Energy recovery control method and device, vehicle and storage medium

Abstract

The invention provides an energy recovery control method and device, a vehicle and a storage medium, and the method comprises the steps: monitoring the current driving working condition of the vehicle, and obtaining vehicle operation parameters, the current hydraulic braking force of vehicle braking and the current feedback braking force of a vehicle motor when the current driving working condition is a braking working condition; and the vehicle operation parameters, the current hydraulic braking force and the current feedback braking force are subjected to torque prediction through a pre-trained prediction model, target recovery torque is obtained, and a vehicle motor and a vehicle brake are controlled to output braking torque to a vehicle power system according to the target recovery torque. According to the method, it is monitored that the vehicle is in the braking working condition, the target recovery torque matched with the vehicle running parameters, the hydraulic braking force and the feedback braking force is rapidly and accurately predicted by combining the prediction model with the real-time vehicle running condition in time, cooperative control is conducted on a motor and braking through the recovery torque, and energy recovery with the maximum vehicle efficiency is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, in particular to an energy recovery control method and device, a vehicle and a storage medium. BACKGROUND

[0002] With the popularization and development of new energy vehicles, new energy vehicles are deeply loved by users due to their environmental protection, energy saving, low vehicle cost and other characteristics. The driving range is still one of the core factors affecting the user experience. Therefore, as a key technology for improving the energy utilization efficiency of electric vehicles and prolonging the driving range, the energy recovery technology has become crucial.

[0003] At present, energy recovery is to convert the kinetic energy generated during vehicle braking into electric energy, thereby improving the driving range of the vehicle. A fixed brake pedal opening-motor speed-recovery torque mapping table is usually used to determine the regenerative braking torque at the current brake pedal opening and current motor speed to achieve energy recovery. However, this method of determining the regenerative braking torque for energy recovery using a static and fixed mapping table cannot adapt to the real-time changes in the driving conditions of the vehicle, and most of the braking energy is still wasted, thereby affecting the energy recovery efficiency. SUMMARY

[0004] Therefore, the present application aims to provide an energy recovery control method and device, a vehicle and a storage medium to solve the problem that the current method of determining the regenerative braking torque for energy recovery cannot adapt to the real-time changes in the driving conditions of the vehicle, most of the braking energy is still wasted, and the energy recovery efficiency is affected.

[0005] According to a first aspect of the present application, an energy recovery control method is provided, which comprises: monitoring the current driving condition of the vehicle; if the current driving condition is a braking condition, obtaining the vehicle operating parameter, the current hydraulic braking force of the vehicle braking and the current feedback braking force of the vehicle motor; performing torque prediction on the vehicle operating parameter, the current hydraulic braking force and the current feedback braking force by using a pre-trained prediction model to obtain a target recovery torque; controlling the vehicle motor and the vehicle braking to output braking torque to the vehicle power system according to the target recovery torque.

[0006] Optionally, if the current driving condition is a braking condition, obtaining the vehicle operating parameter, the current hydraulic braking force of the vehicle braking and the current feedback braking force of the vehicle motor comprises: determining whether the current driving condition is a braking condition according to the real-time monitored pedal opening of the vehicle; acquire vehicle operating parameters in the braking condition, wherein the vehicle operating parameters comprise at least one of vehicle weight, vehicle speed, and remaining power; acquire hydraulic braking force and feedback braking force of the vehicle in the historical braking condition as current hydraulic braking force and current feedback braking force of the vehicle.

[0007] Optionally, the torque prediction of the vehicle operating parameters, the current hydraulic braking force, and the current feedback braking force through the pre-trained prediction model to obtain the target recovery torque comprises: input the vehicle operating parameters, the current hydraulic braking force, and the current feedback braking force into the pre-trained prediction model, and determine the torque mapping relationship between the vehicle operating parameters, the current hydraulic braking force, the current feedback braking force, and the recovery torque through the prediction model; output the target recovery torque matched with the vehicle operating parameters, the current hydraulic braking force, and the current feedback braking force by using the torque mapping relationship.

[0008] Optionally, before the torque prediction of the vehicle operating parameters, the current hydraulic braking force, and the current feedback braking force through the pre-trained prediction model to obtain the target recovery torque, the method further comprises: acquire historical vehicle operating parameters, historical hydraulic braking force, historical feedback braking force, and historical recovery torque in the historical braking condition; divide the historical vehicle operating parameters, the historical hydraulic braking force, the historical feedback braking force, and the historical recovery torque into a test set and a training set; train an initial model by using the training set, and perform error back propagation on the initial model by using the test set to obtain a trained prediction model.

[0009] Optionally, the control of the vehicle motor and the vehicle brake to output braking torque to the vehicle power system according to the target recovery torque comprises: determine regenerative feedback braking torque of the vehicle motor according to the target recovery torque; determine to-be-compensated hydraulic braking torque of the vehicle brake according to the regenerative feedback braking torque of the vehicle motor; control the vehicle motor to output the regenerative feedback braking torque to the vehicle power system, and control the vehicle brake to output the to-be-compensated hydraulic braking torque to the vehicle power system.

[0010] Optionally, the determination of the regenerative feedback braking torque of the vehicle motor according to the target recovery torque comprises: acquire motor operating parameters of the vehicle motor; According to the target recovery torque and the motor operating parameter, a regenerative feedback braking torque of the vehicle motor is determined.

[0011] Optionally, the control of the vehicle motor to output the regenerative feedback braking torque to the vehicle power system and the control of the vehicle brake to output the hydraulic braking torque to be compensated to the vehicle power system comprises: An available feedback braking torque of the vehicle motor is determined. In a case where the regenerative feedback braking torque is less than or equal to the available feedback braking torque, the control of the vehicle motor to output the regenerative feedback braking torque to the vehicle power system and the control of the vehicle brake to output the hydraulic braking torque to be compensated to the vehicle power system.

