An energy recovery method, system and device for self-adapting vehicle weight and a storage medium

Abstract

The application discloses an adaptive vehicle weight energy recovery method, system, device and storage medium, comprising: acquiring the empty weight and the load weight of a target vehicle, determining the real-time vehicle load of the target vehicle according to the empty weight and the load weight; acquiring the real-time vehicle speed of the target vehicle, determining the real-time sliding resistance of the target vehicle according to the real-time vehicle speed and the real-time vehicle load; inputting the real-time vehicle load, the real-time vehicle speed and the real-time sliding resistance into a pre-trained brake recovery torque prediction model to obtain a target brake recovery torque; and performing energy recovery control on the target vehicle according to the target brake recovery torque. The application considers the influence of the vehicle load, the vehicle speed and the sliding resistance on the brake recovery torque under different vehicle working conditions, improves the accuracy of the energy recovery control, thereby improving the efficiency of the energy recovery in the vehicle sliding stage, improving the driving experience and the riding experience of the user, and being applicable to the technical field of vehicle control.

Description

TECHNICAL FIELD

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

[0002] With the development of intelligent networking of automobiles, vehicle monitoring and control technology is becoming more and more intelligent. Braking energy recovery (Braking Energy Recovery System) of electric vehicles (referring to hybrid electric vehicles, pure electric vehicles and extended-range electric vehicles), also known as regenerative braking or energy regeneration braking, refers to the release of excess energy during vehicle deceleration / braking or inertial sliding. Under the premise of ensuring braking efficiency, the driving motor is controlled to work as a generator, and through the energy conversion device connected to the driving shaft, a part of the mechanical energy (kinetic energy or potential energy) of the vehicle is converted into other forms of energy (electric energy) and stored in the energy storage device (various batteries, super capacitors, ultra-high-speed flywheels or their composite) and utilized for subsequent acceleration driving. When used, the power can be quickly released to achieve the goal of recovering braking energy to extend / increase the cruising range of electric vehicles. At the same time, the motor feedback torque is applied to the drive shaft to brake the vehicle.

[0003] At present, the energy recovery of electric vehicles during sliding (i.e. the driver does not step on the accelerator pedal and does not step on the brake pedal) is mostly in the form of providing multiple gear options. The driver can select different intensity gears for energy recovery by operation, and the setting of braking recovery torque of different gears is mostly realized by writing fixed parameters into the controller after driving evaluation. Due to the difference in resistance characteristics of vehicles under different load conditions, the control of braking recovery torque according to fixed parameters will cause differences between the evaluated state and the actual vehicle load state, affecting the efficiency of energy recovery during the sliding stage of the vehicle and also affecting the driving experience and riding experience of the user. SUMMARY

[0004] The present application aims to at least partially solve one of the problems in the prior art.

[0005] To this end, one object of the embodiments of the present application is to provide an energy recovery method with adaptive vehicle weight, which improves the efficiency of energy recovery during the sliding stage of the vehicle and also improves the driving experience and riding experience of the user.

[0006] Another object of the embodiments of the present application is to provide an energy recovery system with adaptive vehicle weight.

[0007] In order to achieve the above technical purpose, the technical solutions adopted by the embodiments of the present application include:

[0008] In a first aspect, an embodiment of the present application provides an energy recovery method for adaptive vehicle weight, comprising the following steps:

[0009] obtaining the empty weight and the load weight of the target vehicle, and determining the real-time vehicle load of the target vehicle according to the empty weight and the load weight;

[0010] obtaining the real-time vehicle speed of the target vehicle, and determining the real-time rolling resistance of the target vehicle according to the real-time vehicle speed and the real-time vehicle load;

[0011] inputting the real-time vehicle load, the real-time vehicle speed and the real-time rolling resistance into a pre-trained brake recovery torque prediction model to obtain a target brake recovery torque;

[0012] controlling energy recovery of the target vehicle according to the target brake recovery torque.

[0013] Further, in an embodiment of the present application, the step of obtaining the empty weight and the load weight of the target vehicle, and determining the real-time vehicle load of the target vehicle according to the empty weight and the load weight specifically comprises:

[0014] obtaining the load weight of the target vehicle through a vehicle-mounted weighing system;

[0015] obtaining the empty weight calibrated when the target vehicle is manufactured;

[0016] taking the sum of the empty weight and the load weight as the real-time vehicle load of the target vehicle.

