Method and device for recovering braking energy of automobile

Abstract

The invention relates to the technical field of new energy automobiles, in particular to an automobile braking energy recovery method and device.The method comprises the steps that at least one driving parameter and target deceleration of an automobile are obtained and input into a preset fuzzy neural network model, the electro-hydraulic brake control proportion of the vehicle is controlled under the condition that the current brake pedal opening degree and the target deceleration of the vehicle are not changed; and according to the electro-hydraulic braking control proportion, the driving motor torque and the mechanical braking force of the vehicle are corrected, so that under the condition that the vehicle is braked according to the corrected driving motor torque and mechanical braking force, generated braking energy is recycled. Therefore, the problems that in the related technology, new energy automobile braking energy recovery is often affected by traffic conditions in the traveling process, the automobile is frequently braked, a large amount of energy is converted into heat energy through a brake pad to be dissipated into the atmosphere, a large amount of energy is wasted, the braking energy recovery rate is low, and meanwhile energy is wasted are solved. And the driving experience of the driver is not good.

Description

Technical Field

[0001] The present application relates to the technical field of new energy vehicles, and in particular to a method and device for recovering braking energy of a vehicle. Background Art

[0002] In the relevant technologies, new energy vehicles have the advantages of being green, environmentally friendly, pollution-free, and having low energy costs, which meet the current requirements of energy conservation and emission reduction. At the same time, under the guidance of national policies, the new energy vehicle industry is developing rapidly. The energy recovery during the braking process through regenerative braking is a significant feature of new energy vehicles that distinguishes them from traditional vehicles. When the vehicle brakes, the drive motor generates regenerative braking torque, at which time the motor reverses, converting the vehicle's kinetic energy into electrical energy and inputting it into the battery for storage.

[0003] However, the braking energy recovery of new energy vehicles in related technologies is often affected by traffic conditions such as congestion and traffic lights during actual travel, and the vehicle will brake frequently. If the driver only subjectively controls the brake pedal opening to brake, and the vehicle brakes with the vehicle's default preset fixed electric braking and hydraulic braking ratio, a large amount of energy will be converted into heat energy through the brake pads and dissipated into the atmosphere, resulting in a large amount of energy waste. The braking energy recovery rate is low and the driver's driving experience is not good, which needs to be solved urgently. Summary of the invention

[0004] The present application provides a method and device for recovering braking energy of an automobile, so as to solve the problems in the related art that the recovery of braking energy of new energy automobiles is often affected by the traffic conditions during the actual travel process, and the vehicle will brake frequently. If the driver only subjectively controls the opening of the brake pedal to brake, and the vehicle is braked with the vehicle's default preset fixed electric brake and hydraulic brake ratio, a large amount of energy will be converted into heat energy through the brake pads and dissipated into the atmosphere, thereby causing a large amount of energy waste, a low braking energy recovery rate, and a poor driving experience for the driver.

[0005] The first aspect of the present application provides a method for recovering braking energy of an automobile, comprising the following steps: obtaining at least one driving parameter and a target deceleration of the vehicle; inputting the at least one driving parameter and the target deceleration into a preset fuzzy neural network model to obtain an electro-hydraulic braking control ratio for controlling the vehicle without changing the current brake pedal opening and the target deceleration of the vehicle; correcting the driving motor torque and mechanical braking force of the vehicle according to the electro-hydraulic braking control ratio to recover the generated braking energy when the vehicle is braked according to the electro-hydraulic braking control ratio outputting the corrected driving motor torque and mechanical braking force.

[0006] Through the above technical means, embodiments of the present application can input at least one driving parameter and a target deceleration of the vehicle into a certain fuzzy neural network model to determine the electro-hydraulic braking control ratio without changing the current brake pedal opening and the target deceleration of the vehicle, and perform braking energy recovery when the driving motor torque and the mechanical braking force reach the optimal electro-hydraulic braking ratio. Thereby, the intensity of braking energy recovery is dynamically adjusted by intelligently adjusting the electro-hydraulic coordinated braking ratio, greatly improving the braking energy recovery efficiency. At the same time, there is no need for the driver to frequently step on the brake pedal, ensuring the braking comfort of the vehicle during actual road driving and enhancing the driving experience of the driver.

[0007] Optionally, in an embodiment of the present application, before inputting the at least one driving parameter and the target deceleration into the preset fuzzy neural network model, it further includes: collecting initial driving data of the target vehicle driving under multiple target working conditions; screening out the final driving data that meets the preset effective conditions from the initial driving data; determining the maximum driving motor braking recovery torque corresponding to the final driving data, and obtaining the preset fuzzy neural network model based on the maximum driving motor braking recovery torque.

[0008] Through the above technical means, embodiments of the present application can calculate the maximum driving motor braking torque corresponding to the vehicle under different driving parameters using actual data, and then use the maximum driving motor braking torque to determine a certain fuzzy neural network model, effectively improving the data accuracy of the present application and the effectiveness of the maximum driving motor braking torque, providing strong data support for determining the optimal braking energy recovery strategy.

[0009] Optionally, in an embodiment of the present application, the determining the maximum driving motor braking recovery torque corresponding to the final driving data and obtaining the preset fuzzy neural network model based on the maximum driving motor braking recovery torque includes: identifying key parameters during the deceleration process of the final driving data; dynamically adjusting the electro-hydraulic coordinated braking ratio of the target vehicle during the braking process according to the key parameters to find the maximum driving motor braking recovery torque corresponding to the final driving data, so as to determine the preset fuzzy neural network model.

[0010] Through the above technical means, embodiments of the present application can identify key parameters during the deceleration process of the vehicle, thereby dynamically adjusting the electro-hydraulic coordinated braking ratio of the vehicle during the braking process, finding the corresponding maximum driving motor braking recovery torque, effectively improving the intelligent level of a certain fuzzy neural network model in the present application, and ensuring the braking energy recovery rate of the vehicle.

[0011] Optionally, in an embodiment of the present application, it further includes: calculating the energy loss of the target vehicle during braking according to the target loss function; optimizing the braking motor torque and hydraulic braking force of the target vehicle during braking according to the energy loss to optimize the preset fuzzy neural network model.

