VGT position parameter self-learning method

Abstract

The invention discloses a VGT position parameter self-learning method, and relates to the technical field of valve control, and the method comprises the steps: carrying out the motor control through calibration and linearization, controlling a valve to swing back and forth at a limit position, and recording the corresponding voltage of each group of limit position sensors. The change of the valve angle is recorded, and the corresponding relation between the voltage and the angle is established, so that the characteristic of each motor can be identified in the process, an accurate calibration curve is generated, and meanwhile, the individual difference of the motors can be eliminated, so that each motor has consistent performance under the same voltage; according to the calibrated system, angle fluctuation caused by motor characteristic difference can be reduced, the stability and reliability of the control system are improved, through software calibration and linearization, dependence on an expensive high-precision sensor can be reduced to a certain extent, the hardware cost of the system is reduced, and the calibration process can be carried out when the system is installed or regularly carried out.

Description

Technical Field

[0001] The invention relates to the technical field of valve control, and in particular to a VGT position parameter self-learning method. Background Art

[0002] The VGT valve is a key component in the turbocharger system. Traditional valve controllers can only adjust the angle by visual observation and manual testing, which results in large errors and cannot achieve precise control of the valve angle. In the early days, valve controllers mainly relied on manual visual observation and manual testing to adjust the angle. This method completely relied on the operator's experience and subjective judgment, which not only resulted in large errors, but also made it difficult to achieve precise valve angle control. Since the valve could not be accurately adjusted to the appropriate position, the turbocharger system was inefficient and could not fully exert its due performance, which also increased the system's energy consumption and losses.

[0003] With the development of technology, position sensors are used in the existing technology to achieve precise control of valves. Although the control accuracy is improved to a certain extent, it also brings new problems. On the one hand, the high-precision position sensors are expensive, which greatly increases the overall cost of the turbocharger system and affects the competitiveness of the product in the market. On the other hand, despite the use of position sensors, the control accuracy still cannot meet the increasing industrial needs and complex and changing working environment requirements;

[0004] In practical applications, turbocharger systems need to cope with a variety of working conditions, such as different ambient temperatures, long-term operation of motors, and constantly changing system loads. However, existing valve control technology shows obvious deficiencies in the face of these complex situations. Under different ambient temperatures, the performance of the valve will be greatly affected. Traditional technology cannot automatically adjust the control parameters according to temperature changes, resulting in unstable control accuracy. The motor will experience performance degradation during long-term operation, and existing technology cannot effectively compensate for motor aging, thereby affecting the accuracy of valve control. In addition, when the system load changes, it is difficult for existing control technology to quickly and accurately adjust the valve angle to adapt to the new working state. For this reason, we propose a VGT position parameter self-learning method. Summary of the invention

[0005] The purpose of the present invention is to provide a VGT position parameter self-learning method.

[0006] In order to solve the problems raised in the above background technology, the present invention provides the following technical solutions: a VGT position parameter self-learning method, including using calibration and linearization to control the motor, controlling the valve to swing back and forth at the extreme position, and recording the corresponding voltage of each group of extreme position sensors, the VGT position parameter self-learning method has the following specific steps:

[0007] Step 1: Initial calibration, establish a dynamic environmental adaptability compensation mechanism, gradually increase the duty cycle of the motor voltage, and record the actual angle of the valve at each voltage to generate a voltage-angle curve. At the same time, start the calibration mode and set the voltage duty cycle signal source to a zero output state;

[0008] Step 2: Data storage: The calibration data is stored in the controller memory for use by the subsequent control algorithm, and the motor aging compensation strategy is introduced. Assuming that the motor has been in use for t, the motor performance is established based on the historical operation data of the motor.

[0009] Step 3: Linearization algorithm, based on the calibration data, uses piecewise linear interpolation and polynomial fitting methods to calculate the voltage-angle formula, calculates the slope and intercept of the interval straight line segment according to adjacent data points, and establishes a mathematical model of voltage and angle;

[0010] Step 4: Control algorithm adjustment: During the control process, the corresponding voltage value is searched or calculated according to the target angle, and piecewise linear interpolation is selected to divide the voltage-angle curve into several small intervals. In each small interval, a straight line segment is used to approximate the relationship between voltage and angle, and it is output to the motor driver.

