Vehicle energy recovery control method and device, medium and vehicle

Abstract

The embodiment of the invention provides a vehicle energy recovery control method and device, a medium and a vehicle, and relates to the technical field of brake control. The method comprises the steps that a braking request of a target vehicle is responded, and current braking judgment parameters of the target vehicle are obtained; under the condition that it is determined that the target vehicle meets the preset energy recovery condition based on the current braking judgment parameters, the vehicle operation parameters are input into an intelligent decision-making model, and a braking force distribution strategy result is obtained; based on the braking force distribution strategy result, braking control is conducted on a motor control system and a braking system; the motor control system is used for providing regenerative braking force and generating recovery energy suitable for supplementing energy to the power battery. According to the embodiment of the invention, the vehicle operation parameters collected in real time are input into the self-adaptive adjustment intelligent decision-making model, and the braking force distribution strategy suitable for the current operation condition can be output, so that the accuracy and adaptability of braking force distribution are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of brake control technology, and in particular to a vehicle energy recovery control method, device, medium and vehicle. Background Art

[0002] With growing global attention to environmental protection and sustainable energy development, new energy vehicles (NEVs) have become widely adopted as a green travel option. Energy recovery systems (ERSs) are key technologies for improving energy efficiency and extending driving range in NEVs, particularly pure electric vehicles. In electric and hybrid vehicles, the Regenerative Braking System (RBS) converts kinetic energy generated during braking into electrical energy and stores it in the power battery, improving energy efficiency and extending vehicle range.

[0003] However, the existing braking force distribution strategy is not very accurate and cannot reasonably guarantee the balance between braking performance and energy recovery goals. It mainly implements braking force distribution based on fixed rules and has low adaptability to the environment and working conditions. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a vehicle energy recovery control method, device, medium and vehicle, so as to improve the adaptability and accuracy of braking force distribution.

[0005] In a first aspect, an embodiment of the present application provides a method for controlling energy recovery of a vehicle, comprising: Responding to a braking request of a target vehicle and obtaining a current braking determination parameter of the target vehicle; When it is determined based on the current braking determination parameters that the target vehicle meets the preset energy recovery conditions, the vehicle operating parameters collected in real time are input into the adaptively adjusted intelligent decision model to obtain a braking force distribution strategy result output by the intelligent decision model; Based on the braking force distribution strategy result, the motor control system and the brake system are respectively brake-controlled; wherein, the motor control system is used to provide regenerative braking force and generate recovered energy suitable for replenishing energy to the power battery.

[0006] In an embodiment of the present application, by inputting the vehicle operating parameters collected in real time into an adaptively adjusted intelligent decision-making model, a braking force distribution strategy adapted to the current operating conditions can be output, thereby effectively improving the accuracy and adaptability of the braking force distribution.

[0007] In some possible embodiments, the current braking determination parameters include current expected deceleration, current battery state of charge, and current vehicle speed; The determining, based on the current braking determination parameter, that the target vehicle meets a preset energy recovery condition includes: If it is determined that the current expected deceleration is less than a preset deceleration threshold, the current battery state of charge is within a preset battery state of charge range, and the current vehicle speed is within a preset vehicle speed range, then it is determined that the target vehicle meets the preset energy recovery condition.

[0008] In the embodiment of the present application, whether the energy recovery conditions are met is comprehensively judged by combining the three parameters of deceleration, battery state of charge and vehicle speed, thereby improving the comprehensiveness and reliability of the energy recovery condition judgment.

[0009] In some possible embodiments, the current braking determination parameter includes a current expected deceleration; The method further comprises: If it is determined that the current expected deceleration is not less than a preset deceleration threshold, it is determined that the target vehicle does not meet the preset energy recovery conditions, and the target vehicle is braked according to a preset emergency braking strategy; wherein the preset emergency braking strategy is to use only the braking system to provide the braking force required by the vehicle.

[0010] In an embodiment of the present application, when it is determined that the deceleration is not less than a threshold value, it is directly determined that the energy recovery condition is not met, and the emergency braking state is entered, thereby improving the efficiency of emergency braking condition judgment.

[0011] In some possible embodiments, the current braking determination parameters include current expected deceleration, current battery state of charge, and current vehicle speed; The method further comprises: If it is determined that the current expected deceleration is less than a preset deceleration threshold and the current battery state of charge is not within a preset battery state of charge range, it is determined that the target vehicle does not meet the preset energy recovery conditions, and braking control is performed on the target vehicle according to a preset conventional braking strategy; Alternatively, if it is determined that the current expected deceleration is less than a preset deceleration threshold and the current vehicle speed is not within a preset vehicle speed range, it is determined that the target vehicle does not meet the preset energy recovery conditions, and braking control is performed on the target vehicle according to a preset conventional braking strategy; The preset conventional braking strategy is to use only the braking system to provide the braking force required by the vehicle.

