Electric vehicle energy recovery method and device, storage medium, controller and product

Abstract

The invention provides an electric vehicle energy recovery method and device, a storage medium, a controller and a product. The method comprises the steps that vehicle control information, driving habit information and road information of a vehicle are collected; the collected vehicle control information, the driving habit information and the road information are subjected to preset processing, and a first variable mathematical model, a second variable mathematical model and a third variable mathematical model are obtained respectively; establishing an energy recovery strategy mathematical model based on the first variable mathematical model, the second variable mathematical model and the third variable mathematical model; performing optimization solution on the energy recovery strategy mathematical model through an optimization algorithm to obtain a predicted optimal energy recovery strategy of the electric vehicle; and controlling the electric vehicle according to the obtained predicted optimal energy recovery strategy. According to the scheme provided by the invention, the current optimal energy recovery strategy can be determined to optimize the service life of the battery, and the endurance mileage of the whole vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the field of control, and in particular to an electric vehicle energy recovery method, device, storage medium, controller and product. Background Art

[0002] Vigorously developing new energy vehicles has become the main task of my country's automobile industry in recent years, and the industrialization of new energy vehicles has also become an important implementation goal of major automobile companies. Improving the technology and performance level of new energy vehicles has become the most urgent need of the current automobile industry.

[0003] The auxiliary system of a car is the most important system that determines the performance of new energy vehicles. This emerging technology can enhance the driving experience of the car and improve the safety of operation. However, the energy recovery strategy of electric vehicles is modeled, which can easily cause errors in mileage control. Summary of the invention

[0004] The main purpose of the present invention is to overcome the defects of the above-mentioned related technologies and to provide an electric vehicle energy recovery method, device, storage medium, controller and product to solve the problem that the energy recovery strategy of electric vehicles in the related technologies is modeled and easily causes errors in mileage control.

[0005] On the one hand, the present invention provides an electric vehicle energy recovery method, comprising: collecting vehicle control information, driving habit information and road information of the vehicle; performing preset processing on the collected vehicle control information, driving habit information and road information to obtain a first variable mathematical model, a second variable mathematical model and a third variable mathematical model respectively; establishing an energy recovery strategy mathematical model based on the first variable mathematical model, the second variable mathematical model and the third variable mathematical model obtained after the preset processing; optimizing and solving the established energy recovery strategy mathematical model through an optimization algorithm to obtain a predicted optimal energy recovery strategy for the electric vehicle; and controlling the electric vehicle according to the obtained predicted optimal energy recovery strategy.

[0006] Optionally, the collected vehicle control information is subjected to preset processing to obtain a first variable mathematical model, including: discretizing the collected vehicle control information using a preset discrete algorithm; and constructing a first variable mathematical model based on the vehicle control information obtained after the discretization processing.

[0007] Optionally, the collected driving habit information is preset processed to obtain a second variable mathematical model, including: associating the collected driving status information and the vehicle power consumption information according to a corresponding relationship to form more than two groups of driving related information; clustering each group of the formed driving related information to obtain more than two categories; converting the more than two categories into more than two data levels according to the vehicle power consumption information, and constructing a second variable mathematical model.

[0008] Optionally, the collected road information is subjected to preset processing to obtain a third variable mathematical model, including: clustering the collected road information to obtain two or more classifications, and constructing a third variable mathematical model based on the two or more classifications; wherein the charging station location and the destination location are synthesized according to preset rules as a parameter of the third variable mathematical model, and the road traffic information is used as a parameter of the third variable mathematical model.

[0009] Optionally, the established mathematical model of the energy recovery strategy is optimized and solved by an optimization algorithm to obtain the predicted optimal energy recovery strategy of the electric vehicle, including: optimizing and solving the established mathematical model of the energy recovery strategy by a particle swarm algorithm to obtain the predicted optimal energy recovery strategy of the electric vehicle.

[0010] Optionally, the energy recovery strategy includes: a first energy recovery strategy, a second energy recovery strategy and a third energy recovery strategy; the first energy recovery strategy controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the braking force size and / or whether it is emergency braking; and / or, the second energy recovery strategy controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to whether it is emergency braking; and / or, the third energy recovery strategy controls the front and rear wheels of the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the motor temperature and status.

