Motor control optimization method and system for vehicle

Abstract

The invention discloses a motor control optimization method and system for a vehicle, and the method comprises the steps: collecting the vehicle data of a whole vehicle through a data collection module, carrying out the real-time collection and dynamic analysis of the vehicle data, and obtaining the complexity of the vehicle data; the method comprises the following steps: analyzing a boundary threshold value of data change related to motor control in combination with the complexity of a data acquisition state, analyzing motor parameters through vehicle data to obtain an interference evaluation boundary, and analyzing an adjustable range boundary of motor direct control parameters in combination with the boundary threshold value; accuracy of analysis of related data of the motor is increased through dynamic analysis of the collection state of vehicle data, the range of motor control optimization is more reasonable, finally, self-adaptive optimization control of motor control is carried out, accuracy of analysis of a self-adaptive control optimization algorithm along with changes of the vehicle operation environment is greatly improved, and the system performance is improved. And thus, the motor control system can be controlled and optimized more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and in particular to a motor control optimization method and system for a vehicle. Background Art

[0002] The vehicle motor controller is the nerve center connecting the motor and the battery. It is used to adjust the performance of the vehicle. By receiving the driver's instructions, it can achieve precise control of the motor's speed, torque, direction and other parameters. As the load and environmental conditions change continuously during vehicle operation, the motor control optimization algorithm processes a large amount of data to adjust and optimize the motor parameters in real time and make quick decisions. For example, in the prior art, the adaptive control algorithm improves the motor performance by improving the vehicle's control algorithm and system design, and can adjust the motor parameters in real time to adapt to complex changes. However, the control accuracy of the adaptive control algorithm is affected by the quality and state of vehicle data acquisition, such as the amount of vehicle data and data errors acquired in real time. When the battery is insufficient or the road conditions are bad, sensor acquisition fails, resulting in a huge change in the amount of vehicle data and increased errors. The adaptive control optimization algorithm is based on low-quality vehicle data from faulty sensors, which leads to misjudgment and over-optimization of the optimization algorithm. In order to improve the optimization accuracy and system stability of the adaptive control optimization algorithm, so that the vehicle can correspond to the corresponding control optimization degree under different levels of complexity, the present invention proposes a motor control optimization method and system for a vehicle. Summary of the invention

[0003] In order to solve the above problems, that is, to solve the problems mentioned in the background technology, the present invention provides a motor control optimization method and system for vehicles. First, the vehicle data collection situation is dynamically analyzed to obtain the real-time dynamic increase in complexity of the vehicle data. The boundary threshold of motor control and data change is analyzed in combination with the analysis of the complexity of the data collection state. The motor parameters are analyzed through the vehicle data. Then, the error analysis is performed based on the vehicle data to obtain the interference assessment boundary. The interference assessment boundary is used to represent the correction of the vehicle data collection error. In combination with the boundary threshold, the adjustable range of the motor direct control parameter is analyzed. The fit of the motor data is increased through step-by-step analysis, so that the range of motor control optimization is more reasonable. When the vehicle data changes complexly, the real-time increase in complexity of the vehicle data, the boundary threshold and the adjustable boundary are used to reduce the dimension of the data. Finally, the motor control is adaptively optimized. The accuracy of the adaptive control optimization algorithm in analyzing changes in the vehicle operating environment is greatly improved, so that the motor control system can be more accurately controlled and optimized.

[0004] The present invention proposes a motor control optimization method for a vehicle, which optimizes the control parameters of the motor controller according to the vehicle data collected by the sensor. The specific analysis process is as follows: Step 1: The vehicle data during the driving process includes all the data generated by the vehicle. The real-time data of the motor operation is obtained through the sensor, and the real-time state of the total vehicle data collection is analyzed to obtain the complexity corresponding to the real-time state change at the i-th moment. ; Step 2: The complexity of vehicle data collection in adaptive scenarios corresponding to different complex environments is different. The motor parameters in the vehicle data that actually affect the motor operation control include direct control parameters and indirect parameters. All motor parameters in the vehicle data of motor operation at different times are recorded as a multidimensional state vector, and the boundary threshold of motor control is obtained through multidimensional state vector analysis; Step 3: Perform error interference analysis on the vehicle data collected by the sensor during motor operation to obtain the interference assessment boundary of data collection, and then calculate the adjustable range boundary of the dynamic drive of the motor's direct controllable range in combination with different adaptive scenarios; Step 4: Determine the particle search range through the adjustable range boundary of the motor drive and the interference assessment boundary of the data acquisition, and optimize the parameters through the particle swarm search algorithm to convert the nonlinear relationship Perform transformation and determine the optimal parameters of the system control algorithm by searching the optimal position; Step 5: Use the neural network algorithm to optimize the control parameters of the motor, build a dynamic model of the vehicle system and its components, and combine the vehicle speed, engine speed, battery state of charge, SOC vehicle status signal and neural network to predict the vehicle speed and torque.