[0012] In an embodiment of the present application, when it is determined that the deceleration is less than a threshold value, the accuracy of determining conventional braking conditions is improved by determining that the battery state of charge or the vehicle speed is not within a preset range.

[0013] In some possible embodiments, inputting the real-time collected vehicle operating parameters into the adaptively adjusted intelligent decision model to obtain a braking force distribution strategy result output by the intelligent decision model includes: Generating corresponding vehicle operation time series data based on the real-time collected vehicle operation parameters; wherein the vehicle operation parameters include maximum available regenerative braking force, front electric motor force, rear electric motor force, rear wheel hydraulic braking force, front wheel hydraulic braking force, vehicle speed, front wheel speed, rear wheel speed, and desired deceleration; Extracting features from the vehicle operation time series data based on the convolutional neural network in the intelligent decision-making model to obtain spatial features; Extracting features from the vehicle operation time series data based on the long short-term memory network in the intelligent decision-making model to obtain time series features; The intelligent decision-making model is used to perform prediction based on the spatial characteristics and the time series characteristics to obtain a braking force distribution strategy result output by the intelligent decision-making model.

[0014] In an embodiment of the present application, a convolutional neural network and a long short-term memory network are used to extract the features of the input parameters, and a braking force distribution strategy is predicted based on the fused features, thereby further improving the accuracy and real-time performance of the braking force distribution.

[0015] In some possible embodiments, using the intelligent decision model to perform prediction based on the spatial features and the time series features to obtain a braking force distribution strategy result output by the intelligent decision model includes: Using the intelligent decision model to make a prediction based on the spatial characteristics and the time series characteristics to obtain a corresponding braking force distribution coefficient output value; calculating, based on a preset loss function, respectively an energy recovery efficiency loss and a braking performance loss corresponding to an output value of the braking force distribution coefficient, and determining a corresponding comprehensive loss value based on the energy recovery efficiency loss and the braking performance loss; The model parameters of the intelligent decision-making model are iteratively updated using the gradient descent method with the goal of minimizing the comprehensive loss value until the preset convergence conditions are reached, and the braking force distribution strategy result output by the intelligent decision-making model is obtained based on the final braking force distribution coefficient output value.

[0016] In an embodiment of the present application, the model parameters of the intelligent decision-making model are iteratively updated by utilizing the gradient descent method with the goal of minimizing the comprehensive loss, so that the model parameters can be adjusted in real time, thereby further improving the accuracy and adaptability of the braking force distribution.

[0017] In some possible embodiments, performing braking control on the motor control system and the brake system respectively based on the braking force distribution strategy result includes: Determining a regenerative braking command and a hydraulic braking command based on a braking force distribution coefficient represented by a result of the braking force distribution strategy; Braking control is performed on the motor control system and the brake system based on the regenerative braking command and the hydraulic braking command, respectively.

[0018] In an embodiment of the present application, the accuracy of the braking force control is further improved by respectively determining the regenerative braking instruction and the hydraulic braking instruction based on the braking force distribution strategy result, and performing braking control on the motor control system and the braking system respectively according to the corresponding instructions.

[0019] In a second aspect, an embodiment of the present application provides an energy recovery control device for a vehicle, comprising: a determination parameter acquisition module, configured to respond to a braking request of a target vehicle and acquire a current braking determination parameter of the target vehicle; a braking strategy output module, configured to input the real-time collected vehicle operating parameters into the adaptively adjusted intelligent decision model when it is determined based on the current braking determination parameters that the target vehicle satisfies a preset energy recovery condition, and obtain a braking force distribution strategy result output by the intelligent decision model; A braking control module is used to perform braking control on the motor control system and the braking system respectively based on the braking force distribution strategy result; wherein, the motor control system is used to provide regenerative braking force and generate recovered energy suitable for replenishing energy to the power battery.

[0020] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor can implement the method described in any embodiment of the first aspect when executing the program.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any embodiment of the first aspect can be implemented.

[0022] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program, wherein when the computer program is executed by a processor, it can implement the method described in any embodiment of the first aspect.

