THE PATENTS ACT, 1970 (39 of 1970) & The Patents Rules 2003

COMPLETE SPECIFICATION

(SECTION 10 and Rule 13)

1. Title of the Invention:

A SYSTEM AND METHOD FOR AUTOMATED CALIBRATION

OF AN ENGINE PARAMETER IN A VEHICLE

2. Applicants: a. Name: Bosch Limited

Nationality: INDIA

Address: Post Box No 3000, Hosur Road, Adugodi, Bangalore

- 560030, Karnataka, India b. Name: Robert Bosch GmbH

Nationality: GERMANY

Address: Stuttgart, Feuerbach, Germany

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 invention relates to a system for automated calibration of an engine parameter in a vehicle.

Background of the invention:

[0002] A calibration process has a long lead time, and several iterations are performed to optimize it and bring to 100% maturity. In the process there are also several errors that might be introduced due to the calibration engineer. Overall quality of the data set has to improve. Due to manual calibration techniques there is a data review step that is introduced which adds to the overall timeline of a calibration process.

[0003] A patent literature 201841027905 discloses a device for calibrating an Engine Control Unit (ECU) of a vehicle in a dynamometer. The patent literature provides a device for calibrating the ECU of the vehicle in a dynamometer. The device comprises a housing. Further, a plurality of actuators enclosed in the housing. An interface module is also provided in the housing. The interface module is adapted to connect the plurality of actuators, the ECU, and the dynamometer with a controller. Also, the dynamometer is controlled by respective control module. The device automates end-to-end calibration of the ECU. The automation of the calibration, measurement, and verification activities for the ECU of the vehicle without iterations results in high reproducibility and less time and development cost.

Brief description of the accompanying drawings:

[0004] An embodiment of the disclosure is described with reference to the following accompanying drawing,

[0005] Fig. 1 illustrates a block diagram of a system for automated calibration of an engine parameter in a vehicle, according to an embodiment of the present invention, and

[0006] Fig. 2 illustrates a method for automated calibration of the engine parameter in the vehicle, according to the present invention. Detailed description of the embodiments:

[0007] Fig. 1 illustrates a block diagram of a system for automated calibration of an engine parameter in a vehicle, according to an embodiment of the present invention. The system 100 comprises a device 102 interfaced with an Engine Control Unit (ECU) 114 of the vehicle 112 through a communication interface 108 for calibration. The device 102 configured to receive input dataset from a computing unit 106 comprising operating variables of an engine of the vehicle 112. The operating variables comprises but not limited to a throttle position, an engine speed, an air/fuel ratio, an engine temperature, an exhaust temperature, and the like, characterized in that, the device 102 comprises a calibration module 104 to calibrate the engine parameter. The calibration module 104 configured to, process the input dataset based on the engine parameter selected for calibration and calibrates the engine parameter. The calibrated engine parameter is then stored in a memory element (not shown) of the ECU 114. The calibration module 104 is selected from a model-based module and a rule-based module corresponding to the engine parameter selected for calibration. The calibration module 104 iterates the calibration until the calibrated engine parameter satisfies a preset criteria.

[0008] The device 102 comprises a controller (not shown) along with the memory element such as Random Access Memory (RAM) and/or Read Only Memory (ROM), Analog-to-Digital Converter (ADC) and vice-versa Digital-to- Analog Convertor (DAC), clocks, timers and at least one processor (capable of implementing machine learning) connected with the each other and to other components through communication bus channels. The memory element is prestored with logics or instructions or programs or applications, preset criteria, which is accessed by the processor as per the defined routines. The internal components of the controller are not explained for being state of the art, and the same must not be understood in a limiting manner. The controller may also comprise communication units to communicate with a server or cloud 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 Ecu 114 of the vehicle 112 is similar to the controller.

[0009] In accordance to an embodiment of the present invention, the device 102 is at least one selected from a group comprising a cloud server, a portable computer, the computing unit 106 itself, a smartphone, and a workstation and the like. The computing unit 106 itself is possible to be used as the device 102 without any external devices 102 such as cloud server. Further, the computing unit 106 refers to computing device used to access the cloud server and the ECU 114 of the vehicle 112 in a setup 110 through the communication interface 108. Further, the engine parameter for calibration are selected from but not limited to throttle position, an ignition angle, an injection quantity, an engine position, a combustion phase, an ambient temperature, a drive mode, an emission control, and an exhaust temperature, and the like.

[0010] In accordance to an embodiment of the present invention, the vehicle 112 is preferably a two-wheeler such as a motorcycle, a scooter, a moped, etc. The calibration module 104 is applicable for the two-wheeler and also equally adaptable to be used for three-wheelers such as auto-rickshaws, four wheelers such as cars and the other existing and new vehicles 112 (even snow mobiles) where the required calibration is required.