[0017] Further, in an embodiment of the present application, the step of obtaining the real-time vehicle speed of the target vehicle specifically comprises:

[0018] obtaining the real-time tire rotating speed, the real-time tire air pressure and the real-time environment temperature of the target vehicle;

[0019] predicting the real-time tire rolling radius of the target vehicle according to the real-time vehicle load, the real-time tire rotating speed, the real-time tire air pressure and the real-time environment temperature;

[0020] determining the real-time vehicle speed of the target vehicle according to the real-time tire rolling radius and the real-time tire rotating speed.

[0021] Further, in an embodiment of the present application, the step of determining the real-time rolling resistance of the target vehicle according to the real-time vehicle speed and the real-time vehicle load specifically comprises:

[0022] According to the real-time vehicle load, a corresponding coasting resistance fitting curve is obtained;

[0023] According to the real-time vehicle speed and the coasting resistance fitting curve, a real-time coasting resistance of the target vehicle is determined;

[0024] The coasting resistance fitting curve is a quadratic function curve of coasting resistance and vehicle speed.

[0025] Further, in an embodiment of the present application, the energy recovery method further comprises the step of pre-training the brake recovery torque prediction model, which specifically comprises:

[0026] Obtaining a plurality of vehicle load data, vehicle speed data and coasting resistance data of the target vehicle under test conditions;

[0027] Generating a training sample according to the vehicle load data, the vehicle speed data and the coasting resistance data, and determining an optimal brake recovery torque corresponding to the training sample based on driving evaluation;

[0028] Determining a sample label of the training sample according to the optimal automatic recovery torque, and constructing a training data set according to the training sample and the corresponding sample label;

[0029] Inputting the training data set into a pre-constructed BP neural network for training to obtain the trained brake recovery torque prediction model.

[0030] Further, in an embodiment of the present application, the step of inputting the training data set into a pre-constructed BP neural network for training to obtain the trained brake recovery torque prediction model specifically comprises:

[0031] Inputting the training data set into the BP neural network to obtain a brake recovery torque prediction result;

[0032] Determining a loss value of the BP neural network according to the brake recovery torque prediction result and the sample label;

[0033] Updating the model parameters of the BP neural network according to the loss value through a back propagation algorithm, and returning to the step of inputting the training data set into the BP neural network;

[0034] When the loss value reaches a preset first threshold value or the number of iterations reaches a preset second threshold value, the training is stopped, and the trained brake recovery torque prediction model is obtained.

[0035] Further, in an embodiment of the present application, the energy recovery method further comprises the following steps:

[0036] In response to the first operation instruction received by the target vehicle, a corresponding energy recovery correction coefficient is determined according to the first operation instruction, and the target brake recovery torque is adjusted according to the energy recovery correction coefficient.

[0037] In a second aspect, an embodiment of the present application provides an energy recovery system adaptive to vehicle weight, comprising:

[0038] A real-time vehicle load determination module is configured to acquire an empty load of the target vehicle and a load weight, and determine a real-time vehicle load of the target vehicle according to the empty load and the load weight.

[0039] A real-time coasting resistance determination module is configured to acquire a real-time vehicle speed of the target vehicle, and determine a real-time coasting resistance of the target vehicle according to the real-time vehicle speed and the real-time vehicle load.

[0040] A brake recovery torque prediction module is configured to input the real-time vehicle load, the real-time vehicle speed and the real-time coasting resistance into a pre-trained brake recovery torque prediction model to obtain a target brake recovery torque.

[0041] An energy recovery control module is configured to perform energy recovery control on the target vehicle according to the target brake recovery torque.

[0042] In a third aspect, an embodiment of the present application provides an energy recovery device adaptive to vehicle weight, comprising:

[0043] At least one processor;

[0044] At least one memory configured to store at least one program;

[0045] When the at least one program is executed by the at least one processor, the at least one processor is caused to implement the energy recovery method adaptive to vehicle weight.

[0046] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, wherein a program executable by a processor is stored, and the program executable by the processor is configured to implement the energy recovery method adaptive to vehicle weight when executed by the processor.

