flow
- Vortex
- Satori (non electrical, but with wireless feedback)
'Wheel On' Motorbrakes are
- Fortius
- Cosmos
- Bushido
- Genius
'Direct Drive' magnetic (electrical) brakes are
- Flux (S), Flux 2
'Direct Drive' motorbrakes are
- Neo, Neo 2
Tacx calls some of their trainers 'smart'. Smart means, that these trainers support the newer (standardized) ANT+ FE-C protocol together with Bluetooth 4.0.
Other name additions are VR, Multiplayer (typically bundled with TTS software, a steering device and a multiplayer license).
Note: There is a so called 'PC Smart Upgrade (T2990)'. This is a bundle with TTS4 (advanced), a wireless 'control device' (T2022, with a built-in receiver for legacy heart belts) and an USB ANT+ antenna (T2028). The 'control device' talks the old proprietary ANT+ protocol.
Tacx products
Cable based USB headunits
- T1904 green-ring headunit (Upper left)
- T1932 blue-ring (Upper right)
- T1902 solid-green (Lower left)
- T1942 solid-blue (Lower right)
Tacx product number overview
WIP
Abbreviation | Description |
---|---|
M | motor brake |
E | eddy current (magnetic) |
EU | 50 Hz / 230 V (Europe) |
US | 60 Hz / 110 V (US) |
HU | headunit |
RJ12 | RJ12 cable |
CAD | socket for Cadence |
ANT | legacy ANT+ |
ANTFEC | ANT FE-C controlled |
Acc | Accessory |
First some notes about 32 and 64 bit compatibility of some of the PC products: The (non wireless) PC headunits are plain vanilla USB (1.1) and they work with 32 bit and 64 bit. The problem with the older headunits is, that TACX do not support a firmware loader for the older firmware and the newer TTS software does not support the older communication protocol of the T1902 firmware.
Tacx № | Product | Type | Year | Description | Additional Information |
---|---|---|---|---|---|
T1601 | Cycleforce Excel/Basic brake | E, EU | 199x | electro-magnetic brake, RJ12, CAD | similar, but not identical to Flow brake i.e. PC-headunit T1904 and T1932 can not drive legacy T1601 |
T1620 | Cycleforce Excel bundle | E, EU | 1995 ? | T1601 brake, T1642 headunit | |
T1640 | Cycleforce Grand Excel bundle | E, EU | 1995 ? | T1601 brake, T1642 headunit | also contains a so called 'grand excel USB interface' ? |
T1642 | Cycleforce Excel stand-alone unit | E, EU | 1995 ? | stand-alone headunit | has parallel port to connect PC or Printer |
T1652 | Cycleforce Basic stand-alone unit | E, EU | 1995 ? | stand-alone headunit | |
T1670 | Cycleforce Basic bundle | E, EU | 1995 ? | T1601 brake, T1652 headunit | |
T1680 | Flow bundle | E, EU | T1901 brake, T1682 headunit, T1690 skyliner | ||
T1682 | Flow stand-alone unit (orange) | E, EU/US | stand-alone headunit | ||
T1684 | Flow bundle | E, US | T1911 brake (US), T1682 headunit, T1690 skyliner | ||
T1690 | front wheel skyliner | Acc | |||
Tacx № | Product | Type | Year | Description | Additional Information |
T1900 | i-Magic bundle | E, EU | T1901 brake, T1902 PC-headunit, TTS3 software | ||
T1901 | Flow, i-Magic brake | E, EU | new electro-magnetic brake, RJ12, CAD | controllable with T1902, T1904, T932 (1942 headunit with special firmware) | |
T1902 | i-Magicsolid green PC-headunit | E/(M), EU/US | ? | USB PC-headunit, RJ12 and steering connector | Needs firmware after every power up. Compatible to brakes T1601, T1901, T1911 (T1941, T1946 motorbrakes with special firmware) |
T1904 | green ring PC-headunit | E/M, EU/US | ? | USB PC-headunit, RJ12 and steering connector | built-in firmware. Can drive brakes T1901, T1911, T1941, T1946. NOT compatible with T1601 brake |
T1905 | steering frame | Acc | Mini-DIN, Connects to for T1901, T1904, T1935, T1942 headunits | potentiometer inside - like old game-port analog joystick | |
T1911 | Flow, i-Magic brake (US) | E, US | for 110V power | controllable with T1902, T1904, T932 (1942 headunit with special firmware) | |
T1912 | Flow, i-Magic bundle (US) | E, US | T1911 brake, T1902 headunit, TTS3 software | ||
T1915 | i-Magic upgrade Kit | E/(M), EU/US | T1902 headunit, simple Software | no TTS software?? | |
T1925 | Fortius upgrade kit | E/M, EU/US | T1932 Blue Ring PC-headunit, Software | TTS4 Basic?? | |
T1930 | Fortius Multiplayer bundle | M, EU | T1941 brake, T1932 PC-headunit, T1905 steering, Software | ||
T1932 | blue ring PC-headunit | E/M, EU/US | USB PC-headunit, RJ12 and steering connector | built-in firmware. Can drive brakes T1901, T1911, T1941, T1946. NOT compatible with T1601 brake | |
T1935 | Fortius Multiplayer bundle | M, US | T1946 brake, T1932 headunit, T1905 steering, Software | ||
T1940 | Fortius bundle | M, EU | T1941 breke, T1932 headunit | no steering frame, no one year multiplayer license | |
T1941 | Fortius brake | M, EU | motorbrake, powerback with RJ12, CAD | 19200, 8N1 3.3V TTL communication | |
T1949.50 | Fortius power unit | M, EU | just the powerback for T1941 | ||
T1942 | Fortiussolid blue PC-headunit | (E)/M, EU/US | USB PC-headunit, RJ12 and steering connector | Needs firmware after every power up. For motorbrakes T1941, T1946. (T1601, T1901, T1911 with special firmware) | |
T1945 | Fortius bundle (US) | M, US | T1946 brake, T1932 headunit | no steering frame, no one year multiplayer license | |
T1946 | Fortius brake (US) | M, US | motorbrake, powerback with RJ12, CAD | 19200, 8N1 3.3V TTL communication | |
T1949.50 | Fortius power unit | M, US | just the powerback for T1946 | ||
Tacx № | Product | Type | Year | Description | Additional Information |
T1960 | Vortex bundle | E, EU | 2008 | T1961 brake, (legacy) headunit | Tacx PDF |
T1961 | Vortex brake | E, EU | wireless legacy-ANT+ controlled 230V 50/(60) Hz magnetic brake | 8 Neo magnets, 8 electro-magnets, max power 950W (60 kph) | |
T1970 | Cosmos bundle | M, EU | ? | T1941 Motorbrake, T1972 stand-alone headunit | upgradable with every PC-headunit for T1941/T1946 brakes |
T1975 | Cosmos bundle (US) | M, US | T1946 Motorbrake (US), T1972 stand-alone headunit | upgradable with every PC-headunit for T1941/T1946 brakes | |
T1972 | Cosmos Computer standa-alone unit | stand-alone headunit for motorbrakes, RJ12 | |||
T1980 | Bushido bundle | M | 2008 | T1981 brake, T1982 stand-alone headunit | No main power required, legacy-ANT+ PDF 1, PDF 2 |
T1981 | Bushido brake | M | wireless legacy-ANT+ controlled motorbrake | No main power required , controllable via ANT+ (PC/TTS4, Tacx Cycling App, T1982 stand-alone unit) | |
T1982 | Bushido Computer stand-alone unit | Dark Grey stand-alone headunit, legacy-ANT+ | TTS4 PC-software can talk to T1982, T1982 can talk to T1981 | ||
Tacx № | Product | Type | Year | Description | Additional Information |
T2000 | i-Genius Multiplayer bundle | M | 2012 | Brake, T2022 headunit, T2028 antenna, TTS4 software, T2420 steering, multiplayer license | |
T2010 | i-Genius Multiplayer Smart bundle | M | probably later rebranded to Genius Smart (T2080), | ||
T2020 | i-Genius bundle | M | Brake, T2022 headunit, T2028 antenna, TTS4 software | ||
T2022 | Genius remote | Acc | legacy-ANT+ Controller 'blue ufo' handle bar with 5KHz EM heart-belt receiver | can control Bushido, Genius, Ironman | |
T2028 | ANT+ Antenna | Acc | USB ANT+ receiver with antenna and a long USB cable | ||
T2050 | Ironman bundle | M | Rebranded T2020 i-Genius ? | ||
T2060 | Ironman Smart bundle | M | Rebranded T2080FC plus World Championship Kona DVD ? | ||
T2080 | Genius Smart bundle | M | 2015 | ANT+ FE-C and Bluetooth, controlled via App | new portable ANT+ FE-C (fitness equipment control) |
T2080FC | Genius Smart Full Connect bundle | M | ANT+ FE-C and Bluetooth, T2022 headunit, T2028 antenna, TTS4 software, | ||
Notes | |||||
Tacx № | Product | Type | Year | Description | Additional Information |
TODO | |||||
T2162 | (green) i-vortex headunit? | green sides, ANT+ wireless | |||
T2170 | i-Vortex | ||||