[0012] By the above technical means, the embodiment of the present application can optimize a certain fuzzy neural network model by using a certain algorithm and the target loss function, and then optimize the braking motor torque and hydraulic braking force during braking, ensuring a high braking energy recovery rate and braking comfort during braking.

[0013] Optionally, in an embodiment of the present application, it further includes: detecting the actual energy demand of the driver; determining whether to recover the braking energy of the vehicle based on the actual energy demand.

[0014] By the above technical means, the embodiment of the present application can consider the actual energy demand of the driver, and timely adjust the electro-hydraulic braking ratio in the fuzzy neural network model when the driver does not need braking energy recovery, effectively improving the human-machine interaction level of the present application, ensuring the driver's experience, and helping to maintain the customer stickiness of the product.

[0015] The embodiment of the second aspect of the present application provides a braking energy recovery device for an automobile, including: an acquisition module for acquiring at least one driving parameter and a target deceleration of the vehicle; a processing module for inputting the at least one driving parameter and the target deceleration into a preset fuzzy neural network model to obtain an electro-hydraulic braking control ratio for controlling the vehicle without changing the current braking pedal opening and the target deceleration of the vehicle; a recovery module for correcting the driving motor torque and mechanical braking force of the vehicle according to the electro-hydraulic braking control ratio, so as to recover the generated braking energy when the vehicle brakes by outputting the corrected driving motor torque and mechanical braking force according to the electro-hydraulic braking control ratio.

[0016] By the above technical means, the embodiment of the present application can determine the electro-hydraulic braking control ratio that does not change the current braking pedal opening and the target deceleration of the vehicle by inputting the driving parameters and the target deceleration of the vehicle into a certain fuzzy neural network model, ensuring the braking safety and reliability of the vehicle when controlling the vehicle according to the electro-hydraulic braking control ratio; recovering the braking energy when the driving motor torque and the mechanical braking force reach the optimal electro-hydraulic braking ratio, realizing the dynamic adjustment of the intensity of braking energy recovery by intelligently adjusting the electro-hydraulic coordinated braking ratio, greatly improving the braking energy recovery efficiency, and at the same time, the driver does not need to frequently step on the braking pedal, ensuring the braking comfort of the vehicle during actual road driving and improving the driving experience of the driver.

[0017] Optionally, in an embodiment of the present application, it further includes: a collection module, configured to collect initial driving data of the target vehicle driving under multiple target working conditions before inputting the at least one driving parameter and the target deceleration into the preset fuzzy neural network model; a screening module, configured to screen out final driving data that meets the preset valid conditions from the initial driving data; a first determination module, configured to determine the maximum driving motor braking recovery torque corresponding to the final driving data, and obtain the preset fuzzy neural network model based on the maximum driving motor braking recovery torque.

[0018] By means of the above technical means, the embodiment of the present application can calculate the maximum driving motor braking torque corresponding to the vehicle under different driving parameters by using actual data, and then use the maximum driving motor braking torque to determine a certain fuzzy neural network model, effectively improving the data accuracy of the present application and the effectiveness of the maximum driving motor braking torque, and providing strong data support for determining the optimal braking energy recovery strategy.

[0019] Optionally, in an embodiment of the present application, the first determination module includes: an identification unit, configured to identify key parameters during the deceleration process of the final driving data; an adjustment unit, configured to dynamically adjust the electro-hydraulic coordinated braking ratio of the target vehicle during the braking process according to the key parameters, so as to find the maximum driving motor braking recovery torque corresponding to the final driving data, and determine the preset fuzzy neural network model.

[0020] By means of the above technical means, the embodiment of the present application can identify key parameters during the deceleration process of the vehicle, so as to dynamically adjust the electro-hydraulic coordinated braking ratio of the vehicle during the braking process, find the corresponding maximum driving motor braking recovery torque, and effectively improve the intelligent level of the fuzzy neural network model of the present application, ensuring the braking energy recovery rate of the vehicle.

[0021] Optionally, in an embodiment of the present application, it further includes: a calculation module, configured to calculate the energy loss of the target vehicle during the braking process according to the target loss function; an optimization module, configured to optimize the braking motor torque and hydraulic braking force of the target vehicle during the braking process according to the energy loss, so as to optimize the preset fuzzy neural network model.

[0022] By means of the above technical means, the embodiment of the present application can optimize a certain fuzzy neural network model by using a certain algorithm and the target loss function, and then optimize the braking motor torque and hydraulic braking force during the braking process, ensuring a high braking energy recovery rate and braking process comfort during the braking process.

[0023] Optionally, in an embodiment of the present application, it further includes: a detection module for detecting the actual energy demand of the driver; a second determination module for determining whether to recover the braking energy of the vehicle based on the actual energy demand.

[0024] By the above technical means, the embodiment of the present application can consider the actual energy demand of the driver, timely adjust the electro-hydraulic braking ratio in the fuzzy neural network model when the driver does not need braking energy recovery, effectively improve the human-machine interaction level of the present application, ensure the driving experience of the driver, and help maintain the customer stickiness of the product.

[0025] An embodiment of the third aspect of the present application provides a vehicle, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the braking energy recovery method of the vehicle as described in the above embodiment.

[0026] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the program is executed by a processor, it implements the braking energy recovery method of the vehicle as described above.

[0027] An embodiment of the fifth aspect of the present application provides a computer program product, including a computer program, and when the computer program is executed, it is used to implement the braking energy recovery method of the vehicle as described above.

[0028] The additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. Description of the Drawings

[0029] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0030] Figure 1 It is a flowchart of a braking energy recovery method for a vehicle according to an embodiment of the present application;

[0031] Figure 2 It is a schematic diagram of a fuzzy neural network model according to an embodiment of the present application;

[0032] Figure 3 It is a flowchart of a random gradient descent method optimization algorithm according to an embodiment of the present application;

[0033] Figure 4 It is a flowchart of a braking energy recovery control method for a new energy vehicle based on a fuzzy neural network according to an embodiment of the present application;

[0034] Figure 5Schematic structural diagram of a braking energy recovery device for a vehicle according to an embodiment of the present application;

[0035] Figure 6 Schematic structural diagram of a vehicle according to an embodiment of the present application.