[0012] According to a second aspect of the present application, an energy recovery control device is provided, and the device comprises: A working condition monitoring module is configured to monitor a current driving working condition of a vehicle. A data acquisition module is configured to acquire a vehicle operating parameter, a current hydraulic braking force of a vehicle brake and a current feedback braking force of a vehicle motor in a case where the current driving working condition is a braking working condition. A torque prediction module is configured to perform torque prediction on the vehicle operating parameter, the current hydraulic braking force and the current feedback braking force through a pre-trained prediction model to obtain a target recovery torque. A control module is configured to control the vehicle motor and the vehicle brake to output braking torques to a vehicle power system according to the target recovery torque.

[0013] According to still another aspect of the present application, a vehicle is also provided, and the vehicle comprises a vehicle controller, a motor controller, a vehicle motor, a brake controller, a vehicle brake and a vehicle power system, and the vehicle is configured to perform the energy recovery control method as described above.

[0014] According to still another aspect of the present application, a readable storage medium is also provided, and the readable storage medium stores a computer program, and the computer program is configured to be executed by a processor to implement the steps of the energy recovery control method as described above.

[0015] The energy recovery control method provided in the embodiment of the present application, by monitoring the current driving condition of the vehicle, in the case of the current driving condition being the braking condition, obtaining the vehicle operating parameter, the current hydraulic braking force of the vehicle braking and the current feedback braking force of the vehicle motor, performing torque prediction on the vehicle operating parameter, the current hydraulic braking force and the current feedback braking force by the pre-trained prediction model to obtain the target recovery torque, and controlling the vehicle motor and the vehicle braking to respectively output the braking torque to the vehicle power system according to the target recovery torque. The embodiment of the present application monitors that the vehicle is in the braking condition, and timely adopts the prediction model combined with the real-time vehicle driving condition to quickly and accurately predict the target recovery torque matched with the vehicle operating parameter, the hydraulic braking force and the feedback braking force, thereby improving the accuracy of torque prediction, adopting the recovery torque to cooperatively control the motor and the braking, improving the efficiency of energy recovery, and realizing the energy recovery with the maximum vehicle efficiency.

[0016] The above description is only a summary of the technical solutions of the present application. In order to enable the technical means of the present application to be more clearly understood, and to be implemented according to the content of the description, and in order to enable the above and other purposes, characteristics and advantages of the present application to be more apparent and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0017] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a better understanding of the preferred embodiments, and are not to be considered as limitations on the present application. Moreover, in the entire drawings, the same reference numerals are used to denote the same components. In the drawings: Figure 1 is a step flow chart of an energy recovery control method provided by the embodiment of the present application; Figure 2 is Figure 1 is a flow chart of step 102 in the energy recovery control method provided by the embodiment of the present application in the foregoing method; Figure 3 is Figure 1 is a flow chart of step 103 in the energy recovery control method provided by the embodiment of the present application in the foregoing method; Figure 4 is Figure 1 is a flow chart of step 104 in the energy recovery control method provided by the embodiment of the present application in the foregoing method; Figure 5 is a scene schematic diagram of the energy recovery control method provided by the embodiment of the present application; Figure 6 is a structure schematic diagram of an energy recovery control device provided by the embodiment of the present application; Figure 7 is a structure schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below with reference to the drawings. However, those skilled in the art can understand that, in the embodiments of the present application, many technical details are presented in order to make the readers better understand the present application. However, the technical solutions claimed by the present application can be implemented even without these technical details and based on various changes and modifications of the following embodiments. The division of the following embodiments is for the convenience of description, and should not constitute any limitation on the specific embodiments of the present application, and the embodiments can be combined with each other and cited to each other without contradiction.

[0019] Reference Figure 1 , a step flow chart of an energy recovery control method provided by an embodiment of the present application is shown, and the method can include: Step 101, monitoring the current driving condition of the vehicle.

[0020] In the embodiment of the present application, the vehicle controller monitors the current driving condition of the vehicle by reading the signals collected by each sensor on the vehicle, and the current driving condition includes acceleration, deceleration, braking, sliding and the like. Among them, the braking condition refers to the condition that the vehicle gradually decelerates under the combined action of the reverse power generation torque of the driving motor, the hydraulic braking force and the resistance of each group when there is no accelerator pedal opening degree but there is a brake pedal opening degree. In the embodiment, it is necessary to monitor whether the current driving condition of the vehicle is a braking condition, and energy recovery is performed in the braking condition.

[0021] In a specific implementation, the vehicle controller can use an accelerator pedal position sensor to monitor whether the driver has an acceleration intention. When the pedal opening degree is 0%, i.e. completely released, it indicates that the driver has no acceleration demand. A brake pedal position / travel sensor is used to detect when the brake pedal is depressed or the travel is greater than 0, which can preliminarily determine that the braking condition is entered. A wheel speed sensor is used to monitor the speed of the four wheels to obtain the current speed of the vehicle and determine whether the wheels are locked or skid. The driving condition is monitored by integrating the sensor data.

[0022] Step 102, in the case that the current driving condition is a braking condition, obtaining the vehicle operating parameters, the current hydraulic braking force of the vehicle braking and the current feedback braking force of the vehicle motor.

[0023] In the embodiment of the present application, in the case that the current driving condition is a braking condition, vehicle operating parameters are obtained from the vehicle-mounted sensors and control units, wherein the vehicle operating parameters are used to reflect the real-time driving state of the vehicle, the vehicle operating parameters can include at least one of the vehicle weight, the vehicle speed and the remaining power, and the current hydraulic braking force of the vehicle braking and the current feedback braking force of the vehicle motor are obtained, wherein the hydraulic braking force is the braking force generated by the vehicle braking system, which pushes the brake pad to rub the brake disc through the hydraulic pressure to convert the kinetic energy of the vehicle into heat energy consumption, and the motor feedback braking force is the braking force generated by the vehicle driving motor when braking in the role of "generator", which slows down the vehicle through the reverse torque generated by the motor, and at the same time converts the kinetic energy of the vehicle into electrical energy and stores it in the battery.