[0011] Optionally, the first energy recovery strategy controls the vehicle to perform motor regenerative braking and / or mechanical braking according to the braking force size and / or whether it is emergency braking, including: if the braking force is greater than a preset threshold, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if the braking force is less than or equal to the preset threshold and it is emergency braking, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if the braking force is less than or equal to the preset threshold and it is not emergency braking, the electric vehicle is controlled to perform motor regenerative braking; and / or, the second energy recovery strategy controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to whether it is emergency braking. movement, including: if it is emergency braking, controlling the electric vehicle to perform a combination of motor regenerative braking and mechanical braking; if it is not emergency braking, controlling the electric vehicle to perform motor regenerative braking; and / or, the third energy recovery strategy, according to the motor temperature and state, controlling the front and rear wheels of the electric vehicle to perform motor regenerative braking and / or mechanical braking, including: if the motor temperature exceeds a preset temperature threshold or the motor is on the verge of failure, controlling the front and rear wheels of the vehicle to perform mechanical braking; if the motor temperature does not exceed the preset temperature threshold and the motor is not on the verge of failure, controlling the front wheels of the vehicle to perform a combination of motor regenerative braking and mechanical braking, and controlling the rear wheels of the vehicle to perform mechanical braking.

[0012] On the other hand, the present invention provides an electric vehicle energy recovery device, including: a collection unit, used to collect vehicle control information, driving habit information and road information of the vehicle; a processing unit, used to perform preset processing on the vehicle control information, driving habit information and road information collected by the collection unit, and obtain a first variable mathematical model, a second variable mathematical model and a third variable mathematical model respectively; an establishment unit, used to establish an energy recovery strategy mathematical model based on the first variable mathematical model, the second variable mathematical model and the third variable mathematical model obtained after the preset processing; a solving unit, used to optimize and solve the established energy recovery strategy mathematical model through an optimization algorithm, and obtain a predicted optimal energy recovery strategy of the electric vehicle; a control unit, used to control the electric vehicle according to the obtained predicted optimal energy recovery strategy.

[0013] Optionally, the processing unit performs preset processing on the collected vehicle control information to obtain a first variable mathematical model, including: using a preset discrete algorithm to discretize the collected vehicle control information; and constructing a first variable mathematical model based on the vehicle control information obtained after the discretization processing.

[0014] Optionally, the processing unit performs preset processing on the collected driving habit information to obtain a second variable mathematical model, including: associating the collected driving status information and the vehicle power consumption information according to a corresponding relationship to form more than two groups of driving related information; clustering each group of the formed driving related information to obtain more than two categories; converting the more than two categories into more than two data levels according to the vehicle power consumption information, and constructing a second variable mathematical model.

[0015] Optionally, the processing unit performs preset processing on the collected road information to obtain a third variable mathematical model, including: clustering the collected road information to obtain two or more classifications, and constructing a third variable mathematical model based on the two or more classifications; wherein the charging station location and the destination location are synthesized according to preset rules as a parameter of the third variable mathematical model, and the road traffic information is used as a parameter of the third variable mathematical model.

[0016] Optionally, the solving unit optimizes and solves the established mathematical model of the energy recovery strategy through an optimization algorithm to obtain the predicted optimal energy recovery strategy of the electric vehicle, including: optimizing and solving the established mathematical model of the energy recovery strategy through a particle swarm algorithm to obtain the predicted optimal energy recovery strategy of the electric vehicle.

[0017] Optionally, the energy recovery strategy includes: a first energy recovery strategy, a second energy recovery strategy and a third energy recovery strategy; the first energy recovery strategy controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the braking force size and / or whether it is emergency braking; and / or, the second energy recovery strategy controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to whether it is emergency braking; and / or, the third energy recovery strategy controls the front and rear wheels of the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the motor temperature and status.

[0018] Optionally, the first energy recovery strategy controls the vehicle to perform motor regenerative braking and / or mechanical braking according to the braking force size and / or whether it is emergency braking, including: if the braking force is greater than a preset threshold, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if the braking force is less than or equal to the preset threshold and it is emergency braking, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if the braking force is less than or equal to the preset threshold and it is not emergency braking, the electric vehicle is controlled to perform motor regenerative braking; and / or, the second energy recovery strategy controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to whether it is emergency braking. movement, including: if it is emergency braking, controlling the electric vehicle to perform a combination of motor regenerative braking and mechanical braking; if it is not emergency braking, controlling the electric vehicle to perform motor regenerative braking; and / or, the third energy recovery strategy, according to the motor temperature and state, controlling the front and rear wheels of the electric vehicle to perform motor regenerative braking and / or mechanical braking, including: if the motor temperature exceeds a preset temperature threshold or the motor is on the verge of failure, controlling the front and rear wheels of the vehicle to perform mechanical braking; if the motor temperature does not exceed the preset temperature threshold and the motor is not on the verge of failure, controlling the front wheels of the vehicle to perform a combination of motor regenerative braking and mechanical braking, and controlling the rear wheels of the vehicle to perform mechanical braking.