[0011] Step 5: Regular calibration, real-time monitoring of the system's operating status parameters, regular calibration and data recording according to the system's operating conditions. During the calibration process, the newly generated data is compared and analyzed with the last calibrated data, and the voltage-angle curve is updated at the same time;

[0012] Step 6: Fuzzy logic optimization step: introduce evaluation indicators, use fuzzy logic algorithm to comprehensively evaluate valve response time, motor current fluctuation and system stability, and dynamically adjust self-learning parameters and strategies based on the evaluation results.

[0013] As a further solution of the present invention: In the step 1, a dynamic environmental adaptability compensation mechanism is established. When the ambient temperature changes in the interval [T1, T2], the voltage-angle curve is dynamically corrected according to the temperature change rate. Assuming the ambient temperature is T and the correction function is f(T), the voltage value V in the corrected voltage-angle formula is adjusted to:

[0014] V'=V+f(T)

[0015] Among them, V is the original voltage value, V' is the corrected voltage value, and the correction function formula is as follows:

[0016] f(T)=k*(T-T0) 2

[0017] Among them, k is a coefficient determined according to experiments, T0 is the reference temperature, and the control accuracy of the system under different environments is controlled at the same time.

[0018] As a further solution of the present invention: in the step one, the VGT system is connected to a dedicated calibration device to start the calibration mode in the main control system in which it is running, and confirm that the system is in a stable initial state. After the system is ready, the voltage duty cycle signal source is set to a zero output state, and at the same time, a high-frequency data acquisition device is used to monitor and record the actual angle change of the valve in real time during the process of increasing the motor voltage.

[0019] As a further solution of the present invention: in the step 2, after completing the initial calibration and generating accurate voltage-angle data, the control starts the data storage program, organizes and encodes the calibration data according to a specific data structure, and writes the structured data into the specified storage area in the memory of the controller in sequence. During the data storage process, a data storage log file is generated, and key information such as the time, data volume, and storage location of each data storage is recorded.

[0020] As a further solution of the present invention: In the step 2, a motor aging compensation strategy is introduced. Assuming that the motor has been in use for a period of time t, a motor performance degradation model is established based on the historical operation data of the motor. When t changes, the coefficients in the voltage-angle formula are adjusted as follows:

[0021] A'=A*g(t)

[0022] Wherein, g(t) is a time-dependent function, A is the coefficient of the original voltage-angle, and A' is the coefficient of the adjusted voltage-angle.

[0023] As a further solution of the present invention: In the step 3, piecewise linear interpolation is selected to divide the voltage-angle curve into several small intervals, and a straight line segment is used in each small interval to represent the relationship between voltage and angle. According to two adjacent data points (voltage value and corresponding angle value), the slope and intercept of each group of interval straight line segments are measured, and the slope and intercept of the straight line segment are calculated. Then, the slope calculation formula of the straight line segment is:

[0024] k=(θ1-θ2) / (V1-V2)

[0025] The intercept calculation formula is as follows:

[0026] b=θ1-k*V1

[0027] Here, the voltages of adjacent data points are assumed to be V1 and V2, and the corresponding angles are θ1 and θ2.

[0028] As a further solution of the present invention: in the step four, during the operation of the control system, the target angle instructions are received in real time from the upper control system and the user input, the target angle includes the valve angle value calculated according to the operating conditions of the engine, the vehicle speed and the load, and a model is established by a linear interpolation method. In the divided voltage-angle interval, the interval where the target angle is located is located, and the corresponding voltage value is calculated according to the linear function relationship of the interval.

[0029] As a further solution of the present invention: in the step five, a time monitoring module is established to record the operating time of the system. At the same time, the operating status parameters of the system are monitored in real time and calibrated. After the calibration is completed, the new calibration data is stored in the controller memory to replace the old calibration data, and the relevant mathematical models and control algorithm parameters are updated.

[0030] As a further solution of the present invention: in the step six, the basic framework of the fuzzy logic system is established, the input variables, output variables and fuzzy rule base of the evaluation index are determined, the value of the evaluation index is fuzzified, and the fuzzy reasoning algorithm is used to deduce the fuzzy value of the output variable according to the input fuzzified evaluation index value and fuzzy rules, and the specific numerical adjustment amount is obtained after processing.