[0024] It should be noted that in the embodiment, the current hydraulic braking force of the vehicle braking is provided by the brake controller, and the current feedback braking force of the vehicle motor is provided by the motor controller, which can be the current hydraulic braking force and the current feedback braking force collected in real time, or the hydraulic braking force and the feedback braking force output in the last braking condition as the current hydraulic braking force and the current feedback braking force, which will not be described here.

[0025] In step 103, the vehicle operating parameters, the current hydraulic braking force and the current feedback braking force are subjected to torque prediction through a pre-trained prediction model to obtain a target recovery torque.

[0026] In the embodiment of the present application, when the vehicle is in a braking condition, i.e. when the energy recovery condition is met, since the brake control mainly consists of motor feedback braking and hydraulic braking, and the traditional hydraulic braking is uncontrollable, in order to ensure maximum energy recovery under the condition of braking safety, the relationship between the motor feedback braking and the hydraulic braking needs to be reasonably designed in the embodiment. Therefore, in combination with the real-time changing driving state of the vehicle, the vehicle operating parameters, the current hydraulic braking force and the current feedback braking force are subjected to torque prediction through a pre-trained prediction model to obtain a target recovery torque.

[0027] It should be noted that the recovery torque is a controllable reverse drag force generated by the driving motor in the generator mode, which is used to slow down the vehicle and recover energy. Specifically, the recovery torque is the reverse drag force generated by the driving motor when the electric vehicle or hybrid vehicle changes from "motor" mode to "generator" mode during braking or coasting, which is used to resist the movement of the vehicle to generate braking force, and at the same time converts part of the kinetic energy of the vehicle into electrical energy and stores it in the battery.

[0028] In a specific implementation, the vehicle operating parameter, the current hydraulic braking force and the current regenerative braking force are input to the pre-trained prediction model, and the torque mapping relationship between the vehicle operating parameter, the current hydraulic braking force and the current regenerative braking force and the recovery torque is determined through the prediction model; the torque mapping relationship is a mapping relationship between the vehicle operating parameter, the hydraulic braking force, the regenerative braking force and the recovery torque obtained through deep learning, so that the target recovery torque matched with the vehicle operating parameter, the current hydraulic braking force and the current regenerative braking force is output by using the torque mapping relationship.

[0029] In step 104, the vehicle motor and the vehicle brake are controlled to respectively output braking torque to the vehicle power system according to the target recovery torque.

[0030] In the embodiment of the application, the vehicle controller determines the regenerative feedback braking torque that needs to be provided by the vehicle motor according to the target recovery torque, and after obtaining the regenerative feedback braking torque of the motor, the vehicle controller needs to determine the hydraulic braking torque that needs to be provided by the vehicle brake for compensation, so as to control the vehicle motor to output the regenerative feedback braking torque to the vehicle power system, and control the vehicle brake to output the hydraulic braking torque for compensation to the vehicle power system, thereby achieving energy recovery.

[0031] It should be noted that the regenerative feedback braking torque that needs to be output by the motor is determined according to the target recovery torque and the feedback capability of the motor, the regenerative feedback braking torque is the braking torque that can be output by the motor to the vehicle power system for energy recovery, and the hydraulic braking torque for compensation is the braking torque that needs to be output by the vehicle brake based on the braking torque of the motor to the vehicle power system for energy recovery.

[0032] The energy recovery control method provided in the embodiment of the application can monitor the current driving condition of the vehicle, acquire the vehicle operating parameter, the current hydraulic braking force of the vehicle brake and the current feedback braking force of the vehicle motor in the case that the current driving condition is a braking condition, perform torque prediction on the vehicle operating parameter, the current hydraulic braking force and the current feedback braking force through a pre-trained prediction model to obtain a target recovery torque, and control the vehicle motor and the vehicle brake to respectively output braking torque to the vehicle power system according to the target recovery torque. The embodiment of the application can monitor that the vehicle is in a braking condition, and timely use the prediction model to quickly and accurately predict the target recovery torque matched with the vehicle operating parameter, the hydraulic braking force and the feedback braking force in combination with the real-time driving condition of the vehicle, thereby improving the accuracy of torque prediction, improving the efficiency of energy recovery by using the recovery torque to cooperatively control the motor and the brake, and achieving energy recovery with maximum vehicle efficiency.

[0033] Referring to Figure 2 , it is shown Figure 1A flowchart of step 102 of the energy recovery control method is provided. The method is basically the same as the energy recovery control method provided by the first embodiment of the present application, and the difference is that step 102 can specifically include the following steps. In step 1021, it is determined whether the current driving condition is a braking condition according to the pedal opening degree of the vehicle monitored in real time. In step 1022, vehicle operating parameters in the braking condition are obtained; wherein the vehicle operating parameters include at least one of the vehicle weight, the vehicle speed, and the remaining power. In step 1023, the hydraulic braking force of the vehicle braking and the feedback braking force of the vehicle motor in the historical braking condition are obtained as the current hydraulic braking force of the vehicle braking and the current feedback braking force of the vehicle motor.

[0034] In the embodiment of the present application, it is determined whether the current driving condition is a braking condition according to the pedal opening degree of the vehicle monitored in real time. The pedal opening degree of the vehicle includes the accelerator pedal opening degree and the brake pedal opening degree. The vehicle controller can use the sensor of the accelerator pedal position to monitor whether the driver has an acceleration intention. When the accelerator pedal opening degree is 0%, that is, the accelerator pedal is completely released, it indicates that the driver has no acceleration demand. At the same time, the stroke sensor of the brake pedal position is used. When it is detected that the brake pedal is depressed or the brake pedal opening degree is greater than 0%, it can be preliminarily determined that the braking condition is entered.

