Description:Complete Specification:
The following specification describes and ascertains the nature of this invention and the manner in which it is to be performed:


Field of the invention:
[0001] The present disclosure relates to a control unit and method to determine slip in a drive wheel of a vehicle.

Background of the invention:
[0002] A rider safety is a very important parameter to consider while designing a two-wheeler. As the rider is exposed to the environment, accidents or even falls cause severe injuries or turn fatal. Thus, improving rider safety is paramount and needs to be concentrated on. A loss of rear wheel traction occurs when the rider requests power but due to less friction with the road surface (loose sand, oil patches, wet roads, bad tires etc.), the rear wheel spins freely. This can have two effects: in first, the rear wheel never finds traction and the bike falls in the direction lean (low side). In second, the rear wheel finds sudden traction and the bike moves aggressively in the opposite side of lean like a pendulum and throws the rider away (high side). If these traction loss events can be detected, the power to the wheels can be cut to avoid these events and the bike can find traction.

[0003] According to existing prior art, there exists a system and method for estimating turning circle diameter and traction loss of a vehicle. The system controls the air pressure of the ride air springs of the lift axle based on the vehicle steering angle. It increases the traction automatically in the vehicle during a sever turn. The prior art uses two wheel speed sensors to detect the slip situation at all times. Similarly, another prior art discloses a “Joint Wheel-Slip and Vehicle-Motion Estimation Based on Inertial, GPS, and Wheel-Speed Sensors” by Karl Berntorp. This is for a four-wheeler and discloses about different sensors (GPS, wheel speed sensor and IMU) used for determining the wheel slip and vehicle motion. The paper concentrates on connectivity between and sensors and using the sensors data as an estimator. In yet another prior art, a “tire Modeling and Friction Estimation” by Jacob Svendenius is disclosed. The tire modelling and friction is modelled at different instances of driving such as cornering, cambers, and braking. One of the main inputs for all this is wheel slip information. A feedforward filter on the brake torque that predicts the disturbances on the wheel speed due to the application of the brakes is present. But still this is only during braking and the actual slip is still calculated using sensors on all wheels. In all the above-mentioned prior arts, wheel speed sensors are still used for determining the wheel slip scenario. The current Traction Control (TC) feature uses two wheel speed sensors front and back. If the rear wheel speed is more than the front, after multiple processing steps the event is considered as a wheel slip event.

[0004] According to a prior art US6577944, a traction control system is disclosed. There is provided a method for controlling the driving traction of a wheel on a surface to reduce slippage of the wheel on the surface without the need to monitor the rotational speed of the wheel where the wheel is driven by a power unit. A threshold value of maximum acceptable acceleration for the power unit is established. The rotational speed of the power unit is measured for a first selected time interval. The rotational speed of the power unit is measured for a second selected time interval. The difference between the rotational speed of the power unit in the second time interval and the rotational speed of the power unit in the first time interval is determined. The difference between the rotational speed of the power unit in the second and first time intervals are compared with the established threshold value. If the difference in rotational speed of the power unit is greater than the established threshold value, a corrective action is initiated to reduce the rotational speed of the power unit.

Brief description of the accompanying drawings:
[0005] An embodiment of the disclosure is described with reference to the following accompanying drawings,
[0006] Fig. 1 illustrates a block diagram of a control unit to determine slip in a drive wheel of a vehicle, according to an embodiment of the present invention, and
[0007] Fig. 2 illustrates a method flow diagram for determining slip in the drive wheel of the vehicle, according to the present invention.

Detailed description of the embodiments:
[0008] Fig. 1 illustrates a block diagram of a control unit to determine slip in a drive wheel of a vehicle, according to an embodiment of the present invention. The control unit 110 configured to receive input signals 102 comprising an engine speed, an engine torque, a clutch status, and a front wheel speed from respective sensors, while the vehicle 100 is in motion. The engine speed is determined from crankshaft position sensor, engine torque sensor is derived from the engine speed signal or from an engine torque sensor, the clutch status is determined through clutch switch, the front wheel speed is obtained from the wheel speed sensor. The control unit 110, characterized in that, process the engine speed through a computational module 106, process the input signals 102 and an output signal of the computational module 106 through a Machine Learning (ML) model 108, and determine occurrence of slip in the drive wheel 112 of the vehicle 100 based on output of the ML model 108.

[0009] According to an embodiment of the present invention, the computational module 106 processes the engine speed signal through a Discreet Fourier Transform (DFT) operation. The output of the DFT operation is a real part, an imaginary part, and a phase part.

[0010] According to the present invention, the ML model 108 is configured to estimate any one of a rear wheel speed and a wheel slip. While the ML model 108 is configured to estimate the rear wheel speed, the control unit 110 calculates the wheel slip using the difference between the front wheel speed and the estimated rear wheel speed. Once the wheel slip value is obtained, the control unit 110 compares the value with a threshold value to determine occurrence of wheel slip.

[0011] According to an embodiment of the present invention, the ML model 108 is trained using Recurrent Neural Network using dataset of input signals 102, but not limited to the same.

