Energy recovery control method, device, medium and vehicle of vehicle

Abstract

The embodiment of the application provides a kind of energy recovery control method, equipment, medium and vehicle of vehicle, it is related to brake control technical field.The method comprises: in response to the braking request of target vehicle, and the current braking determination parameter of target vehicle is acquired;In the case where it is determined that the target vehicle meets the preset energy recovery condition based on the current braking determination parameter, vehicle operating parameter is input into intelligent decision model, and braking force distribution strategy result is obtained;Braking control is carried out on motor control system and brake system based on braking force distribution strategy result;Wherein, motor control system is used to provide regenerative braking force and produce recovery energy suitable for energy supplement to power battery.The embodiment of the application can output braking force distribution strategy suitable for current operating condition by inputting real-time collected vehicle operating parameter into self-adaptive intelligent decision model, so as to effectively improve the accuracy and adaptability of braking force distribution.

Description

Technical Field

[0001] This application relates to the field of braking control technology, and more specifically, to a method, device, medium, and vehicle for energy recovery control. Background Technology

[0002] With increasing global attention to environmental protection and sustainable energy development, new energy vehicles have become widely popular as a green mode of transportation. Energy recovery systems are one of the key technologies for improving energy efficiency and extending the driving range of new energy vehicles, especially pure electric vehicles. In electric and hybrid vehicles, the regenerative braking system (RBS) utilizes the kinetic energy generated during braking to convert it into electrical energy and store it in the battery, thereby improving the vehicle's energy efficiency and increasing its driving 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 targets. In addition, it mainly relies on fixed rules to achieve braking force distribution, which is not very adaptable to the environment and operating conditions. Summary of the Invention

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

[0005] In a first aspect, embodiments of this application provide a method for controlling energy recovery in a vehicle, including:

[0006] In response to a braking request from the target vehicle, the current braking determination parameters of the target vehicle are obtained;

[0007] If the target vehicle meets the preset energy recovery conditions based on the current braking determination parameters, the real-time collected vehicle operating parameters are input into the adaptively adjusted intelligent decision model to obtain the braking force distribution strategy result output by the intelligent decision model.

[0008] Based on the results of the braking force distribution strategy, braking control is performed on the motor control system and the braking system respectively; wherein, the motor control system is used to provide regenerative braking force and generate recoverable energy suitable for replenishing the power battery.

[0009] In this embodiment of the application, by inputting the real-time collected vehicle operating parameters into the 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 braking force distribution.

[0010] 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;

[0011] The step of determining whether the target vehicle meets the preset energy recovery conditions based on the current braking determination parameters includes:

[0012] 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 the target vehicle is determined to meet the preset energy recovery conditions.

[0013] In this embodiment, the energy recovery conditions are comprehensively judged by combining three parameters: deceleration, battery state of charge, and vehicle speed, thereby improving the comprehensiveness and reliability of the energy recovery condition judgment.

[0014] In some possible embodiments, the current braking determination parameter includes the current desired deceleration;

[0015] The method further includes:

[0016] If it is determined that the current expected deceleration is not less than a preset deceleration threshold, then 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 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.

[0017] In this embodiment of the application, 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.

[0018] 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;

[0019] The method further includes:

[0020] 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, then 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.

[0021] 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, then 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 conventional braking strategy.

[0022] The preset conventional braking strategy is to use only the braking system to provide the braking force required by the vehicle.

[0023] In this embodiment of the application, when the deceleration is determined to be less than a threshold, the accuracy of judging normal braking conditions is improved by judging the battery state of charge or the vehicle speed is not in a preset range.

[0024] In some possible embodiments, the step of inputting the real-time collected vehicle operating parameters into an adaptively adjusted intelligent decision-making model to obtain the braking force distribution strategy result output by the intelligent decision-making model includes:

[0025] Based on real-time collected vehicle operating parameters, corresponding vehicle operating time series data are generated; wherein, the vehicle operating parameters include maximum available regenerative braking force, front electric motor power, rear electric motor power, rear wheel hydraulic braking force, front wheel hydraulic braking force, vehicle speed, front wheel speed, rear wheel speed, and desired deceleration;

[0026] Based on the convolutional neural network in the intelligent decision-making model, spatial features are extracted from the vehicle operation time series data.