[0035] In the embodiment, after it is determined that the current driving condition is a braking condition, the vehicle operating parameters are obtained from the vehicle-mounted sensors and control units. The vehicle operating parameters include at least one of the vehicle weight, the vehicle speed, and the remaining power. The vehicle weight can be obtained by the vehicle-mounted weighing sensor or estimated according to the vehicle type and the load condition. The vehicle speed is collected in real time by the vehicle speed sensor. The remaining power can be obtained by the battery management system. The real-time vehicle operating data obtained in the embodiment is used to reflect the real-time state of the vehicle, so as to perform subsequent torque prediction and braking force distribution.

[0036] After it is determined that the current driving condition is a braking condition, the current hydraulic braking force and the current feedback braking force collected in real time can be obtained from the brake controller and the motor controller. The braking condition data similar to the current driving condition can also be extracted from the historical braking data. According to the current vehicle operating parameters, the similar braking condition is searched in the historical braking data. The hydraulic braking force and the feedback braking force of the motor are extracted from the matched historical braking condition. The extracted historical data is used as the initial value of the current hydraulic braking force and the motor feedback braking force.

[0037] The embodiment of the present application quickly obtains the real-time vehicle operating data, the current hydraulic braking force, and the motor feedback braking force by monitoring the vehicle driving condition. The complex and changeable driving environment is comprehensively considered, and the delay of data collection and processing is reduced.

[0038] Referring to Figure 3 , it is shown Figure 1 The flow chart of step 103 in the energy recovery control method provided by the application is basically the same as the energy recovery control method provided by the first embodiment of the application, and the difference is that step 103 can specifically include: Step 1031, input the vehicle running parameter, the current hydraulic braking force and the current regenerative braking force into the pre-trained prediction model, and determine the torque mapping relationship between the vehicle running parameter, the current hydraulic braking force and the current regenerative braking force and the recovery torque through the prediction model; Step 1032, output the target recovery torque matched with the vehicle running parameter, the current hydraulic braking force and the current regenerative braking force by using the torque mapping relationship.

[0039] In the embodiment of the application, after obtaining the real-time vehicle running parameter and the current hydraulic braking force and the current regenerative braking force, these data are input into the pre-trained prediction model, wherein the vehicle running parameter includes vehicle weight, vehicle speed, remaining power and the like, the prediction model can be a neural network model based on machine learning or deep learning, which can establish the torque mapping relationship between the vehicle running parameter, the hydraulic braking force, the regenerative braking force and the recovery torque through a large amount of historical data training, and can perform torque prediction and output the model of the recovery torque.

[0040] In the embodiment, the vehicle running parameter, the current hydraulic braking force and the current regenerative braking force are input into the prediction model as input features, and the prediction model determines the torque mapping relationship between the input parameters and the recovery torque through the internal weights and the activation function according to the input parameters. The torque mapping relationship is the predicted value of the recovery torque under the current vehicle running parameter, the hydraulic braking force and the regenerative braking force. The target recovery torque matched with the vehicle running parameter, the current hydraulic braking force and the current regenerative braking force is output by using the torque mapping relationship. Specifically, the current vehicle running parameter, the hydraulic braking force and the regenerative braking force are substituted into the torque mapping relationship, and the target recovery torque matched with the current input parameters is mapped according to the mapping relationship. The target recovery torque predicted by the model is output and used for subsequent brake force distribution and energy recovery control.

[0041] The embodiment of the application can quickly and accurately predict the target recovery torque matched with the current vehicle running parameter, the hydraulic braking force and the regenerative braking force by comprehensively considering the vehicle driving condition through the prediction model, can handle complex nonlinear relationships, and improves the accuracy of torque prediction, thereby improving the efficiency of energy recovery.

[0042] In some embodiments of the application, before step 103 performs torque prediction on the vehicle running parameter, the current hydraulic braking force and the current regenerative braking force through the pre-trained prediction model to obtain the target recovery torque, it can further include: First, historical vehicle operating parameters, historical hydraulic braking force, historical feedback braking force and historical recovery torque under historical braking conditions are acquired; Second, the historical vehicle operating parameters, historical hydraulic braking force, historical feedback braking force and historical recovery torque are divided into a test set and a training set; Second, the initial model is trained using the training set, and the initial model is subjected to error back propagation using the test set to obtain the trained prediction model.

[0043] In the embodiments of the application, the prediction model is used to accurately predict the target recovery torque according to the input vehicle operating parameters, hydraulic braking force and feedback braking force. In the historical driving data of the vehicle, the historical vehicle operating parameters, historical hydraulic braking force, historical feedback braking force and historical recovery torque under historical braking conditions are acquired, wherein the historical vehicle operating parameters include vehicle weight, vehicle speed, remaining power and the like, the historical hydraulic braking force is historical braking pressure data recorded by a brake pressure sensor, which is converted into a braking torque, the historical feedback braking force is historical motor feedback braking torque recorded by a motor controller, and the historical recovery torque is historical recovery torque data recorded by energy recovery, which provides rich data support for model training and helps the model to learn complex mapping relationships, thereby improving the prediction accuracy.

[0044] In the process of training the prediction model, the acquired historical data is divided into a training set and a test set, wherein the historical data can be randomly divided into the training set and the test set according to a certain proportion, for example, 80% training set and 20% test set, the training set is used for model training, and the test set is used for verifying the prediction accuracy of the model. Before training starts, the training set and the test set can be subjected to data cleaning and standardization processing. After the data division is completed, the training and optimization process of the model is started. The training set data is used to train the initial model using machine learning or deep learning algorithm. The initial model learns the mapping relationship between the input features (vehicle operating parameters, hydraulic braking force and feedback braking force) and the output features (recovery torque) in the training set to establish a preliminary prediction model. The test set data is then used to verify the initial model, and the prediction error such as mean square error, mean absolute error and the like is calculated. According to the error result, the model parameters are optimized using the error back propagation algorithm, the weights and biases of the model are adjusted, and the prediction error is reduced. After multiple rounds of training and error back propagation optimization, the trained prediction model is obtained.