[0036] Reference numerals:

[0037] 10 - Braking energy recovery device for a vehicle: 100 - Acquisition module, 200 - Processing module, and 300 - Recovery module; 601 - Memory, 602 - Processor, and 603 - Communication interface. Detailed implementation manners

[0038] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation to the present application.

[0039] The braking energy recovery method and device for a vehicle according to an embodiment of the present application will be described below with reference to the accompanying drawings. In view of the problem that in the related art, the braking energy recovery of new energy vehicles is often affected by traffic conditions during actual travel, the vehicle brakes frequently. If the driver only subjectively controls the opening of the brake pedal for braking and the vehicle brakes according to the default preset fixed ratio of electric braking to hydraulic braking, a large amount of energy will be converted into heat by the brake pads and dissipated into the atmosphere, resulting in a large amount of energy waste. At the same time, the braking energy recovery rate is low and the driving experience of the driver is also poor. The present application provides a braking energy recovery method for a vehicle. In this method, the driving parameters and target deceleration of the vehicle can be input into a certain fuzzy neural network model to determine the electro-hydraulic braking control ratio of the vehicle without changing the current brake pedal opening and target deceleration of the vehicle, and braking energy recovery is performed when the drive motor torque and mechanical braking force reach the optimal electro-hydraulic braking ratio. Thus, the intensity of braking energy recovery is dynamically adjusted by intelligently adjusting the electro-hydraulic coordinated braking ratio, greatly improving the braking energy recovery efficiency. At the same time, the driver does not need to frequently step on the brake pedal, ensuring the braking comfort of the vehicle during actual road driving and improving the driving experience of the driver. Thus, the problems in the related art that the braking energy recovery of new energy vehicles is often affected by traffic conditions during actual travel, the vehicle brakes frequently. If the driver only subjectively controls the opening of the brake pedal for braking and the vehicle brakes according to the default preset fixed ratio of electric braking to hydraulic braking, a large amount of energy will be converted into heat by the brake pads and dissipated into the atmosphere, resulting in a large amount of energy waste. At the same time, the braking energy recovery rate is low and the driving experience of the driver is also poor are solved.

[0040] Specifically, Figure 1 is a flowchart of a braking energy recovery method for a vehicle provided by an embodiment of the present application.

[0041] As Figure 1 shown, the braking energy recovery method for the vehicle includes the following steps:

[0042] In step S101, at least one driving parameter and a target deceleration of the vehicle are obtained.

[0043] In some embodiments, some vehicles, such as new energy vehicles, will generate a certain amount of braking energy during braking. That is, during braking, the drive motor will generate a regenerative braking torque. At this time, the motor rotates in reverse, converting the kinetic energy of the vehicle into electrical energy and inputting it into the battery for storage. This process can be understood as a braking energy recovery process.

[0044] During the braking energy recovery process, it is often the driver who steps on the brake pedal to brake. Only after the relevant sensors recognize the change in the pedal opening will energy recovery be carried out. At this time, a large amount of energy has been converted into heat and dissipated through the brake pads, resulting in a large amount of energy waste. Based on this, the embodiment of the present application can obtain at least one driving parameter and a target deceleration of the vehicle, so as to recover the braking energy in time when the vehicle decelerates to generate braking energy.

[0045] Among them, the target deceleration can be understood here as the ideal braking deceleration when achieving the vehicle braking target in the actual driving scenario. For example, -2m / s 2 , -3m / s 2 etc. Among them, the negative sign indicates deceleration.

[0046] In order to obtain a better braking energy recovery rate, when obtaining the target deceleration of the vehicle, the embodiment of the present application can, but is not limited to, obtain the current optimal speed of the vehicle, so as to determine the target deceleration of the vehicle according to the optimal speed. Among them, the current optimal speed can be calculated from at least one driving parameter of the vehicle currently.

[0047] For example, the present application can know from the vehicle's online map or navigation that a red light is about to turn on 150 meters ahead, that is, it is necessary to wait for the red light 150 meters ahead. At this time, the embodiment of the present application can obtain the current vehicle speed of the vehicle as 40 km / h, and then calculate that the current optimal speed is to reduce the speed to 0 km / h when reaching the red light stop line.

[0048] Considering the need to stop before the red light, the braking energy recovery rate, and the riding comfort, etc., the target deceleration that can achieve the maximum braking energy recovery rate can be calculated as -1.5m / s 2, at this time, the vehicle can decelerate according to the target deceleration. When it reaches the red light, the speed exactly reaches the optimal speed of 0 m / s, and it meets the driver's braking comfort and a relatively high braking energy recovery rate, reducing energy waste.

[0049] The embodiment of the present application can obtain at least one driving parameter and the target deceleration of the vehicle, which is convenient for determining the braking process of the vehicle in a timely manner according to the at least one driving parameter and the target deceleration, facilitating the recovery of the braking energy generated by the vehicle in a timely manner, and at the same time facilitating the maintenance of the driver's experience.

[0050] Step S102, input the at least one driving parameter and the target deceleration into a preset fuzzy neural network model to obtain the electro-hydraulic braking control ratio for controlling the vehicle without changing the current braking pedal opening and the target deceleration of the vehicle.

[0051] It can be understood that the preset fuzzy neural network model here refers to a fuzzy neural network model that has been pre-trained and can calculate how the vehicle achieves the maximum braking energy recovery rate.

[0052] In the actual execution process, the actual situations of vehicles are different, and the process and the optimal strategy of braking energy recovery will correspondingly change. For the convenience of the actual use of vehicles, the present application can train a certain fuzzy neural network model and apply machine learning to the control of the braking energy recovery intensity of new energy vehicles. Thus, the at least one driving parameter and the target deceleration can be input into a certain fuzzy neural network model, and the electro-hydraulic coordination braking ratio can be intelligently and dynamically adjusted through the algorithm in the certain fuzzy neural network model, thereby intelligently adjusting the braking energy recovery strategy, and it is helpful to integrate the fuzzy neural network model into the relevant control center of the vehicle for convenient use.

[0053] Specifically, the embodiment of the present application can input the at least one driving parameter and the target deceleration into a certain fuzzy neural network model, and then the fuzzy neural network model can calculate and output the electro-hydraulic braking control ratio for controlling the vehicle without changing the current braking pedal opening and the target deceleration of the vehicle according to the at least one driving parameter and the target deceleration. By not changing the original current braking pedal opening and the target deceleration, the embodiment of the present application can ensure the braking safety and reliability of the vehicle when controlling the vehicle according to the electro-hydraulic braking control ratio.