[0023] In a sixth aspect, an embodiment of the present application provides a vehicle, comprising a controller, wherein the controller is configured to execute the method described in any embodiment of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A schematic flow chart of a vehicle energy recovery control method provided in an embodiment of the present application; Figure 2 This is a schematic diagram of determining the braking mode of a vehicle provided in an embodiment of the present application. Figure 3 A schematic structural diagram of an energy recovery control device for a vehicle provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0028] It's important to note that existing energy recovery strategies face the following challenges in comprehensively optimizing energy recovery efficiency and braking performance: 1. Balancing energy recovery objectives with braking performance is difficult; when allocating regenerative braking force to hydraulic braking, it's difficult to simultaneously optimize braking safety and energy recovery efficiency. 2. Poor adaptability to environmental and operating conditions: Traditional control strategies are often based on fixed rules and are unable to adapt to the complex and ever-changing real-world road conditions and driving behaviors. 3. Lack of real-time performance: Under complex operating conditions and with limited computing resources, it's difficult to optimize braking allocation strategies in real time.

[0029] In response to the problems existing in the above-mentioned prior art, an embodiment of the present application provides an energy recovery strategy based on deep learning, which achieves dual optimization of energy recovery efficiency and braking performance by intelligently optimizing braking force distribution.

[0030] like Figure 1 As shown, an embodiment of the present application provides a vehicle energy recovery control method, which may include the following steps: S1. Respond to a braking request of a target vehicle and obtain current braking determination parameters of the target vehicle.

[0031] Specifically, when the driver triggers braking by depressing the brake pedal, relevant parameters are first obtained as current braking determination parameters. These parameters are used to determine whether preset energy recovery conditions are met. If so, a combined braking strategy of regenerative braking and hydraulic braking is adopted; otherwise, regenerative braking is not performed. The current braking determination parameters can include one or more of the following: expected deceleration, vehicle speed, and battery state of charge.

[0032] S2. When it is determined that the target vehicle meets the preset energy recovery conditions based on the current braking judgment parameters, the vehicle operating parameters collected in real time are input into the adaptively adjusted intelligent decision model to obtain the braking force distribution strategy result output by the intelligent decision model.

[0033] Specifically, when it is determined based on the current braking judgment parameters that the target vehicle meets the preset energy recovery conditions, the adaptively adjusted intelligent decision-making model is called, and the current real-time collected vehicle operating parameters are input into it to obtain the braking force distribution strategy result output by the intelligent decision-making model.

[0034] Exemplarily, the intelligent decision-making model can adopt a deep learning model, and the deep learning model is trained by acquiring data from a preset historical period in a preset cycle to adaptively adjust the parameters of the model, thereby improving the real-time performance of the model output.

[0035] S3. Based on the braking force distribution strategy result, the motor control system and the brake system are respectively brake-controlled; wherein the motor control system is used to provide regenerative braking force and generate recovered energy suitable for replenishing energy to the power battery.

[0036] In some possible embodiments, step S3 may include: S301, determining a regenerative braking command and a hydraulic braking command based on a braking force distribution coefficient represented by a braking force distribution strategy result; S302 : Perform braking control on the motor control system and the brake system respectively based on the regenerative braking instruction and the hydraulic braking instruction.

[0037] For example, the braking force distribution strategy results may include distribution coefficients (proportional values) representing hydraulic braking and regenerative braking. Based on these distribution coefficients, the motor control system and brake system can be controlled to meet the current desired braking force. The motor control system is used to provide regenerative braking force, and during regenerative braking, it can generate corresponding recovered energy, which is used to charge the vehicle's power battery.

[0038] It should be noted that during the energy recovery process, feedback information such as the power battery status and vehicle driving status is continuously monitored. If abnormal conditions such as excessive battery temperature or abnormal vehicle vibration occur, the energy recovery strategy is promptly adjusted or suspended to ensure vehicle operation safety. In addition, this feedback information can be re-input into the algorithm model to optimize subsequent energy recovery decisions, forming a closed-loop control.

[0039] Based on this, by inputting the real-time collected vehicle operating parameters into the adaptively adjusted intelligent decision-making model, it is possible to output a braking force distribution strategy that is adapted to the current operating conditions, thereby effectively improving the accuracy and adaptability of the braking force distribution.

[0040] In some possible embodiments, the current braking determination parameters include the current desired deceleration, the current battery state of charge, and the current vehicle speed; In step S2, determining whether the target vehicle meets a preset energy recovery condition based on the current braking determination parameter includes: S201: If it is determined that the current expected deceleration is less than a preset deceleration threshold, the current battery state of charge is within a preset battery state of charge range, and the current vehicle speed is within a preset vehicle speed range, then it is determined that the target vehicle meets a preset energy recovery condition.