[0005] Specifically, the vehicle data of the motor is the operation collection data of the whole vehicle, which is recorded as historical operation data and real-time data from the time dimension, and the detection indicators corresponding to all the changing parameters in the motor operation adaptive scene are extracted and recorded as represents the number of detection indicators in the vehicle data that change with the adaptive scene, i represents the extraction time in the time dimension, and the vehicle data collected at different times are analyzed in real time. The total number of detection indicators in the vehicle data is N, and the number of detection indicator changes corresponding to the adaptive scenes at different times is recorded as Then, the changes of detection indicators corresponding to each detection time i are analyzed to obtain the indicator change ratio of real-time changes in data collection. , and then calculate the complexity of real-time changes in vehicle data corresponding to different motor adaptive scenarios based on the changes in indicators , calculate the ratio of the change in detection index data , , ,in , and They represent the change values ​​of the same detection indicator in the adaptive scenario at the i-th moment and the detection indicator at the i-1th moment, respectively. .

[0006] Specifically, in the step 2, the number of parameters of the motor parameters in different adaptive scenarios changes dynamically, and the corresponding adjustment range changes accordingly. The characteristics of the dynamic change boundary of the data related to the motor are dynamically analyzed according to the historical operation data in the vehicle data to obtain the boundary threshold of the adaptive scenario. The number of indirect parameters related to the motor corresponding to the change of the detection index at the i-th moment is recorded as , the number of changes in the detection index of the motor's direct control parameter is recorded as , the complexity is According to the analysis of the boundary control equation, a point set is obtained, which includes the control data of the motor parameters. Then, the elliptic partial differential equation of the dynamic boundary is established according to the point set, and the extreme value of the elliptic differential equation is analyzed with the point set as the value range. Then, the boundary threshold is calculated according to the extreme value. , the equation is as follows: in, is the elliptic function of the dynamic boundary characteristics, is the auxiliary variable, that is, the complexity of data changes at the i-th moment, is the time variation function obtained based on historical data, is the change function of the corresponding feature of the dynamic boundary, and It is obtained based on the historical data of motor operation, and then the extreme value is solved by the elliptic partial differential equation, and the boundary threshold is obtained by using the extreme value analysis.

[0007] Specifically, in step three, the interference assessment boundary is obtained by performing error assessment on the vehicle data collected by the sensor. In an adaptive scenario, the sensor collects the operation data of the vehicle. The transmission signals of different sensors affect each other in the same adaptive scenario. The vehicle data collected by all sensors are analyzed in layers. Layer The probability that sensors are assigned to the same group follows a quadratic distribution, , then perform error analysis on the sensor data based on the binomial distribution, calculate the confidence interval of the data, determine the confidence level of the vehicle data, and finally calculate the interference assessment boundary of the error .

[0008] Furthermore, as the vehicle operating environment and motor operating parameters change, the most adaptive control parameters of the motor change, and the adjustable range boundaries of the dynamic drive corresponding to different adaptive scenarios of the motor operation are calculated. The control range of the direct control parameters of the motor operation control is obtained by training the historical operation data with the neural network algorithm. The input vector of the system is The output is a q-dimensional vector ,at the same time and The relationship is , determine the use of neural function Approaching the boundary threshold , is the corresponding point value of the interference assessment boundary, To adapt to the data change dimension in the scene, the adjustable range boundary is , satisfying the following performance indicator function: .