[0054] Among them, electro-hydraulic braking refers to an electro-hydraulic braking system, which realizes the braking function through key components such as an electronic pedal angle sensor, an electronic control unit, and an electro-hydraulic regulating brake valve. The pedal sensor monitors and converts the driver's stepping force into an electrical signal. The control unit calculates the current according to these signals and drives the electromagnetic proportional coil of the brake valve, thereby accurately adjusting the braking pressure output.

[0055] Regenerative braking is one of the unique braking methods for new energy vehicles. During braking, the motor can be converted into a generator to generate electrical energy for energy recovery. To maximize the recovery of braking energy and ensure braking safety, the electro-hydraulic braking system needs to reasonably control the proportion of regenerative braking and hydraulic braking.

[0056] The fuzzy neural network in the embodiment of this application can output and dynamically adjust the electro-hydraulic braking control ratio of the vehicle without changing the current braking pedal opening and the target deceleration of the vehicle, so as to achieve a better braking energy recovery effect and driving experience.

[0057] For example, in an emergency braking situation, the electro-hydraulic braking system will respond quickly and allocate sufficient braking force to ensure that the vehicle can decelerate and stop quickly. At this time, the electro-hydraulic braking control ratio may be biased towards hydraulic braking to provide stronger braking force. In the case of auxiliary braking, the electro-hydraulic braking system will allocate braking force according to the driver's braking intention and the vehicle state. For example, when slowly decelerating or driving downhill, the system may make more use of regenerative braking to recover energy and reduce brake wear.

[0058] The embodiment of this application can output the electro-hydraulic braking ratio of the vehicle without changing the current braking pedal opening and the target deceleration of the vehicle through a certain fuzzy neural network model, and output different braking strategies in different situations of the vehicle, so as to achieve the best braking energy recovery effect as much as possible while ensuring the normal braking and safety of the vehicle, which helps to improve the driving experience of the driver.

[0059] Optionally, in an embodiment of this application, before inputting at least one driving parameter and the target deceleration into the preset fuzzy neural network model, it further includes: collecting the initial driving data of the target vehicle driving under multiple target working conditions; screening out the final driving data that meets the preset valid conditions from the initial driving data; determining the maximum driving motor braking recovery torque corresponding to the final driving data, and obtaining the preset fuzzy neural network model based on the maximum driving motor braking recovery torque.

[0060] Based on the relevant descriptions of other embodiments, it can be understood that this application can use a certain fuzzy neural network model to output the electro-hydraulic braking control ratio, so as to achieve the best braking energy recovery rate as much as possible. Since the best braking energy recovery rate is not easy to calculate directly, this application can, but is not limited to, indirectly calculate by finding the maximum driving motor braking torque of the target vehicle under different driving parameters, that is, the maximum torque that the motor can generate during braking. Here, the target vehicle can be understood as a new energy vehicle used for experiments or inferences to determine the maximum driving motor braking torque target of the vehicle under different driving parameters.

[0061] The maximum braking torque of the drive motor plays a decisive role in the maximum energy that can be recovered during vehicle braking. When the vehicle brakes, the drive motor enters the power generation state and converts the vehicle's kinetic energy into electrical energy. At this time, the greater the braking torque of the motor, the more electrical energy can be generated, and thus the more energy can be recovered. Therefore, when calculating the braking energy recovery amount, the factor of the maximum braking torque of the drive motor must be considered. Secondly, the maximum braking torque of the drive motor also affects the response speed and stability of the braking energy recovery system. In practical applications, the braking energy recovery system needs to quickly respond to the vehicle's braking demand and stably recover energy. If the braking torque of the motor is too small, it may cause the system to respond slowly or be unable to stably recover energy, thus affecting the braking effect and energy recovery efficiency. Therefore, when designing the braking energy recovery system, it is necessary to reasonably match the braking torque of the motor and the braking demand to ensure the stability and efficiency of the system.

[0062] In the embodiments of the present application, the maximum braking torque of the drive motor of the target vehicle under different driving parameters can be determined by, but not limited to, certain experiments. The experimental process can be understood as first collecting the initial driving data of the target vehicle driving under multiple target working conditions, and then screening out the final driving data that meets the preset effective conditions; determining the maximum braking recovery torque corresponding to the final driving data, so as to obtain a preset fuzzy neural network model based on the maximum braking recovery torque.

[0063] It should be noted that the main role of the target vehicle here is to collect the experimental data required for training the fuzzy neural network model. The target vehicle can be the same as the vehicle in actual application or can be selected separately. The preset effective conditions can be understood as the standards or conditions that the data used for finally calculating the maximum braking recovery torque of the drive motor should meet. For example, the data value is within the effective range, etc.

[0064] For example, the present application can design some actual road test routes for typical vehicles. Among them, these routes should cover the urban, suburban and highway sections as much as possible, the vehicle speed covers 0-120 km / h, and there are deceleration conditions in each test process, so as to cover as many different vehicle speeds and deceleration magnitudes as possible.

[0065] Then, this application can collect and process the initial driving data of the target vehicle during actual road driving. For example, the driving parameters of the target vehicle during actual road driving are collected by arranging sensors on the vehicle or by obtaining vehicle message signals, such as vehicle speed, vehicle acceleration, brake pedal opening, accelerator pedal opening, drive motor torque, brake hydraulic master cylinder pressure and other parameters. Subsequently, these data are screened and processed to find different driving parameters within the effective range, that is, the final driving data, and then the maximum drive motor braking recovery torque corresponding to the final driving data is determined. For example, the maximum drive motor braking recovery torque corresponding to different vehicle speeds and vehicle accelerations, etc., and the braking energy recovery rate of this braking process is calculated. The formula can be but is not limited to the following:

[0066]

[0067] Among them, the battery recovery energy calculation method can be but is not limited to being expressed as:

[0068]

[0069] The vehicle kinetic energy loss energy calculation method can be but is not limited to being expressed as:

[0070]

[0071] Among them, m is the vehicle mass, v1 is the vehicle speed at the start of the braking process, and v2 is the vehicle speed at the end of the braking process.