[0031] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:

[0032] 1. The present invention gradually increases the voltage, records the change of the valve angle, and establishes the corresponding relationship between the voltage and the angle, so that the process can identify the characteristics of each motor and generate an accurate calibration curve. At the same time, it can eliminate the individual differences of the motors, so that each motor has consistent performance under the same voltage. The calibrated system can reduce the angle fluctuation caused by the difference in motor characteristics, improve the stability and reliability of the control system, and reduce the dependence on expensive high-precision sensors to a certain extent through software calibration and linearization, and reduce the hardware cost of the system. The calibration process can be performed when the system is installed or regularly, without complex real-time feedback and adjustment, and at the same time simplifying the maintenance of the system;

[0033] 2. The present invention ensures that the system can still accurately control the valve angle when the temperature range [T1, T2] changes through a dynamic environmental adaptability compensation mechanism, and corrects the voltage-angle curve in real time according to the temperature change rate, effectively overcoming the disadvantages of traditional technologies being affected by ambient temperature, and introduces a motor aging compensation strategy. As the motor is used for a longer period of time, the voltage-angle formula coefficient is automatically adjusted to ensure control accuracy after long-term use, thereby achieving adaptive and precise control of the system over motors in different operating stages, greatly improving the system's performance and stability over the entire life cycle, and further improving the system's performance and stability through comprehensive evaluation and dynamic adjustment of key indicators such as valve response time, motor current fluctuation, and system stability. The system can adjust self-learning parameters and strategies in real time according to the evaluation results, so that the system can automatically adapt to different working conditions and operating states, and always maintain the best working state. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Schematic diagram of the VGT position parameter self-learning method in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The specific embodiments of the present invention are further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0036] The present invention provides a VGT position parameter self-learning method, which includes using calibration and linearization to control the motor, controlling the valve to swing back and forth at the limit position, and recording the corresponding voltage of each group of limit position sensors. The specific steps of the VGT position parameter self-learning method are as follows:

[0037] Step 1: Initial calibration, establish a dynamic environmental adaptability compensation mechanism, gradually increase the duty cycle of the motor voltage, and record the actual angle of the valve at each voltage to generate a voltage-angle curve. At the same time, start the calibration mode and set the voltage duty cycle signal source to a zero output state;

[0038] Step 2: Data storage: The calibration data is stored in the controller memory for use by the subsequent control algorithm, and the motor aging compensation strategy is introduced. Assuming that the motor has been in use for t, the motor performance is established based on the historical operation data of the motor.

[0039] Step 3: Linearization algorithm, based on the calibration data, uses piecewise linear interpolation and polynomial fitting methods to calculate the voltage-angle formula, calculates the slope and intercept of the interval straight line segment according to adjacent data points, and establishes a mathematical model of voltage and angle;

[0040] Step 4: Control algorithm adjustment: During the control process, the corresponding voltage value is searched or calculated according to the target angle, and piecewise linear interpolation is selected to divide the voltage-angle curve into several small intervals. In each small interval, a straight line segment is used to approximate the relationship between voltage and angle, and it is output to the motor driver.

[0041] Step 5: Regular calibration, real-time monitoring of the system's operating status parameters, regular calibration and data recording according to the system's operating conditions. During the calibration process, the newly generated data is compared and analyzed with the last calibrated data, and the voltage-angle curve is updated at the same time;

[0042] Step 6: Fuzzy logic optimization step: introduce evaluation indicators, use fuzzy logic algorithm to comprehensively evaluate valve response time, motor current fluctuation and system stability, and dynamically adjust self-learning parameters and strategies based on the evaluation results.

[0043] In one embodiment of the present invention: in step 1, a dynamic environmental adaptability compensation mechanism is established. When the ambient temperature changes in the interval [T1, T2], the voltage-angle curve is dynamically corrected according to the temperature change rate. Assuming the ambient temperature is T and the correction function is f(T), the voltage value V in the corrected voltage-angle formula is adjusted to:

[0044] V'=V+f(T)

[0045] Among them, V is the original voltage value, V' is the corrected voltage value, and the correction function formula is as follows:

[0046] f(T)=k*(T-T0) 2

[0047] Among them, k is a coefficient determined according to experiments, T0 is the reference temperature, and the control accuracy of the system under different environments is controlled at the same time.

[0048] In one embodiment of the present invention: in step one, the VGT system is connected to a dedicated calibration device to start the calibration mode in the main control system in which it is running, and confirm that the system is in a stable initial state. After the system is ready, the voltage duty cycle signal source is set to a zero output state, and a high-frequency data acquisition device is used to monitor and record the actual angle change of the valve in real time during the process of increasing the motor voltage.

[0049] In one embodiment of the present invention: in step two, after completing the initial calibration and generating accurate voltage-angle data, the control starts the data storage program, organizes and encodes the calibration data according to a specific data structure, and writes the structured data into the specified storage area in the controller's memory in sequence. During the data storage process, a data storage log file is generated, and key information such as the time, data volume, and storage location of each data storage is recorded.