[0019] Another aspect of the present invention provides a storage medium having a computer program stored thereon, wherein the program implements the steps of any of the aforementioned methods when executed by a processor.

[0020] In another aspect, the present invention provides an electric vehicle controller, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the aforementioned methods when executing the program.

[0021] In another aspect, the present invention provides an electric vehicle controller, comprising any of the energy recovery devices described above.

[0022] In yet another aspect, the present invention provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any of the aforementioned methods are implemented.

[0023] According to the technical solution of the present invention, the information of the control system, battery system and road system during the driving process of the vehicle is uniformly controlled and processed, and the current optimal energy recovery strategy is determined according to the driver's driving habits and the location information of the charging station, so as to optimize the battery life, improve the vehicle's cruising range, and eliminate the mileage anxiety of electric vehicle driving. In addition, the driving information of the whole vehicle and the road information are combined and connected with each other, which can not only avoid the vehicle from breaking down due to low power, but also reduce the frequency of the driver adjusting the energy recovery level according to the power, improve driving safety, and enhance the safety and robustness of the control system operation.

[0024] According to the technical solution of the present invention, the vehicle speed, remaining power, battery health status, power consumption status and driving status information are combined with road traffic and charging station location information for discretization processing, and the vehicle's optimal energy recovery strategy is determined by a multi-objective particle swarm algorithm to optimize the battery life, achieve stability and durability of the vehicle's operating endurance, improve the reliability, convenience and comfort of vehicle driving, ensure the overall safety of vehicle driving, and improve the power and economy of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 is a method schematic diagram of an embodiment of the electric vehicle energy recovery method provided by the present invention;

[0027] Figure 2 A schematic diagram of the classification of collected data information is shown;

[0028] Figure 3 A schematic diagram of a process for processing collected data is shown;

[0029] Figure 4 The particle swarm algorithm process is shown;

[0030] Figure 5a A first energy recovery strategy braking force distribution flow chart is shown;

[0031] Figure 5b A second energy recovery strategy braking force distribution flow chart is shown;

[0032] Figure 5c A third energy recovery strategy braking force distribution flow chart is shown;

[0033] Figure 6 is a method schematic diagram of a specific embodiment of the electric vehicle energy recovery method provided by the present invention;

[0034] Figure 7 It is a structural block diagram of an embodiment of an electric vehicle energy recovery control device provided by the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] The auxiliary system of the car is the most important system that determines the performance of new energy vehicles. This emerging technology can enhance the driving experience of the car and improve the safety of operation. However, the energy recovery strategy of electric vehicles is stereotyped, which can easily cause errors in mileage control. In addition, the vehicle's cruising range is short, the basic charging facilities are not perfect, and the driver cannot be guaranteed to arrive at the destination accurately during driving and cannot replenish energy in time, which causes a lot of troubles for the driver. These are all problems that the pure electric vehicle industry needs to solve.

[0038] Therefore, it is very necessary to predict the optimal energy recovery strategy based on various driving information, dynamically adjust the energy recovery strategy, optimize the energy consumption of the entire vehicle, eliminate the driving anxiety caused by the short range of pure electric vehicles, alleviate people's concerns about electric vehicles, effectively help drivers arrange travel plans in a timely manner, and improve people's travel efficiency.

[0039] The invention provides an energy recovery method for an electric vehicle.

[0040] Figure 1 It is a method schematic diagram of an embodiment of the electric vehicle energy recovery method provided by the present invention.

[0041] like Figure 1 As shown, according to one embodiment of the present invention, the electric vehicle energy recovery method includes at least step S110, step S120, step S130, step S140 and step S150.

[0042] Step S110, collecting vehicle control information, driving habit information and road information of the vehicle.