[0047] The advantages and beneficial effects of the present application will be partially given in the following description, partially will become obvious from the following description, or will be understood through the practice of the present application:

[0048] The embodiment of the present application obtains the empty load of the target vehicle and the load weight, determines the real-time vehicle load of the target vehicle according to the empty load and the load weight, then obtains the real-time vehicle speed of the target vehicle, determines the real-time rolling resistance of the target vehicle according to the real-time vehicle speed and the real-time vehicle load, and finally inputs the real-time vehicle load, the real-time vehicle speed and the real-time rolling resistance into the pre-trained brake recovery torque prediction model to obtain the target brake recovery torque, so that the energy recovery control can be performed on the target vehicle according to the target brake recovery torque. The embodiment of the present application dynamically identifies the real-time vehicle load, determines the real-time rolling resistance of the target vehicle according to the real-time vehicle load and the real-time vehicle speed, and combines the pre-trained brake recovery torque prediction model to obtain the optimal target brake recovery torque, which considers the influence of the vehicle load, the vehicle speed and the rolling resistance on the brake recovery torque under different vehicle working conditions, improves the accuracy of the energy recovery control, and thus improves the efficiency of the energy recovery in the vehicle rolling stage and the driving experience and the riding experience of the user. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following introduces the drawings needed to be used in the embodiments of the present application as follows, and it should be understood that the drawings introduced in the following are only for facilitating the clear description of the partial embodiments in the technical solutions of the present application, and the other drawings can be obtained by the person skilled in the art without any creative labor on the premise of the drawings.

[0050] Figure 1 A step flow chart of an energy recovery method of self-adaptive vehicle weight provided by the embodiment of the present application is shown in the figure.

[0051] Figure 2 A structure block diagram of an energy recovery system of self-adaptive vehicle weight provided by the embodiment of the present application is shown in the figure.

[0052] Figure 3 A structure block diagram of an energy recovery device of self-adaptive vehicle weight provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0053] The embodiments of the present application are described in detail below, and the examples of the embodiments are shown in the drawings, wherein the same or similar reference signs represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application. For the step numbers in the following embodiments, they are only set for facilitating the description and explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiments can be adaptively adjusted according to the understanding of the person skilled in the art.

[0054] In the description of the present application, the meaning of plurality is two or more, if the first, second is described only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or implicitly indicating the sequence of indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as generally understood by those skilled in the art.

[0055] Referring to Figure 1 The embodiment of the present application provides an energy recovery method of self-adaptive vehicle weight, and specifically comprises the following steps:

[0056] S101, obtaining the empty weight and the load weight of the target vehicle, and determining the real-time vehicle load of the target vehicle according to the empty weight and the load weight.

[0057] Specifically, the real-time vehicle load is the sum of the empty weight and the load weight (including the total weight of passengers and carried objects) of the target vehicle. It can be understood that the greater the load weight, the greater the inertial force and the coasting resistance of the vehicle. When the load weight is different, even if the vehicle speed is the same, the corresponding optimal brake recovery torque is also different. Therefore, the embodiment of the present application determines the real-time vehicle load of the target vehicle for subsequent prediction of real-time brake recovery torque, which can improve the accuracy of brake recovery torque, thereby improving the efficiency of vehicle energy recovery.

[0058] Further as an optional implementation, the step of obtaining the empty weight and the load weight of the target vehicle, and determining the real-time vehicle load of the target vehicle according to the empty weight and the load weight specifically comprises:

[0059] S1011, obtaining the load weight of the target vehicle through a vehicle-mounted weighing system;

[0060] S1012, obtaining the empty weight calibrated when the target vehicle is manufactured;

[0061] S1013, taking the sum of the empty weight and the load weight as the real-time vehicle load of the target vehicle.

[0062] Specifically, the vehicle-mounted weighing system is a full-automatic weighing instrument aiming at weighing the load of the vehicle, mainly composed of a weighing sensor, a collector and a display instrument, etc., and can measure the value of the load of the vehicle in real time and efficiently. The embodiment of the present application applies the vehicle-mounted weighing system to all vehicle types, obtains the load weight of the target vehicle through the weighing sensor of the vehicle-mounted weighing system, and combines the empty weight calibrated when the target vehicle is manufactured, so as to accurately calculate the real-time vehicle load of the target vehicle.