[0012] According to the present invention, the threshold value of the wheel slip is corrected by a correction factor which is selected based on vehicle speed. In other words, there exists a map or table which comprises vehicle speed and corresponding correction factor, which is applied to the threshold value. Thus the control unit 110 uses a dynamic threshold value instead of static/fixed threshold value.

[0013] According to an embodiment of the present invention, the control unit 110 is applicable for vehicle 100 such as a two-wheeler vehicle such as motorcycle, scooter, a three wheeler vehicle such as auto-rickshaw, a four-wheeler vehicle such as cars and other vehicles 100. Specifically, the control unit 110 is applicable for vehicle 100 with or without Anti-lock Braking System (ABS).

[0014] According to an embodiment of the present invention, the control unit 110 configured to adjust torque to eliminate the slip. The torque adjustment is implemented through at least one of an injection control, an ignition control, and an air flow control.

[0015] According to the present invention, the control unit 110 continuously determines slip or initiates the slip determination only after boundary conditions comprising parameters such as engine RPM, engine torque, clutch status are satisfied with respective preset values.

[0016] In accordance to an embodiment of the present invention, the control unit 110 is provided with necessary signal detection, acquisition, and processing circuits. The control unit 110 is the one which comprises input interface, output interfaces having pins or ports, the memory element 104 such as Random Access Memory (RAM) and/or Read Only Memory (ROM), Analog-to-Digital Converter (ADC) and a Digital-to-Analog Convertor (DAC), clocks, timers, counters and at least one processor (capable of implementing machine learning) connected with each other and to other components through communication bus channels. The memory element 104 is pre-stored with logics or instructions or programs or applications or modules/models and/or threshold values/ranges, reference values, predefined/predetermined criteria/conditions, which is/are accessed by the at least one processor as per the defined routines. The internal components of the control unit 110 are not explained for being state of the art, and the same must not be understood in a limiting manner. The control unit 110 may also comprise communication units such as transceivers to communicate through wireless or wired means such as Global System for Mobile Communications (GSM), 3G, 4G, 5G, Wi-Fi, Bluetooth, Ethernet, serial networks, and the like. The control unit 110 is implementable in the form of System-in-Package (SiP) or System-on-Chip (SOC) or any other known types. Examples of control unit 110 comprises but not limited to, microcontroller, microprocessor, microcomputer, etc.

[0017] Further, the processor may be implemented as any or a combination of one or more microchips or integrated circuits interconnected using a parent board, hardwired logic, software stored in the memory element 104 and executed by a microprocessor, firmware, an application specific integrated circuit (ASIC), and/or a field programmable gate array (FPGA). The processor is configured to exchange and manage the processing of various Artificial Intelligence (AI) modules.

[0018] According to the present invention, the control unit 110 is part of at least one of an internal device and an external device. The internal device is at least one Electronic Control Unit (ECU) selected from a group comprising is at least one of an Engine Management System (EMS) control unit, a Tire Pressure Monitoring System (TPMS) control unit, a Telematics Control Unit (TCU) control unit, an Anti-lock Braking System (ABS) control unit, an Electronic Stability Program (ESP) control unit and a combination thereof. The external device is at least one of a cloud based device and a communication device. The external device is connected through a Telematic Control Unit (TCU) of the vehicle 100 through at least one a wired and wireless means known in the art. The communication device corresponds to electronic computing devices which enable a rider or driver or a user to communicate with others such as smartphone, wearable electronics such as smart watch, etc. The cloud based device corresponds to cloud computing architecture having network of servers, databases connected with each other and vehicle 100 for processing of inputs and providing outputs. Thus, the processing is done by any one of the internal device and the external device or both. In case of both, the processing is shared as per the respective loading and capacity of processing.

[0019] According to the present invention, a working of the control unit 110 is explained. Consider a motorcycle is the vehicle 100 which is driven by a rider for a certain distance. During the drive cycle, the control unit 110 continuously receives input signals 102 comprising the engine speed from crankshaft position sensor, engine torque derived from the engine speed or through respective sensor, the front wheel speed from wheel speed sensor and clutch status from the clutch switch. The control unit 110 checks for entry conditions, and if fulfilled, the control unit 110 processes the engine speed through the computational module 106. Once the output of the computational module 106 is obtained, the control unit 110 processes the input signal 102 and the output of the computational module 106 through the ML model 108. The control unit 110 finally determines occurrence of the slip in the drive wheel 112 of the vehicle 100 based on the output of the ML model 108. Once the slip is determined, the control unit 110 performs torque modulation / adjustment / intervention to eliminate the slip.

[0020] According to the present invention, the real time data for the input signals 102 recorded during road trials/testing are considered to train the ML model 108. Further, the trained ML model 108 uses the same input signals 102 for real time determination of the wheel slip. The target is to use the ML model 108 in the control unit 110 of the vehicle and as all the inputs are calculated during the drive cycle. The monitored data is fed as input to the ML model 108 to determine occurrence of the slip.