T2171 | i-Vortex resistance unit 110/230 Volt | ||||
T2172 | i-Vortex headunit | white/gray with blue sides, ANT+ wireless | |||
T2179 | Skyliner | , vortex, i-vortex, Flow ... | |||
T2180 | Vortex Smart | ||||
T2181 | Vortex Smart resistance unit | ||||
T2180FC | Vortex Smart Full connect | ||||
Tacx № | Cat | Type | Year | Description | Additional Information |
TODO | |||||
T2200 | Flow | E, EU | 2011 | ||
T2210 | Flow (US) | E, US | |||
T2220 | Flow Multiplayer | E, EU | 2011 | ||
T2230 | Flow Multiplayer (US) | E, US | 2011 | ||
T2240 | Flow Smart | E | 2015 | ANT+ FE-C and Bluetooth, controlled via App | |
T2240FC | Flow Smart Full connect | E | 2017 | ANT+ FE-C and Bluetooth plus T2022, T2028, TTS4 software | |
T2250 | i-Flow | E, EU | 2012 | ||
T2250 | i-Flow | E, US | 2012 | ||
Tacx № | Cat | Type | Year | Description | Additional Information |
T2420 | Blacktrack steering | Acc | wireless legacy-ANT+ steering frame | mountable with ... |
Product | Power (W) (@ km/h) | Incline (%) | Torque (Nm) | Brake Force (N) | Flywheel | Flywheel inertia (kg * m^2) | Calibration | Simu. of descent |
---|---|---|---|---|---|---|---|---|
Basic T1601 | 600 W | 5% | ~2kg ? | Spin Down | No | |||
Flow T1901/T1911 | 800 W | 1.65 | ||||||
Fortius, Cosmos T1941/T1946 | 1000 W | virtual | test run | yes | ||||
Genius T2021 | 1500 W | 20% | virtual | yes | ||||
Vortex T1961 | 950 W | 1.65 kg | ||||||
Bushido T1981 | 1400 W | 1.65 kg | ||||||
Flow (smart) T2240 | 800 W (40) | 6% | 15.3 | 45 | 1,6 kg | 11.8 kg | Spin down | No Source |
Bushido smart T2780 | 1400 W (40) | 15% | 44 | 128 | virtual & 1,2 kg | mass & virtual (60kg) | Spin down | No Source |
Vortex smart T2180 | 950 W (40) | 7% | 16.3 | 48 | 1.65 kg | 11.8 kg | Spin Down | No Source |
Satori smart T2400 | 950 W (40) | n/a | 16.3 | 48 | 1,6 kg | 16.9 kg | Spin down | No Source |
Genius Smart T2081 | 2000 W (40) | 20% | 51 | 150 | virtual | virtual (125kg) | Auto | Yes Source |
Flux, T2900 | 1500 W (40) | 10% | 22.1 | 65 | 7 kg | 22.8 kg | Spin down | No Source |
Flux S, T2900S | 1500 W (40) | 10% | 22.1 | 65 | 7 kg | 22.8 kg | Spin down | No Source |
Flux 2, T2980 | 2000 W (40) | 16% | 41 | 120 | 7.6 kg | 31.2 kg | Spin down | No Source |
Neo | 2200 W (40) | 25% | 85 | 250 | virtual | virtual (125 kg) | not required | Yes Source |
Neo 2 | 2200 W (40) | 25% | 85 | 250 | virtual | virtual (125 kg) | not required | Yes Source |
Firmware loading
The headunits do not have a non volatile memory except the eeprom, which contains the initial USB descriptor and the individual device ID. So, the firmware has to be loaded after every power up (under linux i.e. with the fxload tool).
Tacx always says, that the solid-green will work only on 32bit systems. To clarify this:
It is NOT(!) a problem with 32bit or 64bit systems.
You can easily load the firmware with the 'fxload' tools under every operating system.There is a little python script, that can do the thing without any native binaries.
You can find the original firmwares on most of the Tacx DVD inside the driver directory. The T1942 firmware file is named FortiusSWPID1942Renum.hex. The original T1902 firmware is part of a the I-magic.sys file. You can cut it out of the File with a little helper tool (LINK).
Steering frame T1905
The steering frame connects via a Mini-DIN socket to the T1902, T1904, T1932, T1942 headunits. Only two wires are used. Inside the steering they connect to a 100 kohm potentiomert.T1902 and T1942 head units measure the resistance the game-port style(See wikipedia). There is a NE585 (4x NE555) timer inside.
Controlling the resistance
The eddy-current (magnetic) brakes have 6 permanent magnets (newer brakes have 8 magnets) and the same numer of (headunit controlled) electro-magnets. With the electro-magnets switched off, the only magnetic force comes from the permanent magnets.
What happens if the electro magnets are switched on, depends on the timing of the switching. The source of the magnetic field is your powerline sinus voltage. On one half of the sinus period, the electro magnetic field reduces (compensates) the field of the permanent magnets and in the other half of the period the electro magnetic field increases the permanent magnetic field.
The headunit switchs the electro magnets on and off, synchronized to the powerline phase to increase or decrease the permant magnetic field. The length of the pulse depends on the selected resistance.
It's is a little like a RPC (reverse phase control) device synced with your powerline frequency.NOTE: Literature recommends 'phase angle control' for inductive loads, but as far as I understood the brake control, TACX uses RPC. TODO: Have to verify this!
Inside the T1902 and T1942
The CPU in the 'solid' headunits are a ezusb an2131s from Cypress that is fairly flexible (see AN2131).
Pin# Port C | dir | Dev | function | |
---|---|---|---|---|
C.0 | IN | Serial0 | B | Rx Alt-Function (OUT) - for T1941 motorbrake communication |
C.1 | OUT | Serial0 | B | Tx Alt-Function - for T1941 motorbrake communication Can be 'missused' as magnetic field PAC/PWM/RPC when used with T1601/T1901 eddy current brake |
C.2 | IN | INT0 | B/G | Wheel-Sensor (only when powered) for T1901-EddyCurrent-Brake (T1902: Rx) |
C.3 | IN | INT1 | B/G | Power-Line-Frequency zero crossing (only when T1601/T1901 is powered) |
C.4 | IN | T0 | B/G | CAD on T1901 brake, works also with unpowered T1601/T1901 (detected by sampling) |
C.5 | IN | T1 | B/G | HR - works without brake connected (detected by sampling) |
C.6 | (IN) | unused? | ||
C.7 | OUT | G | 'PAC/PWM/RPC-controls' magnetic field of T1601/T1901 eddy current brake. Can be 'missused' as TX when used with T1941 motorbrake |
( 'B' is 'blue' device, 'G' is 'green' device )
The TACX USB vendor ID is 0x3561.
The blue-ring headunit has ID '3561:1932' and the green-ring has '3561:1904'.I own a blue-ring and green-ring headunit and a both are all-in-one units, that can handle both brakes (the eddy-current-brake T1902 and the motorbrake T1940) Note: the newer 'blue ring' and 'green ring' headunits can not driver the old T1601 eddy current brake sold with the Basic, Excel and Grand Excel.
Device | USB Id | Notes |
---|---|---|
T1902 | 3561:1902 | Old 'solid green' IMagic headunit (with or without loaded firmware) |
T1904 | 3561:1904 | New 'white green' IMagic headunit (white body with green or (sometimes) white ring - firmware inside) |
T1932 | 3561:1932 | New 'white blue' VR headunit (white body with blue ring - firmware inside |
T1942 V1 | 3561:e6be | Old 'solid blue' Fortius headunit (without firmware loaded) |
T1942 V2 | 3561:1942 | Old 'solid blue' Fortius headunit (with firmware loaded) |
You can load the firmware of the 'solid blue' device (FortiusSWPID1942Renum.hex) also to the solid green/yellow/white.The solid green headunit 'magically' converts to a 'solid blue' one. This works at least on the devices I own.
BUT: You have to control the brake different, because the PCB layout between the CPU (PortC) and the serial cable is a little different. The green unit uses PINC.7 to controll the magnetic field, whereas the blue unit uses the serial interface on PINC.0 / PINC.1.
ATTENTION: maybe the powerline signal from the magnetic brake has 16v voltage level (no 3.3TTL). Mabye the blue headunit cannot handle this (but mine is still alive). I have not checked the wireing on the PCB.
On linux:
where 'xyz' is the bus number and 'abc' is the device number
For example try the following:
In this example, the device now has a new ID 012 on bus 002 and a new unit ID '3561:1942'That's the ID of the 'solid blue'. 3561 is the ID of 'Tacx bv'.
Funny - isn't it.
T1902 USB 'legacy' protocol: 6 Bytes OUT, 21 Bytes IN
Outbound:
The device can send up to 6 bytes. Less bytes are allowed.