[0009] Furthermore, within the adjustable range of the motor The direct control parameters of the motor are further optimized by using the control strategy of the particle swarm algorithm in the neural network system. The particle population is described as , there are The particle is located in the search space, and the objective function is calculated to obtain the The individual extreme value and group extreme value of each particle are denoted as and , , According to the principle that each particle compares its own fitness value with the individual extreme value and the group extreme value after each update, it is continuously updated to determine the optimal fitness position of the group and the individual.

[0010] The direct control parameters of the motor include speed and torque. During the optimization process of the motor control parameters, the vehicle data of the entire vehicle is dynamically analyzed, and then the control parameters of the motor are optimized based on the particle swarm algorithm in the neural network algorithm.

[0011] The present invention also proposes a motor control optimization system for a vehicle. The system includes a control module, a data acquisition module, a boundary analysis module, a parameter optimization module, and a dynamic adaptive module. The control module is the core of the algorithm. It realizes intelligent control of the motor by sending different control signals to the vehicle's motor and coordinates the joint control of various modules in the vehicle. The data acquisition module includes a speed sensor, a pressure sensor, a humidity sensor, and a temperature sensor. It collects the current signal of the motor under different adaptive scenarios, and then converts the different signals into the form of vehicle data for storage. The boundary analysis module, the dynamic adaptive module, and the parameter optimization module optimize and analyze the data of the motor operation.

[0012] The beneficial effects of the present invention are: 1. In the present invention, a neural network algorithm is used to intelligently control the motor parameters, so that the motor can adapt to the environment during operation, and the vehicle motor can dynamically adjust the motor control parameters according to the real-time status and driving environment to achieve more efficient and stable power output. When operating in a complex environment, the various subsystems can be coordinated to improve the efficiency and stability of the system.

[0013] 2. The present invention analyzes the vehicle data of the whole vehicle with the motor running. When the vehicle load and the motor operating environment change, the optimal control parameters of the motor also change accordingly. Although the control parameters can be optimized by intelligent algorithms in the prior art, the analysis algorithm is restricted by data quality. When the operating environment changes complexly, the amount of vehicle data increases. The adaptive optimization algorithm needs to process a large amount of data and perform complex calculations to achieve the optimization parameters, resulting in more obvious system delays, affecting the vehicle's power performance and response speed. The present invention analyzes the real-time status of the collection and update of the vehicle data of the whole vehicle to obtain the complexity of data changes. When the vehicle operation scenario is complex, the number of data items updated in real time by the vehicle increases, and the complexity of data changes increases. Combined with the analysis of the complexity of the data collection status, the boundary threshold of motor control and data changes is analyzed. According to the parameter changes in the vehicle data with the degree of correlation with the motor, the changes in the entire vehicle data are analyzed to obtain the boundary threshold of the motor in different adaptive scenarios. In this process, not only the real-time performance of the data in the adaptive process is improved, but also the efficiency of the motor intelligent control is improved.

[0014] 3. The complexity and boundary threshold of the data are obtained through the collection and monitoring of the vehicle data. The motor parameters are analyzed through the vehicle data. The interference assessment boundary is obtained by error analysis based on the vehicle data. The correction of the vehicle data collection error is represented by the interference assessment boundary, and the adjustable range of the motor direct control parameters is analyzed in combination with the boundary threshold. The fit of the motor data is increased through step-by-step analysis, making the range of motor control optimization more reasonable. When the vehicle data changes in complexity, the complexity, boundary threshold and adjustable boundary of the vehicle data that increase in real time are used to reduce the dimension of the data. Finally, the adaptive optimization control of the motor control is performed, which greatly improves the accuracy of the adaptive control optimization algorithm in analyzing changes in the vehicle operating environment, so that the motor control system can be more accurately controlled and optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is an analysis flow chart of the present invention; Figure 2 It is the overall module diagram of the present invention. DETAILED DESCRIPTION