[0027] Based on the long short-term memory network in the intelligent decision-making model, feature extraction is performed on the vehicle operation time series data to obtain time series features;

[0028] The intelligent decision-making model is used to make predictions based on the spatial features and the time series features to obtain the braking force allocation strategy results output by the intelligent decision-making model.

[0029] In this embodiment, features of the input parameters are extracted by combining convolutional neural networks and long short-term memory networks, and braking force allocation strategy is predicted based on the fused features, thereby further improving the accuracy and real-time performance of braking force allocation.

[0030] In some possible embodiments, the step of using the intelligent decision-making model to predict based on the spatial features and the time series features to obtain the braking force allocation strategy result output by the intelligent decision-making model includes:

[0031] The intelligent decision-making model is used to make predictions based on the spatial features and the time series features to obtain the corresponding braking force distribution coefficient output value.

[0032] Based on a preset loss function, the energy recovery efficiency loss and braking performance loss corresponding to the output value of the braking force distribution coefficient are calculated respectively, and the corresponding comprehensive loss value is determined based on the energy recovery efficiency loss and the braking performance loss.

[0033] 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 condition is reached. The braking force allocation strategy result output by the intelligent decision-making model is obtained based on the final braking force allocation coefficient output value.

[0034] In this embodiment, the model parameters of the intelligent decision-making model are iteratively updated using the gradient descent method with the goal of minimizing the overall loss. This allows for real-time adjustment of the model parameters, further improving the accuracy and adaptability of braking force distribution.

[0035] In some possible embodiments, the braking control of the motor control system and the braking system based on the braking force distribution strategy results includes:

[0036] The regenerative braking command and the hydraulic braking command are determined based on the braking force distribution coefficients characterized by the braking force distribution strategy results.

[0037] The motor control system and the braking system are respectively controlled by the regenerative braking command and the hydraulic braking command.

[0038] In this embodiment, regenerative braking commands and hydraulic braking commands are determined based on the results of the braking force distribution strategy, and braking control is performed on the motor control system and the braking system according to the corresponding commands, thereby further improving the accuracy of braking force control.

[0039] Secondly, embodiments of this application provide a vehicle energy recovery control device, comprising:

[0040] The determination parameter acquisition module is used to respond to the braking request of the target vehicle and acquire the current braking determination parameters of the target vehicle.

[0041] The braking strategy output module is used to input the real-time collected vehicle operating parameters into the adaptively adjusted intelligent decision model when the target vehicle meets the preset energy recovery conditions based on the current braking judgment parameters, so as to obtain the braking force distribution strategy result output by the intelligent decision model.

[0042] The 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 results; wherein, the motor control system is used to provide regenerative braking force and generate recovered energy suitable for replenishing the power battery.

[0043] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, can implement the method described in any embodiment of the first aspect.

[0044] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the method described in any embodiment of the first aspect.

[0045] Fifthly, embodiments of this application provide a computer program product, the computer program product including 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.

[0046] In a sixth aspect, embodiments of this application provide a vehicle including a controller, the controller being configured to perform the method described in any embodiment of the first aspect. Attached Figure Description

[0047] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 A schematic flowchart of a vehicle energy recovery control method provided in an embodiment of this application;

[0049] Figure 2 This is a schematic diagram of vehicle braking mode determination provided in an embodiment of this application.

[0050] Figure 3 This is a schematic diagram of the structure of a vehicle energy recovery control device provided in an embodiment of this application;

[0051] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0052] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0053] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0054] It should be noted that existing energy recovery strategies have the following problems in comprehensively optimizing energy recovery efficiency and braking performance: 1. Difficulty in balancing energy recovery targets and braking performance; when allocating regenerative braking force and hydraulic braking force, it is difficult to simultaneously optimize braking safety and energy recovery efficiency. 2. Poor adaptability to environment and operating conditions; traditional control strategies are mostly based on fixed rules and cannot adapt to complex and changing actual road conditions and driving behaviors. 3. Insufficient real-time performance; under complex operating conditions and with limited computing resources, it is difficult to optimize braking allocation strategies in real time.

[0055] To address the problems existing in the prior art, this 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.

[0056] like Figure 1 As shown in the figure, this application provides a vehicle energy recovery control method, which may include the following steps:

[0057] S1. Respond to the braking request of the target vehicle and obtain the current braking determination parameters of the target vehicle.