[0041] Exemplarily, the energy recovery condition can be set with parameter conditions from three aspects, including: the current expected deceleration is less than a preset deceleration threshold, the current battery state of charge is within a preset battery state of charge range, and the current vehicle speed is within a preset vehicle speed range. When all three parameters meet the corresponding thresholds or ranges, the preset energy recovery condition is considered to be met.

[0042] When it is determined that the target vehicle meets the preset energy recovery conditions, the vehicle is controlled to enter a compound braking state; in this state, the motor and hydraulic braking system coordinate control to jointly complete braking.

[0043] Based on this, by combining the three parameters of deceleration, battery state of charge and vehicle speed to comprehensively judge whether the energy recovery conditions are met, the comprehensiveness and reliability of the energy recovery condition judgment are improved.

[0044] In some possible embodiments, the current braking determination parameter includes a current desired deceleration; The vehicle energy recovery control method further includes: If it is determined that the current expected deceleration is not less than the preset deceleration threshold, it is determined that the target vehicle does not meet the preset energy recovery conditions, and the target vehicle is braked according to the preset emergency braking strategy; wherein the preset emergency braking strategy is to use only the braking system to provide the braking force required by the vehicle.

[0045] like Figure 2As shown, for example, when obtaining the current braking determination parameter, the current expected deceleration can be first obtained, and the current expected deceleration can be compared with the preset deceleration threshold. If it is determined that the current expected deceleration is less than the preset deceleration threshold, other types of current braking determination parameters are obtained for further comparison and determination; if it is determined that the current expected deceleration is not less than the preset deceleration threshold (i.e. , is the current expected deceleration, is the deceleration threshold for the vehicle to enter an emergency braking state), it is directly determined that the target vehicle does not meet the preset energy recovery conditions and enters an emergency braking state.

[0046] For example, in an emergency braking state, only hydraulic braking is used without regenerative braking. In other words, the preset emergency braking strategy is to use only the braking system to provide the required braking force of the vehicle (determined according to the current expected deceleration).

[0047] Based on this, when it is determined that the deceleration is not less than the threshold, it is directly determined that the energy recovery condition is not met and the emergency braking state is entered, thereby improving the efficiency of emergency braking condition judgment.

[0048] In some possible embodiments, the current braking determination parameters include the current desired deceleration, the current battery state of charge, and the current vehicle speed; The vehicle energy recovery control method further includes: If it is determined that the current expected deceleration is less than the preset deceleration threshold and the current battery state of charge is not within the preset battery state of charge range, it is determined that the target vehicle does not meet the preset energy recovery conditions, and the target vehicle is braked according to the preset conventional braking strategy; Alternatively, if it is determined that the current expected deceleration is less than a preset deceleration threshold and the current vehicle speed is not within a preset vehicle speed range, it is determined that the target vehicle does not meet the preset energy recovery conditions, and braking control is performed on the target vehicle according to a preset conventional braking strategy; Among them, the preset conventional braking strategy is to use only the braking system to provide the braking force required by the vehicle.

[0049] For example, the current expected deceleration can be first obtained and compared with a preset deceleration threshold. If it is determined that the current expected deceleration is less than the preset deceleration threshold, the current battery state of charge or the current vehicle speed can be obtained for further comparison and determination.

[0050] For example, if it is determined that the current expected deceleration is less than the preset deceleration threshold, and the current battery state of charge is not within the preset battery state of charge range, it is determined that the target vehicle does not meet the preset energy recovery conditions (i.e. ,and , In other words, when the battery state of charge is too high or too low, energy recovery should not be performed to protect battery safety. At this time, braking control should be performed according to the conventional braking strategy.

[0051] For example, if it is determined that the current expected deceleration is less than the preset deceleration threshold and the current vehicle speed is not within the preset vehicle speed range, it is determined that the target vehicle does not meet the preset energy recovery conditions (i.e. ,and , In other words, when the vehicle speed is too high or too low, regenerative braking should not be performed to ensure braking stability. At this time, braking control should be performed according to the conventional braking strategy.

[0052] It is understandable that, in the conventional braking state, only hydraulic braking is used and regenerative braking is not performed. That is, the preset conventional braking strategy is to use only the braking system to provide the braking force required by the vehicle.

[0053] Based on this, when it is determined that the deceleration is less than a threshold, the accuracy of judging normal braking conditions is improved by judging that the battery state of charge or the vehicle speed is not within a preset range.