[0016] Please refer to the attached Figure 1 To Attachment Figure 2 To describe the preferred embodiments of the present invention. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention. Specific embodiments: With the continuous development of new energy vehicle technology, motor control technology is a key core technology, which is of great significance for improving vehicle performance and realizing intelligent driving. Therefore, improving new energy vehicle motor control and optimizing control decisions are of great significance to motor control; the drive motor controller is mainly composed of a control mainboard, a drive, an interface circuit, a capacitor, a resistor, a sensor, etc., and needs to provide functions such as idling, motor forward rotation, energy recovery, hill-holding, and communication protection. The motor controller responds to the control and sends a feedback signal to realize the control and adjustment of the driving motor operating state; the intelligence and adaptability of motor control are also important directions for future development. When the vehicle load and the motor operating environment change, the optimal control parameters of the motor also change accordingly. The control parameters are optimized by an adaptive analysis algorithm, but the adaptive analysis algorithm is restricted by data quality. When the operating environment changes complexly, the amount of vehicle data increases. The adaptive optimization algorithm needs to process a large amount of data and perform complex calculations to achieve the optimized parameters, resulting in a more obvious system delay, which affects the vehicle's power performance and response speed. In order to improve the efficiency of vehicle motor control, the present invention proposes a motor control optimization method for a vehicle, which optimizes the control parameters of the motor controller according to the vehicle data collected by the sensor. The specific analysis process is as follows: Step 1: The vehicle data during the driving process includes all the data generated by the vehicle. The real-time data of the motor operation is obtained through the sensor, and the real-time state of the total vehicle data collection is analyzed to obtain the complexity corresponding to the real-time state change at the i-th moment. ; As the vehicle operating environment changes, the real-time collection and update status of vehicle data is constantly changing. In complex environments, the number of detection items in vehicle data increases, and the more complex the real-time status changes are; Step 2: The complexity of vehicle data of vehicle operation in different complex environment scenarios is different. The number of data indirectly related to the operation of the vehicle motor changes with the adaptive environment. In order to improve the efficiency of adaptive control and reduce the complex data analysis process, the boundary threshold of vehicle data changes in different adaptive scenarios is analyzed. The motor parameters in the vehicle data that actually affect the motor operation control include direct control parameters and indirect parameters. All motor parameters in the vehicle data related to the motor operation at different times are recorded as a multidimensional state vector, and the boundary threshold of the motor control is obtained through multidimensional state vector analysis; Step 3: Perform error interference analysis on the vehicle data collected by the sensor during the operation of the motor to obtain the interference assessment boundary of the data collection, and then calculate the adjustable range boundary of the dynamic drive of the motor's direct adjustable range in combination with different adaptive scenarios, and the control range of the control parameters of the motor within the range limited by the adjustable boundary; Step 4: Determine the particle search range through the adjustable range boundary of the motor drive and the interference assessment boundary of the data acquisition, and optimize the parameters through the particle swarm search algorithm to convert the nonlinear relationship Perform transformation and determine the optimal parameters of the system control algorithm by searching the optimal position; Step 5: Use the neural network algorithm to optimize the control parameters of the motor, build a dynamic model of the vehicle system and its components, and combine the vehicle speed, engine speed, battery state of charge, SOC vehicle status signal and neural network to predict the future vehicle speed and torque.

[0017] Common motor control algorithms in the prior art also include vector control, direct torque control, field-oriented control, pulse width modulation, sliding mode control, etc. Optimization methods such as adaptive control algorithms and vector control algorithms improve motor performance by improving vehicle control algorithms and system design; The motor controller usually includes components such as the control module, driver and power conversion module. These components work together to convert the direct current of the battery into the alternating current required by the motor and achieve precise control of the motor. The parameter optimization of the motor control algorithm is a complex system process that requires comprehensive consideration of multiple factors such as the characteristics of the motor, application scenarios and control requirements. Neural network control: Use neural networks to learn and adapt to the nonlinear characteristics of the system, and train the neural network to output the optimal control parameters.

[0018] Adaptive control: Automatically adjust control parameters according to the real-time operating status of the system and changes in the external environment. The adaptive control algorithm can cope with various uncertainties and interferences and improve the robustness and stability of the system.

[0019] In electric vehicles, the choice of motor control method depends on the specific needs and application scenarios of the vehicle. For example, in situations where high performance and high efficiency are required, vector control or direct torque control may be selected; while in situations where there are strict requirements on cost, more economical control methods such as voltage control or current control may be selected.