[0045] It should be noted that the initial model can be trained using a decision tree algorithm to obtain the prediction model. The decision tree is built according to the principle of minimizing the loss function. The decision-making process using the decision tree starts from the root node. In this embodiment, the input parameters such as hydraulic braking force and regenerative braking force, vehicle weight, and remaining battery power are all used as attributes. Each leaf node stores an attribute of a category. Starting from the root node, the corresponding attribute features are tested, and the output branch is selected according to its value until a leaf node is reached. The classification result of the leaf node is output as the decision result.

[0046] In some embodiments of this application, the prediction model can also employ a population search algorithm to predict torque. The population H includes I search individuals. The position of each particle in the population is determined by four types of parameters: hydraulic braking force, regenerative braking force, vehicle operating parameters, and road friction coefficient. That is, the position dimension of each particle is four. Therefore, the population can be represented by a 1*4 matrix. During the search process, a fitness function is used to evaluate the quality of individuals or solutions. The fitness function is randomly generated within the corresponding value range of the population and serves as the basis for updating the positions of subsequent search individuals, causing the initial solution to gradually approach the optimal solution. The crowd search algorithm coordinates the values ​​of hydraulic braking force, regenerative braking force, vehicle operating parameters, and road friction coefficient. Its uncertain reasoning behavior utilizes the approximation capability of fuzzy systems to simulate human intelligent search behavior, establishing a connection between the objective function and the step size. The search step size of the crowd search algorithm is fuzzy in the form of a Gaussian membership function. By analyzing human self-interest and predictive behavior, mathematical modeling is performed to obtain the self-interest direction, altruistic direction, and predictive direction for any individual. After determining the search step size and search direction, the individual searcher's position is updated, and the optimal recovery torque output value is calculated.

[0047] The embodiments of this application are based on the vehicle braking status reflected by vehicle operating parameters, hydraulic braking force and regenerative braking force, etc., and use a pre-trained prediction model to accurately and efficiently predict the output target recovery torque, so as to use the accurate recovery torque for braking torque distribution.

[0048] Reference Figure 4 , showed Figure 1 A flowchart of step 104 in an energy recovery control method is provided. This method is basically the same as the energy recovery control method provided in the first embodiment of this application, except that step 104 may specifically include: Step 1041: Determine the regenerative braking torque of the vehicle motor based on the target recovery torque; Step 1042: Determine the hydraulic braking torque to be compensated for the vehicle braking based on the regenerative braking torque of the vehicle motor. In step 1043, the vehicle controller controls the vehicle motor to output the regenerative feedback braking torque to the vehicle power system, and controls the vehicle brake to output the to-be-compensated hydraulic braking torque to the vehicle power system.

[0049] In the embodiment, after determining the target recovery torque, the vehicle controller determines the regenerative feedback braking torque of the vehicle motor according to the target recovery torque. After obtaining the regenerative feedback braking torque of the motor, in order to ensure that the braking torque of the braking system and the feedback braking torque of the motor work cooperatively and avoid overloading of the braking system or insufficient braking force, the vehicle controller needs to determine the to-be-compensated hydraulic braking torque that needs to be provided by the braking system according to the regenerative feedback braking torque of the vehicle motor, so as to control the vehicle motor to output the regenerative feedback braking torque to the vehicle power system, and control the vehicle brake to output the to-be-compensated hydraulic braking torque to the vehicle power system, thereby realizing energy recovery.

[0050] As a specific implementation in the embodiment, the regenerative feedback braking torque that needs to be provided by the vehicle motor is determined according to the target recovery torque, and the to-be-compensated hydraulic braking torque that needs to be provided by the vehicle braking system is determined according to the regenerative feedback braking torque of the motor. The target recovery torque is the expected amount of energy to be recovered, which is predicted based on the vehicle operating parameters, the current hydraulic braking force and the current feedback braking force. The target recovery torque reflects the total braking torque that needs to be output by the vehicle brake and the vehicle motor. The regenerative feedback braking torque refers to the braking torque that needs to be output by the motor during braking, which is used to convert the kinetic energy of the vehicle into electrical energy and store the electrical energy in the battery. The to-be-compensated hydraulic braking torque refers to the braking torque that needs to be supplemented by the hydraulic brake when the regenerative feedback braking torque of the motor is insufficient to meet the demand of the target recovery torque.

[0051] Specifically, after determining the target recovery torque, considering that the braking torque that can be provided by the motor is limited by factors such as the characteristic curve, the state of charge and the temperature of the battery, the braking torque that can be provided by the motor is limited. Therefore, the motor operating parameters of the vehicle motor are obtained, the braking torque of the motor is estimated according to the motor operating parameters, the braking torque includes the braking torque of the motor at the current speed and the braking torque under the vehicle dynamics limit, and the minimum value among the target recovery torque, the braking torque of the motor at the current speed and the braking torque under the vehicle dynamics limit is determined as the regenerative feedback braking torque of the vehicle motor. After determining the regenerative feedback braking torque of the motor, the to-be-compensated hydraulic braking torque that needs to be provided by the braking system is calculated according to the difference between the target recovery torque and the regenerative feedback braking torque of the motor, that is, the to-be-compensated hydraulic braking torque that needs to be provided by the braking system is obtained by subtracting the regenerative feedback braking torque of the motor from the target recovery torque, so as to ensure that the braking torque of the braking system and the feedback braking torque of the motor work cooperatively.