[0072] It should be noted that the specific method for determining the maximum drive motor braking torque and the parameters required can be selected or adjusted by those skilled in the art according to the actual situation. Here, only an exemplary description is given without specific limitation.

[0073] The embodiments of this application can calculate the maximum drive motor braking torque corresponding to the vehicle under different driving parameters by using actual data, and then use the maximum drive motor braking torque to determine a certain fuzzy neural network model, effectively improving the data accuracy of this application and the validity of the maximum drive motor braking torque calculation result, and providing strong data support for determining the optimal braking energy recovery strategy.

[0074] Optionally, in an embodiment of this application, determining the maximum drive motor braking recovery torque corresponding to the final driving data and obtaining a preset fuzzy neural network model based on the maximum drive motor braking recovery torque includes: identifying the key parameters in the deceleration process of the final driving data; dynamically adjusting the electro-hydraulic coordinated braking ratio of the target vehicle during the braking process according to the key parameters to find the maximum drive motor braking recovery torque corresponding to the final driving data, so as to determine the preset fuzzy neural network model.

[0075] Those skilled in the art can understand that the electro-hydraulic braking control ratio will change with the actual driving conditions of the vehicle. Only by continuously and dynamically adjusting the electro-hydraulic braking control ratio can the maximum driving motor braking recovery torque corresponding to the final driving data and its corresponding maximum braking energy recovery rate be obtained, and thus the neural network model can be determined.

[0076] In some other embodiments, when constructing a certain fuzzy neural network model in the present application, in order to improve the accuracy of the output electro-hydraulic braking control ratio, the key parameters in the deceleration process of the final driving data can be identified, so as to dynamically adjust the electro-hydraulic coordinated braking ratio of the target vehicle during braking according to the key parameters, in order to find the maximum driving motor braking recovery torque corresponding to the final driving data, and then determine a certain fuzzy neural network model.

[0077] Among them, the key parameters can be specifically determined or adjusted by those skilled in the art according to the actual situation. For example, vehicle speed and vehicle acceleration, etc. The present application only makes an exemplary illustration and does not make specific limitations. Thus, the embodiments of the present application can dynamically adjust the electro-hydraulic coordinated braking ratio of the target vehicle during braking according to the key parameters, find the maximum driving motor braking recovery torque corresponding to the final driving data, and finally achieve better braking energy recovery according to the electro-hydraulic braking control ratio corresponding to the maximum driving motor braking recovery torque.

[0078] Figure 2 It is a schematic diagram of the fuzzy neural network model of an embodiment of the present application. As Figure 2 shown, in the embodiments of the present application, the fuzzy neural network model includes but is not limited to 5 layers, namely the input layer, the fuzzification layer, the fuzzy rule layer, the normalization calculation layer and the output layer. Among them, the input layer includes n key parameters of the deceleration process, corresponding to n nodes in the first layer, and the expression can be but is not limited to the following:

[0079] x = [x1, x2,..., x n

[0080] Subsequently, the data is transmitted from the input layer to the membership function calculation layer, that is, the fuzzification layer. In this layer, the membership degrees of the key parameters of the deceleration process in the first layer need to be calculated. Each node represents a membership function. Here, the Gaussian function is selected as the membership function, and the formula can be but is not limited to:

[0081]

[0082] where i = 1, 2,..., n; j = 1, 2,..., m i . n is the number or dimension of the input quantities, and m i is the fuzzy segmentation number of x i , ​represents the central value of the membership function, σ ij represents the width value, and the total number of nodes in this layer is

[0083] Among them, the fuzzy set of vehicle acceleration a can be expressed as {L (low), M (medium), H (high)}; the universe of discourse can be expressed as {0, 1};

[0084] The vehicle speed v can be fuzzified as {L (low), M (medium), H (high)}; the universe of discourse can be expressed as {0, 120};

[0085] The fuzzy set of the electric motor braking torque T can be expressed as {L (low), M (medium), H (high)}; the universe of discourse can be expressed as {0, 280};

[0086] The fuzzy set of the electric braking distribution ratio K can be expressed as {L (low), M (medium), H (high)}; the universe of discourse can be expressed as {0, 1}.

[0087] Each node in the third layer represents a fuzzy rule, that is, matching the antecedent of the fuzzy rule and calculating the utility of each rule. If there are n groups of memberships in the second layer, in the embodiments of the present application, a membership function can be taken from each group without repetition and combined together to form the nodes in the third layer. The formula can be but is not limited to expressed as:

[0088]

[0089] Among them, i1 ∈ {1, 2,... m1}, i2 ∈ {1, 2,... m2}... i n ∈ {1, 2,... m n},, and the total number of nodes in this layer

[0090] Table 1 is the fuzzy rule table of an embodiment of the present application and can be expressed as follows:

[0091] Table 1

[0092] a v T K L L L L L L M M L L H H M L L H M M L H ... ... ... ... H H H L

[0093] The number of nodes in the fourth layer is the same as that in the third layer, that is:

[0094] N4 = N3 = m

[0095] It is used to perform normalization calculation on the applicability of each rule, that is:

[0096]

[0097] The fifth layer is the output layer, which realizes defuzzification calculation, that is

[0098]

[0099] where, w ij is the central value of the j-th membership function of y i and can be expressed in vector form as: Expanding it can be expressed as follows:

[0100]

[0101] The embodiments of the present application can identify the key parameters during the deceleration process of the vehicle, thereby dynamically adjusting the electro-hydraulic coordinated braking ratio of the target vehicle during braking, timely finding out the corresponding maximum driving motor braking recovery torque, effectively improving the intelligent level of the fuzzy neural network model of the present application, and ensuring the braking energy recovery rate of the vehicle.

[0102] Optionally, in an embodiment of the present application, it further includes: calculating the energy loss of the target vehicle during braking according to the target loss function; optimizing the braking motor torque and hydraulic braking force of the target vehicle during braking according to the energy loss to optimize the preset fuzzy neural network model.