[0058] Specifically, when the driver triggers braking by pressing the brake pedal, relevant parameters are first acquired as current braking determination parameters. These parameters are used to determine whether the 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 types of current braking determination parameters may include one or more of the following: desired deceleration, vehicle speed, and battery state of charge.

[0059] S2. Based on the current braking judgment parameters, if the target vehicle meets the preset energy recovery conditions, the real-time collected vehicle operating parameters are input into the adaptively adjusted intelligent decision model to obtain the braking force distribution strategy results output by the intelligent decision model.

[0060] Specifically, when the target vehicle meets the preset energy recovery conditions based on the current braking judgment parameters, the adaptive intelligent decision model is invoked, and the currently collected real-time vehicle operating parameters are input into it to obtain the braking force distribution strategy result output by the intelligent decision model.

[0061] For example, the intelligent decision-making model can employ a deep learning model, which is trained by acquiring data from a preset historical period according to a preset cycle, so as to adaptively adjust the model's parameters and thereby improve the real-time performance of the model's output.

[0062] S3. Based on the results of the braking force distribution strategy, braking control is performed on the motor control system and the braking system respectively; wherein, the motor control system is used to provide regenerative braking force and generate recoverable energy suitable for replenishing the power battery.

[0063] In some possible embodiments, step S3 may include:

[0064] S301. The regenerative braking command and the hydraulic braking command are determined based on the braking force distribution coefficient characterized by the braking force distribution strategy results.

[0065] S302. Based on regenerative braking commands and hydraulic braking commands, brake control is performed on the motor control system and the braking system, respectively.

[0066] For example, the braking force distribution strategy result may include a distribution coefficient (proportional value) characterizing hydraulic braking and regenerative braking. Based on this distribution coefficient, the motor control system and the braking system can be controlled separately to perform braking to meet the current desired braking force requirement. The motor control system provides regenerative braking force and can generate corresponding recovered energy during regenerative braking to charge the vehicle's battery.

[0067] It should be noted that during the energy recovery process, feedback information such as the status of the power battery and the vehicle's driving status is continuously monitored. If abnormal situations such as excessively high battery temperature or abnormal vehicle vibration occur, the energy recovery strategy is adjusted or suspended in a timely manner to ensure vehicle operating safety. Furthermore, this feedback information can be re-inputted into the algorithm model to optimize subsequent energy recovery decisions, forming a closed-loop control system.

[0068] Based on this, by inputting the real-time collected vehicle operating parameters into the adaptive 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 braking force distribution.

[0069] 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;

[0070] In step S2, based on the current braking determination parameters, it is determined that the target vehicle meets the preset energy recovery conditions, including:

[0071] S201. If it is determined that the current expected deceleration is less than the preset deceleration threshold, and the current battery state of charge is within the preset battery state of charge range, and the current vehicle speed is within the preset vehicle speed range, then it is determined that the target vehicle meets the preset energy recovery conditions.

[0072] For example, the energy recovery conditions can be set from three aspects: 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. The preset energy recovery conditions are considered to be met only when all three parameters meet the corresponding thresholds or ranges.

[0073] When the target vehicle meets the preset energy recovery conditions, the vehicle is controlled to enter a compound braking state; in this state, the electric motor and hydraulic braking system coordinate and control to complete the braking together.

[0074] Based on this, by combining three parameters—deceleration, battery state of charge, and vehicle speed—to comprehensively determine whether the energy recovery conditions are met, the comprehensiveness and reliability of the energy recovery condition judgment are improved.

[0075] In some possible embodiments, the current braking determination parameter includes the current desired deceleration;

[0076] Vehicle energy recovery control methods also include:

[0077] If it is determined that the current expected deceleration is not less than the preset deceleration threshold, then 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 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.

[0078] like Figure 2 As shown, for example, when obtaining the current braking determination parameters, the current expected deceleration can be obtained first, and then compared with a 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 judgment; if it is determined that the current expected deceleration is not less than the preset deceleration threshold (i.e., ... , To reduce the current expected speed, If the deceleration threshold for the vehicle to enter emergency braking state is set, it is directly determined that the target vehicle does not meet the preset energy recovery conditions and enters emergency braking state.

[0079] For example, in an emergency braking situation, only hydraulic braking is used, and regenerative braking is not performed. That is, the preset emergency braking strategy is to use only the braking system to provide the braking force required by the vehicle (determined based on the current desired deceleration).