Byte № | Description | Notes |
---|---|---|
0 | desired 'force' value. | Range is 0x00...0xFF 0x80 is 'neutral' (electrical magnetic field switched off). Values less than 0x80 reduce brake force (electrical magnetic field reduces the static magnetic fields) and values greater than 0x80 increase the brake force (electrical magnetic field increase the static magnetic fields). |
1 | start/stop control | Only Bits 0-2 are used: * 0x01 PAUSE/START manual control of stop watch * 0x02 AUTOPAUSE - if wheel is less than '20' * 0x04 AUTOSTART if wheel is greater or equal 20 To force a start without wheeling you need to start the stopwatch (Bit0=1) and disable auto-stopping (Bit1=0). Bit2 does not matter. Auto-Start/Stop is achieved with 0x06 |
2 | Set stop watch high byte | optional |
3 | Set stop watch mid byte | optional |
4 | Set stop watch low byte | optional |
5 | Set stop watch hundreds | optional, different for older firmwares |
Inbound
Byte № | Description | Notes |
---|---|---|
0 | Status and Cursors | Bit0: 0x01=HeartBeat Bit1: 0x02=Power-Detect Bit2+3: Powerline frequency * 0x0C: 50Hz * 0x08: 60Hz * 0x04: unused * 0x00: <50Hz Bit4: 0x10=Enter Button Bit5: 0x20=Down Button Bit6: 0x40=Cancel Button Bit7: 0x80=Up Button |
1 | WheelSpeed High | turns of the wheel in the last second? |
2 | WheelSpeed Low | |
3 | Cadence | RPM (revelation per minute) |
4 | Heartrate | BPM (beats per minute) |
5 | Stopwatch Seconds High | |
6 | Stopwatch Seconds Mid | |
7 | Stopwatch Seconds Low | |
8 | Stopwatch Hundreds | |
9 | Resistence value of brake | |
10 | PedalSensor | Bit 5: 0x00 or 0x10 |
11 | Axis 1 | floating between 0xBf-0xC3 |
12 | Axis 2 | 0x00-0xff Steering if plugged https://en.wikipedia.org/wiki/Game_port |
13 | Axis 3 | Unused? always 0x00 |
14 | Axis 4 | Unused? always 0x00 |
15 | Counter | running 0-255 every 70-80 ms, (old firmware fa, 1a) |
16 | Wheel Count | Number of Counts of (metal) wheel since last call (~70-80ms)? |
17 | Year | YY: individual Year of production of YOUR unit (20YY) |
18 | Serial High | YOUR individual Device-ID (high) |
19 | Serial Low | YOUR individual Device-ID (low) |
20 | Firmware-Version | 0x1c new, 0x1a old |
Bytes 17-19: matchs YOUR sticker on headunit backside
Newer USB 12/48 Bytes protocol
All outbound messages are motorbrake command messages, that are just handled as described above.After adding a checksum, marshalling and framing, they are directly sent to the serial.
For inbound messages, the first 24 bytes are from the headunit. The second 24 bytes are unmarshalled answers from the motorbrake. Note: Normal answers have 23 bytes plus 2 bytes checksum. So the last byte is the first byte of the checksum. The second checksum byte is discarded inside the headunit.
The CAD-information is copied from the motorbrake data block to the headunit data block
headunit Inbound (Bytes 0..23)
The first 24 bytes of every inbound message contains data from the headunit.
Version Message
Outbound
Bytes № | Description | Notes |
---|---|---|
0..3 | Version-Command | 02 00 00 00 (0x00000002 if coded as uint32 in LE) |
Inbound
Bytes № | Description | Notes |
---|---|---|
TODO |
Control Message
Outbound
Bytes № | Description | Notes |
---|---|---|
0...3 | Controll-Command | 01 08 01 00 (LE coded 0x00010801 as uint32) |
4, 5 (LE) | Power, Incline, Speed | depends on 'mode' value Fortius: Power 50-1000w, Incline -5..20% |
6 | Pedal echo | Host software should echo the pedal bit. This is some kind of 'is alive' signaling. |
7 | 0x00 | always zero ? |
8 | Mode | IDLE/NONE=0, ERGO/SLOPE=2, CALIBRATE/SPEED=3 |
9 | Weight | for ERGO: weight=0x0a; for SLOPE: weight=rider+bike weight in kg, IDLE/NONE: set weight=0x52 |
10, 11 (LE) | Calibrate | in mode '0' and '2': val = (calibrate + 8) * 130 with calibrate [-8..8] - set to '0' while calibrating (mode 3) |
Inbound Control Message
Bytes № | Description | Notes |
---|
Difference of USB 12/64 Bytes protocol (headunits T1904, T1932)
The T1904 and T1932 can handle both cable based brake types: magnetic brakes and the motor brakes (but for some reason not the old T1601 magnetic brake).Once, the protocol was developed to handle the Fortius motor brake via a serial communication the headunits emulates the data frame of the serial communication, when the headunit is connected to a magnetic (eddy current) brake. Beside the case color (light blue, light lemon green) and the different USB id (3561:1904 and 3561:1932), there is (as far as I know) NO difference between T1904 and T1932 headunits.
The newer headunits do not longer use a AN2141 (EZ-USB) processor. Instead, they use an NXP LPC2141 (FBD64) with 32 kB Flash, 8 kb RAM and 2 kB USB RAM Link.
If the headunit is not connected to a magnetic brake, or the brake is not powered, the headunit sends 24 byte frames. When connected to a (powered) magnetic brakes, every received frame is 64 bytes long. So, even if you do not send any commands to the headunit, the headunits sends 64 byte frames.
When sending 64 bytes, the checksum byte # 47 has a static value of 0x55. Byte #48 has static value 0x64. Bytes 49..63 are zeros.
If there is no steering connected the headunits sends a little higher default value (0x0a0d = 2573). When connected the steering values typically are between 0x300 (full right) and 0x500 (full left). Byte #46 changes to a fixed value of 0x02 after sending ANY data to the headunit. So this value do not longer 'bounces' the 'mode' value of a run command.
Bytes #40, 41 is the 'bounced' value of the 'load' value of a run command.Idling, bytes #36,37 and bytes #38,39 are 0x040f.
The communication between the headunit and the Fortius motorbrake is a serial 3.3V 'TTL' signal (not RS232) with 19200 baud and 8N1 coding.Note: the used timer on the EZ-USB can only generate a 18750 baud signal.
Data frame
Marshalling and Checksum
Before transfering the data to the Fortius brake, the headunit marshalls the data frame and adds a checksum.
Every frame starts with 0x01 and ends with 0x17.
Every byte is recoded into a Hexcode before going on the wire. So every byte needs two byteson the serial. Every byte is splitted into 4 bit nibbles and converted to ASCII (chracters '0'-'9' and 'A'-'F'). The only exception is the start and end byte (0x01,0x17). They are sent raw.
Python code is:
There is a 16 bit checksum at the end. (hexcoded the checksum nees 4 bytes on the wire).The checksum includes the 0x01 start frame byte, but not the end frame byte.
Python code is:
Build your own controller
If you have a motor brake, you can build your own controlling device instead of using a Tacx headunit.
It is HIGHLY recommend to use 3.3V TTL logic, because the brake is very probably not 5V tolerant
I tried it with a (standalone) Raspi W Zero and with a 1$ CH341 budget USB2TTL device. I should also work with FTDI RS232R or CP2102 bases adapters, as long as they have 3.3V signal level.
If you do not like to solder or crimp your own cable:
From 'Makeblock' there is a cable with a RJ12/RJ25 (6p6c) socket on one side an Dupont sockets on the other side. Price is about 2$-3$ for a bundle with two cables. The Makeblock part no. is MB14230. They even use the same wire colors as the original cable.
The cable is only 20cm long, but with a full connected (straight through) female-female 6p6c coupler (i.e. from 'inLine' part no. 69999 EAN: 4043718012909 or from 'Goobay' part no. 50592 EAN: 4040849505928), you can use the original cable in addition
Alternatively, you can also use a USB extension cable.
CH341 budget USB2TTY
Just wire USB/TTL-GND to RJ12-Pin 2 (black, GND), USB/TTL-Tx to RJ12-Pin 3 (Red, Host-Tx, Brake Rx) and USB/TTL-Rx to RJ12-Pin 6 (blue, Host-Rx, Brake Tx).
Raspberry Pi
On Raspi GND is Pin 6, Tx is Pin 8 and Rx is Pin 10.
All devices are using the default ANT+ network key. The default key is set after a reset of the ANT dongle. Please send a ANT reset command to the USB dongle to (re)set all you networks to the default network key.
Device parameters
Tacx brakes and the other Tacx devices are using several different ANT channels, periods and device types.