[0043] Specifically, the vehicle speed, remaining power, battery health status, power consumption status, driving status, road traffic flow, destination and charging station location information are collected, and the collected data information is divided into vehicle control information, driving habit information and road information, wherein the vehicle control information includes at least one of battery health information, vehicle speed control information and remaining power information; the driving habit information includes at least one of driving status information and vehicle power consumption information; the road information includes at least one of charging station location information, road traffic flow information and destination location information. Figure 2 The classification diagram of the collected data information is shown. The classification of data information can be found in Figure 2 shown.

[0044] Step S120, performing preset processing on the collected vehicle control information, driving habit information and road information to obtain a first variable mathematical model, a second variable mathematical model and a third variable mathematical model respectively.

[0045] Specifically, the collected vehicle control information, driving habit information and road information are semantically segmented and transformed, and then respectively processed by preset methods to obtain a first variable mathematical model, a second variable mathematical model and a third variable mathematical model.

[0046] In a specific implementation, the collected vehicle control information is processed by a preset process to obtain a first variable mathematical model, including the following steps:

[0047] (1) Discretizing the collected vehicle control information using a preset discrete algorithm.

[0048] In a specific implementation, the collected vehicle control information is discretized using the equal width method. Specifically, each item of the vehicle control information is quantized; for each quantized item of information, the continuous value range is divided into two or more intervals, and then the width of the interval is automatically calculated according to the value range and the number of intervals to obtain the interval range of each interval, and the data of each item of information is grouped according to the interval range of the two or more data intervals, and the data falling into each interval is discretized, and each data is represented by the discretized interval representative value, and the interval representative value can be, for example, a level divided according to a preset rule, such as a level divided according to the remaining power.

[0049] (2) Constructing a first variable mathematical model based on the vehicle control information obtained after discretization processing.

[0050] In a specific implementation, the vehicle speed control information, the battery health information, and the remaining power information are combined with the pre-acquired empirical data to construct a data model. For example, the influence of the vehicle speed control information, the battery health information, and the remaining power information on the energy feedback information (e.g., gain effect or loss effect) is integrated into the constructed mathematical model. If there is a gain effect, this information is used as a gain in the model, and if there is a loss effect, this information is used as a loss in the model.

[0051] The constructed mathematical model is, for example, D=Ax+By+Cz, where x, y and z represent vehicle speed control information, battery health information and remaining power information respectively, A, B and C are corresponding coefficients, and D can represent the vehicle's cruising range. Within the parameters of this model, the larger the three are, the farther the vehicle can run. Therefore, in this model, the larger the final value of D is, the better.

[0052] In a specific implementation, the collected driving habit information is processed by a preset process to obtain a second variable mathematical model, including the following steps:

[0053] (1) The collected driving state information and the vehicle power consumption information are associated according to a corresponding relationship to form two or more sets of driving associated information.

[0054] Specifically, different driving state information is associated with corresponding vehicle power consumption information to form driving association information of different driving states and their corresponding vehicle power consumption information. The driving association information is association information of driving state information and vehicle power consumption information.

[0055] (2) performing clustering processing on each group of the driving-related information to obtain two or more categories.

[0056] Specifically, the formed driving association information is clustered using a clustering algorithm according to the driving state information and the vehicle power consumption information, and is divided into two or more categories. For example, the driving relationship information is clustered using a K-means clustering algorithm to obtain two or more categories. The K-means clustering algorithm is an unsupervised learning method that divides the data points in a data set into K categories so that the data points in each category are as similar as possible, while the data points between different categories are as different as possible.

[0057] The K-means algorithm continuously optimizes the cluster centers through an iterative process, minimizing the sum of the squared distances from each data point to its nearest cluster center. Specifically, the algorithm is implemented through the following steps: Initialize cluster centers: Select K initial cluster centers. Assign data points: Assign each data point to the category to which the nearest cluster center belongs. Update cluster centers: Calculate a new cluster center for each category, which is the average of all data points in that category. Repeat iterations: Repeat the above steps of assigning data points and updating cluster centers until the cluster center no longer changes or the maximum number of iterations is reached.

[0058] (3) converting the two or more classifications into two or more data levels according to the vehicle power consumption information, thereby assigning a corresponding data level to each set of the driving-related information formed, and constructing a second variable mathematical model;

[0059] Specifically, the data level of each of the two or more classifications can be converted according to the vehicle power consumption information (power consumption), so that the corresponding driving-related information is assigned a corresponding data level according to the classification to which each group of driving-related information belongs. For example, after the classification is completed, the two or more classifications are converted into two or more data levels according to the power consumption, wherein the smaller the power consumption, the higher the corresponding data level. According to the data level of each group of driving-related information, different information entropy is assigned to each group of driving-related information, so as to construct a second variable mathematical model.