[0063] S102, acquire a real-time vehicle speed of the target vehicle, and determine a real-time rolling resistance of the target vehicle according to the real-time vehicle speed and a real-time vehicle load.

[0064] Further as an optional implementation, the step of acquiring the real-time vehicle speed of the target vehicle specifically comprises:

[0065] S1021, acquire a real-time tire rotating speed, a real-time tire air pressure and a real-time environment temperature of the target vehicle;

[0066] S1022, predict a real-time tire rolling radius of the target vehicle according to the real-time vehicle load, the real-time tire rotating speed, the real-time tire air pressure and the real-time environment temperature;

[0067] S1023, determine the real-time vehicle speed of the target vehicle according to the real-time tire rolling radius and the real-time tire rotating speed.

[0068] In some optional embodiments, the step of acquiring the real-time tire rotating speed, the real-time tire air pressure and the real-time environment temperature of the target vehicle specifically comprises:

[0069] S10211, acquire the real-time tire rotating speed of the target vehicle through a wheel speed sensor, or acquire a real-time motor rotating speed of the target vehicle through a motor controller, and determine the real-time tire rotating speed according to the real-time motor rotating speed and a reduction ratio of the target vehicle;

[0070] S10212, acquire the real-time tire air pressure of the target vehicle through a tire pressure sensor, and acquire the real-time environment temperature of the target vehicle through a temperature sensor.

[0071] Specifically, the real-time tire rotating speed can be directly measured through the wheel speed sensor, or calculated through the ratio of the motor rotating speed and the reduction ratio; the tire pressure sensor can directly measure the air pressure inside the tire, and the temperature sensor can directly measure the environment temperature where the target vehicle is located. It can be understood that the tire rotating speed, the tire air pressure and the environment temperature are all factors that can affect the tire rolling radius, and the measurement of these parameters can improve the accuracy of the subsequent real-time tire rolling radius prediction, thereby improving the accuracy of the vehicle speed calculation.

[0072] In some optional embodiments, the step of predicting the real-time tire rolling radius of the target vehicle according to the real-time tire load, the real-time tire rotating speed, the real-time tire air pressure and the real-time environment temperature specifically comprises:

[0073] S10221, acquire a preset tire rolling radius mapping table, and determine a first tire rolling radius according to the real-time tire load, the real-time tire rotating speed, the real-time tire air pressure and the tire rolling radius mapping table;

[0074] S10222, determining a tire deformation correction coefficient according to the real-time ambient temperature;

[0075] S10223, predicting a real-time tire rolling radius according to the first tire rolling radius and the tire deformation correction coefficient.

[0076] Specifically, the tire rolling radius mapping table of the embodiment of the present application is calibrated through test experiments. For a test vehicle of the same vehicle model as the target vehicle, the corresponding tire rolling radius is determined, such as through image analysis, under different working conditions of tire load, tire speed, and tire air pressure. Test data under multiple working conditions are collected to form a tire rolling radius mapping table. The first tire rolling radius can be determined according to the real-time tire load, the real-time tire speed, the real-time tire air pressure, and the tire rolling radius mapping table through table lookup. In addition, considering the influence of the real-time ambient temperature on the real-time tire rolling radius, the embodiment of the present application introduces a tire deformation correction coefficient, which can also be obtained through table lookup according to the real-time ambient temperature (the related mapping table is formed according to empirical data), and the real-time tire rolling radius can be obtained by combining the first tire rolling radius and the tire deformation correction coefficient.

[0077] It can be understood that the tire rolling radius mapping table of the embodiment of the present application is constructed based on a test vehicle of the same vehicle model as the target vehicle, so that the tire size of the target vehicle does not need to be considered when performing table lookup, and the tire size has been taken as a known condition of the tire rolling radius mapping table.

[0078] In some optional embodiments, the real-time tire rolling radius can be represented as R = Map (load, speed, Pressure) + a, where R represents the real-time tire rolling radius, Map (load, speed, Pressure) represents the first tire rolling radius obtained through table lookup, a represents the tire deformation correction coefficient, load represents the real-time tire load, speed represents the real-time tire speed, and Pressure represents the real-time tire air pressure.