[0054] In some possible embodiments, in step S2, the real-time collected vehicle operating parameters are input into the adaptively adjusted intelligent decision model to obtain a braking force distribution strategy result output by the intelligent decision model, including: S211. Generate corresponding vehicle operation time series data based on the real-time collected vehicle operation parameters; wherein the vehicle operation parameters include maximum available regenerative braking force, front electric motor force, rear electric motor force, rear wheel hydraulic braking force, front wheel hydraulic braking force, vehicle speed, front wheel speed, rear wheel speed, and expected deceleration; S212. Extracting features from the vehicle operation time series data based on the convolutional neural network in the intelligent decision-making model to obtain spatial features; S213. Extract features from the vehicle operation time series data based on the long short-term memory network in the intelligent decision-making model to obtain time series features; S214. Use the intelligent decision-making model to make predictions based on spatial features and time series features, and obtain a braking force distribution strategy result output by the intelligent decision-making model.

[0055] It should be noted that a variety of sensors are integrated into pure electric vehicles to collect vehicle operating parameters in real time, including maximum available regenerative braking force, front electric motor force, rear electric motor force, rear wheel hydraulic braking force, front wheel hydraulic braking force, vehicle speed, front wheel speed, rear wheel speed, etc.

[0056] An intelligent decision-making model is built based on a hybrid architecture of long short-term memory (LSTM) and convolutional neural network (CNN) to predict the optimal braking force distribution plan (braking force distribution strategy results) based on the collected data.

[0057] Based on this, the features of the input parameters are extracted through the combination of convolutional neural networks and long short-term memory networks, and the braking force distribution strategy is predicted based on the fused features, thereby further improving the accuracy and real-time performance of the braking force distribution.

[0058] In some possible embodiments, step S214, using the intelligent decision model to perform prediction based on spatial features and time series features to obtain a braking force distribution strategy result output by the intelligent decision model, may include: S2141. Using an intelligent decision-making model to perform prediction based on spatial characteristics and time series characteristics, to obtain a corresponding braking force distribution coefficient output value; S2142: Calculating the energy recovery efficiency loss and the braking performance loss corresponding to the output value of the braking force distribution coefficient based on a preset loss function, and determining a corresponding comprehensive loss value based on the energy recovery efficiency loss and the braking performance loss; S2143. Use the gradient descent method to iteratively update the model parameters of the intelligent decision-making model with the goal of minimizing the comprehensive loss value until the preset convergence conditions are reached, and obtain the braking force distribution strategy result output by the intelligent decision-making model based on the final braking force distribution coefficient output value.

[0059] It should be noted that when entering the combined braking mode of regenerative braking + hydraulic braking, the intelligent decision-making model built based on deep learning can be used to predict the braking force distribution strategy.

[0060] The process of establishing the intelligent decision-making model is as follows: Step 1: Design the core objectives of the intelligent optimization algorithm; Design an energy recovery strategy based on deep learning by inputting vehicle state parameters , output the braking force distribution strategy results, including the regenerative braking force distribution coefficient and hydraulic braking force distribution coefficient The optimization goal of the model is to maximize the energy recovery efficiency and optimize braking performance .

[0061] Step 2, input and output definitions; (1) Input vector definition: Input status parameters It mainly includes the following components:

[0062] in, Indicates the maximum available regenerative braking force in N. : Regenerative braking force of the front / rear axles respectively, unit: N. : The hydraulic braking force of the front / rear axles respectively, unit N. v Indicates vehicle speed in m / s. Indicates the front wheel speed in rad / s.

[0063] (2) Output target definition: Output braking force distribution coefficient:

[0064] Indicates the regenerative braking force distribution coefficient.

[0065] Indicates the hydraulic braking force distribution coefficient.

[0066] Step 3: Establish the deep learning model structure; use the convolutional neural network (CNN) to extract the spatial features of the input data, and use the long short-term memory network (LSTM) to capture the time series features, and finally calculate the braking force distribution coefficient through the fully connected layer. and .

[0067] Step 3.1, data feature extraction (CNN module); Input status parameters (such as vehicle speed, front and rear electric brake force, hydraulic brake force, etc.) as the input of the convolutional neural network (CNN) to extract the spatial features of the input data.

[0068] The output of the convolutional layer is:

[0069] in, Represents the convolution operation, which is used to extract local features from the input data; Represents the convolutional layer bias term; ReLU represents the activation function, defined as , to ensure that the output is non-negative.