[0060] In a specific implementation, the collected road information is processed by a preset process to obtain a third variable mathematical model, including the following steps:

[0061] The collected road information is clustered to obtain two or more classifications. For example, the road information includes at least one of the charging station location information, the road traffic information and the destination location information. Clustering is performed according to the road traffic volume to obtain two or more classifications, and then a mathematical model of the vehicle's full vehicle range is constructed based on the two or more classifications, that is, the third variable mathematical model. The charging station location and the destination location are synthesized according to preset rules as a parameter of the third variable mathematical model, and the road traffic information is used as a parameter of the third variable mathematical model.

[0062] Specifically, a clustering algorithm is used to classify the charging station location information, road traffic information and destination location information, thereby forming a mathematical model of G=Mp+Nq. Among them, the charging station location information and the destination location information are combined into a parameter p. The larger the value of the parameter p, the longer the vehicle's cruising range. For example, the charging station location information and the destination location information are weighted according to their respective corresponding preset weights to obtain the weighted parameter p, that is, p=aP1+bP2, P1 and P2 are the charging station location information and the destination location information respectively; a and b are the weights corresponding to the charging station location information and the destination location information respectively. q represents the road traffic flow information, which is divided into different levels according to the size of the traffic flow, and is arranged in reverse or forward order according to the level according to demand. M and N are the coefficients corresponding to p and q respectively, and G represents the vehicle's cruising range.

[0063] Figure 3 The figure shows a schematic diagram of the process of processing the collected data. Figure 3 As shown, the collected data is first classified into vehicle control information, driving habit information and road information, and then semantic information conversion is performed, and the optimal mathematical model is constructed through cluster analysis or discrete processing.

[0064] Step S130, establishing an energy recovery strategy mathematical model based on the first variable mathematical model, the second variable mathematical model and the third variable mathematical model obtained after the preset processing.

[0065] The first variable mathematical model, the second variable mathematical model and the third variable mathematical model obtained above are used as variables x1, x2 and x3 of the energy recovery strategy mathematical model y=f(x1, x2, x3) to establish the energy recovery strategy mathematical model. x1, x2 and x3 respectively represent the influence of three sets of information, namely vehicle control information, driving habit information and road information, on the optimal energy recovery strategy. The definition domains of the three sets of information are determined by historical expert experience values.

[0066] In a specific implementation, the energy recovery strategy mathematical model y=f(x1, x2, x3)=aX1+bX2+cX3, where f(x) is a function of constructing a mathematical model using empirical data, and a, b, and c are weighted coefficients of the first variable mathematical model, the second variable mathematical model, and the third variable mathematical model, respectively, which can be calibrated in advance through testing. For example, based on the various performances of the energy recovery strategy in the vehicle test, the data calibrated through multiple tests can dynamically adjust these parameters according to the vehicle requirements.

[0067] Step S140, optimizing and solving the established mathematical model of the energy recovery strategy by using an optimization algorithm to obtain a predicted optimal energy recovery strategy for the electric vehicle.

[0068] The predicted optimal energy recovery strategy is the predicted optimal energy recovery strategy that currently achieves the longest cruising range and energy. In a specific embodiment, the established mathematical model of the energy recovery strategy is optimized and solved by a particle swarm algorithm to obtain the predicted optimal energy recovery strategy for the electric vehicle. Specifically, the optimal Y value of the mathematical model of the energy recovery strategy is optimized and solved by a particle swarm algorithm. The Y value is the optimal energy recovery strategy. The optimal solution of the mathematical model of the energy recovery strategy, that is, the optimal Y value, is obtained by solving the mathematical model. The energy recovery strategy corresponding to the optimal solution is the optimal energy recovery strategy. For example, different Y value ranges correspond to different energy recovery strategies. The optimal energy recovery strategy can be determined based on the range of the optimal Y value solved.

[0069] The particle swarm algorithm process is as follows:

[0070] (1) Assuming a population size, randomly initialize the speed and position of each solution in the search space;

[0071] (2) Calculate the value of the fitness function and obtain the historical optimal position of all particles in the population and the global optimal position of the population;

[0072] (3) Determine whether the global optimal position meets the set end conditions. For example, if the optimal position meets the conditions of optimal battery, optimal power, longest distance, fastest speed, good driving experience and fastest charging position, then the optimal solution process of the algorithm is terminated. This position is the demand value of the optimal energy recovery strategy.