[0080] Based on this, when the deceleration is determined to be 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.

[0081] 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;

[0082] Vehicle energy recovery control methods also include:

[0083] 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, then 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.

[0084] Alternatively, 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, then 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.

[0085] The preset conventional braking strategy is to use only the braking system to provide the braking force required by the vehicle.

[0086] For example, the current expected deceleration can be obtained first, and then 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 judgment.

[0087] For example, 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, then it is determined that the target vehicle does not meet the preset energy recovery conditions (i.e., ,and , These are the upper and lower limits of the battery's state of charge (SOC). In other words, when the battery's SOC is too high or too low, energy recovery should not be performed to protect the battery's safety, and braking control should be carried out according to the conventional braking strategy.

[0088] For example, 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 speed range, then it is determined that the target vehicle does not meet the preset energy recovery conditions (i.e., ,and , These are the upper and lower speed limits, respectively. In other words, when the vehicle speed is too high or too low, regenerative braking should not be used to ensure braking stability; instead, conventional braking strategies should be employed for braking control.

[0089] Understandably, under normal braking conditions, only hydraulic braking is used, and regenerative braking is not performed. In other words, the preset normal braking strategy is to use only the braking system to provide the braking force required by the vehicle.

[0090] Based on this, when the deceleration is determined to be less than the threshold, the accuracy of judging normal braking conditions is improved by judging the battery charge state or the vehicle speed is not within the preset range.

[0091] In some possible embodiments, in step S2, the real-time collected vehicle operating parameters are input into the adaptively adjusted intelligent decision-making model to obtain the braking force distribution strategy result output by the intelligent decision-making model, including:

[0092] S211. Generate corresponding vehicle operation time series data based on real-time collected vehicle operation parameters; wherein, vehicle operation parameters include maximum available regenerative braking force, front electric motor power, rear electric motor power, rear wheel hydraulic braking force, front wheel hydraulic braking force, vehicle speed, front wheel speed, rear wheel speed, and desired deceleration;

[0093] S212. Based on the convolutional neural network in the intelligent decision-making model, feature extraction is performed on the vehicle operation time series data to obtain spatial features;

[0094] S213. Based on the long short-term memory network in the intelligent decision-making model, feature extraction is performed on the vehicle operation time series data to obtain time series features;

[0095] S214. Using an intelligent decision-making model to make predictions based on spatial and time series characteristics, the braking force allocation strategy output by the intelligent decision-making model is obtained.

[0096] It should be noted that pure electric vehicles integrate a variety of sensors to collect vehicle operating parameters in real time, including maximum available regenerative braking force, front electric motor power, rear electric motor power, rear wheel hydraulic braking force, front wheel hydraulic braking force, vehicle speed, front wheel speed, and rear wheel speed.

[0097] An intelligent decision-making model is built based on a hybrid architecture of Long Short-Term Memory Network (LSTM) and Convolutional Neural Network (CNN) to predict the optimal braking force allocation scheme (braking force allocation strategy result) based on the collected data.

[0098] Based on this, features of the input parameters are extracted by combining convolutional neural networks and long short-term memory networks, and braking force allocation strategy is predicted based on the fused features, thereby further improving the accuracy and real-time performance of braking force allocation.

[0099] In some possible embodiments, step S214, which uses the intelligent decision-making model to make predictions based on spatial and time-series features to obtain the braking force allocation strategy result output by the intelligent decision-making model, may include:

[0100] S2141. Using an intelligent decision-making model to predict based on spatial and time series characteristics, the corresponding braking force distribution coefficient output value is obtained.

[0101] S2142. Calculate the energy recovery efficiency loss and braking performance loss corresponding to the output value of the braking force distribution coefficient based on the preset loss function, and determine the corresponding comprehensive loss value based on the energy recovery efficiency loss and braking performance loss.

[0102] S2143. 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 condition is reached. The braking force allocation strategy result output by the intelligent decision-making model is obtained based on the final braking force allocation coefficient output value.

[0103] It should be noted that when entering the combined braking mode of regenerative braking and hydraulic braking, a deep learning-based intelligent decision-making model can be used to predict the braking force distribution strategy.