[0070] Step 3.2, dynamic feature extraction (LSTM module); In order to capture time series features (such as the dynamics of vehicle state changes), an LSTM network is used to process time series input:

[0071] in, Represents the LSTM hidden layer state; Represents the LSTM unit state; Represents the hidden layer and unit states at the previous time step.

[0072] Step 3.3, output layer (fully connected layer) The features of CNN and LSTM are integrated and the distribution coefficient is calculated through the fully connected layer:

[0073] in, Represents the weights and biases of the fully connected layer; Indicates that the output is normalized to a probability value to ensure .

[0074] Step 4, loss function definition; The objective loss function consists of two parts: energy recovery efficiency loss and loss of braking performance .

[0075] Step 4.1, calculation of energy recovery efficiency loss; Energy recovery efficiency is the ratio of actual recovered energy to theoretical maximum recovered energy:

[0076] in, Indicates the kinetic energy actually recovered; It is the theoretical maximum recovered kinetic energy.

[0077] The energy recovery efficiency loss is defined as:

[0078] Step 4.2, Loss of Braking Performance calculate; Braking performance depends on total braking force Braking force required by the driver Deviation:

[0079] Among them, the total braking force It can be converted according to the actual deceleration corresponding to the braking control; the required braking force It can be converted according to the corresponding expected deceleration.

[0080] Step 4.3, comprehensive loss function is established; Combining energy recovery efficiency and braking performance, the comprehensive loss function is defined as:

[0081] in and is the weight coefficient, which is used to adjust the impact of the two parts of loss on the braking force distribution decision.

[0082] Step 5, optimization process and constraints; Step 5.1, braking force distribution optimization; Regenerative braking force and hydraulic braking force are optimized according to the distribution coefficient, where: Regenerative braking force:

[0083] Hydraulic braking force:

[0084] Step 5.2, constraints: (1) Braking balance constraint: The braking forces on the front and rear axles must be balanced:

[0085] (2) Maximum braking force limit:

[0086] Step 5.3, optimization target establishment; The final optimization goal is to minimize the comprehensive loss function:

[0087] Exemplarily, the parameters of the deep learning model can be iteratively updated using a gradient descent method until a preset convergence condition is reached.

[0088] Step 5.4, convergence conditions are determined; The key to gradient descent is calculating the gradient of the loss function with respect to the model parameters. To achieve model convergence, the loss function is differentiated and the parameters are updated. Gradient descent convergence is determined by checking whether the change in the loss function is sufficiently small. Convergence is considered achieved when the difference in the loss function between two iterations is less than a predetermined threshold.

[0089] For example, the specific convergence conditions are:

[0090] in, It is a preset small positive number, usually called the convergence threshold. If the change in the loss function is less than the threshold, the iteration stops.

[0091] It should be noted that this application has the following beneficial effects compared to the prior art: (1) Improved energy recovery efficiency: The embodiments of the present application achieve a significant improvement in energy recovery efficiency through an intelligent braking force distribution strategy. Compared with traditional control methods, energy recovery efficiency is improved by 20%-30%. This is because the embodiments of the present application can adjust the regenerative braking force control strategy in real time according to the dynamic state of the vehicle, maximizing energy recovery during braking. Through the training and prediction of the deep learning model, the optimal energy recovery strategy can be intelligently selected based on the current operating conditions.

[0092] (2) Optimize braking performance and ensure driving safety. The embodiments of the present application not only optimize energy recovery efficiency but also maintain good braking performance. The deep learning algorithm can reasonably allocate regenerative braking force and hydraulic braking force according to the vehicle's braking needs and environmental changes, thereby ensuring the vehicle's braking stability and responsiveness under various working conditions, and avoiding safety hazards such as brake failure or wheel lock caused by excessive energy recovery. Through real-time adjustment of the deep learning model, the error in braking performance is controlled within 3%, effectively ensuring that the driver's braking needs are responded to quickly and accurately.

[0093] (3) Strong adaptability, adapting to complex road conditions and driving behaviors; traditional energy recovery strategies usually perform poorly under different road conditions and driving behaviors because they are often based on fixed rules. By using deep learning algorithms, the embodiments of the present application can dynamically adjust the energy recovery strategy according to the actual state of the vehicle. Whether on urban roads, mountain roads, or highways, the system can make intelligent adjustments based on the real-time collected vehicle speed, braking conditions, and vehicle status to ensure that the vehicle always recovers energy in the best way and provides appropriate braking force. In addition, the deep learning model can learn relevant knowledge about the driving behavior of different drivers and automatically adapt to the personalized needs of the drivers, so that different drivers can get the most optimized driving experience.