[0011] In accordance to an embodiment of the present invention, the model-based module takes input based on the engine parameter to be calibrated and outputs calibrated engine parameter. The model-based module is generated using Machine Learning based regression analysis. In an embodiment, the calibration module 104 configured to, allow a manual correction/adjustment of the calibrated engine parameter by the calibration engineer. The manual correction is learnt by the modelbased module and rule-based module, for future calibration of the engine parameter for similar vehicle 112. [0012] According to the present invention, a working of the system 100 is envisaged without limiting to the same. Consider the vehicle 112 as motorcycle set in the setup 110 comprising a dynamometer. The setup 110 enables automated calibration of the engine parameter of the vehicle 112 through the device 102 which is the cloud server. The dynamometer i.e. either an engine dynamometer or a chassis dynamometer. The setup 110 further comprises plurality of sensors such as Manifold Air Pressure (MAP) sensor, a Throttle Position Sensor (TPS), a Crank and/or a Cam position and speed sensor, a coolant temperature sensor, an air temperature sensor, an Exhaust Oxygen (Lambda) sensor and the like. The setup 110 still further comprises a dyno controller to operate the dynamometer, through the communication interface 108 such as a Controller Area Network (CAN) interface to enable communication between the device 102 and the dyno controller, the ECU 114, the actuators, the sensors, and the like. Further, the actuators are selected from a group comprising a throttle actuator, a brake actuator, a gear actuator, a clutch actuator, a fuel injection module, a blower, and the like. Each actuator comprises a control unit having a microcontroller flashed with actuator program. Considering the communication interface 108 to be a CAN transceiver, the CAN transceiver transmits and receives the CAN message from the CAN bus. A stepper motor or other motor or other electro-mechanical assembly is used in the actuator. A driver circuit for the stepper motor is provided which is controlled by the control unit.

[0013] In continuation to above setup 110, assume that the objective is to detect the engine position via teeth movement in the working cycle and differentiate between intake stroke and power stroke. Based on the objective, the engine parameter to be calibrated is the engine position/phase, which is set in the calibration module 104. The calibration process is then to identify the region of interest where the ECU 114 should assess the MAP sensor signal with respect to crank wheel teeth for differentiating power and intake strokes. The input dataset of engine operating parameters are fed to the device 102 through a measurement file, which undergoes plausibility check by the calibration module 104. Once the requirement is set in the calibration module 104, the process is automatically taken forward in the device 102 for calibration. The calibration module 104 extracts required data from the input dataset needed for the calibration of the engine parameter after the plausibility check is successful, such as trigger wheel configuration, signals from MAP sensor, crankshaft sensor, etc. The calibration module 104 then processes the extracted input data, in this case the signals from the crankshaft sensor, the MAP sensor and uses rule-based module for calibration. In other words, the calibration module 104 replicates an operator/engineer’s data analysis through rule-based module. The calibration module 104 detects gap in the trigger wheel and falling edge of crankshaft sensor signal at zero cross over. The calibration module 104 sweeps the entire working cycle of the engine with different regions (window length), size, start and end angles/points, followed by calculates the difference between minimum and maximum pressures in each region. The preset criteria for this engine parameter is set as pressure difference to be greater than threshold pressure. If the criteria is not met, the calibration module 104 keeps iterating the steps of sweeping the working cycle for different region followed by calculating the pressure difference and then checking the preset criteria. Once the preset criteria is satisfied/met, the calibration module 104 sets the value in the ECU 114. In a further step, the calibrated engine parameter is manually reviewed and if needed is corrected based on experience by an operator (calibration engineer). If corrected, the calibration module 104 learns the correction for the specific engine parameter and adapts the same in future calibration of the same engine parameter for the similar vehicle 112. An Original Equipment Manufacturer (OEM) or calibration engineer or operator is provided with a working cycle to run on the vehicle 112 for automated run. The analysis is done by the calibration module 104 (or scripts) during the vehicle run (real-time or online). The calibrated data is written/stored back in the ECU 114 of the vehicle 112. Th above example is provided using rule-based module, however similar processes exists for model-based module as well and for different engine parameters. [0014] Fig. 2 illustrates a method for automated calibration of the engine parameter in the vehicle, according to the present invention. The system 100 comprises the device 102 interfaced with the Engine Control Unit (ECU) 114 of the vehicle 112 for calibration through the communication interface 108. The method comprises plurality of steps of which a step 202 comprises receiving input dataset from the computing device 102 comprising operating variables of the engine. The method is characterized by, a step 204 which comprises processing the input dataset based on the engine parameter selected for calibration using the calibration module 104, and calibrating the engine parameter. The calibration module 104 is selected from the model-based module and the rule-based module corresponding to the engine parameter selected for calibration. A step 206 comprises iterating the calibration until the calibrated engine parameter satisfies the preset criteria.

[0015] According to the present invention, the model-based module takes input based on the engine parameter to be calibrated and outputs calibrated engine parameter. The model-based module is generated using Machine Learning based regression analysis. The method further comprises method further comprises, allowing/enabling the manual correction/adjustment of the calibrated engine parameter, and learning the manual correction by the model-based module and rulebased module, for future calibration of the engine parameter. The method also comprises performing plausibility check on the input dataset, and extracting required data from the input data needed for the calibration of the engine parameter, after successful plausibility check. The step of plausibility check is done before processing through any one of the rule-based module or model-based module.

[0016] Further, the engine parameter for calibration are selected from but not limited to the throttle position, the ignition angle, the injection quantity, the engine position, the combustion phase, the ambient temperature, the drive mode, the emission control, and the exhaust temperature. The list of engine parameters are not limited to above but contains other parameters known in the art. [0017] According the present invention, a self-calibrating device 102 based on Artificial Intelligence/ Machine Learning (AI/ML) based learning and scripts is provided. The calibration module 104 provides freedom to the calibration engineer/operator after completion of the calibration to change certain parameters based on the dynamics of the vehicle 112, such as drivability, specific emission requirements and the like. Once the changes are made these changes are learnt inside the calibration module 104 (scripts) for specific calibration parameters and are used to improve/perfect itself. The learning is based on an AI/ML techniques. The solution reduces the calibration time by optimizing the data analysis time, reduces calibration iterations, reduces efforts for measurement analysis and calibration review, and improves the calibration quality.

[0018] 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.