[0050] In one embodiment of the present invention, in step 2, a motor aging compensation strategy is introduced. Assuming that the motor has been in use for a period of time t, a motor performance degradation model is established based on the historical operation data of the motor. When t changes, the coefficients in the voltage-angle formula are adjusted as follows:

[0051] A'=A*g(t)

[0052] Wherein, g(t) is a time-dependent function, A is the coefficient of the original voltage-angle, and A' is the coefficient of the adjusted voltage-angle.

[0053] In one embodiment of the present invention: in step 3, piecewise linear interpolation is selected to divide the voltage-angle curve into several small intervals, and a straight line segment is used in each small interval to represent the relationship between voltage and angle. According to two adjacent data points (voltage value and corresponding angle value), the slope and intercept of each group of interval straight line segments are measured, and the slope and intercept of the straight line segment are calculated. Then, the slope calculation formula of the straight line segment is:

[0054] k=(θ1-θ2) / (V1-V2)

[0055] The intercept calculation formula is as follows:

[0056] b=θ1-k*V1

[0057] Here, the voltages of adjacent data points are assumed to be V1 and V2, and the corresponding angles are θ1 and θ2.

[0058] In one embodiment of the present invention: in step four, during the operation of the control system, target angle instructions are received in real time from the upper control system and user input, the target angle includes the valve angle value calculated according to the engine operating conditions, vehicle speed and load, a model is established using a linear interpolation method, the target angle interval is located in the divided voltage-angle interval, and the corresponding voltage value is calculated based on the linear function relationship of the interval.

[0059] In one embodiment of the present invention: in step five, a time monitoring module is established to record the operating time of the system. At the same time, the operating status parameters of the system are monitored in real time and calibrated. After the calibration is completed, the new calibration data is stored in the controller memory to replace the old calibration data, and the relevant mathematical models and control algorithm parameters are updated.

[0060] In one embodiment of the present invention: in step six, the basic framework of the fuzzy logic system is established, the input variables, output variables and fuzzy rule base of the evaluation index are determined, the value of the evaluation index is fuzzified, and the fuzzy reasoning algorithm is used to deduce the fuzzy value of the output variable based on the input fuzzified evaluation index value and fuzzy rules, and the specific numerical adjustment amount is obtained after processing.

[0061] Embodiment 1

[0062] Four groups of cars of the same model but equipped with traditional turbocharging systems were selected as a control group, and another four groups of cars of the same model installed with the VGT position parameter self-learning system of the present invention were selected as an experimental group.

[0063] Prepare professional testing equipment, including high-precision voltage measuring instruments, angle measuring instruments, temperature sensors and data acquisition systems, to record various data during the experiment.

[0064] Different test scenarios were set up, including urban roads, highways, mountain roads, and different ambient temperature ranges (-10°C to 40°C).

[0065] For the experimental group of cars, initial calibration was performed according to the steps in the content of the invention, and the voltage-angle curve data generated by the initial calibration at different ambient temperatures were recorded.

[0066] The experimental and control groups were allowed to drive in different test scenarios under the same starting conditions. During the driving process, the following data were monitored and recorded in real time:

[0067] Experimental group: motor voltage, valve angle, ambient temperature, vehicle speed, engine operating conditions, motor current fluctuation, valve response time, and system stability related parameters.

[0068] Control group: Similar parameters were recorded using traditional methods. However, as the traditional system could not accurately measure some key data, only available performance data could be recorded, including vehicle speed fluctuations and fuel consumption.

[0069] Every 180 days (or every 5,000 kilometers), the experimental group of cars are calibrated regularly, the newly generated data is compared with the data from the last calibration, and the system parameters are updated.

[0070] Performance at different ambient temperatures:

[0071] In low temperature environments, the VGT system of the experimental group of cars can quickly adjust parameters through a dynamic environmental adaptability compensation mechanism, allowing the engine to enter normal working conditions more quickly after a cold start, and the turbine response time is significantly shortened. In a -5°C environment, the time from starting the turbine of the experimental group of cars to reaching normal boost pressure is about 30% shorter than that of the control group.