[0020] The vehicle data of the motor is the operation data collected from the whole vehicle, which is recorded as historical operation data and real-time status data from the time dimension. The detection indicators corresponding to all the changing parameters in the motor operation adaptive scene are extracted and recorded as represents the number of detection indicators in the vehicle data that change with the adaptive scene, i represents the extraction time in the time dimension, and the vehicle data collected at different times are analyzed in real time. The total number of detection indicators in the vehicle data is N, and the number of detection indicator changes corresponding to the adaptive scenes at different times is recorded as Then, the changes of detection indicators corresponding to each detection time i are analyzed to obtain the indicator change ratio of real-time changes in data collection. , and then calculate the complexity of real-time changes in vehicle data corresponding to different motor adaptive scenarios based on the changes in indicators , calculate the ratio of the change in detection index data , , ,in , and They represent the change values ​​of the same detection indicator in the adaptive scenario at the i-th moment and the detection indicator at the i-1th moment, respectively. ,Different operating environments correspond to different adaptive scenarios, and ,complexity is used to represent the changes in the data collection ,state brought by the environment.

[0021] In the second step, the number of parameters of the motor parameters in different adaptive scenarios changes dynamically, and the corresponding adjustment range changes accordingly. The characteristics of the dynamic boundary of the motor adjustment range change are dynamically analyzed according to the historical operation data to obtain the boundary threshold of the adaptive scenario. The number of indirect parameters related to the motor corresponding to the current i-th moment is recorded as , the number of changes in the detection index of the motor's direct control parameter is recorded as , the complexity is According to the analysis of the boundary control equation, a point set is obtained, which includes the control data of the motor parameters. Then, the elliptic partial differential equation of the dynamic boundary is established according to the point set, and the extreme value of the elliptic differential equation is analyzed with the point set as the value range. Then, the boundary threshold is calculated according to the extreme value. , the equation is as follows: in, is the elliptic function of the dynamic boundary characteristics, is the auxiliary variable, that is, the complexity of data changes at the i-th moment, is the time variation function obtained based on historical data, is the change function of the corresponding feature of the dynamic boundary, and It is obtained based on the historical data of motor operation, and then the extreme value is solved by the elliptic partial differential equation. The boundary threshold is obtained by using the extreme value analysis. The boundary threshold represents the boundary of the data change related to the motor control when the vehicle data of the whole vehicle changes.

[0022] The control process of different types of motors is the same. For example, permanent magnet synchronous motors and three-phase motors have four parameters for the electrical characteristics of permanent magnet synchronous motors: electronic stator resistance, d-axis inductance, q-axis inductance, and permanent magnet flux. Most control methods usually assume that these parameters are fixed for the sake of simplicity. However, due to manufacturing errors and the influence of temperature and stator current saturation during the operation of permanent magnet synchronous motors, the parameters of permanent magnet synchronous motors will change accordingly and are difficult to measure in real time. The original control method cannot achieve a good control effect. In the step 3, the interference assessment boundary is obtained by performing error assessment on the vehicle data collected by the sensor. In an adaptive scenario, the sensor collects the operation data of the vehicle. The transmission signals of different sensors affect each other in the same adaptive scenario. The vehicle data collected by all sensors are analyzed in layers. Layer The probability that sensors are assigned to the same group follows a quadratic distribution, , then perform error analysis on the sensor data based on the binomial distribution, calculate the confidence interval of the data, determine the confidence level of the vehicle data, and finally calculate the interference assessment boundary of the error .

[0023] As the vehicle operating environment and motor operating parameters change, the most adaptive control parameters of the motor change. The adjustable range boundaries of the dynamic drive corresponding to different adaptive scenarios of the motor operation are calculated. The control range of the direct control parameters of the motor operation control is obtained by training the historical operation data with the neural network algorithm. The input vector of the system is , the output is a q-dimensional vector ,at the same time and The relationship is , determine the use of neural function Approaching the boundary threshold , is the corresponding point value of the interference assessment boundary, To adapt to the data change dimension in the scene, the adjustable range boundary is , satisfying the following performance indicator function: .

[0024] Through the relationship between the dynamic response and mapping of the system control motor, the mapping relationship between the system input and output, the nonlinear relationship and the linear relationship, the state equation describing the system input-output relationship is: By setting an operator , The specific description is As the input of multivariable control, is the intermediate control quantity, assuming that the system input Dimensional vector , and the output is Dimensional vector ,at the same time and The relationship is: ,in Defined as There is a functional relationship at all times and it is a set of vectors that are continuous in the field, specifically described as ,in , known of The derivative is , if the operator Satisfy the following formula This can be obtained from the original system When a system is reversible, the inverse system can be considered as a way to achieve it. Characterizes the length of the pure integral link in the original system.