[0052] In a specific implementation, after determining the regenerative feedback braking torque of the vehicle motor and the hydraulic braking torque to be compensated of the vehicle braking, the vehicle controller sends control instructions to the vehicle motor and the vehicle braking system respectively, controls the vehicle motor to output the regenerative feedback braking torque to the vehicle power system, and controls the vehicle braking to output the hydraulic braking torque to be compensated to the vehicle power system. According to the regenerative feedback braking torque, the motor controller is sent an instruction to control the motor to output a corresponding feedback braking torque to the vehicle power system, and according to the hydraulic braking torque to be compensated, the vehicle braking system is sent an instruction to control the braking component to output a corresponding hydraulic braking torque to the vehicle power system.

[0053] The embodiments of the present application reasonably allocate the braking torques of the motor and the braking system based on the predicted target recovery torque, accurately control the braking torques of the motor and the braking system, ensure the maximum energy recovery efficiency, and achieve efficient energy recovery.

[0054] In some embodiments of the present application, step 1041 determines the regenerative feedback braking torque of the vehicle motor according to the target recovery torque, which can specifically include the following steps: Sub-step 01: Obtain motor operating parameters of the vehicle motor. Sub-step 02: Determine the regenerative feedback braking torque of the vehicle motor according to the target recovery torque and the motor operating parameters.

[0055] In the embodiments of the present application, since the feedback capability of the motor changes in real time, the current braking torque that can be provided by the motor needs to be evaluated in combination with the current state of the motor, such as the motor speed, the battery state, etc. In a specific implementation, the motor operating parameters of the motor are obtained through a sensor, which can include the speed, current, voltage, temperature, etc. of the motor, for reflecting the current working state of the motor. According to the obtained motor operating parameters, the current capability of the motor is analyzed, and the braking torque of the motor under the current speed and the braking torque of the motor under the vehicle dynamics limit are monitored. The minimum value among the target recovery torque, the braking torque of the motor under the current speed, and the braking torque of the motor under the vehicle dynamics limit is determined as the regenerative feedback braking torque of the vehicle motor, so as to reasonably allocate the braking torques of the vehicle motor and the braking system, ensure the maximum energy recovery efficiency, and avoid overloading of the motor or overcharging of the battery.

[0056] The embodiments of the present application determine the braking torques that need to be allocated to the motor and the braking system based on the target recovery torque and the motor operating state, so as to accurately control the braking torques of the motor and the braking system and ensure the maximum energy recovery efficiency.

[0057] In some embodiments of the present application, step 1043 controls the vehicle motor to output the regenerative feedback braking torque to the vehicle power system, and controls the vehicle brake to output the hydraulic braking torque to be compensated to the vehicle power system, which can specifically include the following steps: Sub-step 01, determining the available feedback braking torque of the vehicle motor; Sub-step 02, in the case that the regenerative feedback braking torque is less than or equal to the available feedback braking torque, controlling the vehicle motor to output the regenerative feedback braking torque to the vehicle power system, and controlling the vehicle brake to output the hydraulic braking torque to be compensated to the vehicle power system.

[0058] In the embodiments of the present application, the available feedback braking torque of the vehicle motor refers to the maximum regenerative braking torque that the motor can safely provide under the current instantaneous conditions (including the current motor speed, battery SOC, battery temperature, system temperature, etc.), which is a real-time changing upper limit value determined by system constraints. In specific implementation, the current available feedback braking torque of the motor can be evaluated in real time according to the current speed, temperature, and battery state of the motor, according to the motor state parameters and the limitations of the energy recovery system, to avoid motor overload or battery overcharge and ensure the safety of the energy recovery process. Therefore, the embodiments of the present application determine the available feedback braking torque of the vehicle motor in real time, monitor the size relationship between the available feedback braking torque of the vehicle motor and the regenerative feedback braking torque determined in advance based on the target recovery torque, and control the vehicle motor to output the regenerative feedback braking torque to the vehicle power system and control the vehicle brake to output the hydraulic braking torque to be compensated to the vehicle power system in the case that the regenerative feedback braking torque is less than or equal to the available feedback braking torque, otherwise, the energy recovery cannot be performed according to the regenerative feedback braking torque, to ensure the safety of the motor.

[0059] In the embodiments of the present application, the regenerative feedback braking torque of the motor is compared with the available feedback braking torque, to ensure that the regenerative feedback braking torque of the motor is less than or equal to the available feedback braking torque during the energy recovery process, which indicates that the motor has the ability to provide the regenerative feedback braking torque, the vehicle controller sends an instruction to the motor controller to control the motor to output the available feedback braking torque to the vehicle power system, and the vehicle controller also sends an instruction to the vehicle brake system to control the vehicle brake system to output the hydraulic braking torque to be compensated to the vehicle power system, to ensure that the braking torques of the motor and the brake system work cooperatively and avoid uneven distribution of braking torques or insufficient braking.

[0060] The embodiments of the present application ensure that the braking meets the requirements of the target recovery torque through the cooperative control of the motor and the brake system, avoid the situations of insufficient braking or overload, thereby improving the stability and safety of the braking process and realizing the energy recovery with the maximum efficiency of the vehicle.

[0061] For the skilled in the art to be able to more clearly understand the energy recovery control method described in the above embodiments, refer to Figure 5 , a scene schematic diagram of the energy recovery control method provided by the embodiments of the application is shown, wherein the vehicle includes a vehicle controller, a motor controller, a vehicle motor, a brake controller, a vehicle brake and a vehicle power system, the vehicle is used to execute the above-mentioned energy recovery control method, based on the residual electric quantity, the vehicle weight, the vehicle speed and other vehicle operating parameters of the vehicle, and the feedback braking force of the vehicle motor and the hydraulic braking force of the vehicle brake component, the vehicle controller adopts a pre-trained prediction model to predict a target recovery torque, sends the target recovery torque to the motor controller to obtain the braking torque that the motor needs to output, the motor controller communicates with the brake controller of the vehicle to synchronize the braking torque output by the motor to the brake controller, the brake controller determines the braking torque that the vehicle brake component needs to output, finally, the vehicle motor outputs a regenerative feedback braking torque to the vehicle power system, and the vehicle brake outputs a hydraulic braking torque to be compensated to the vehicle power system, so as to realize energy recovery.