[0079] In some optional embodiments, the step of determining the real-time vehicle speed of the target vehicle according to the real-time tire rolling radius and the real-time tire speed specifically includes:

[0080] S10231, determining the real-time tire rolling circumference of the target vehicle according to the real-time tire rolling radius;

[0081] S10232, determining the real-time vehicle speed of the target vehicle according to the product of the real-time tire rolling circumference and the real-time tire speed.

[0082] Specifically, according to the real-time tire rolling radius, the real-time tire rolling circumference can be calculated as 2πR, and the real-time vehicle speed can be obtained according to the product of the real-time tire rolling circumference and the real-time tire rotating speed, which can be expressed as V=2πR*speed or V=2πR*n / ratio, wherein speed represents the real-time tire rotating speed, n represents the real-time motor rotating speed, and ratio represents the speed reduction ratio, and speed=n / ratio. It can be understood that the above calculation formula does not involve the conversion of units such as speed per hour, and the unit conversion can be performed according to the actual situation in specific application, and the embodiment of the present application will not be described here.

[0083] Further as an optional implementation, the step of determining the real-time rolling resistance of the target vehicle according to the real-time vehicle speed and the real-time vehicle load specifically comprises:

[0084] S1024, obtaining a corresponding rolling resistance fitting curve according to the real-time vehicle load;

[0085] S1025, determining the real-time rolling resistance of the target vehicle according to the real-time vehicle speed and the rolling resistance fitting curve;

[0086] Wherein, the rolling resistance fitting curve is a quadratic function curve of the rolling resistance and the vehicle speed pre-fitted.

[0087] Specifically, the embodiment of the present application calibrates the corresponding rolling resistance of the target vehicle at different vehicle speeds under a specific vehicle load through experiments, and then performs curve fitting through a quadratic function to obtain the rolling resistance fitting curve corresponding to the specific vehicle load; the rolling resistance fitting curves under a plurality of different specific vehicle loads are determined, so that the real-time rolling resistance of the target vehicle can be determined according to the real-time vehicle load and the real-time vehicle speed.

[0088] In the embodiment of the present application, the function form of the rolling resistance fitting curve can be expressed as: f=A*V 2 +B*V+C, wherein A, B and C are resistance determination parameters to be fitted.

[0089] S103, inputting the real-time vehicle load, the real-time vehicle speed and the real-time rolling resistance into the pre-trained brake recovery torque prediction model to obtain the target brake recovery torque.

[0090] Specifically, the brake recovery torque prediction model of the embodiment of the present application is obtained by training the test data through the BP neural network, and the real-time vehicle load, the real-time vehicle speed and the real-time rolling resistance are input into the brake recovery torque prediction model, so that the corresponding real-time brake recovery torque can be obtained.

[0091] Further as an optional implementation, the energy recovery method further comprises the step of pre-training the brake recovery torque prediction model, which specifically comprises:

[0092] A1, acquire a plurality of vehicle load data, vehicle speed data and coasting resistance data of the target vehicle under test conditions;

[0093] A2, generate a training sample according to the vehicle load data, the vehicle speed data and the coasting resistance data, and determine an optimal brake recovery torque corresponding to the training sample based on driving evaluation;

[0094] A3, determine a sample label of the training sample according to the optimal automatic recovery torque, and construct a training data set according to the training sample and the corresponding sample label;

[0095] A4, input the training data set to the pre-constructed BP neural network for training to obtain a trained brake recovery torque prediction model.

[0096] Specifically, when constructing the training data set, for a test vehicle of the same vehicle model as the target vehicle, the driving evaluation of the test personnel on the brake recovery torque of different gears under different vehicle load, vehicle speed and coasting resistance conditions is obtained, and the corresponding optimal automatic recovery torque is selected as the sample label; the test data under a plurality of working conditions is collected, and the training data set is obtained.

[0097] It can be understood that the training data set of the embodiment of the application is constructed based on the test vehicle of the same vehicle model as the target vehicle, so that other fixed parameters of the target vehicle do not need to be considered during model training, and the brake recovery torque prediction model obtained by training is a prediction model for the target vehicle.