[0025] is the n-dimensional state vector of the system,

[0026] For the system dimensional input vector,

[0027] For the system dimensional output vector, and Multivariate nonlinear mapping relationships with local resolution.

[0028] In the adjustable range of the motor The direct control parameters of the motor are further optimized by using the control strategy of the particle swarm algorithm in the neural network system. The particle population is described as , there are The particle is located in the search space, and the objective function is calculated to obtain the The individual extreme value and group extreme value of each particle are denoted as and , , According to the principle that each particle compares its own fitness value with the individual extreme value and the group extreme value after each update, it is continuously updated to determine the optimal fitness position of the group and the individual.

[0029] For example, the speed of the motor With location Update to find the speed that best suits the control. , By limiting the speed and position values ​​to the positive and negative maximum values ​​respectively, we can get the formulas for updating speed and position: , in is the inertia weight, For iteration Second-rate, For particle Iteration speed, and is the acceleration factor; and The random number is set to between.

[0030] The intelligent control algorithm of vehicle motor also includes PID control algorithm, fuzzy control algorithm, neural network control algorithm, etc. The mathematical expression formula of PID controller is: in, is the proportionality coefficient, is the integration time constant, is the differential time constant, is the difference between the given input signal and the actual output signal, Among them, the fitness function , They are: Where T is the simulation run time, is the error between the given value and the output value of the system, where , , is the weight coefficient, Adjust the time for the system, is the system rise time, is the maximum number of speed values ​​of the motor during operation, is the maximum value of the rotation speed, is the target speed.

[0031] The direct control parameters of the motor include speed and torque. During the optimization process of the motor control parameters, the vehicle data of the entire vehicle is dynamically analyzed, and then the control parameters of the motor are optimized based on the particle swarm algorithm in the neural network algorithm.

[0032] Motor optimization process: 1. Set the target to be optimized and clarify the optimization target; 2. Establish a motor model. Establish a mathematical model of the motor to describe the characteristics and behavior of the motor, including the relationship between input voltage, current and output speed and torque, and further analyze the control strategy and algorithm of the motor; 3. Select the optimization algorithm: PID control algorithm, fuzzy control algorithm, neural network control algorithm; 4. Evaluate and optimize the performance. The evaluation indicators may include speed control accuracy, steady-state error, dynamic response time, and energy consumption. Further optimization and adjustment will be made based on the evaluation results.

[0033] A motor control optimization system for a vehicle, the system includes a control module, a data acquisition module, a boundary analysis module, a parameter optimization module, and a dynamic adaptive module. The control module is the core of the algorithm, and realizes intelligent motor control by sending different control signals to the motor of the vehicle, and coordinates the joint control of various modules in the vehicle. The subroutine of the data acquisition module collects the motor speed, rotor position, and other information of the motor, and provides data support for the control of the running state of the drive motor. The state detection subroutine determines whether a fault occurs during the operation of the system; the data acquisition module includes a speed sensor, a pressure sensor, a humidity sensor, and a temperature sensor. The sensor is a device for detecting, measuring, and sensing environmental physical quantities, converting physical phenomena into measurable and perceptible electrical signals, and transmitting them to the control system or other equipment for processing. The sensor includes various types, including optical sensors, temperature sensors, pressure sensors, and sound sensors, and each sensor has its detection range, accuracy, and response; The current signal of the motor in different adaptive scenarios is collected, and then the different signals are converted into vehicle data for storage. The boundary analysis module, dynamic adaptive module and parameter optimization module optimize and analyze the motor operation data. In order to optimize the acceleration performance, the motor control system is parameter adjusted and the algorithm is optimized. The key parameters include the current, voltage and torque settings of the motor controller, and the PID parameters in the motor control algorithm. By reasonably adjusting these parameters, the motor can output greater power and torque during the acceleration process, thereby improving the acceleration performance.

[0034] Accelerating performance optimization also requires the participation of the battery management system (BMS), which dynamically adjusts the battery output power according to the battery status and performance characteristics; The field excitation control strategy of the motor controller can also be adopted to change the magnetic field distribution by adjusting the field excitation parameters of the motor control, thereby increasing the torque output of the motor; the motor control system should be matched with the vehicle's transmission system, drive system, etc. to ensure that the motor's power output can be fully utilized. It can also optimize the vehicle's mass distribution, reduce air resistance and other measures to improve the acceleration performance of the vehicle.