[0104] The process of establishing the intelligent decision-making model is as follows:

[0105] Step 1: Design the core objectives of the intelligent optimization algorithm;

[0106] Design a deep learning-based energy recovery strategy, by inputting vehicle state parameters. Output braking force distribution strategy results, including regenerative braking force distribution coefficient. and hydraulic braking force distribution coefficient The optimization objective of the model is to maximize energy recovery efficiency. and optimize braking performance .

[0107] Step 2, define input and output;

[0108] (1) Definition of input vector:

[0109] Input status parameters It mainly includes the following components:

[0110]

[0111] in, This indicates the maximum available regenerative braking force, in N. : Regenerative braking force of the front and rear axles, respectively, in N. : These are the hydraulic braking forces of the front and rear axles, respectively, in N. v This indicates vehicle speed, measured in m / s. This indicates the front wheel speed, measured in rad / s.

[0112] (2) Output target definition:

[0113] Output braking force distribution coefficient:

[0114] This represents the regenerative braking force distribution coefficient.

[0115] This represents the hydraulic braking force distribution coefficient.

[0116] Step 3: Establish the deep learning model structure; extract spatial features of the input data using a convolutional neural network (CNN), capture time-series features using a long short-term memory network (LSTM), and finally calculate the braking force allocation coefficient through a fully connected layer. and .

[0117] Step 3.1, Data Feature Extraction (CNN Module);

[0118] Input status parameters (For example, vehicle speed, front and rear electric motor power, hydraulic braking force, etc.) are used as inputs to a convolutional neural network (CNN) to extract spatial features of the input data.

[0119] The output of the convolutional layer is:

[0120] in, This represents a convolution operation used to extract local features from the input data; ReLU represents the bias term of the convolutional layer; ReLU represents the activation function, defined as follows: This is to ensure that the output is non-negative.

[0121] Step 3.2, Dynamic Feature Extraction (LSTM Module);

[0122] To capture time-series features (such as the dynamics of vehicle state changes), an LSTM network is used to process the time-series input:

[0123] in, Indicates the hidden state of the LSTM layer; Indicates the state of the LSTM cell; This represents the hidden layer and cell state of the previous time step.

[0124] Step 3.3, Output Layer (Fully Connected Layer)

[0125] The features from CNN and LSTM are fused, and the allocation coefficients are calculated through a fully connected layer.

[0126]

[0127] in, This represents the weights and biases of the fully connected layer; This means normalizing the output to probability values ​​to ensure... .

[0128] Step 4, define the loss function;

[0129] The target loss function consists of two parts: energy recovery efficiency loss. and braking performance loss .

[0130] Step 4.1, Calculation of energy recovery efficiency loss;

[0131] Energy recovery efficiency is the ratio of actual recovered energy to the theoretical maximum recovered energy.

[0132]

[0133] in, This represents the actual kinetic energy recovered. This represents the theoretical maximum recoverable kinetic energy.

[0134] Energy recovery efficiency loss is defined as:

[0135] Step 4.2, Braking performance loss calculate;

[0136] Braking performance depends on total braking force Braking force required by the driver Deviation:

[0137]

[0138] Among them, total braking force The required braking force can be calculated based on the actual deceleration corresponding to the braking control. It can be calculated based on the corresponding expected deceleration.

[0139] Step 4.3, Establish the comprehensive loss function;

[0140] Combining energy recovery efficiency and braking performance, the comprehensive loss function is defined as follows:

[0141]

[0142] in and It is a weighting coefficient used to adjust the impact of the two losses on the braking force distribution decision.

[0143] Step 5: Optimize the process and constraints;

[0144] Step 5.1, Optimize braking force distribution;

[0145] The regenerative braking force and hydraulic braking force are optimized based on the allocation coefficient, where:

[0146] Regenerative braking force:

[0147] Hydraulic braking force:

[0148] Step 5.2, Constraints and Limitations:

[0149] (1) Braking balance constraint: The braking forces of the front and rear axles must be balanced:

[0150]

[0151] (2) Maximum braking force limit:

[0152]

[0153] Step 5.3, optimize goal setting;

[0154] The ultimate optimization objective is to minimize the overall loss function:

[0155]

[0156] For example, the gradient descent method can be used to iteratively update the parameters of a deep learning model until a preset convergence condition is met.