[0073] (4) If it is determined that the global optimal position does not meet the set end condition, the optimal value is further sought, that is, the speed and position of each particle are updated so that each particle iterates the latest speed and position of each particle according to the historical optimal energy recovery strategy and the global optimal energy recovery strategy; in this update, some out-of-bounds particles need to be adjusted, such as the reverse energy recovery strategy, excessive feedback current, strategy that violates the braking demand, etc., which do not conform to the historical experience value and need data adjustment;

[0074] (5) After the iterative update is completed, the fitness function values ​​of all particles are evaluated to obtain a new optimal energy recovery strategy;

[0075] (6) updating the optimal energy recovery strategy of the particle history;

[0076] (7) Update the global optimal energy recovery strategy of the group; then determine whether the global optimal energy recovery strategy meets the set end condition. If so, end the iteration; otherwise, repeat the above iterative steps (3) to (7) until the optimal energy recovery strategy is found.

[0077] Figure 4 The particle swarm algorithm process is shown. The above particle swarm algorithm can be combined with Figure 4 To understand.

[0078] Step S150: controlling the electric vehicle according to the obtained predicted optimal energy recovery strategy.

[0079] Specifically, the obtained optimal energy recovery strategy is fed back to the VCU controller of the electric vehicle to complete the optimal energy recovery strategy control of the entire vehicle, thereby improving the driving experience and increasing the cruising range and driving safety of the entire vehicle.

[0080] The optimal energy recovery strategy is to reasonably distribute the braking force of the front and rear axles while ensuring safe and smooth braking of the vehicle, with the maximum energy recovery rate as the goal, so that more braking force on the drive shaft is distributed to motor braking, so as to achieve perfect coordination between friction braking and motor braking, ensure safety and maximize energy utilization, and achieve stability and durability of the vehicle's operating endurance.

[0081] The energy recovery strategy includes: a first energy recovery strategy, a second energy recovery strategy and a third energy recovery strategy.

[0082] The first energy recovery strategy, i.e., the ideal braking force distribution control strategy, controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the magnitude of the braking force and / or whether it is an emergency braking. If the braking force is greater than a preset threshold, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if the braking force is less than or equal to the preset threshold and it is an emergency braking, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if the braking force is less than or equal to the preset threshold and it is not an emergency braking, the electric vehicle is controlled to perform motor regenerative braking.

[0083] Figure 5a The first energy recovery strategy braking force distribution flow chart is shown. Figure 5a As shown, the brake pedal opening is collected to determine the braking force. If the braking force is greater than the preset threshold, the vehicle controller VCU sends a motor regenerative braking and mechanical braking combined signal for braking; if the braking force is less than or equal to the preset threshold, it is further determined whether it is an emergency braking signal. If it is an emergency braking signal, that is, an emergency brake is encountered, the vehicle controller VCU sends a motor regenerative braking and mechanical braking combined signal for braking. If it is not an emergency braking signal, the vehicle controller VCU sends a motor regenerative braking signal for braking.

[0084] When the vehicle is lightly braked, it does not require too much braking force, and only the regenerative braking of the front axle can meet the braking requirements; if an emergency braking situation occurs, the braking intensity increases, and the motor braking alone can no longer meet the braking requirements. Friction braking force needs to be added, and the braking is coordinated with each other. In this case, if the braking force allocated to the front axle can be fully borne by the motor, then the electric brake force is fully involved. If the electric brake force does not meet the above requirements, mechanical braking force is required to provide the remaining braking force required by the front axle. The ideal braking force distribution control strategy can reduce the braking distance of the car and can recover the braking energy to a large extent.

[0085] The second energy recovery strategy, i.e., the maximum braking force distribution control strategy, controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to whether it is emergency braking. If it is emergency braking, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if it is not emergency braking, the electric vehicle is controlled to perform motor regenerative braking.

[0086] Figure 5b The second energy recovery strategy braking force distribution flow chart is shown. Figure 5bAs shown, it is determined whether it is an emergency braking signal. If it is determined to be an emergency braking signal, that is, an emergency brake is encountered, the vehicle controller VCU sends a motor regenerative braking and mechanical braking combined signal for braking. If it is not determined to be an emergency braking signal, the vehicle controller VCU sends a motor regenerative braking signal for braking. The maximum braking capacity allocation strategy is to use the motor braking method as much as possible when the wheel is not locked, so as to maximize the feedback energy.