[0098] Further, as an optional implementation, the step of inputting the training data set to the pre-constructed BP neural network for training to obtain the trained brake recovery torque prediction model specifically includes:

[0099] A41, input the training data set to the BP neural network to obtain a brake recovery torque prediction result;

[0100] A42, determine a loss value of the BP neural network according to the brake recovery torque prediction result and the sample label;

[0101] A43, update the model parameters of the BP neural network through a back propagation algorithm according to the loss value, and return to the step of inputting the training data set to the BP neural network;

[0102] A44, when the loss value reaches a preset first threshold value or the number of iterations reaches a preset second threshold value, stop training to obtain the trained brake recovery torque prediction model.

[0103] After the data in the training data set is input into the initialized BP neural network model, the prediction result output by the model, i.e., the brake recovery torque prediction result, can be obtained. The accuracy of the model prediction can be evaluated according to the brake recovery torque prediction result and the aforementioned sample label, so as to update the parameters of the model. For the brake recovery torque prediction model, the accuracy of the model prediction result can be measured by a loss function. The loss function is defined on a single training data and is used to measure the prediction error of a training data. Specifically, the loss value of a training data is determined by the label of the training data and the prediction result of the model for the training data. In actual training, a training data set has many training data, so a cost function is generally used to measure the overall error of the training data set. The cost function is defined on the entire training data set and is used to calculate the average value of the prediction errors of all training data, which can better measure the prediction effect of the model. For a general machine learning model, based on the aforementioned cost function, plus a regular term that measures the complexity of the model, the target function for training can be obtained. Based on the target function, the loss value of the entire training data set can be obtained. There are many commonly used loss functions, such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross-entropy loss function, etc., which can be used as the loss function of the machine learning model. Here, they will not be described one by one. In the embodiment of the present application, any one of the loss functions can be selected to determine the loss value of the training. Based on the loss value of the training, the parameters of the model are updated by using the back propagation algorithm, and after several iterations, the trained brake recovery torque prediction model can be obtained. Specifically, the number of iterations can be preset, or the training can be considered to be completed when the test set reaches the accuracy requirement.

[0104] S104, energy recovery control is performed on the target vehicle according to the target brake recovery torque.

[0105] Specifically, the target brake recovery torque is sent to the motor controller through the body controller, and the motor controller performs energy recovery control according to the target brake recovery torque.

[0106] Further, as an optional embodiment, the energy recovery method further comprises the following steps:

[0107] S105, in response to the first operation instruction received by the target vehicle, a corresponding energy recovery correction coefficient is determined according to the first operation instruction, and the target brake recovery torque is adjusted according to the energy recovery correction coefficient.

[0108] Specifically, in the intelligent screen interconnection system, the driver can set different energy recovery correction gears according to the strength of the energy recovery felt during driving, and different energy recovery correction gears correspond to different energy recovery correction coefficients a. After the driver actively sets the energy recovery correction gear, the adjusted target brake recovery torque can be represented as F=F0+ a, wherein F represents the adjusted target brake recovery torque, and F0 represents the target brake recovery torque before adjustment. The vehicle body controller sends the adjusted target brake recovery torque to the motor controller for execution, so that the driver can dynamically fine-tune the vehicle energy recovery, and the efficiency of the vehicle energy recovery and the driving experience of the driver are further improved.

[0109] The method steps of the embodiments of the present application are described above. It can be understood that the embodiments of the present application dynamically identify the real-time vehicle load, determine the real-time coasting resistance of the target vehicle according to the real-time vehicle load and the real-time vehicle speed, and predict the optimal target brake recovery torque by combining the pre-trained brake recovery torque prediction model. The influence of vehicle load, vehicle speed and coasting resistance on brake recovery torque under different vehicle working conditions is considered, the accuracy of energy recovery control is improved, the efficiency of energy recovery in the vehicle coasting stage is improved, and the driving experience and riding experience of the user are also improved.

[0110] Referring to Figure 2 The embodiments of the present application provide an energy recovery system with adaptive vehicle weight, comprising:

[0111] A real-time vehicle load determination module is configured to obtain the empty load mass and the load weight of the target vehicle, and determine the real-time vehicle load of the target vehicle according to the empty load mass and the load weight.

[0112] A real-time coasting resistance determination module is configured to obtain the real-time vehicle speed of the target vehicle, and determine the real-time coasting resistance of the target vehicle according to the real-time vehicle speed and the real-time vehicle load.