[0072] In a high temperature environment, the system of the experimental group of cars can still maintain stable performance. By correcting the voltage-angle curve to ensure the accuracy of valve control, when driving in a high temperature environment of 40°C, the engine power output fluctuation of the experimental group of cars is smaller than that of the control group, and the fuel consumption is also relatively reduced by about 8%;

[0073] As the mileage increases, the motor aging compensation strategy of the experimental group of cars begins to work. After 50,000 kilometers of driving, compared with the initial state, the valve control accuracy of the experimental group of cars has hardly decreased. However, since the control group of cars does not have the motor aging compensation function, the valve response time is significantly prolonged after the same mileage, and the engine power output is also weakened.

[0074] By analyzing the data of the experimental group of cars in different road scenarios, it was found that they can respond to throttle changes more quickly in congested urban roads, reducing the sense of frustration during starting and acceleration. When driving on highways, they can automatically adjust the valve angle according to vehicle speed and load to keep the engine in the best working state, and fuel economy is significantly improved. On the same highway test section, the average fuel consumption of the experimental group of cars was about 10% lower than that of the control group.

[0075] Embodiment 2

[0076] Two industrial generators of the same model were selected, one of which was equipped with a traditional turbocharger system as a control group, and the other was equipped with the VGT position parameter self-learning system of the present invention as an experimental group.

[0077] Various sensors are installed on the generator's air intake and exhaust pipes to monitor parameters such as pressure, temperature, and flow. Voltage and angle measuring devices are also installed on the motor and valve.

[0078] Different load change situations were simulated, including a step increase and a rapid switch from a low load (30% rated power) to a high load (100% rated power).

[0079] The experimental group generators were initially calibrated, a complete voltage-angle relationship model was established, and the data storage and motor aging monitoring functions were started.

[0080] Two generators were started simultaneously and operated under different load conditions while recording the following data:

[0081] Experimental group: parameters of motor voltage, valve angle, ambient temperature, generator output power, motor current fluctuation, valve response time, and system stability.

[0082] Control group: Recorded similar parameters that traditional systems can monitor, including output power fluctuations and fuel consumption.

[0083] Every 200 hours, the generators in the experimental group are regularly calibrated and data updated.

[0084] Load adaptability:

[0085] In the case of rapid load changes, the VGT system of the experimental group generator can quickly adjust the valve angle to adapt to the new working conditions. When the load suddenly increases from 50% to 80%, the response time of the experimental group generator is only about 50% of that of the control group, and it can stabilize the output power in a shorter time.

[0086] Through real-time adjustment of the voltage-angle curve, the fuel consumption rate of the experimental group's generator under different loads was significantly reduced. When running at high load, the fuel consumption of the experimental group was reduced by about 15% compared with the control group.

[0087] After a long period of operation, the system stability of the experimental group generator was significantly better than that of the control group. Through the fuzzy logic optimization steps, the experimental group system was able to automatically adjust the parameters, reducing the motor current fluctuation and valve vibration. After 1000 hours of operation, the key components such as the motor and valve were inspected and it was found that the degree of wear of the experimental group was significantly lower than that of the control group.

[0088] Due to the ability to precisely control the valve angle, the power generation efficiency of the experimental group's generator was significantly improved. Under the same input energy conditions, the output electrical energy of the experimental group increased by about 10% compared with the control group, greatly improving energy utilization efficiency.

[0089] The above two groups of embodiments show that the high reliability and stability of the system reduce the number of repairs and the need to replace parts due to failures and performance degradation, while extending the service life of key components, reducing maintenance costs and indirect losses caused by downtime, while improving the use efficiency and economic benefits of the equipment.

[0090] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. For those skilled in the art, various changes, modifications, substitutions and variations of these embodiments are made without departing from the principles and spirit of the present invention, and still fall within the scope of protection of the present invention.

[0091] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0092] The above contents are merely examples and explanations of the present invention. Various modifications or additions to the specific embodiments described or replacements in similar ways by technicians in the technical field shall fall within the protection scope of the present invention as long as they do not deviate from the invention or exceed the scope defined by the claims.

[0093] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A VGT position parameter self-learning method, including using calibration and linearization to control the motor, controlling the valve to swing back and forth at the extreme position, and recording the corresponding voltage of each group of extreme position sensors, characterized in that: The specific steps of the VGT position parameter self-learning method are as follows: Step 1: Initial calibration, establish a dynamic environmental adaptability compensation mechanism, gradually increase the duty cycle of the motor voltage, and record the actual angle of the valve at each voltage to generate a voltage-angle curve; Step 2: Data storage: The calibration data is stored in the controller memory for use by the subsequent control algorithm, and the motor aging compensation strategy is introduced. Assuming that the motor has been in use for t, the motor performance is established based on the historical operation data of the motor. Step 3: Linearization algorithm, based on calibration data, uses linear interpolation and polynomial fitting methods to calculate the voltage-angle formula and establish a mathematical model of voltage and angle; Step 4: Control algorithm adjustment: During the control process, the corresponding voltage value is searched or calculated according to the target angle and output to the motor driver; Step 5: Regular calibration: perform regular calibration according to the system operation status and update the voltage-angle curve at the same time; Step 6: Fuzzy logic optimization step: introduce evaluation indicators, use fuzzy logic algorithm to comprehensively evaluate valve response time, motor current fluctuation and system stability, and dynamically adjust self-learning parameters and strategies based on the evaluation results.