Tacx Device Name | ANT Device-Type (*1) | Channel frequency | Channel period | =Hz | Notes |
---|---|---|---|---|---|
(i)Vortex Brake | 0x3d | 66 = 0x42 | 0x2000 = 8192 | 4 Hz | GoldenCheetah has demystified the protocol. Check i.e. ANT.h and ANTMessage.cpp |
Vortex Display | 0x3e | 78 = 0x4e | 0x0f00 = 3840 | ~8.53 Hz | T2172 light-blue, T2162 yellow-green |
Bushido Brake | 0x51 | 60 = 0x3c | 0x1000 = 4096 | 8 Hz | pyBushido and Cyclismo both have demystified the protocol |
Bushido Display | 0x52 | 60 = 0x3c | 0x1000 = 4096 | 8 Hz | hosts sends 4E #ch# AC commands |
Genius Brake | 0x53 | 60 = 0x3c | 0x1000 = 4096 | 8 Hz | |
Blacktrack Steering | 0x54 | 60 = 0x3c | 0x0800 = 2048 | 16 Hz | Steering T2420. Probably also NEO track T2430. Slave => Master: Keep alive ? [01 00 00 00 00 00 00 00] ? steering |
Cursor Control | 0x55 | 60 = 0x3c | 0x1000 = 4096 | 8 Hz | The small blue round (Bushido headunit) controller |
Flux Brake | 0x56 | 66 = 0x42 | 0x2000 = 8192 | 4 Hz | TTS4 knows this device, but maybe it was never released (with legacy ANT protocol) Keepalive / Control messages from host to brake: host sends: 4E #ch# 10 00 00 aa 7e 00 00 00 |
Flow Brake | 0x5f | 66 = 0x42 | 0x2000 = 8192 | 4 Hz | Same as Flux Brake: see above |
Note *1: With ANT+ Pairing Bit add 0x80 to the ANT Device-Type
Commands and Answers
All older Tacx ANT+ devices handle at least the 3 commands. A command always starts with 'AC' followed by the command number.All answers start with 'AD' followed by the command number, followed by the payload.
Host Cmd Nr | type | Data from Host | Answer (example) | note |
---|---|---|---|---|
01 | Get Device Serial | ac 01 00 00 00 00 00 00 | ad 01 01 0c 00 00 25 78 | Big endian: '01'=20 ('00'=19??), '0c'=12 year of production, '00 00 25 78' is MY serial => 20-12-09592 |
02 | Get SW Version | ac 02 00 00 00 00 00 00 | ad 02 01 01 01 e9 00 00 | Big endian: here 01.01.01e9 = 1.1.489 |
04 | Battery Status | ac 04 00 00 00 00 00 00 | ad 04 03 xx xx xx xx xx | Here 03 = OK, xx xx xx xx xx contains data from the last command |
ANT+ Battery Status Values
Status | Value | Notes |
---|---|---|
New | 1 | |
Good | 2 | |
OK | 3 | |
Low | 4 | |
Critical | 5 | |
Charging | 6 | Not used? |
unknown | 7 |
Regular Pages from the device
Every devices send regular data pages.
Cursor Control Page
Byte | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
---|---|---|---|---|---|---|---|---|
Value | 00 | 00 | 0x | FF | 00 | 00 | 00 | 00 |
Byte 2 contains a 4 bit (OR-ed) value with
Bit Nr. | value | meainng |
---|---|---|
0 | x = 1 | Up |
1 | x = 2 | Right |
2 | x = 4 | Down |
3 | x = 8 | Left |
Not much to describe here. The brake talks standard ANT FE-C
Published online 2013 Aug 19. doi: 10.1371/journal.pone.0072025
PMID: 23977198
Michael Müller, Editor
This article has been cited by other articles in PMC.
Abstract
The purpose this study was to examine the effects of caffeine ingestion on performance and energy expenditure (anaerobic and aerobic contribution) during a 4-km cycling time trial (TT) performed after a carbohydrate (CHO) availability-lowering exercise protocol. After preliminary and familiarization trials, seven amateur cyclists performed three 4-km cycling TT in a double-blind, randomized and crossover design. The trials were performed either after no previous exercise (CON), or after a CHO availability-lowering exercise protocol (DEP) performed in the previous evening, followed by either placebo (DEP-PLA) or 5 mg.kg−1 of caffeine intake (DEP-CAF) 1 hour before the trial. Performance was reduced (−2.1%) in DEP-PLA vs CON (421.0±12.3 vs 412.4±9.7 s). However, performance was restored in DEP-CAF (404.6±17.1 s) compared with DEP-PLA, while no differences were found between DEP-CAF and CON. The anaerobic contribution was increased in DEP-CAF compared with both DEP-PLA and CON (67.4±14.91, 47. 3±14.6 and 55.3±14.0 W, respectively), and this was more pronounced in the first 3 km of the trial. Similarly, total anaerobic work was higher in DEP-CAF than in the other conditions. The integrated electromyographic activity, plasma lactate concentration, oxygen uptake, aerobic contribution and total aerobic work were not different between the conditions. The reduction in performance associated with low CHO availability is reversed with caffeine ingestion due to a higher anaerobic contribution, suggesting that caffeine could access an anaerobic “reserve” that is not used under normal conditions.
Introduction
The importance of endogenous carbohydrate (CHO) availability for high-intensity exercise performance has been well described in the literature –. Several studies – have shown that performance during high-intensity exercise is impaired when endogenous CHO availability (i.e., muscle and liver glycogen stores) is reduced. For example, Langfort et al. reported that after three days of a low-CHO diet (∼ 5% CHO) the average power output measured during a 30-s Wingate test in healthy men not engaged in any competitive sport was significantly reduced (from 581±7 to 533±7 W) when compared with a normal diet (∼ 50% CHO). According to these authors, the reduction in performance (∼9%) with low CHO availability was due to a lower contribution of the anaerobic energy system. Similarly, Miura et al. found a reduction in the anaerobic work capacity of healthy, non-athletic men when exercise was performed after a muscle-glycogen-depletion protocol compared to a control condition (10.33±2.41 vs 12.83±2.21 kJ, respectively), suggesting that low CHO availability can reduce the anaerobic contribution to total energy expenditure during high-intensity exercise. In addition, reduction in self-selected power output during high-intensity interval training when performed with low endogenous CHO availability has been also reported in well-trained subjects, and it may be associated with a reduction in the anaerobic contribution –.
While low CHO availability seems to reduce the anaerobic contribution and impair performance during high-intensity exercise, acute ingestion of caffeine seems to have the opposite effect , . Doherty observed an increase of 10% and 14% in the anaerobic energy supply (measured by maximum accumulated oxygen deficit) and performance (time to exhaustion), respectively, during high-intensity exercise performed at 125% of the maximal oxygen uptake (VO2max) after caffeine ingestion (5 mg.kg−1). Using the same exercise intensity and caffeine dose, Bell et al. reported a 7–8% increase in total anaerobic energy contribution and time to exhaustion. Recently, a similar increase in the anaerobic contribution (6.5%) and time to exhaustion (14%) at 120% VO2peak was also found by Simmonds et al. after caffeine ingestion (5 mg.kg−1). Although all of the aforementioned studies have investigated the effects of caffeine on performance during time-to-exhaustion tests, some studies have also found a positive effect of caffeine on performance during time-trials –; however, anaerobic contribution has not been measured in these studies. Taken together, these findings suggest that acute ingestion of caffeine may improve performance during high-intensity exercise via an increase in the anaerobic contribution.
The mechanisms by which caffeine increases the anaerobic contribution and performance during high-intensity exercise is not fully understood, but it has been proposed that caffeine intake would promote an inhibitory action on adenosine receptors, which would increase the activity of the enzyme phosphofructokinase, thereby increasing anaerobic glycolysis , . Alternatively, caffeine may act on the central nervous system leading to an increase in motivational drive and neuromuscular excitability, which, in turn, results in a lowered rating of perceived exertion (RPE) for a given workload and improved neuromuscular function, as measured via electromyography activity (EMG) . In addition, it has also been suggested that caffeine attenuates muscle sensory signals to the brain and decreases the threshold of activation of motor neurons . All of these central alterations could lead to an ability to produce more work anaerobically.
Although several studies have investigated the isolated effects of both CHO availability and caffeine intake on anaerobic contribution and performance –, –, no study has examined whether acute caffeine ingestion could counteract the negative effects of low CHO availability on both the anaerobic contribution and performance. This seems to be particularly important since many athletes perform two training sessions in the same day, or participate in multi-stage event races (e.g., tour de France), where the time to replenish endogenous CHO stores between sessions or races may not be sufficient. Furthermore, most studies with either caffeine – or CHO availability – have focused on investigating their effects during time-to-exhaustion tests. However, time trials (TT) appear to be more reliable and to have greater external validity compared to constant-workload tests until exhaustion. Furthermore, during a high-intensity TT, where athletes are free to vary power output, anaerobic metabolism seems to exert a decisive effect on both performance and the distribution of work –.
Therefore, the purpose of this study was to examine whether caffeine ingestion promotes an increase in the anaerobic contribution and performance during a 4-km cycling TT, when athletes begin the trial after reduced endogenous CHO availability –. We hypothesized that low CHO availability would reduce the anaerobic contribution and performance during a 4-km cycling TT; however, this reduction in the anaerobic contribution and performance would be attenuated or even reversed with caffeine supplementation.