[0113] A brake recovery torque prediction module is configured to input the real-time vehicle load, the real-time vehicle speed and the real-time coasting resistance into a pre-trained brake recovery torque prediction model to obtain a target brake recovery torque.

[0114] An energy recovery control module is configured to perform energy recovery control on the target vehicle according to the target brake recovery torque.

[0115] The contents in the above method embodiments are applicable to the system embodiments, the system embodiments specifically realize the same functions as the above method embodiments, and achieve the same beneficial effects as the above method embodiments.

[0116] Referring to Figure 3The embodiment of the present application provides an energy recovery device of self-adaptive vehicle weight, comprising:

[0117] at least one processor;

[0118] at least one memory for storing at least one program;

[0119] When the at least one program is executed by the at least one processor, the at least one processor implements the energy recovery method of self-adaptive vehicle weight.

[0120] The contents in the method embodiment are applicable to the device embodiment, the device embodiment specifically implements the same functions as the method embodiment, and achieves the same beneficial effects as the method embodiment.

[0121] The embodiment of the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a program executable by a processor, and the program executable by the processor is used for executing the energy recovery method of self-adaptive vehicle weight when the program executable by the processor is executed by the processor.

[0122] The computer readable storage medium of the embodiment of the present application can execute the energy recovery method of self-adaptive vehicle weight provided by the method embodiment of the present application, can execute the step of any combination of the method embodiment, has the corresponding functions and beneficial effects of the method.

[0123] The embodiment of the present application further discloses a computer program product or a computer program, and the computer program product or the computer program comprises computer instructions stored in a computer readable storage medium. The processor of a computer device can read the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method shown in the figure. Figure 1 The method shown in the figure.

[0124] In some alternative embodiments, the functions / operations mentioned in the block diagram can not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, two blocks shown in succession can actually be executed substantially simultaneously or the above blocks can be executed in reverse order at times. In addition, the embodiments presented and described in the flowcharts of the present application are provided by way of example, and the purpose is to provide a more comprehensive understanding of the technology. The disclosed method is not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are independently executed.

[0125] Furthermore, although the present application is described in the context of functional modules, it is to be understood that one or more of the functions and / or features described above can be integrated in a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It will also be appreciated that detailed discussion of the actual implementation of each module is unnecessary to an understanding of the present application. Rather, the actual implementation of the modules, in conjunction with their attributes, functions, and internal relationships, are to be understood within the context of the devices disclosed herein. Thus, those skilled in the art with access to the teachings presented herein will be able to devise suitable implementations of the present application without undue experimentation. It is also to be understood that the particular concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is defined by the appended claims and equivalents thereof.

[0126] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0127] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a list of executable instructions for implementing logic functions, which can be specifically embodied in any computer readable medium for use by an instruction execution system, device or apparatus, such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, device or apparatus, or in conjunction with these instructions execution system, device or apparatus. For the purpose of this specification, "computer readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by an instruction execution system, device or apparatus, or in conjunction with these instruction execution system, device or apparatus.

[0128] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

[0129] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, various steps or methods can be implemented in software or firmware which are stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies, known in the art, or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions upon an application of data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0130] In the above description of the present specification, the description referring to the terms "one embodiment", "another embodiment", or "certain embodiments" or the like means that a specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. The illustrative expressions of the above terms do not necessarily refer to the same embodiment or example in the present specification. Also, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0131] Although the embodiments of the present application have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, alternatives and variations to these embodiments can be made without departing from the principles and spirit of the application, the scope of which is defined by the claims and their equivalents.

[0132] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the above-described embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present application, and these equivalent modifications or substitutions are included in the scope defined by the claims of the present application.