[0157] Step 5.4, convergence conditions are determined;

[0158] The key to gradient descent is calculating the gradient of the loss function with respect to the model parameters. To ensure model convergence, the loss function is differentiated, and the parameters are updated. The convergence condition of gradient descent is determined by checking if the change in the loss function is sufficiently small. Convergence is considered achieved when the difference in the loss function values ​​between two iterations is less than a predetermined threshold.

[0159] For example, the specific convergence condition is as follows:

[0160]

[0161] in, This is a preset, small positive number, often referred to as the convergence threshold. If the change in the loss function is less than the threshold, the iteration stops.

[0162] It should be noted that this application has the following advantages compared to the prior art:

[0163] (1) Improved energy recovery efficiency; This application embodiment achieves a significant improvement in energy recovery efficiency through an intelligent braking force distribution strategy. Compared with traditional control methods, the energy recovery efficiency is improved by 20%-30%. This is because this application embodiment can adjust the control strategy of regenerative braking force in real time according to the dynamic state of the vehicle, maximizing the recovery of energy during the braking process. Through the training and prediction of deep learning models, the optimal energy recovery strategy can be intelligently selected according to the current operating conditions.

[0164] (2) Optimize braking performance and ensure driving safety; the embodiments of this 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-up 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.

[0165] (3) Strong adaptability, adapting to complex road conditions and driving behaviors; traditional energy recovery strategies often 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 this 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 intelligently adjust according to the real-time collected vehicle speed, braking situation, and vehicle state to ensure that the vehicle always recovers energy in the optimal way and provides appropriate braking force. In addition, the deep learning model can learn the driving behavior-related knowledge of different drivers and automatically adapt to the personalized needs of drivers, so that different drivers can obtain the optimal driving experience.

[0166] (4) High real-time performance, ensuring rapid system response; Since deep learning algorithms can process vehicle status data in real time and make decisions quickly, the embodiments of this application have high real-time performance during the processing. 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 scheme in a very short time, ensuring timely and accurate braking response.

[0167] (5) The system is highly robust; by using a deep learning model to train a large-scale historical dataset, the embodiments of this application can not only cope with common driving conditions, but also adapt to some complex and uncertain driving conditions. For example, when special conditions such as road slippage or emergency braking occur, the deep learning model can automatically adjust its strategy based on historical experience and real-time data, thereby enhancing the robustness and reliability of the system.

[0168] Please refer to Figure 3, Figure 3 A block diagram illustrating the composition of a vehicle energy recovery control device provided in some embodiments of this application is shown. It should be understood that this vehicle energy recovery control device is similar to the one described above. Figure 1 Corresponding to the method embodiments, it is able to perform each step involved in the above method embodiments. The specific functions of the energy recovery control device of the vehicle can be found in the description above. To avoid repetition, detailed descriptions are appropriately omitted here.

[0169] Figure 3 The vehicle's energy recovery control device includes at least one software function module that can be stored in a memory or embedded in the vehicle's energy recovery control device in the form of software or firmware. The vehicle's energy recovery control device includes:

[0170] The determination parameter acquisition module 310 is used to respond to the braking request of the target vehicle and acquire the current braking determination parameters of the target vehicle.

[0171] The braking strategy output module 320 is used to input the real-time collected vehicle operating parameters into the adaptive intelligent decision model when the target vehicle meets the preset energy recovery conditions based on the current braking judgment parameters, so as to obtain the braking force distribution strategy result output by the intelligent decision model.

[0172] 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 results; wherein, the motor control system is used to provide regenerative braking force and generate recoverable energy suitable for replenishing the power battery.

[0173] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention. The energy recovery control device for a vehicle provided by the embodiments of the present invention can implement the energy recovery control method for a vehicle provided by any one of the method embodiments of the present invention.

[0174] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the aforementioned method, and will not be elaborated further here.

[0175] like Figure 4 As shown, some embodiments of this 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. When the processor 420 reads the program from the memory 410 via a bus 430 and executes the program, it can implement any of the methods included in the above-described vehicle energy recovery control method.

[0176] Processor 420 can process digital signals and may include various computing architectures. For example, it may be a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements multiple instruction set combinations. In some examples, processor 420 may be a microprocessor.

[0177] Memory 410 can be used to store instructions executed by processor 420 or data related to the execution of instructions. These instructions and / or data may include code for implementing some or all of the functions of one or more modules described in the embodiments of this application. The processor 420 of this disclosure embodiment can be used to execute instructions in memory 410 to implement the methods shown above. Memory 410 includes dynamic random access memory, static random access memory, flash memory, optical memory, or other memories well known to those skilled in the art.