Methods
Participants
Before beginning the study, participants answered a questionnaire on readiness for physical activity (PAR-Q) and performed a cardiac screening test, including electrocardiogram. Seven amateur cyclists (age 32.3±5.4 years, body mass 73.6±7.4 kg, height 173.1±5.3 cm, body fat 10.5±4.7%, peak power output [PPO] 227.8±10.2 W, and VO2peak 58.1±6.3 mL.kg−1.min−1) participated in this study. The participants had been training for at least 4 years, performed a weekly training volume of 12.1±4.3 h.wk−1 (250±101.3 km.wk−1) and competed regularly (∼20 competitions per year). The sample size required was estimated from the equation n = 8e2/d2, as suggested by Hopkins , where n, e, and d denote predicted sample size, coefficient of variation, and the magnitude of the treatment effect, respectively. Coefficient of variation was assumed to be 0.9% . Expecting a magnitude of effect for the treatment of 3.1% , detection of a very conservative 1% difference as statistically significant would require at least 6 participants. The participants were informed about the risks associated with the study protocol and signed a consent form agreeing to participate in the experiments. This investigation was approved by the Ethics and Research Committee of the Federal University of Alagoas.
Experimental Design
Each athlete visited the laboratory on seven different occasions. On the first visit, athletes underwent an anthropometric assessment and an incremental test. During the second visit (after ∼48 h), athletes performed a 4-km cycling familiarization trial. During the next visits, the athletes performed three 4-km cycling TT in a randomized, double-blind and repeated-measures crossover design, separated by 7 days for washout, under the following conditions: 1) 12–14 h after a validated exercise-protocol designed to reduce endogenous CHO availability, followed by placebo (DEP-PLA) or caffeine (5 mg.kg−1, DEP-CAF) ingestion one hour before the trial and 2) 12–14 h after a full-rest, followed by placebo ingestion one hour before the trial (CON). In the evenings before DEP-PLA and DEP-CAF trials, two additional visits were required and the athletes came to the laboratory to perform a validated protocol for reducing the endogenous CHO availability. All of the experimental trials were performed in the morning to avoid the impact of circadian variation , . The athletes were asked to refrain from vigorous physical activities, caffeine and alcohol 24 h before each test. The temperature and relative humidity during the trials were 23.2±1.5°C and 43.1±4.2%, respectively.
Incremental Test
The incremental test was performed on a cycle ergotrainer (Tacx™ T1680 Flow, Netherlands) and consisted of a 3-min warm-up at a power output (PO) corresponding to 100 W, followed by increments of 30 W every 3 min until voluntary exhaustion or when the athletes were not able to maintain pedal frequency between 80–90 rpm . The ventilation (VE), VO2 and carbon dioxide production (VCO2) were measured breath-by-breath throughout the test with a gas analyzer (Quark CPET, Cosmed, Rome, Italy). The gas analyzer was calibrated before each test in accordance with the manufacturer’s recommendations. The HRmax and VO2peak were taken as the highest value reached in the last stage and as the mean value obtained during the last 30 s of the test, respectively. The PPO was determinate as highest PO maintained during a complete stage. When the last stage was not completed, the PPO was determined in according the methods of Kuipers et al. .
Familiarization Trial
Forty-eight hours after the incremental test, the athletes performed a familiarization session with the TT procedures (cycle ergotrainer, Tacx™ T1680 Flow, Netherlands). The seat was fully adjustable vertically and horizontally for each cyclist before the TT, and cycling shoes were used to secure the feet to the pedals. The seat position was recorded and replicated during all subsequent experimental sessions. The athletes were instructed to perform the TT in the shortest possible time and to remain seated throughout test. The gear ratio was standardized at the beginning of each TT (53×16). However, immediately after the TT had started, participants were free to change the gear and pedal frequency as desired. The athletes were instructed to record all foods (type, amount and hour) consumed in the 48 hours before the familiarization test .
Time-trials
The TT sequence began ∼96 hours after the familiarization test. Before each trial, the cycle ergotrainer was calibrated in accordance with the manufacturer’s recommendations. The TT was preceded by three maximal voluntary contractions (MVC) of the quadriceps muscles and a 5-min warm-up at 100 W (90 rpm) followed by a 5-min rest period (Figure 1). The distance and PO were recorded at a frequency of 1 Hz (Tacx Trainer software 3.0, Wassenaar, Netherlands). Feedback of the distance covered was provided verbally every 200 m of the TT. The RPE was recorded every 1 km using the Borg 15-point category scale . The VO2, respiratory exchange ratio (RER), HR, electromyographic activity (EMG), aerobic and anaerobic mechanical power output (Paer and Pan, respectively), work total (Wtot), total aerobic (Waer) and anaerobic work (Wan) were determined every 200 m and pooled for each 1 km. Blood samples (25 µL from an ear lobe) were obtained before the warm-up (rest), immediately before (Pre-TT) and 1 min after the TT (post-TT) to determine the plasma lactate concentrations [La]. The blood samples were transferred into micro-tubes containing sodium fluoride (NaF 1%) and then centrifuged at 3000 rpm at 5°C for 10 minutes. Plasma [La] was measured through enzymatic colorimetric reactions in a spectrophotometer (model Q798U2V5, Quimis®, São Paulo, Brazil) using commercial kits (kit Biotecnica, Varginha, Brazil).
Experimental Protocol.[La]: plasma lactate concentrations; MVC: maximal voluntary contraction; EMG: electromyographic activity; VO2: oxygen uptake; RER: respiratory exchange ratio; HR: heart rate; PPO: power output; Paer: aerobic mechanical power output; Pan: anaerobic mechanical power output.
Calculations of Aerobic and Anaerobic Mechanical Power Output
The Pan and Paer were calculated from RER, VO2 and using gross mechanical efficiency estimated during the warm up, in accordance with Hettinga et al. . Briefly, metabolic aerobic power (Pmet) during the warm up and TT was calculated by multiplying VO2 with the oxygen equivalent using the following equation:
We assumed a RER equal to 1.00 during the time trials . Gross mechanical efficiency was determined during the warm up, by dividing external PO (i.e. 100 W) by calculated Pmet. Aerobic mechanical power output (Paer) during the time trial was calculated by multiplying Pmet by gross efficiency. Anaerobic mechanical power output was calculated by subtracting the calculated Paer from the total measured mechanical PO.
CHO-availability-lowering Exercise Protocol
Participants arrived at the laboratory at ∼8∶00 PM, at least two hours after their last evening meal. The protocol employed for reducing the endogenous CHO availability has previously been validated and has been shown to reduce endogenous CHO availability to ∼30% of pre-exercise values –. The protocol consisted of a constant PO exercise at an intensity corresponding to 70% PPO (159.9±7.0 W) for 90 min. After 5 min of rest, the athletes performed six 1-min exercise bouts at 125% PPO (285.1±13.0 W) interspersed with 1-min rest periods. During the protocol, the pedal frequency was maintained between 80–90 rpm.
Dietary Control
During the morning and afternoon of the CHO availability-lowering exercise protocol, participants followed, up to the beginning of the exercise, the same dietary pattern contained in their food record. However, after the exercise protocol was finished (∼ 10∶00 PM), the athletes received a low-CHO diet (total energy 710.4±28 kcal, 12.7±0.1% CHO, 60.6±0.1% fat and 26.7±0.1% protein). Furthermore, the athletes received the same standardized, low-CHO breakfast (total energy 710.4±28 kcal, 12.7±0.1% CHO, 60.6±0.1% fat and 26.7±0.1% protein) one hour before the trial in the next morning (∼ 8∶00 AM). In the CON trial, the athletes were asked to replicate the diet recorded 24 hours before the trial, and ate a standardized meal derived from their diet record (total energy 737.0±103.7 kcal, 55.8±21.4% CHO, 26.5±14.7% fat and 17.7±7.8% protein). The breakfast consumed an hour before the CON trial was also derived from the diet recorded and consisted of 55.8±21.4% CHO, 26.5±14.7% fat and 17.7±7.8% protein (total energy 737.0±103.7 kcal).
Maximal Isometric Contraction Measurement
Before the MVC, participants performed a standardized warm-up, in a chair with the trunk-thigh angle at 90° and the knee at 60° from full leg extension (0°), consisting of four 5-s contractions of the knee extensors, interspersed by 30-s rest periods, at intensities corresponding to 50, 60, 70 and 80% of the maximum subjective force . Thereafter, participants performed three 5-s MVC (two legs), each separated by 60-s intervals. The peak force produced by the quadriceps muscles was recorded using a load cell (EMG System of Brazil, São José dos Campos, Brazil). The athletes were verbally encouraged during all MVCs to achieve their maximal force.
Acquisition and Analysis of the Electromyographic Signal
During the MVC and time trials, EMG signals of the vastus lateralis (VL) muscle of the right leg were recorded via bipolar Ag-AgCl surface electrode (Hal, São Paulo, Brazil) at an interelectrode distance of 20 mm. We chose the VL muscle because it has been reported as the most appropriate to monitor EMG activity in the lower limb during a 4-km cycling TT . The reference electrode was placed over the anterior surface of the tibia. The skin preparation, placement and location of the electrodes were in accordance with the recommendations of SENIAM . To prevent movement artifact, the electrode wires were taped to the skin using adhesive tape (MicroporeTM 3 M, São Paulo, Brazil). Five seconds of raw EMG signal was recorded each 200 m with a sample rate of 2000 Hz (model 410c EMG System of Brazil Ltda, São Paulo, Brazil). Raw EMG signals were full-wave rectified and filtered with second-order Butterworth band-pass filters with cut-off frequencies set at 10 and 400 Hz to remove external interference noise and movement artifacts. Integrated EMG (iEMG) obtained each 200 m during the TT was normalized by dividing by the iEMG calculated at the point coinciding with peak torque of the highest MVC. Data processing was performed using MATLAB software.