[0103] In some embodiments, during the training process and actual application process of the fuzzy neural model, certain errors may occur, which may further affect the actual braking energy recovery process and cause a decrease in the braking energy recovery rate. Based on this, the embodiments of the present application can calculate the energy loss of the target vehicle during braking through a certain target loss function, thereby optimizing the braking motor torque and hydraulic braking force of the target vehicle during braking, and further achieving the purpose of optimizing the fuzzy neural network model.

[0104] Among them, the target loss function can be understood here as the loss function used when calculating the energy loss, and can be specifically selected or adjusted by those skilled in the art according to the actual situation. The present application only makes an exemplary description and does not make specific limitations.

[0105] For example, the present application can, but is not limited to, optimize the model using the stochastic gradient descent method. Specifically, first, it is necessary to define the loss function, optimize the braking motor torque and hydraulic braking force during braking, and ensure a high braking energy recovery rate and braking process comfort during braking.

[0106] Figure 3 is the flowchart of the stochastic gradient descent method optimization algorithm for an embodiment of the present application. As Figure 3 shown:

[0107] Step S301: Determine the optimization objective and construct a loss function using the mean squared error. Here, the loss function can be understood as a function used to measure the difference between the target value (such as the actual braking energy recovery rate) and the predicted value (the braking energy recovery rate predicted by the model), that is, a function used to measure energy loss. In the embodiments of the present application, the target loss function during gradient descent can be determined using the mean squared error, and the optimization objective is to find its minimum value. The formula can be expressed as follows, but is not limited thereto:

[0108]

[0109] Among them, J(θ0,θ1) represents the mean squared error (MSE, which refers to the average of the squared errors of all sample points) containing two parameters θ0 and θ1, y i represents the target value of the sample with count i, and θ0 + θ1x i refers to the value predicted by the model, represents the sum of the squares of the differences between the two and then taking the mean.

[0110] Step S302: Initialize two parameters, and then calculate the gradient prediction value through forward propagation. The formula can be expressed as follows, but is not limited thereto:

[0111]

[0112] That is, take the partial derivatives of J(θ0,θ1) with respect to θ0 and θ1 respectively.

[0113] Step S303: Set the step size to α, calculate the error between the predicted value and the true value, then the next step size can update the two parameters, and its expression can be:

[0114]

[0115] That is, take the two partial derivatives of θ0 and θ1 calculated in Step S302 as the slopes, and multiply by the step size α as the values by which θ0 and θ1 decrease for each step size. Taking θ0 as an example, The calculation of θ1 is the same by analogy.

[0116] Step S304: Determine whether the result, such as the value of the loss function, converges or reaches the maximum preset number of iterations;

[0117] Step S305: If the result converges or reaches the maximum preset number of iterations, stop;

[0118] Step S306: If the result does not converge and does not reach the maximum preset number of iterations, repeat the calculation of the gradient and update the parameter values until the stop condition is met.

[0119] It should be noted that in the embodiments of the present application, when constructing (training) a certain fuzzy neural network model, the energy loss during the braking process under the target working conditions can be used to optimize the braking motor torque, hydraulic braking force, and a certain fuzzy neural network model during the braking process; or in the actual application scenario, according to the energy loss during the actual application braking process of the vehicle, a certain fuzzy neural network model, the braking motor torque, and the hydraulic braking force during the braking process can be further optimized. The embodiments of the present application are only for illustrative purposes and are not specifically limited.

[0120] The embodiments of the present application can use a certain algorithm and target loss function to optimize a certain fuzzy neural network model, and then optimize the braking motor torque and hydraulic braking force during the braking process to ensure a higher braking energy recovery rate and braking process comfort during the braking process.

[0121] Step S103: Correct the driving motor torque and mechanical braking force of the vehicle according to the electro-hydraulic braking control ratio, so that when the vehicle brakes by outputting the corrected driving motor torque and mechanical braking force according to the electro-hydraulic braking control ratio, the generated braking energy can be recovered.

[0122] As a possible implementation manner, after the fuzzy neural network model outputs the electro-hydraulic braking ratio, the vehicle can correct the driving motor torque and mechanical braking force of the vehicle according to the electro-hydraulic braking ratio, so that when the actual driving motor torque and actual mechanical braking force of the vehicle reach the electro-hydraulic braking ratio output by the fuzzy neural network model, the braking energy generated by the vehicle can be recovered.

[0123] For example, the fuzzy neural network model outputs the electro-hydraulic braking ratio, and the vehicle automatically adjusts the magnitudes of the driving motor torque and mechanical braking force of the vehicle according to the electro-hydraulic braking ratio, so that the two cooperate with each other. On the basis of meeting the target deceleration requirement, the electro-hydraulic braking control ratio is automatically allocated, so that the vehicle brakes by outputting the corrected driving motor torque and mechanical braking force according to the electro-hydraulic braking ratio, and then the best braking effect can be achieved on the basis of meeting braking safety and comfort.

[0124] When actually driving a vehicle, the vehicle can obtain information through an online map or navigation, etc., and automatically obtain the current optimal speed and target deceleration of the vehicle. After obtaining the target deceleration of the vehicle, the vehicle can intelligently adjust the ratio of electric braking and mechanical braking according to the target deceleration, so as to maximize the electric braking ratio of the vehicle on the basis of meeting braking comfort, thereby obtaining a higher braking energy recovery rate.

[0125] The embodiments of the present application can dynamically adjust the braking energy recovery intensity by intelligently adjusting the electro-hydraulic coordination braking ratio, greatly improving the braking energy recovery efficiency without the driver frequently stepping on the braking pedal, ensuring the braking comfort during the actual road driving of the vehicle, and enhancing the driving experience of the driver.

[0126] Optionally, in an embodiment of the present application, it further includes: detecting the actual energy demand of the driver; determining whether to recover the braking energy of the vehicle based on the actual energy demand.

[0127] In other embodiments, considering that the actual driving habits of some drivers and the actual energy demands in different driving situations are different, therefore, the embodiments of the present application can also detect the actual energy demand of the driver so as to determine whether to recover the braking energy of the vehicle according to the actual energy demand of the driver.

[0128] For example, some drivers are used to emergency braking. Then, in most cases, the electro-hydraulic braking system will tend to hydraulic braking to provide stronger braking force. At this time, if regenerative braking is used, the braking force may decrease. To ensure the driving experience of the driver, the embodiments of the present application can first detect the actual energy demand of the driver. For example, after the vehicle starts, the driver is asked through the central large screen whether to turn on the braking energy recovery function. If the driver does not need braking energy recovery, the electro-hydraulic braking ratio in the fuzzy neural network model can be adjusted in time.