[0035] In the process of intelligent control of the motor, the three currents output by the inverter circuit detected by the current sensor are , , , the stator current information after the three-phase stationary coordinate system is converted to the two-phase stationary coordinate system , The stator flux information output by the stator flux observer , At the same time, it serves as the input and output of the torque observer. and torque coefficient information . The difference between the reference torque value and the observed torque value is used as the output of the torque regulator, and the output logic switch value , The relationship between torque and stator and rotor flux is: when and When the size is constant, Proportional to , approximately proportional to , so the space voltage vector can be adjusted to control , and thus control changes.

[0036] When the present invention is used specifically, the vehicle data of the entire vehicle is collected through the data collection module of the system, and the collection status of the vehicle data is dynamically analyzed to obtain the complexity of real-time dynamic update of the vehicle data, and the boundary threshold of motor control and data change is analyzed in combination with the analysis of the complexity of the data collection state, and the motor parameters are analyzed through the vehicle data, and then the error analysis is performed based on the vehicle data to obtain the interference assessment boundary, and the correction of the vehicle data collection error is represented by the interference assessment boundary, and the adjustable range boundary of the motor direct control parameter is analyzed in combination with the boundary threshold, and the fit of the motor data is increased through step-by-step analysis, so that the range of motor control optimization is more reasonable, and when the vehicle data changes are complex, the complexity of the vehicle data that increases in real time, the boundary threshold and the adjustable boundary are used to reduce the dimension of the data, and finally the motor control is adaptively optimized. The accuracy of the adaptive control optimization algorithm in analyzing changes with the vehicle operating environment is greatly improved, so that the motor control system can obtain more accurate control optimization.

[0037] The technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A motor control optimization method for a vehicle, characterized in that: The control parameters of the motor controller are optimized based on the vehicle data collected by the sensor. The specific analysis process is as follows: Step 1: The vehicle data during the driving process includes all the data generated by the vehicle. The real-time data of the motor operation is obtained through the sensor, and the real-time state of the total vehicle data collection is analyzed to obtain the complexity corresponding to the real-time state change at the i-th moment. ; Step 2: The complexity of vehicle data collection in adaptive scenarios corresponding to different complex environments is different. The motor parameters in the vehicle data that actually affect the motor operation control include direct control parameters and indirect parameters. All motor parameters in the vehicle data of motor operation at different times are recorded as a multidimensional state vector, and the boundary threshold of motor control is obtained through multidimensional state vector analysis; Step 3: Perform error interference analysis on the vehicle data collected by the sensor during motor operation to obtain the interference assessment boundary of data collection, and then calculate the adjustable range boundary of the dynamic drive of the motor's direct controllable range in combination with different adaptive scenarios; Step 4: Determine the particle search range through the adjustable range boundary of the motor drive and the interference assessment boundary of the data acquisition, and optimize the parameters through the particle swarm search algorithm to convert the nonlinear relationship Perform transformation and determine the optimal parameters of the system control algorithm by searching the optimal position; Step 5: Use the neural network algorithm to optimize the control parameters of the motor, build a dynamic model of the vehicle system and its components, and combine the vehicle speed, engine speed, battery state of charge, SOC vehicle status signal and neural network to predict the vehicle speed and torque.

2. The motor control optimization method for a vehicle according to claim 1, characterized in that: The vehicle data of the motor is the operation data collected from the whole vehicle, which is recorded as historical operation data and real-time data from the time dimension. The detection indicators corresponding to all the changing parameters in the motor operation adaptive scene are extracted and recorded as represents the number of detection indicators in the vehicle data that change with the adaptive scene, i represents the extraction time in the time dimension, and the vehicle data collected at different times are analyzed in real time. The total number of detection indicators in the vehicle data is N, and the number of detection indicator changes corresponding to the adaptive scenes at different times is recorded as Then, the changes of detection indicators corresponding to each detection time i are analyzed to obtain the indicator change ratio of real-time changes in data collection. , and then calculate the complexity of real-time changes in vehicle data corresponding to different motor adaptive scenarios based on the changes in indicators , calculate the ratio of the change in detection index data , , ,in , and They represent the change values ​​of the same detection indicator in the adaptive scenario at the i-th moment and the detection indicator at the i-1th moment, respectively. .