[0062] Refer to Figure 6 , a structure schematic diagram of an energy recovery control device provided by the embodiments of the application is shown, the device includes: A working condition monitoring module 201 is configured to monitor the current driving working condition of the vehicle. A data acquisition module 202 is configured to acquire vehicle operating parameters, a current hydraulic braking force of the vehicle brake and a current feedback braking force of the vehicle motor in the case that the current driving working condition is a braking working condition. A torque prediction module 203 is configured to perform torque prediction on the vehicle operating parameters, the current hydraulic braking force and the current feedback braking force through a pre-trained prediction model to obtain a target recovery torque. A control module 204 is configured to control the vehicle motor and the vehicle brake to output braking torques to a vehicle power system according to the target recovery torque.

[0063] Optionally, the data acquisition module 202 includes: A working condition determining sub-module is configured to determine whether the current driving working condition is a braking working condition according to the pedal opening degree of the vehicle monitored in real time. A first acquisition sub-module is configured to acquire vehicle operating parameters in the braking working condition; wherein the vehicle operating parameters include at least one of the vehicle weight, the vehicle speed and the residual electric quantity. A second acquisition sub-module is configured to acquire the hydraulic braking force of the vehicle brake and the feedback braking force of the vehicle motor in the historical braking working condition as the current hydraulic braking force of the vehicle brake and the current feedback braking force of the vehicle motor.

[0064] Optionally, the torque prediction module 203 comprises: a prediction submodule configured to input the vehicle operating parameter, the current hydraulic braking force and the current regenerative braking force into a pre-trained prediction model, and determine a torque mapping relationship between the vehicle operating parameter, the current hydraulic braking force, the current regenerative braking force and the recovery torque through the prediction model; an output submodule configured to output a target recovery torque matched with the vehicle operating parameter, the current hydraulic braking force and the current regenerative braking force according to the torque mapping relationship.

[0065] Optionally, the device further comprises: a historical data acquisition module configured to acquire historical vehicle operating parameters, historical hydraulic braking forces, historical regenerative braking forces and historical recovery torques under historical braking conditions; a data division module configured to divide the historical vehicle operating parameters, the historical hydraulic braking forces, the historical regenerative braking forces and the historical recovery torques into a test set and a training set; a model training module configured to train an initial model using the training set, and perform error back propagation on the initial model using the test set to obtain a trained prediction model.

[0066] Optionally, the control module 204 comprises: a first determination submodule configured to determine a regenerative feedback braking torque of a vehicle motor according to the target recovery torque; a second determination submodule configured to determine a hydraulic braking torque to be compensated of the vehicle braking according to the regenerative feedback braking torque of the vehicle motor; a control submodule configured to control the vehicle motor to output the regenerative feedback braking torque to a vehicle power system, and control the vehicle braking to output the hydraulic braking torque to be compensated to the vehicle power system.

[0067] Optionally, the first determination submodule comprises: a parameter acquisition unit configured to acquire motor operating parameters of the vehicle motor; a determination unit configured to determine the regenerative feedback braking torque of the vehicle motor according to the target recovery torque and the motor operating parameters.

[0068] Optionally, the control submodule comprises: a determination unit configured to determine an available feedback braking torque of the vehicle motor; a control unit configured to, in a case where the regenerative feedback braking torque is less than or equal to the available feedback braking torque, control the vehicle motor to output the regenerative feedback braking torque to the vehicle power system, and control the vehicle braking to output the hydraulic braking torque to be compensated to the vehicle power system.

[0069] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0070] The energy recovery control device provided in this application monitors the vehicle's current driving condition. When the current driving condition is braking, it acquires vehicle operating parameters, the current hydraulic braking force, and the current regenerative braking force of the vehicle motor. These parameters, along with the current hydraulic and regenerative braking forces, are used to predict torque using a pre-trained prediction model to obtain the target recovery torque. Based on the target recovery torque, the vehicle motor and brakes are controlled to output braking torque to the vehicle's power system. This application monitors the vehicle as braking and promptly uses a prediction model combined with real-time vehicle driving conditions to quickly and accurately predict the target recovery torque that matches the vehicle operating parameters, hydraulic braking force, and regenerative braking force. This improves the accuracy of torque prediction. By using the recovery torque to coordinate the control of the motor and brakes, the efficiency of energy recovery is improved, achieving energy recovery with maximum vehicle efficiency.

[0071] Reference Figure 7 This application also provides an electronic device, such as... Figure 7 As shown, it includes a processor 301, a communication interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304. Processor 301, Memory 303 is used to store processor-executable instructions; The processor 301 is configured to execute the instructions to implement the energy recovery control method as described below: Monitor the vehicle's current operating condition; When the current driving condition is braking, the vehicle operating parameters, the current hydraulic braking force of the vehicle brakes, and the current regenerative braking force of the vehicle motor are obtained. The vehicle operating parameters, current hydraulic braking force, and current regenerative braking force are used to predict torque using a pre-trained prediction model to obtain the target recovery torque. Based on the target recovery torque, the vehicle motor and the vehicle brake are controlled to output braking torque to the vehicle power system respectively.

[0072] The communication bus mentioned in the terminal can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0073] The communication interface is used for communication between the terminal and other devices.

[0074] The memory can include a random access memory (RAM) and can also include a non-volatile memory, such as at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0075] The processor mentioned above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0076] In another embodiment provided in the present application, a vehicle is also provided, the vehicle comprising a vehicle controller, a motor controller, a vehicle motor, a brake controller, a vehicle brake, and a vehicle power system, and the vehicle is configured to execute the energy recovery control method.

[0077] In another embodiment provided in the present application, a computer readable storage medium is also provided, the readable storage medium storing a computer program, and the computer program is configured to execute the energy recovery control method when executed by a processor.