[0129] The embodiments of the present application can consider the actual energy demand of the driver, and adjust the electro-hydraulic braking ratio in the fuzzy neural network model in time when the driver does not need braking energy recovery, effectively improving the human-machine interaction level of the present application, ensuring the driving experience of the driver, and helping to maintain the customer stickiness of the product.

[0130] The following elaborates on the present application in detail with a specific embodiment.

[0131] Figure 4 It is a flowchart of a braking energy recovery control method for a new energy vehicle based on a fuzzy neural network according to an embodiment of the present application. As Figure 4 shown:

[0132] Step S401: Design a typical vehicle actual road test route to collect the parameter information required for constructing the fuzzy neural network model;

[0133] Step S402: Collect the key parameters during the deceleration process in the test working condition, such as vehicle speed, vehicle deceleration, etc.;

[0134] Step S403: Use these key parameters to construct a fuzzy neural network model, so as to use the fuzzy neural network model to dynamically adjust the electro-hydraulic braking ratio of the vehicle during braking without changing the current brake pedal opening and the target deceleration of the vehicle;

[0135] Step S404: Use the gradient descent method to optimize the motor braking torque and hydraulic braking force, so as to optimize the fuzzy neural network model;

[0136] Step S405: Apply the fuzzy neural network model to the actual road driving process. By continuously adjusting the electro-hydraulic braking ratio and comparing the braking energy recovery rate, control the vehicle to output the motor braking torque and hydraulic braking force according to the corresponding electro-hydraulic braking ratio when the braking energy recovery rate is the largest, and recover the braking energy at the same time.

[0137] According to the braking energy recovery method of the vehicle proposed in the embodiment of the present application, the driving parameters and target deceleration of the vehicle can be input into a certain fuzzy neural network model to determine the electro-hydraulic braking control ratio of the vehicle without changing the current brake pedal opening and the target deceleration of the vehicle, and recover the braking energy when the driving motor torque and mechanical braking force reach the optimal electro-hydraulic braking ratio. Thus, the intensity of braking energy recovery is dynamically adjusted by intelligently adjusting the electro-hydraulic coordinated braking ratio, greatly improving the braking energy recovery efficiency. At the same time, there is no need for the driver to frequently step on the brake pedal, ensuring the braking comfort of the vehicle during actual road driving and enhancing the driving experience of the driver. Thus, it solves the problems in the related art that the braking energy recovery of new energy vehicles is often affected by the traffic conditions during actual travel, the vehicle brakes frequently. If only the driver subjectively controls the brake pedal opening for braking and the vehicle brakes according to the default fixed electro-braking and hydraulic braking ratio preset by the vehicle, a large amount of energy will be converted into heat by the brake pads and dissipated into the atmosphere, resulting in a large amount of energy waste, low braking energy recovery rate, and poor driving experience of the driver.

[0138] Next, refer to the drawings to describe the braking energy recovery device of the vehicle proposed in the embodiment of the present application.

[0139] Figure 5 is a schematic structural diagram of the braking energy recovery device of the vehicle according to the embodiment of the present application.

[0140] As Figure 5 shown, the braking energy recovery device 10 of the vehicle includes: an acquisition module 100, a processing module 200, and a recovery module 300.

[0141] Among them, the acquisition module 100 is used to acquire at least one driving parameter and the target deceleration of the vehicle.

[0142] The processing module 200 is configured to input at least one driving parameter and a target deceleration into a preset fuzzy neural network model to obtain an electro-hydraulic braking control ratio for controlling the vehicle without changing the current brake pedal opening and the target deceleration of the vehicle.

[0143] The recovery module 300 is configured to correct the driving motor torque and the mechanical braking force of the vehicle according to the electro-hydraulic braking control ratio, so as to recover the generated braking energy when the vehicle brakes by outputting the corrected driving motor torque and the mechanical braking force according to the electro-hydraulic braking control ratio.

[0144] Optionally, in an embodiment of the present application, it further includes: a collection module, a screening module, and a first determination module.

[0145] Wherein, the collection module is configured to collect initial driving data of the target vehicle driving under multiple target working conditions before inputting at least one driving parameter and a target deceleration into the preset fuzzy neural network model.

[0146] The screening module is configured to screen out the final driving data that meets the preset valid conditions from the initial driving data.

[0147] The first determination module is configured to determine the maximum driving motor braking recovery torque corresponding to the final driving data, and obtain the preset fuzzy neural network model based on the maximum driving motor braking recovery torque.

[0148] Optionally, in an embodiment of the present application, the first determination module includes: an identification unit and an adjustment unit.

[0149] Wherein, the identification unit is configured to identify the key parameters in the deceleration process of the final driving data.

[0150] The adjustment unit is configured to dynamically adjust the electro-hydraulic coordinated braking ratio of the target vehicle during braking according to the key parameters, so as to find the maximum driving motor braking recovery torque corresponding to the final driving data, and determine the preset fuzzy neural network model.

[0151] Optionally, in an embodiment of the present application, it further includes: a calculation module and an optimization module.

[0152] Wherein, the calculation module is configured to calculate the energy loss of the target vehicle during braking according to the target loss function.

[0153] The optimization module is configured to optimize the braking motor torque and the hydraulic braking force of the target vehicle during braking according to the energy loss, so as to optimize the preset fuzzy neural network model.

[0154] Optionally, in an embodiment of the present application, it further includes: a detection module and a second determination module.

[0155] Among them, a detection module is configured to detect the actual energy demand of the driver.

[0156] A second determination module is configured to determine whether to recover the braking energy of the vehicle based on the actual energy demand.

[0157] It should be noted that the foregoing explanation of the embodiments of the braking energy recovery method for an automobile also applies to the braking energy recovery device of the automobile in this embodiment, and will not be elaborated here.