[0094] (4) High real-time performance, ensuring rapid system response: Because deep learning algorithms can process vehicle status data in real time and make decisions quickly, the embodiments of the present application have high real-time performance during the processing process. The vehicle's driving status and braking requirements can be transmitted to the control system in real time, and the algorithm can calculate the optimal braking force distribution plan in a very short time, ensuring timely and accurate braking response.

[0095] (5) Strong system robustness: By using deep learning models to train large-scale historical data sets, the embodiments of the present application can not only handle common driving conditions, but also adapt to some complex and uncertain driving conditions. For example, when special conditions such as road slippage and sudden braking occur, the deep learning model can automatically adjust the strategy based on historical experience and real-time data, thereby enhancing the robustness and reliability of the system.

[0096] Please refer to Figure 3, Figure 3 The following is a block diagram showing the composition of the energy recovery control device for a vehicle provided by some embodiments of the present application. It should be understood that the energy recovery control device for the vehicle is similar to the above Figure 1 Corresponding to the method embodiment, the various steps involved in the above method embodiment can be executed. The specific functions of the energy recovery control device of the vehicle can be found in the description above. To avoid repetition, the detailed description is appropriately omitted here.

[0097] Figure 3 The energy recovery control device of a vehicle includes at least one software function module that can be stored in a memory in the form of software or firmware or fixed in the energy recovery control device of the vehicle, and the energy recovery control device of the vehicle includes: a determination parameter acquisition module 310 for responding to a braking request of a target vehicle and acquiring a current braking determination parameter of the target vehicle; A braking strategy output module 320 is configured to input the real-time collected vehicle operating parameters into the adaptively adjusted intelligent decision model when it is determined based on the current braking determination parameters that the target vehicle meets the preset energy recovery conditions, thereby obtaining a braking force distribution strategy result output by the intelligent decision model; The braking control module 330 is used to perform braking control on the motor control system and the braking system respectively based on the braking force distribution strategy result; wherein the motor control system is used to provide regenerative braking force and generate recovered energy suitable for replenishing energy to the power battery.

[0098] It can be understood that the above-mentioned device embodiment corresponds to the method embodiment of the present invention. The vehicle energy recovery control device provided by the embodiment of the present invention can implement the vehicle energy recovery control method provided by any method embodiment of the present invention.

[0099] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method, and will not be described in detail here.

[0100] like Figure 4 As shown, some embodiments of the present application provide an electronic device 400, which includes: a memory 410, a processor 420, and a computer program stored in the memory 410 and executable on the processor 420, wherein the processor 420 reads the program from the memory 410 through the bus 430 and executes the program to implement a method of any embodiment included in the above-mentioned vehicle energy recovery control method.

[0101] Processor 420 can process digital signals and can include various computing architectures, such as a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements a combination of multiple instruction sets. In some examples, processor 420 can be a microprocessor.

[0102] The memory 410 can be used to store instructions executed by the processor 420 or data related to the execution of instructions. These instructions and / or data may include code for implementing some or all functions of one or more modules described in the embodiments of this application. The processor 420 of the embodiment of the present disclosure can be used to execute the instructions in the memory 410 to implement the method shown above. The memory 410 includes dynamic random access memory, static random access memory, flash memory, optical memory, or other memory known to those skilled in the art.

[0103] Some embodiments of the present application further provide a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method described in the method embodiment is executed.

[0104] Some embodiments of the present application further provide a computer program product, which, when running on a computer, enables the computer to execute the method described in the method embodiment.

[0105] Some embodiments of the present application also provide a vehicle, comprising a controller, wherein the controller is configured to execute the method described in the method embodiment.

[0106] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For device embodiments, since they are generally similar to method embodiments, their description is relatively simple, and for relevant details, reference can be made to the description of the method embodiments.

[0107] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a portion of code, and the module, program segment, or a portion of code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0108] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0109] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0110] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures.

[0111] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0112] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

Claims

1. A vehicle energy recovery control method, characterized in that: include: Responding to a braking request of a target vehicle and obtaining a current braking determination parameter of the target vehicle; When it is determined based on the current braking determination parameters that the target vehicle meets the preset energy recovery conditions, the vehicle operating parameters collected in real time are input into the adaptively adjusted intelligent decision model to obtain a braking force distribution strategy result output by the intelligent decision model; Based on the braking force distribution strategy result, the motor control system and the brake system are respectively brake-controlled; wherein, the motor control system is used to provide regenerative braking force and generate recovered energy suitable for replenishing energy to the power battery.