Statistical Analysis
The data are presented as means ± SD. Data distribution was analyzed using the Shapiro-Wilk test. two-way ANOVA with repeated-measures were used to verify the effect of condition and distance on the PO, Pan and Paer response. When a significant effect was found, the main effect was analyzed using the least significant difference test for pairwise comparisons. The Effect size (ES) and 95% confidence intervals (95% CI) were calculated to evaluate differences between conditions for mean values of Wtot, Waer, Wan, PO, Pan, Paer and time to cover the TT. The ES was calculated by dividing the difference between mean values of the conditions by the pooled SD . ES of 0.2, 0.6 and 1.2 were considered as small, moderate and large effects, respectively . To make inferences about true (population) values of the effect of caffeine on performance, the uncertainty in the effect was expressed as likelihoods that the true value of the effect represents substantial change (harm or benefit) . The smallest standardized change was assumed to be 0.20. For all analyses, significance was accepted at P<0.05. All analyses were performed using SPSS software (version 13.0; Chicago, IL).
Results
Performance Parameters
Mean and individual values for performance are shown in Figure 2. Only one participant did not improve his performance with caffeine intake (non-responder) compared to the DEP-PLA condition. The mean time to complete the 4-km cycling TT was moderately slower (Fig. 2) in the DEP-PLA (2.1%) than in the CON (ES = 0.65, 95% CI = 0.09–1.22). However, compared with DEP-PLA, caffeine ingestion (DEP-CAF) moderately reduced 4-km completion time by 4.1% (ES = 0.94, 95% CI = 0.10–1.78). The corresponding qualitative inference was 96.7% ‘benefit very likely’. The effect of caffeine (DEP-CAF) compared to CON was small (ES = 0.45, 95% CI = −0.19–1.09), although performance in five of the seven participants was improved in DEP-CAF compared to the CON condition. The corresponding qualitative inference was 79% ‘benefit likely’.
Time to complete the 4-km cycling TT for control (CON), low carbohydrate availability with placebo ingestion (DEP-PLA) and low carbohydrate availability with caffeine ingestion (DEP-CAF).*Moderate effect of DEP-PLA compared to CON and DEP-CAF (ES = 0.65 and 0.94, respectively). #Small effect of DEP-CAF compared to CON (ES = 0.45). Data are expressed as mean (•) and individual (○) values.
Likewise, the mean PO was 7.0 and 10.8% lower (moderate effect), respectively, in DEP-PLA than in CON and DEP-CAF (ES = 0.77, 95% CI = 0.38–1.16and ES = 0.85, 95% CI = 0.09–1.61, respectively). A small effect was found in mean PO between DEP-CAF and CON (ES = 0.28, 95% CI = −0.19–0.76). The Wtot (Fig. 3) performed in the trial was moderately lower in the DEP-PLA (5.6% and 10.7, respectively) than in the CON (ES = 0.93, 95% CI = 0.06–1.80) and DEP-CAF (ES = 1.18, 95% CI = 0.22–2.14), and slightly higher (small effect) in DEP-CAF than CON (ES = 0.53, 95% CI = −0.08–1.14).
Mean and SD for work total (Wtot), total aerobic (Waer) and anaerobic work (Wan) during the 4-km cycling TT for control (CON), low carbohydrate availability with placebo ingestion (DEP-PLA) and low carbohydrate availability with caffeine ingestion (DEP-CAF).*Moderate effect of DEP-PLA compared to CON (ES = 0.93). §Small and moderate effect of DEP-CAF compared to CON and DEP-PLA (ES = 0.53 and 1.18, respectively). †Small effect of DEP-PLA compared to CON (ES = 0.40). #Moderate and large effects of DEP-CAF compared to CON and DEP-PLA (ES = 0.96 and 1.33, respectively).
When values were expressed every 1-km interval (Table 1), the PO was significantly reduced (P<0.05) in the first kilometer for DEP-PLA, compared with DEP-CAF and CON. In addition, PO at the second kilometer was lower in the DEP-PLA than in the DEP-CAF (P<0.05).
Table 1
Mean and SD for Power output (PO), aerobic mechanical power output (Paer), anaerobic mechanical power output (Pan), oxygen uptake (VO2), heart rate (HR), rating of perceived exertion (RPE) and integrated electromyography (iEMG) for each 1-km.
Distance | ||||
1-km | 2-km | 3-km | 4-km | |
PO (W) | ||||
CON | 245.5±34.2* | 217.9±22.3 | 215.3±27.8 | 245.6±51.3 |
DEP-PLA | 209.0±19.0 | 207.5±15.4 | 202.9±16.7 | 240.3±42.4 |
DEP-CAF | 255.3±50.5* | 237.3±31.3* | 222.8±25.5 | 248.8±34.9 |
Paer (W) | ||||
CON | 143.8±11.3 | 182.2±16.7 | 186.8±19.8 | 190.1±18.8* |
DEP-PLA | 140.9±5.0 | 173.4±5.6 | 176.7±6.5 | 179.5±10.2 |
DEP-CAF | 144.0±15.3 | 180.5±19.8 | 184.9±21.8 | 185.4±22.0 |
Pan (W) | ||||
CON | 101.7±40.4 | 35.7±17.8 | 28.5±13.2 | 55.4±44.3 |
DEP-PLA | 68.0±15.8 | 34.1±10.6 | 26.2±11.6 | 60.9±38.0 |
DEP-CAF | 111.4±39.0* | 56.8±21.1* | 37.9±7.8* | 63.4±25.1 |
VO2 (L.min−1) | ||||
CON | 3.2±0.3 | 4.1±0.3 | 4.2±0.3 | 4.2±0.3 |
DEP-PLA | 3.4±0.2 | 4.1±0.2 | 4.2±0.2 | 4.3±0.2 |
DEP-CAF | 3.3±0.3 | 4.1±0.4 | 4.2±0.5 | 4.2±0.5 |
HR (bpm) | ||||
CON | 154±20 | 171±2 | 175±2 | 180±2 |
DEP-PLA | 149±19 | 168±2 | 172±2 | 178±3 |
DEP-CAF | 156±19* | 174±2* | 178±1* | 182±2 |
RPE (units) | ||||
CON | 11.0±1.7 | 12.6±0.5 | 14.6±1.6 | 16.4±2.4 |
DEP-PLA | 10.7±1.7 | 12.7±1.3 | 14.6±1.1 | 17±1.7 |
DEP-CAF | 10.3±1.5 | 12.4±1.3 | 14.9±1.5 | 17. ±2 |
iEMG (%) | ||||
CON | 47.2±6.8 | 52.0±20.1 | 46.1±9.2 | 52.5±12.6 |
DEP-PLA | 45.5±9.0 | 44.7±6.6 | 45.2±9.3 | 51.7±15.8 |
DEP-CAF | 39.3±1.9 | 41.3±1.7 | 42.9±2.3 | 44.7±5.7 |
iEMG expressed as percentage of EMG value obtained during MVC. CON: control condition; DEP-PLA: low carbohydrate availability with placebo ingestion; DEP-CAF: low carbohydrate availability with caffeine ingestion.
Anaerobic and Aerobic Contribution
Mean Pan during DEP-CAF was moderately greater than in CON (ES = 0.72, 95% CI = 0.089–1.35) and DEP-PLA (ES = 1.18, 95% CI = 0.56–1.78), and slightly lower (small effect) in DEP-PLA than in CON (ES = 0.48, 95% CI = −0.022–0.990). The Pan in DEP-CAF for the first 3 km was significantly higher (P<0.05) than for DEP-PLA, but it was not significantly different from CON (Table 1). No effect was found in the mean Paer during the 4-km cycling TT. However, mean Paer was slightly lower in the last kilometer for DEP-PLA compared with CON (Table 1).
Total Waer (Fig. 3) generated during trials was similar between the conditions (DEP-CAF vs CON: ES = 0.17, 95% CI = −0.74–1.08; DEP-CAF vs DEP-PLA: ES = 0.03, 95% CI = −0.49–0.54 and CON vs DEP-PLA: ES = 0.19, 95% CI = −0.40–0.77), whereas there was a moderate to large difference for total Wan between DEP-CAF and CON (ES = 0.96, 95% CI = 0.19–1.73) and DEP-PLA (ES = 1.33, 95% CI = 0.78–1.88), respectively, but the effect was small between CON and DEP-PLA (ES = 0.40, 95% CI = −0.12–0.93). The PO, Pan and Paer profiles are shown each 200-m interval in Figure 4. In general, caffeine ingestion increased mainly PO and Pan compared to DEP-PLA (Fig. 4).
Mean and SD for power output (upper), anaerobic (middle) and aerobic (lower) mechanic power for each 200 m during the 4-km cycling TT for control (CON), low carbohydrate availability with placebo ingestion (DEP-PLA) and low carbohydrate availability with caffeine ingestion (DEP-CAF).*Significantly different between DEP-CAF and DEP-PLA (P<0.05); #Significantly different between CON and DEP-PLA (P<0.05); †Significantly different between DEP-CAF and CON (P<0.05).