[0158] According to the braking energy recovery device of an automobile proposed in the embodiments of the present application, the driving parameters and the target deceleration of the vehicle can be input into a certain fuzzy neural network model to determine the electro-hydraulic braking control ratio of the vehicle without changing the current braking pedal opening and the target deceleration of the vehicle, and the braking energy recovery is performed when the drive motor torque and the mechanical braking force reach the optimal electro-hydraulic braking ratio. Thus, the intensity of the braking energy recovery is dynamically adjusted by intelligently adjusting the electro-hydraulic coordinated braking ratio, greatly improving the braking energy recovery efficiency. At the same time, it is not necessary for the driver to frequently step on the braking pedal, ensuring the braking comfort of the vehicle during actual road driving and enhancing the driving experience of the driver. Thus, it solves the problems in the related art that the braking energy recovery of new energy vehicles is often affected by the traffic conditions during actual travel, and the vehicle brakes frequently. If only the driver subjectively controls the opening of the braking pedal for braking and the vehicle brakes according to the default fixed electro-braking and hydraulic braking ratio preset by the vehicle, a large amount of energy will be converted into heat energy by the brake pads and dissipated into the atmosphere, resulting in a large amount of energy waste, low braking energy recovery rate, and poor driving experience of the driver.

[0159] Figure 6 This is a schematic structural diagram of a vehicle provided by the embodiments of the present application. The vehicle may include:

[0160] A memory 601, a processor 602, and a computer program stored on the memory 601 and executable on the processor 602.

[0161] When the processor 602 executes the program, it implements the braking energy recovery method for an automobile provided in the foregoing embodiments.

[0162] Further, the vehicle further includes:

[0163] A communication interface 603 for communication between the memory 601 and the processor 602.

[0164] The memory 601 is used to store a computer program executable on the processor 602.

[0165] The memory 601 may include high-speed RAM memory and may also include non-volatile memory, such as at least one magnetic disk memory.

[0166] If the memory 601, the processor 602, and the communication interface 603 are implemented independently, the communication interface 603, the memory 601, and the processor 602 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity in representation, Figure 6 only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0167] Optionally, in a specific implementation, if the memory 601, the processor 602, and the communication interface 603 are integrated on a single chip, the memory 601, the processor 602, and the communication interface 603 can communicate with each other through an internal interface.

[0168] The processor 602 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0169] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the braking energy recovery method of the vehicle as described above is implemented.

[0170] The embodiments of the present application also provide a computer program product, including a computer program, and the computer program can run computer instructions, and when the computer instructions are executed by a processor, the braking energy recovery method of the vehicle provided by the embodiments of the present application is implemented.

[0171] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0172] In addition, the terms "first" and "second" are used only for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of this application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0173] Any process or method description shown in the flowchart or described in other ways herein can be understood to represent a module, segment, or portion of code including one or N executable instructions for implementing a customized logical function or process, and the scope of the preferred embodiments of this application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of this application belong.

[0174] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, which can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or N wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or other appropriate processing if necessary, and then stored in a computer memory.

[0175] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0176] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0177] In addition, each functional unit in various embodiments of the present application may be integrated into a processing module, may exist separately physically for each unit, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0178] The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present application.

Claims

1. A braking energy recovery method for an automobile, characterized in that, Including the following steps: Obtain at least one driving parameter and a target deceleration of the vehicle; Input the at least one driving parameter and the target deceleration into a preset fuzzy neural network model to obtain an electro-hydraulic braking control ratio for controlling the vehicle without changing the current brake pedal opening of the vehicle and the target deceleration; Modify the driving motor torque and mechanical braking force of the vehicle according to the electro-hydraulic braking control ratio, so as to recover the generated braking energy when the vehicle brakes by outputting the modified driving motor torque and mechanical braking force according to the electro-hydraulic braking control ratio.

2. The method according to claim 1, wherein Before inputting the at least one driving parameter and the target deceleration into the preset fuzzy neural network model, it further includes: Collect initial driving data of the target vehicle driving under multiple target working conditions; Select final driving data that meets preset valid conditions from the initial driving data; Determine the maximum driving motor braking recovery torque corresponding to the final driving data, and obtain the preset fuzzy neural network model based on the maximum driving motor braking recovery torque.

3. The method according to claim 2, wherein The determining the maximum driving motor braking recovery torque corresponding to the final driving data and obtaining the preset fuzzy neural network model based on the maximum driving motor braking recovery torque includes: Identify key parameters during the deceleration process of the final driving data; Dynamically adjust the electro-hydraulic coordinated braking ratio of the target vehicle during braking according to the key parameters to find the maximum driving motor braking recovery torque corresponding to the final driving data, so as to determine the preset fuzzy neural network model.

4. The method according to claim 2, characterized in that, It further includes: Calculate the energy loss of the target vehicle during braking according to a target loss function; Optimize the braking motor torque and hydraulic braking force of the target vehicle during braking according to the energy loss to optimize the preset fuzzy neural network model.

5. The method according to claim 1, wherein It further includes: Detect the actual energy demand of the driver; Based on the actual energy demand, determine whether to recover the braking energy of the vehicle.

6. A braking energy recovery device for an automobile, characterized in that, It includes: An acquisition module for obtaining at least one driving parameter and a target deceleration of the vehicle; A processing module for inputting the at least one driving parameter and the target deceleration into a preset fuzzy neural network model to obtain an electro-hydraulic braking control ratio for controlling the vehicle without changing the current brake pedal opening of the vehicle and the target deceleration; A recovery module for modifying the driving motor torque and mechanical braking force of the vehicle according to the electro-hydraulic braking control ratio, so as to recover the generated braking energy when the vehicle brakes by outputting the modified driving motor torque and mechanical braking force according to the electro-hydraulic braking control ratio.

7. The device according to claim 6, characterized in that, It further includes: A collection module for collecting initial driving data of the target vehicle driving under multiple target working conditions before inputting the at least one driving parameter and the target deceleration into the preset fuzzy neural network model; A screening module for selecting final driving data that meets preset valid conditions from the initial driving data; A determination module, configured to determine a maximum driving motor braking recovery torque corresponding to the final driving data, and obtain the preset fuzzy neural network model based on the maximum driving motor braking recovery torque.

8. A vehicle, characterized in that, Comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the braking energy recovery method for an automobile according to any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the braking energy recovery method for an automobile according to any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed, it is used to implement the braking energy recovery method for an automobile according to any one of claims 1-5.

Images