[0178] Some embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, describes the method described in the method embodiments.

[0179] Some embodiments of this application also provide a computer program product that, when run on a computer, causes the computer to perform the methods described in the method embodiments.

[0180] Some embodiments of this application also provide a vehicle including a controller for performing the methods described in the method embodiments.

[0181] 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. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0182] It should be understood, in the several embodiments provided in this application, that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0183] In addition, the functional modules in the various embodiments of this 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.

[0184] If the aforementioned functions are implemented as software functional 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 this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0185] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0186] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0187] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for controlling energy recovery in a vehicle, characterized in that, include: In response to a braking request from the target vehicle, the current braking determination parameters of the target vehicle are obtained; If the target vehicle meets the preset energy recovery conditions based on the current braking determination parameters, the real-time collected vehicle operating parameters are input into the adaptively adjusted intelligent decision model to obtain the braking force distribution strategy result output by the intelligent decision model; wherein, the intelligent decision model adopts a deep learning model, and the deep learning model is trained by acquiring data from the past preset historical period according to a preset period in order to adaptively adjust the parameters of the model. Based on the results of the braking force distribution strategy, braking control is performed on the motor control system and the braking system respectively; wherein, the motor control system is used to provide regenerative braking force and generate recoverable energy suitable for replenishing the power battery; The step of inputting real-time collected vehicle operating parameters into an adaptively adjusted intelligent decision-making model to obtain the braking force distribution strategy output by the intelligent decision-making model includes: Based on real-time collected vehicle operating parameters, corresponding vehicle operating time series data are generated; wherein, the vehicle operating parameters include maximum available regenerative braking force, front electric motor power, rear electric motor power, rear wheel hydraulic braking force, front wheel hydraulic braking force, vehicle speed, front wheel speed, rear wheel speed, and desired deceleration; Based on the convolutional neural network in the intelligent decision-making model, spatial features are extracted from the vehicle operation time series data. Based on the long short-term memory network in the intelligent decision-making model, feature extraction is performed on the vehicle operation time series data to obtain time series features; The intelligent decision-making model is used to make predictions based on the spatial features and the time series features to obtain the braking force allocation strategy results output by the intelligent decision-making model; The step of using the intelligent decision-making model to predict based on the spatial features and the time series features to obtain the braking force allocation strategy result output by the intelligent decision-making model includes: The intelligent decision-making model is used to make predictions based on the spatial features and the time series features to obtain the corresponding braking force distribution coefficient output value. Based on a preset loss function, the energy recovery efficiency loss and braking performance loss corresponding to the output value of the braking force distribution coefficient are calculated respectively, and the corresponding comprehensive loss value is determined 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 condition is reached. The braking force allocation strategy result output by the intelligent decision-making model is obtained based on the final braking force allocation coefficient output value.

2. The energy recovery control method for vehicles according to claim 1, characterized in that, The current braking determination parameters include the current desired deceleration, the current battery state of charge, and the current vehicle speed. The step of determining whether the target vehicle meets the preset energy recovery conditions based on the current braking determination parameters 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 the target vehicle is determined to meet the preset energy recovery conditions.

3. The energy recovery control method for vehicles according to claim 1, characterized in that, The current braking determination parameters include the current desired deceleration; The method further includes: If it is determined that the current expected deceleration is not less than a preset deceleration threshold, then 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 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 energy recovery control method for vehicles according to claim 1, characterized in that, The current braking determination parameters include the current desired deceleration, the current battery state of charge, and the current vehicle speed. The 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, then 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, then 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 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 energy recovery control method for vehicles according to claim 1, characterized in that, The braking control of the motor control system and the braking system based on the braking force distribution strategy results includes: The regenerative braking command and the hydraulic braking command are determined based on the braking force distribution coefficients characterized by the braking force distribution strategy results. The motor control system and the braking system are respectively controlled by the regenerative braking command and the hydraulic braking command.

6. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, can implement the energy recovery control method for the vehicle according to any one of claims 1-5.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the energy recovery control method for a vehicle as described in any one of claims 1-5.

8. A vehicle, characterized in that, Includes a controller for performing the energy recovery control method for a vehicle as described in any one of claims 1-5.

Images