Claims

1. A method of energy recovery with self-adaptive vehicle weight, characterized in that, The method comprises the following steps: obtaining the empty weight and the load weight of the target vehicle, and determining the real-time vehicle load of the target vehicle according to the empty weight and the load weight; obtaining the real-time vehicle speed of the target vehicle, and determining the real-time rolling resistance of the target vehicle according to the real-time vehicle speed and the real-time vehicle load; inputting the real-time vehicle load, the real-time vehicle speed and the real-time rolling resistance into a pre-trained brake recovery torque prediction model to obtain a target brake recovery torque; controlling energy recovery of the target vehicle according to the target brake recovery torque; The energy recovery method further comprises the step of pre-training the brake recovery torque prediction model, which specifically comprises: obtaining a plurality of vehicle load data, vehicle speed data and rolling resistance data of the target vehicle under test conditions; generating training samples according to the vehicle load data, the vehicle speed data and the rolling resistance data, and determining the optimal brake recovery torque corresponding to the training samples based on driving evaluation; determining sample labels of the training samples according to the optimal brake recovery torque, and constructing a training data set according to the training samples and the corresponding sample labels; inputting the training data set into a pre-constructed BP neural network for training to obtain the trained brake recovery torque prediction model; The step of inputting the training data set into the pre-constructed BP neural network for training to obtain the trained brake recovery torque prediction model specifically comprises: inputting the training data set into the BP neural network to obtain brake recovery torque prediction results; determining a loss value of the BP neural network according to the brake recovery torque prediction results and the sample labels; updating model parameters of the BP neural network through a back propagation algorithm according to the loss value, and returning to the step of inputting the training data set into the BP neural network; stopping training when the loss value reaches a preset first threshold value or the number of iterations reaches a preset second threshold value, and obtaining the trained brake recovery torque prediction model.

2. The energy recovery method of claim 1, wherein, The step of obtaining the empty weight and the load weight of the target vehicle, and determining the real-time vehicle load of the target vehicle according to the empty weight and the load weight specifically comprises: obtaining the load weight of the target vehicle through a vehicle-mounted weighing system; obtaining the empty weight calibrated when the target vehicle is manufactured; taking the sum of the empty weight and the load weight as the real-time vehicle load of the target vehicle.

3. The energy recovery method of claim 1, wherein, The step of obtaining the real-time vehicle speed of the target vehicle specifically comprises: obtaining the real-time tire speed, the real-time tire air pressure and the real-time environmental temperature of the target vehicle; predicting the real-time tire rolling radius of the target vehicle according to the real-time vehicle load, the real-time tire speed, the real-time tire air pressure and the real-time environmental temperature; determining the real-time vehicle speed of the target vehicle according to the real-time tire rolling radius and the real-time tire speed.

4. The energy recovery method of claim 1, wherein, The step of determining the real-time rolling resistance of the target vehicle according to the real-time vehicle speed and the real-time vehicle load specifically comprises: obtaining a corresponding rolling resistance fitting curve according to the real-time vehicle load; determining the real-time rolling resistance of the target vehicle according to the real-time vehicle speed and the rolling resistance fitting curve; wherein the rolling resistance fitting curve is a quadratic function curve of rolling resistance and vehicle speed obtained by pre-fitting.

5. The energy recovery method of self-adaptive vehicle weight according to any one of claims 1 to 4, characterized in that, The energy recovery method further comprises the following steps: in response to the first operation instruction received by the target vehicle, determining a corresponding energy recovery correction coefficient according to the first operation instruction, and adjusting the target brake recovery torque according to the energy recovery correction coefficient.

6. An adaptive vehicle mass energy recovery system, characterized by, An energy recovery method for realizing the self-adaptive vehicle weight as claimed in any one of claims 1 to 5, comprising: a real-time vehicle load determination module for obtaining the empty load mass and the load weight of the target vehicle, and determining the real-time vehicle load of the target vehicle according to the empty load mass and the load weight; a real-time rolling resistance determination module for obtaining the real-time vehicle speed of the target vehicle, and determining the real-time rolling resistance of the target vehicle according to the real-time vehicle speed and the real-time vehicle load; a brake recovery torque prediction module for inputting the real-time vehicle load, the real-time vehicle speed and the real-time rolling resistance into a pre-trained brake recovery torque prediction model to obtain a target brake recovery torque; an energy recovery control module for performing energy recovery control on the target vehicle according to the target brake recovery torque.

7. An energy recovery device for self-adapting vehicle weight, characterized by, comprising: at least one processor; at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the at least one processor implements an energy recovery method for self-adaptive vehicle weight as claimed in any one of claims 1 to 5.

8. A computer readable storage medium having stored therein a program which is executable by a processor, characterized in that, The program executable by the processor, when executed by the processor, is used to perform an energy recovery method for self-adaptive vehicle weight as claimed in any one of claims 1 to 5.

Images