2. A VGT position parameter self-learning method according to claim 1, characterized in that: In the step 1, a dynamic environmental adaptability compensation mechanism is established. When the ambient temperature changes in the interval [T1, T2], the voltage-angle curve is dynamically corrected according to the temperature change rate. Assuming the ambient temperature is T and the correction function is f(T), the voltage value V in the corrected voltage-angle formula is adjusted to: V'=V+f(T) Among them, V is the original voltage value, V' is the corrected voltage value, and the correction function formula is as follows: f(T)=k*(T-T0) 2 Among them, k is a coefficient determined according to experiments, T0 is the reference temperature, and the control accuracy of the system under different environments is controlled at the same time.

3. A VGT position parameter self-learning method according to claim 1, characterized in that: In the step 1, the VGT system is connected to a dedicated calibration device to start the calibration mode in the main control system in which it is running, and confirm that the system is in a stable initial state. After the system is ready, the voltage duty cycle signal source is set to a zero output state, and a high-frequency data acquisition device is used to monitor and record the actual angle change of the valve in real time during the process of increasing the motor voltage.

4. A VGT position parameter self-learning method according to claim 1, characterized in that: In the step 2, after completing the initial calibration and generating accurate voltage-angle data, the control starts the data storage program, organizes and encodes the calibration data according to a specific data structure, and writes the structured data into the specified storage area in the controller's memory in sequence. During the data storage process, a data storage log file is generated, and key information such as the time, data volume, and storage location of each data storage is recorded.

5. A VGT position parameter self-learning method according to claim 1, characterized in that: In step 2, a motor aging compensation strategy is introduced. Assuming that the motor has been in use for t, a motor performance degradation model is established based on the historical operation data of the motor. When t changes, the coefficients in the voltage-angle formula are adjusted as follows: A'=A*g(t) Wherein, g(t) is a time-dependent function, A is the coefficient of the original voltage-angle, and A' is the coefficient of the adjusted voltage-angle.

6. A VGT position parameter self-learning method according to claim 1, characterized in that: In the step 3, piecewise linear interpolation is selected to divide the voltage-angle curve into several small intervals. A straight line segment is used in each small interval to represent the relationship between voltage and angle. The slope and intercept of the straight line segment in each interval are measured according to two adjacent data points (voltage value and corresponding angle value), and the slope and intercept of the straight line segment are calculated. The slope calculation formula of the straight line segment is: k=(θ1-θ2) / (V1-V2) The intercept calculation formula is as follows: b=θ1-k*V1 Here, the voltages of adjacent data points are assumed to be V1 and V2, and the corresponding angles are θ1 and θ2.

7. A VGT position parameter self-learning method according to claim 1, characterized in that: In step four, during the operation of the control system, the target angle instructions are received in real time from the upper control system and the user input, the target angle includes the valve angle value calculated according to the engine operating conditions, vehicle speed and load, and a model is established using the linear interpolation method. In the divided voltage-angle interval, the interval where the target angle is located is located, and the corresponding voltage value is calculated based on the linear function relationship of the interval.

8. A VGT position parameter self-learning method according to claim 1, characterized in that: In step five, a time monitoring module is established to record the operating time of the system. At the same time, the operating status parameters of the system are monitored in real time and calibrated. After the calibration is completed, the new calibration data is stored in the controller memory to replace the old calibration data, and the relevant mathematical models and control algorithm parameters are updated.

9. A VGT position parameter self-learning method according to claim 1, characterized in that: In the step six, the basic framework of the fuzzy logic system is established, the input variables, output variables and fuzzy rule base of the evaluation index are determined, the value of the evaluation index is fuzzified, and the fuzzy reasoning algorithm is used to deduce the fuzzy value of the output variable based on the input fuzzified evaluation index value and fuzzy rules, and the specific numerical adjustment amount is obtained after processing.

Images