[0021] Fig. 2 illustrates a method flow diagram for determining slip in the drive wheel of the vehicle, according to the present invention. The method comprises plurality of steps of which a step 202 comprises receiving, by the control unit 110, input signals 102 comprising the engine speed, the engine torque, the clutch status, and the front wheel speed from respective sensors, while the vehicle 100 is in motion. A step 204 comprises processing, by the control unit 110, the engine speed through the computational module 106. A step 206 comprises processing, by the control unit 110, the input signals 102 and the output of the computational module 106 through the ML model 108. A step 208 comprises determining occurrence of slip in the drive wheel 112 of the vehicle 100 based on the output of the ML model 108. The method is performed by the control unit 110.

[0022] According to the step 204, the computational module 106 processes the engine speed signal through the Discreet Fourier Transform (DFT). The output of the DFT is a real part, imaginary part, and the phase part.

[0023] As per the step 206, the ML model 108 is configured for determining output as any one of the rear wheel speed and the wheel slip. While the rear wheel speed is configured to be determined, the ML model 108 calculates the wheel slip using difference of the front wheel speed and the estimated rear wheel speed. Once the wheel slip value is obtained, the method further comprises comparing the value with a threshold value and determining the occurrence of the wheel slip accordingly. According to the present invention, the ML model 108 is trained using Recurrent Neural Network using dataset of input signals 102 but not limited to the same.

[0024] The method comprises adjusting torque to eliminate the slip. The torque adjustment is implemented through at least one of the injection control, the ignition control, and the air flow control.

[0025] According to the present invention, the method is implemented for the vehicle 100 such as the two-wheeler vehicle. However, the method is implementable for other vehicles 100 as mentioned above.

[0026] According to the present invention, the threshold value is corrected by a correction factor which is selected based on vehicle speed. In other words, there exists a map or table which comprises vehicle speed and corresponding correction factor, which is applied to the threshold value. Thus the control unit 110 uses a dynamic threshold value instead of static/fixed threshold value.

[0027] According to the present invention, the control unit 110 is configured/adapted to determine the wheel slip event with the help of crankshaft position sensor (or crankshaft speed sensor) by exploiting the effect of the wheel slip on the crankshaft, thus eliminating the need for wheel speed sensors and the encoder wheel assemblies at the wheels. The engine speed that is read in the control unit 110 is not only a function of the power delivered by the engine but is also indirectly shows the state of the rear wheel. The control unit 110 monitors the crankshaft position signal (or engine speed) to detect traction loss/wheel slip events. The threshold value have the correction factor which is based on vehicle speed. The disadvantage of having a fixed threshold is that the slip varies due different factors and the dynamics involved in motorcycles due to lean etc. The present invention provides wheel-slip detection based on engine parameters.

[0028] It should be understood that embodiments explained in the description above are only illustrative and do not limit the scope of this invention. Many such embodiments and other modifications and changes in the embodiment explained in the description are envisaged. The scope of the invention is only limited by the scope of the claims.
, Claims:We claim:
1. A control unit (110) to determine slip in a drive wheel (112) of a vehicle (100), said control unit (110) configured to:
receive input signals (102) comprising an engine speed, an engine torque, a clutch status, and a front wheel speed from respective sensors, while said vehicle (100) is in motion, characterized in that,
process said engine speed through a computational module (106),
process said input signals (102) and output of said computational module (106) through a Machine Learning (ML) model, and, and
determine occurrence of slip in said drive wheel (112) of said vehicle (100) based on output of said ML model (108).

2. The control unit (110) as claimed in claim 1, wherein said computational module (106) processes said engine speed signal through a Discreet Fourier Transform (DFT).

3. The control unit (110) as claimed in claim 2, wherein output of said DFT operation is a real part, imaginary part, and a phase part.

4. The control unit (110) as claimed in claim 1, wherein said ML model (108) is configured to determine output any one of a rear wheel speed and a wheel slip, wherein while said ML model (108) is trained to estimate a rear wheel speed, said controller calculates a wheel slip using difference of said front wheel speed and said estimated rear wheel speed.

5. The control unit (110) as claimed in claim 1, wherein said ML model (108) is trained using Recurrent Neural Network using dataset of input signals (102).

6. A method for determining slip in a drive wheel (112) of a vehicle (100), said method comprising the steps of:
receiving input signals (102) comprising an engine speed, an engine torque, a clutch status, and a front wheel speed from respective sensors, while said vehicle (100) is in motion, characterized by,
processing said engine speed through a computational module (106),
processing said input signals (102) and output of said computational module (106) through a Machine Learning (ML) model, and
determining occurrence of slip in said drive wheel (112) of said vehicle (100) based on output of said ML model (108).

7. The method as claimed in claim 6, wherein said computational module (106) processes said engine speed signal through a Discreet Fourier Transform (DFT).

8. The method as claimed in claim 7, wherein output of said DFT operation is a real part, imaginary part, and a phase part.

9. The method as claimed in claim 6, wherein said ML model (108) is configured for determining output as any one of a rear wheel speed and a wheel slip, and while said rear wheel speed is configured to be determined, said controller calculates a wheel slip using difference of said front wheel speed and said estimated rear wheel speed.

10. The method as claimed in claim 6, wherein said ML model (108) is trained using Recurrent Neural Network using dataset of input signals (102).