2. The vehicle energy recovery control method according to claim 1, characterized in that: The current braking determination parameters include the current expected deceleration, the current battery state of charge and the current vehicle speed; The determining, based on the current braking determination parameter, that the target vehicle meets a preset energy recovery condition includes: If it is determined that the current expected deceleration is less than a preset deceleration threshold, the current battery state of charge is within a preset battery state of charge range, and the current vehicle speed is within a preset vehicle speed range, then it is determined that the target vehicle meets the preset energy recovery condition.

3. The vehicle energy recovery control method according to claim 1, characterized in that: The current braking determination parameter includes a current expected deceleration; The method further comprises: If it is determined that the current expected deceleration is not less than a preset deceleration threshold, it is determined that the target vehicle does not meet the preset energy recovery conditions, and the target vehicle is braked according to a preset emergency braking strategy; wherein the preset emergency braking strategy is to use only the braking system to provide the braking force required by the vehicle.

4. The vehicle energy recovery control method according to claim 1, characterized in that: The current braking determination parameters include the current expected deceleration, the current battery state of charge and the current vehicle speed; The method further comprises: If it is determined that the current expected deceleration is less than a preset deceleration threshold and the current battery state of charge is not within a preset battery state of charge range, it is determined that the target vehicle does not meet the preset energy recovery conditions, and braking control is performed on the target vehicle according to a preset conventional braking strategy; Alternatively, if it is determined that the current expected deceleration is less than a preset deceleration threshold and the current vehicle speed is not within a preset vehicle speed range, it is determined that the target vehicle does not meet the preset energy recovery conditions, and braking control is performed on the target vehicle according to a preset conventional braking strategy; The preset conventional braking strategy is to use only the braking system to provide the braking force required by the vehicle.

5. The vehicle energy recovery control method according to claim 1, characterized in that: The step of inputting the real-time collected vehicle operating parameters into the adaptively adjusted intelligent decision-making model to obtain the braking force distribution strategy result output by the intelligent decision-making model includes: Generating corresponding vehicle operation time series data based on the real-time collected vehicle operation parameters; wherein the vehicle operation parameters include maximum available regenerative braking force, front electric motor force, rear electric motor force, rear wheel hydraulic braking force, front wheel hydraulic braking force, vehicle speed, front wheel speed, rear wheel speed, and desired deceleration; Extracting features from the vehicle operation time series data based on the convolutional neural network in the intelligent decision-making model to obtain spatial features; Extracting features from the vehicle operation time series data based on the long short-term memory network in the intelligent decision-making model to obtain time series features; The intelligent decision-making model is used to perform prediction based on the spatial characteristics and the time series characteristics to obtain a braking force distribution strategy result output by the intelligent decision-making model.

6. The vehicle energy recovery control method according to claim 5, characterized in that: The using the intelligent decision model to perform prediction based on the spatial features and the time series features to obtain a braking force distribution strategy result output by the intelligent decision model includes: Using the intelligent decision model to make a prediction based on the spatial characteristics and the time series characteristics to obtain a corresponding braking force distribution coefficient output value; calculating, based on a preset loss function, respectively an energy recovery efficiency loss and a braking performance loss corresponding to an output value of the braking force distribution coefficient, and determining a corresponding comprehensive loss value based on the energy recovery efficiency loss and the braking performance loss; The model parameters of the intelligent decision-making model are iteratively updated using the gradient descent method with the goal of minimizing the comprehensive loss value until the preset convergence conditions are reached, and the braking force distribution strategy result output by the intelligent decision-making model is obtained based on the final braking force distribution coefficient output value.

7. The vehicle energy recovery control method according to claim 1, characterized in that: The performing braking control on the motor control system and the brake system respectively based on the braking force distribution strategy result includes: Determining a regenerative braking command and a hydraulic braking command based on a braking force distribution coefficient represented by a result of the braking force distribution strategy; Braking control is performed on the motor control system and the brake system based on the regenerative braking command and the hydraulic braking command, respectively.

8. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the energy recovery control method for a vehicle according to any one of claims 1 to 7 can be implemented when the processor executes the program.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the energy recovery control method for a vehicle according to any one of claims 1 to 7 is executed.

10. A vehicle, characterized in that: The device comprises a controller configured to execute the vehicle energy recovery control method according to any one of claims 1 to 7.

Images