Perceptual, Physiological and Neuromuscular Responses
There was no difference in the RPE, iEMG or VO2 during the 4-km cycling TT between the conditions (Table 1 and and2).2). However, the HR was significantly higher (P<0.05) in the DEP-CAF than in the DEP-PLA in the first 3 km of the trial (Table 2). No difference was found in HR between CON and DEP-CAF (P>0.05). There was no significant (P>0.05) difference in the resting and pos-TT [La] between conditions (Table 3). Nevertheless, the [La] Pos-TT were significantly (P<0.05) higher than in the rest and Pre-TT in all conditions (Table 3).
Table 2
Mean and SD for rating of perceived exertion (RPE), integrated electromyography (iEMG), average oxygen uptake (VO2) and heart rate (HR) during the 4-km cycling TT.
Variables | CON | DEP-PLA | DEP-CAF |
RPE (units) | 13.6±0.7 | 13.8±0.4 | 13.8±1.1 |
iEMG (%) | 49.1±9.4 | 46.8±7.3 | 42.1±6.9 |
VO2 (L.min−1) | 3.9±0.3 | 4.0±0.2 | 4.0±0.4 |
HR (bpm) | 171±13 | 168±14 | 173±14 |
iEMG expressed as percentage of EMG value obtained during MVC. CON: control; DEP-PLA: low carbohydrate availability with placebo ingestion; DEP-CAF: low carbohydrate availability with caffeine ingestion.
Table 3
Mean and SD for lactate concentration at rest, and pre and post the 4-km cycling TT.
Rest | Pre-TT | Post-TT | |
CON | 1.0±0.6 | 1.0±0.6 | 9.1±2.9* |
DEP-PLA | 1.1±0.6 | 0.7±0.2 | 7.9±1.2* |
DEP-CAF | 1.0±0.3 | 0.9±0.2 | 8.8±1.8* |
*Significantly higher than Rest and Pre-TT (P<0.05).
Discussion
The main finding of the present study was that acute caffeine ingestion reversed the impairment in time-trial performance following a protocol designed to lower endogenous CHO availability. Furthermore, the reestablishment of the performance with caffeine ingestion was associated with an increase in the Pan and total anaerobic work generated during the 4-km cycling TT, indicating that caffeine allows access to an anaerobic “reserve” that is not normally used. The increase in the performance with caffeine ingestion seems to be explained by a higher PO and anaerobic contribution during the first 2–3 km of the trial.
Effect of Caffeine on 4-km Cycling TT Performance
Previous studies have reported an increase in high-intensity exercise performance after caffeine ingestion –. Recently, Wiles et al. , using the same caffeine dose as the present study (5 mg.kg−1), reported an improvement (3.1%) in 1-km cycling TT performance compared to a placebo. This improvement was accompanied by a 3.6% increase in the mean PO . In the present study, we observed a 7.0% reduction in mean PO and a 2.1% increase in the time to complete the trial when TT was performed after an exercise protocol designed to reduce CHO availability, in comparison with CON. However, caffeine intake increased mean PO by 10.8% and reduced the time to cover the 4-km TT by 4.1%, when compared with DEP-PLA. When compared with control, caffeine intake increased mean PO by 4.3% and reduced the time to complete the trial by 1.9%. Qualitative inferences indicated that a benefit was ‘very likely’ and ‘likely’ when DEP-CAF was compared to DEP-PLA and CON, respectively, suggesting that performance improvements of 4.1 and 1.9% are meaningful for our participants. Our study demonstrates for the first time that, even with a reduced CHO availability, caffeine intake restores time-trial performance to levels found when endogenous CHO availability is normal.
Athletes adopted a more conservative starting pacing strategy when CHO stores were depleted. It is not fully clear if this conservative starting was caused by an intramuscular effect of the muscle glycogen depletion and/or a psychological strategy. However, despite the subjects being aware that they were depleted, they were not able to identify which capsule (caffeine or placebo) had subsequently been ingested, and, even then, adopted a more aggressive pacing strategy in DEP-CAF than DEP-PLA. Both iEMG and RPE at the beginning of the DEP-PLA trial were also similar to the DEP-CAF trial, even with a lower PO, suggesting that any effect of manipulation may have happened in the muscle. Furthermore, caffeine supplementation restored the PO in the first two kilometers and it was not associated with a reduced PO in the rest of the time trial.
In contrast to the results of the present study, Hettinga et al. reported that a higher PO in the first 2 km of a 4-km cycling TT results in an impairment of the PO in the second half of the trial. It should be noted however, that the pacing strategy during the first 2 km in the Hettinga study was dictated by the researchers, and the participants were “enforced” to perform a constant PO at 105% above the mean PO until the end of the second kilometer. This “enforced”, constant-paced exercise during the first 2 km may have induced a greater physiological strain than self-paced exercise, and provoked a reduction in PO during the second half of the trial , . Therefore, caffeine seems to attenuate the decrement in power output observed early in CON and DEP-PLA conditions, and preserves the ability to optimally perform the second half of the trial.
Even though mean PO was higher in the first 2 km of DEP-CAF compared with DEP-PLA, the RPE was not significantly different between the conditions, suggesting that participants were able to perform the first 2 km of a 4-km cycling TT with a higher PO/RPE ratio when caffeine was ingested. This is in accordance with previous results suggesting that, independent of the physiological or metabolic status, athletes normally adopt a pattern of increase in RPE proportional to the exercise distance completed –. For example, positive (e.g. nutritional supplementation) and negative (e.g. hypoxia) changes in the homeostatic status throughout the TT have been reported to provoke an increase or reduction in PO, respectively, in order to maintain the same RPE template during exercise trials –. Caffeine may influence RPE via a direct blockade of adenosine A2a receptors in the brain , permitting more external work to be performed for a given conscious perception. However, although any alteration in RPE with caffeine should have increased motor drive and neuromuscular excitability , the iEMG was not altered in the present study. Alternatively, caffeine may have had a peripheral effect on increasing muscle function, which, in turn, would reduce muscle sensory signals to the brain and consequently reduce RPE.
Effect of Caffeine on Anaerobic and Aerobic Contribution
According to some studies , , endogenous CHO depletion reduces the contribution of the anaerobic system, possibly due to a limitation in the rates of glycogenolysis and glycolysis. In fact, Blomstrand and Saltin , using a protocol to reduce endogenous CHO availability in one leg, showed that the breakdown of muscle glycogen during 60 minutes of exercise at 75% VO2max was ∼ 48% less in the leg that started the exercise with low muscle glycogen (99±18 µmol.kg dry wt−1) than the leg that began with normal muscle glycogen levels (207±22 µmol.kg dry wt−1). When analyzing each km, we observed an increase in the Pan during the first 3 km for DEP-CAF compared to the DEP-PLA. This large anaerobic production early in the trial was accompanied by a significant increase in the PO, supporting the idea that power distribution during a TT appears to be regulated primarily by changes in the anaerobic contribution , . In related results, Hettinga el al. reported that the Pan was higher during the first 2 km of a 4-km cycling time trial when athletes were asked to perform the first 2 km at a supra-mean PO intensity (105% of the mean PO), but was significantly reduced in the second half of the trial when the athletes were free to reduce the PO. These results are consistent with those reported recently by Aisbett et al. who induced fast-, even-, and slow-starting during the first 25% of a 5-min cycling time trial (approximating the duration of a 4000-m cycling TT), and observed that the oxygen deficit (anaerobic contribution) was greater in the first quarter and lower in the second and third quarters of exercise in the fast-start trial, compared with the two other pacing strategies. In contrast, we found that despite a higher Pan in first 3 km after caffeine ingestion, the Pan in the last km was not impaired when compared with the other conditions, suggesting that caffeine maintained the Pan throughout the trial and promoted an increase in the total anaerobic contribution.
Several studies have suggested that the total amount of anaerobic energy that can be produced during a TT is fixed –. Indeed, Hettinga et al. demonstrated that despite inducing their participants to perform the first 750 m of a 1500-m cycling TT at 105% (supra) and 95% (sub) of the mean PO measured during the even-paced time trial, the total amount of anaerobic work generated over the time trial remained unchanged. Similarly, Aisbett et al. also reported no difference in the total energy provided by the anaerobic system when the cyclists performed a 5-min cycling TT using different starting strategies. These results suggested that the pattern of anaerobic energy distribution can vary with pacing strategy, but that the total anaerobic capacity remains fixed. On the other hand, it has been reported that caffeine intake promotes an increase in the quantity of anaerobic energy produced during high-intensity, time-to-exhaustion exercise –, although this has not been measured during closed-loop exercise such as a TT.