[0078] In the embodiments described above, all or some of the steps can be implemented by hardware, software, firmware or any combination thereof. When implemented by software, all or some of the steps can be implemented in the form of one or more computer programs or program elements. The computer programs reside (at least temporarily) in a memory of a computer during execution. The memory can be a RAM memory, a flash memory, a ROM memory, an EPROM memory, or any other suitable memory. The memory can be integral to or separate from the computer. The computer programs can be written in any suitable programming language, such as C, C++, Java, Visual Basic, etc. The computer programs can be written in assembly or machine language, if desired. The computer programs can be distributed over network coupled file servers, or can be distributed by any other suitable means.

[0079] It is to be understood that the terminology "first", "second", etc. used herein merely identifies one entity or action from another, but does not necessarily imply, or require, any actual relationship or order between such entities or actions. Also, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0080] Each of the embodiments described in the specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, the system embodiments are described in a relatively simple manner, since they are substantially similar to the method embodiments, and the relevant parts can be referred to the description of the method embodiments.

[0081] The above merely provides the preferred embodiments of the application, and not intended to limit the protection scope of the application. Any modification, equivalent replacement, improvement, and the like made within the principle and technical scope of the application shall fall into the protection scope of the application.

Claims

1. An energy recovery control method, characterized in that, The method includes: Monitor the vehicle's current operating condition; When the current driving condition is braking, the vehicle operating parameters, the current hydraulic braking force of the vehicle brakes, and the current regenerative braking force of the vehicle motor are obtained. The vehicle operating parameters, current hydraulic braking force, and current regenerative braking force are used to predict torque using a pre-trained prediction model to obtain the target recovery torque. Based on the target recovery torque, the vehicle motor and the vehicle brake are controlled to output braking torque to the vehicle power system respectively.

2. The method according to claim 1, characterized in that, When the current driving condition is braking, acquiring vehicle operating parameters, the current hydraulic braking force of the vehicle, and the current regenerative braking force of the vehicle motor includes: Based on the real-time monitoring of the vehicle's pedal opening, determine whether the current driving condition is a braking condition; Obtain vehicle operating parameters under the braking condition; wherein, the vehicle operating parameters include at least one of vehicle weight, vehicle speed, and remaining battery power; The hydraulic braking force and the regenerative braking force of the vehicle motor in historical braking conditions are obtained and used as the current hydraulic braking force and the current regenerative braking force of the vehicle motor.

3. The method according to claim 1, characterized in that, The step of using a pre-trained prediction model to predict the target recovery torque by analyzing the vehicle operating parameters, current hydraulic braking force, and current regenerative braking force includes: The vehicle operating parameters, current hydraulic braking force, and current regenerative braking force are input into a pre-trained prediction model, and the prediction model determines the torque mapping relationship between the vehicle operating parameters, current hydraulic braking force, current regenerative braking force, and regenerative torque. Using the torque mapping relationship, a target recovery torque is output that matches the vehicle operating parameters, the current hydraulic braking force, and the current regenerative braking force.

4. The method according to claim 3, characterized in that, Before using a pre-trained prediction model to predict the target recovery torque by analyzing the vehicle operating parameters, current hydraulic braking force, and current regenerative braking force, the process further includes: Acquire historical vehicle operating parameters, historical hydraulic braking force, historical regenerative braking force, and historical regenerative torque under historical braking conditions; The historical vehicle operating parameters, historical hydraulic braking force, historical regenerative braking force, and historical regenerative torque are divided into a test set and a training set. The initial model is trained using the training set, and the initial model is backpropagated using the test set to obtain the trained prediction model.

5. The method according to claim 1, characterized in that, The step of controlling the vehicle motor and the vehicle brake to output braking torque to the vehicle power system according to the target recovery torque includes: Based on the target recovery torque, determine the regenerative braking torque of the vehicle motor; The hydraulic braking torque to be compensated for the vehicle braking is determined based on the regenerative braking torque of the vehicle motor. The vehicle motor is controlled to output the regenerative braking torque to the vehicle power system, and the vehicle brake outputs the hydraulic braking torque to be compensated to the vehicle power system.

6. The method according to claim 5, characterized in that, Determining the regenerative braking torque of the vehicle motor based on the target recovery torque includes: Obtain the motor operating parameters of the vehicle motor; Based on the target recovery torque and motor operating parameters, the regenerative braking torque of the vehicle motor is determined.

7. The method according to claim 5, characterized in that, The control of the vehicle motor to output the regenerative braking torque to the vehicle power system, and the control of the vehicle brake to output the hydraulic braking torque to be compensated to the vehicle power system, include: Determine the available regenerative braking torque of the vehicle's motor; When the regenerative braking torque is less than or equal to the available regenerative braking torque, the vehicle motor is controlled to output the regenerative braking torque to the vehicle power system, and the vehicle brake is controlled to output the hydraulic braking torque to be compensated to the vehicle power system.

8. An energy recovery control device, characterized in that, The device includes: The operating condition monitoring module is used to monitor the current driving condition of the vehicle. The data acquisition module is used to acquire vehicle operating parameters, the current hydraulic braking force of the vehicle brake, and the current regenerative braking force of the vehicle motor when the current driving condition is braking condition. The torque prediction module is used to predict the target recovery torque by using the vehicle operating parameters, current hydraulic braking force, and current regenerative braking force through a pre-trained prediction model. The control module is used to control the vehicle motor and the vehicle brake to output braking torque to the vehicle power system according to the target recovery torque.

9. A vehicle, characterized in that, The vehicle includes a vehicle controller, a motor controller, a vehicle motor, a brake controller, a vehicle brake, and a vehicle power system, and the vehicle is used to perform the energy recovery control method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that, A computer program is stored on the readable storage medium, which, when executed by a processor, implements the energy recovery control method as described in any one of claims 1 to 7.

Images