3. The motor control optimization method for a vehicle according to claim 1, characterized in that: In the second step, the number of parameters of the motor parameters in different adaptive scenarios changes dynamically, and the corresponding adjustment range changes accordingly. The characteristics of the dynamic change boundary of the data related to the motor are dynamically analyzed according to the historical operation data in the vehicle data to obtain the boundary threshold of the adaptive scenario. The number of indirect parameters related to the motor corresponding to the change of the detection index at the i-th moment is recorded as , the number of changes in the detection index of the motor's direct control parameter is recorded as , the complexity is According to the analysis of the boundary control equation, a point set is obtained, which includes the control data of the motor parameters. Then, the elliptic partial differential equation of the dynamic boundary is established according to the point set, and the extreme value of the elliptic differential equation is analyzed with the point set as the value range. Then, the boundary threshold is calculated according to the extreme value. , the equation is as follows: in, is the elliptic function of the dynamic boundary characteristics, is the auxiliary variable, that is, the complexity of data changes at the i-th moment, is the time-varying function obtained from historical data, is the change function of the corresponding feature of the dynamic boundary, and It is obtained based on the historical data of motor operation, and then the extreme value is solved by the elliptic partial differential equation, and the boundary threshold is obtained by using the extreme value analysis.

4. The motor control optimization method for a vehicle according to claim 1, characterized in that: In the step 3, the interference assessment boundary is obtained by performing error assessment on the vehicle data collected by the sensor. In an adaptive scenario, the sensor collects the operation data of the vehicle. The transmission signals of different sensors affect each other in the same adaptive scenario. The vehicle data collected by all sensors are analyzed in layers. Layer The probability that sensors are assigned to the same group follows a quadratic distribution, , then perform error analysis on the sensor data based on the binomial distribution, calculate the confidence interval of the data, determine the confidence level of the vehicle data, and finally calculate the interference assessment boundary of the error .

5. The motor control optimization method for a vehicle according to claim 1, characterized in that: As the vehicle operating environment and motor operating parameters change, the most adaptive control parameters of the motor change. The adjustable range boundaries of the dynamic drive corresponding to different adaptive scenarios of the motor operation are calculated. The control range of the direct control parameters of the motor operation control is obtained by training the historical operation data with the neural network algorithm. The input vector of the system is , the output is a q-dimensional vector ,at the same time and The relationship is , determine the use of neural function Approaching the boundary threshold , is the corresponding point value of the interference assessment boundary, To adapt to the data change dimension in the scene, the adjustable range boundary is , satisfying the following performance indicator function: 。 6. The motor control optimization method for a vehicle according to claim 1, characterized in that: In the adjustable range of the motor The direct control parameters of the motor are further optimized by using the control strategy of the particle swarm algorithm in the neural network system. The particle population is described as , there are The particle is located in the search space, and the objective function is calculated to obtain the The individual extreme value and group extreme value of each particle are denoted as and , , According to the principle that each particle compares its own fitness value with the individual extreme value and the group extreme value after each update, it is continuously updated to determine the optimal fitness position of the group and the individual.

7. The motor control optimization method for a vehicle according to claim 1, characterized in that: The direct control parameters of the motor include speed and torque. During the optimization process of the motor control parameters, the vehicle data of the entire vehicle is dynamically analyzed, and then the control parameters of the motor are optimized based on the particle swarm algorithm in the neural network algorithm.

8. A motor control optimization system for a vehicle, applied in any one of claims 1-7, characterized in that: The system includes a control module, a data acquisition module, a boundary analysis module, a parameter optimization module, and a dynamic adaptive module. The control module is the core of the algorithm. It realizes intelligent control of the motor by sending different control signals to the vehicle's motor and coordinates the joint control of various modules in the vehicle. The data acquisition module includes a speed sensor, a pressure sensor, a humidity sensor, and a temperature sensor. It collects the current signal of the motor under different adaptive scenarios, and then converts the different signals into the form of vehicle data for storage. The boundary analysis module, the dynamic adaptive module, and the parameter optimization module optimize and analyze the motor operation data.

Images