In the present study, we found that the total amount of anaerobic energy was higher in DEP-CAF than in both DEP-PLA and CON, indicating that caffeine exerts a more potent effect on the anaerobic contribution than low CHO availability. Furthermore, the greater Wan during the 4-km cycling TT after caffeine ingestion indicates that the total amount of anaerobic energy expenditure during TT exercise may not be fixed and that caffeine allows access to an anaerobic “reserve” that is not used under normal conditions. The existence of an anaerobic reserve has been demonstrated recently by Corbett et al. , who reported that the total anaerobic energy yield during a 2000-m cycling TT was higher when the participants believed that they were competing against another athlete of similar ability (head-to-head), than when they exercised alone (time trial), suggesting that a motivational stimulus promotes the use of a greater degree of the anaerobic “reserve”. To the best of our knowledge, the present study is the first to demonstrate that caffeine intake increases the total anaerobic work produced during a middle-distance cycling TT, even though the athletes started the trial with a low CHO availability. In addition, although PO and Pan were increased at the beginning and in the middle of the TT with caffeine ingestion, when compared to the DEP-PLA condition, there were no differences in the last 600 m between the conditions, and this was accompanied by a similar [La] Post-TT, suggesting that CAF was not able to increase the anaerobic contribution at the end of the trial.
The mechanism by which caffeine ingestion exerts its effect on the anaerobic contribution remains unclear. Simmonds et al. suggested that caffeine increases the anaerobic contribution through its antagonistic action on the adenosine receptors, which could unlock any inhibitory effect of adenosine on phosphofructokinase enzyme activity in skeletal muscle. Furthermore, Bridge and colleagues have suggested that caffeine ingestion results in an increase in the release of calcium, facilitating the conversion of the enzyme phosphorylase b to it more active form a, which would lead to an acceleration of glycogenolysis. However, this last mechanism seems unlikely in vivo, since a greater mobilization of calcium from sarcoplasmic reticulum has been observed only at high concentrations of caffeine that would be toxic to humans .
Effects of Caffeine on Neuromuscular Responses
It has been hypothesized that caffeine intake improves performance during high-intensity exercise through an increase in electromyography activity . An increase in both EMG activity and performance during short-duration, maximal-dynamic contractions has been demonstrated after caffeine ingestion . In the present study however, although the PO was greater with caffeine intake, there was no difference in iEMG between conditions. These conflicting results could possibly be explained by the different protocols adopted and the muscles analyzed. While we used a cycling time-trial test, and measured the EMG of the vastus lateralis muscle, Bazzucchi et al. assessed elbow flexion torque with an isokinetic dynamometer and EMG was recorded from the biceps brachii. On the other hand, our results are consistent with findings from other studies , that observed no significant differences in the EMG recorded from the vastus lateralis muscle during isometric contractions after caffeine ingestion. However, the measurement and interpretation of EMG during dynamic exercise is difficult and may not be sufficiently sensitive to measure small changes in muscle activation . Therefore, conclusions about the effects of caffeine on iEMG during dynamic exercise have to be interpreted with caution. Nevertheless, in the absence of other methods to quantify muscle activation levels during dynamic exercise, changes in iEMG amplitude are the only way to indirectly measure muscle activation levels during a cycling time trial. Thus, while we interpret our iEMG data with caution, our findings indicate that iEMG activity did not change with caffeine intake.
A potential limitation is that we did not include a control session (without CHO depletion) with caffeine ingestion. Despite the fact that this could have provided a more complete knowledge about the effects of caffeine on pacing strategy and TT performance with different levels of endogenous CHO availability, the inclusion of more experimental sessions had the potential to reduce the motivation of participants to participate in so many trials, potentially affecting our performance results. Thus, we focused the present study on verifying if caffeine could reverse the deleterious effect of low CHO availability on performance. In addition, the standardisation of the starting gear and the prevision of verbal instead visual distance feedback should also be acknowledged. However, the hard gear ratio as the used in the present study (53×16) has been described in the literature and justified due the high-intensity, fast-start nature of the 4-km cycling TT . Verbal instead of visual distance feedback has also been used in previous research . Finally, we were unable to blind the participants to the reduced CHO availability and this may have influenced pacing in the trials. While blinding the participants to the CHO availability in the diet is practically impossible, we cannot fully discard the possibility of any conscious alteration in pacing due to awareness of being in a low-CHO state. However, this could be expected to affect pacing equally in both CHO-depletion conditions, but the participants paced themselves faster in DEP-CAF than DEP-PLA, while iEMG signal was not altered, suggesting that pacing modifications during depleted-CHO condition may have not been “consciously” determined.
Conclusions
In conclusion, the results from the present study have shown that acute ingestion of caffeine induced a higher mean PO and anaerobic contribution during the first 2–3 km of the 4-km time trial. Furthermore, caffeine seems to attenuate the decrement in power output observed early in CON and DEP-PLA conditions, and preserves the ability to optimally perform the second half of the trial. In addition, caffeine ingestion reversed the impairment in time-trial performance caused by low CHO availability to levels found when endogenous CHO availability is normal. This improvement in performance was associated with a greater total anaerobic energy contribution with caffeine ingestion compared to both DEP-PLA and CON, indicating that caffeine exerts a more potent effect on the anaerobic contribution than low CHO availability. Therefore, we suggest that the total amount of anaerobic energy expenditure during TT exercise may not be fixed and that caffeine ingestion (even following a protocol to reduce endogenous CHO availability) allows access an anaerobic “reserve” that is not accessed under normal conditions. Our results suggest that caffeine may have an effect on intramuscular metabolism, i.e. increase on anaerobic contribution and total anaerobic work, rather than any significant effect on muscle recruitment.
Acknowledgments
Silva-Cavalcante MD is grateful to National Counsel of Technological and Scientific Development (CNPq) for his scholarship (133832/2010-4). The authors thank all of the cyclists who took part in this study.
Funding Statement
This project was supported by Coordination of Improvement of Personnel of Superior Level (CAPES-PRODOC, MEC/CAPES 29/2010). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
References
1. Greenhaff PL, Gleeson M, Maughan RJ (1987) The effects of dietary manipulation on blood acid-base status and the performance of high intensity exercise. Eur J Appl Physiol Occup Physiol56: 331–337. [PubMed] [Google Scholar]
2. Langfort J, Zarzeczny R, Pilis W, Nazar K, Kaciuba-Uscitko H (1997) The effect of a low-carbohydrate diet on performance, hormonal and metabolic responses to a 30-s bout of supramaximal exercise. Eur J Appl Physiol76: 128–133. [PubMed] [Google Scholar]
3. Lima-Silva AE, Pires FO, Bertuzzi RC, Lira FS, Casarini D, et al. (2011) Low carbohydrate diet affects the oxygen uptake on-kinetics and rating of perceived exertion in high intensity exercise. Psychophysiology48: 277–284. [PubMed] [Google Scholar]
4. Maughan RJ, Poole DC (1981) The effects of a glycogen-loading regimen on the capacity to perform anaerobic exercise. Eur J Appl Physiol46: 211–219. [PubMed] [Google Scholar]
5. Miura A, Sato H, Sato H, Whipp BJ, Fukuba Y (2000) The effect of glycogen depletion on the curvature constant parameter of the power-duration curve for cycle ergometry. Ergonomics43: 133–141. [PubMed] [Google Scholar]
6. Yeo WK, Paton CD, Garnham AP, Burke LM, Carey AL, Hawley JA (2008) Skeletal muscle adaptation and performance responses to once a day versus twice every second day endurance training regimens. J Appl Physiol105: 1462–1470. [PubMed] [Google Scholar]
7. Yeo WK, McGee SL, Carey AL, Paton CD, Garnham AP, et al. (2010) Acute signalling responses to intense endurance training commenced with low or normal muscle glycogen. Exp Physiol95: 351–358. [PubMed] [Google Scholar]
8. Hulston CJ, Venables MC, Mann CH, Martin C, Philp A, et al. (2010) Training with low muscle glycogen enhances fat metabolism in well-trained cyclists. Med Sci Sports Exerc42: 2046–2055. [PubMed] [Google Scholar]
9. Collomp K, Ahmaidi S, Audran M, Chanal JL, Prefaut C (1991) Effects of caffeine ingestion on performance and anaerobic metabolism during the Wingate test. Int J Sports Med12: 439–443. [PubMed] [Google Scholar]
10. Doherty M (1998) The effects of caffeine on the maximal accumulated oxygen deficit and short-term running performance. Int J Sports Nutr8: 95–104. [PubMed] [Google Scholar]
11. Bell DG, Jacobs IRA, Ellerington K (2001) Effect of caffeine and ephedrine ingestion on anaerobic exercise performance. Med Sci Sports Exerc33: 1399–1403. [PubMed] [Google Scholar]
12. Simmonds MJ, Minahan CL, Sabapathy S (2010) Caffeine improves supramaximal cycling but not the rate of anaerobic energy release. Eur J Appl Physiol109: 287–295. [PubMed] [Google Scholar]
13. Wiles JD, Coleman D, Tegerdine M, Swaine M (2006) The effects of caffeine ingestion on performance time, speed and power during a laboratory- based 1 km cycling time-trial. J Sports Sci24: 1165–1171. [PubMed] [Google Scholar]
14. Astorino TA, Cottrell T, Lozano AT, Aburto-Pratt K, Duhon J (2012) Increases in cycling performance in response to caffeine ingestion are repeatable.Nutr Res. 32: 78–84. [PubMed] [Google Scholar]