[0087] The third energy recovery strategy, i.e., the parallel braking control strategy, controls the front and rear wheels of the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the motor temperature and state. If the motor temperature exceeds a preset temperature threshold or the motor is on the verge of failure, the front and rear wheels of the vehicle are controlled to perform mechanical braking; if the motor temperature does not exceed the preset temperature threshold and the motor is not on the verge of failure, the front wheels of the vehicle are controlled to perform a combination of motor regenerative braking and mechanical braking, and the rear wheels of the vehicle are controlled to perform mechanical braking.

[0088] Figure 5c The third energy recovery strategy braking force distribution flow chart is shown. Figure 5c As shown, the motor temperature and state are judged. When receiving the status information of motor overheating or imminent failure, the vehicle controller VCU sends the front and rear wheel mechanical brake signals for braking; if the motor overheating and imminent failure status information is not received, the vehicle controller VCU sends the front wheel motor regenerative braking and mechanical braking combined signal, and the rear wheel mechanical braking signal for braking. That is, when receiving the status information of motor overheating or imminent failure, the VCU will control the vehicle control to provide energy recovery by mechanical braking, and the motor's braking energy recovery is used as an auxiliary control demand.

[0089] Regenerative braking and mechanical braking are used together on the front axle, while friction braking is used entirely on the rear axle. Parallel braking is only assisted by motor braking, and the main braking force is still provided by friction braking. This braking method is suitable for when the vehicle motor is overheated or on the verge of failure.

[0090] In order to clearly illustrate the technical solution of the present invention, the execution process of the electric vehicle energy recovery method provided by the present invention is described below with reference to a specific embodiment.

[0091] Figure 6 FIG. 1 is a schematic diagram of a specific embodiment of the electric vehicle energy recovery method provided by the present invention. Figure 6As shown in the figure, firstly, the vehicle speed, remaining power, battery health status, power consumption status and driving status are collected through sensors in various parts of the vehicle, and then the charging station, road traffic and destination information are obtained according to the vehicle navigation. The collected data is classified or discretized, and then a mathematical model for calculating the optimal energy recovery strategy is constructed. The mathematical model is optimized by the particle swarm algorithm to obtain the optimal energy recovery strategy, and the obtained optimal energy recovery strategy is fed back to the VCU for the logic control of the whole vehicle, thereby improving the driving experience and improving the vehicle's cruising range and driving safety.

[0092] The invention provides an energy recovery control device for an electric vehicle.

[0093] Figure 7 FIG. 1 is a structural block diagram of an embodiment of an electric vehicle energy recovery control device provided by the present invention. Figure 7 As shown, the electric vehicle energy recovery device 100 includes: a collection unit 110 , a processing unit 120 , a creation unit 130 , a solution unit 140 and a control unit 150 .

[0094] The collecting unit 110 is used to collect vehicle control information, driving habit information and road information of the vehicle.

[0095] Specifically, the vehicle speed, remaining power, battery health status, power consumption status, driving status, road traffic flow, destination and charging station location information are collected, and the collected data information is divided into vehicle control information, driving habit information and road information, wherein the vehicle control information includes at least one of battery health information, vehicle speed control information and remaining power information; the driving habit information includes at least one of driving status information and vehicle power consumption information; the road information includes at least one of charging station location information, road traffic flow information and destination location information. Figure 2 The classification diagram of the collected data information is shown. The classification of data information can be found in Figure 2 shown.

[0096] The processing unit 120 is used to perform preset processing on the vehicle control information, driving habit information and road information collected by the collection unit to obtain a first variable mathematical model, a second variable mathematical model and a third variable mathematical model respectively.

[0097] Specifically, the collected vehicle control information, driving habit information and road information are semantically segmented and transformed, and then respectively processed by preset methods to obtain a first variable mathematical model, a second variable mathematical model and a third variable mathematical model.

[0098] In a specific implementation, the collected vehicle control information is processed by a preset process to obtain a first variable mathematical model, including the following steps:

[0099] (1) Discretizing the collected vehicle control information using a preset discrete algorithm.

[0100] In a specific implementation, the collected vehicle control information is discretized using the equal width method. Specifically, each item of the vehicle control information is quantized; for each quantized item of information, the continuous value range is divided into two or more intervals, and then the width of the interval is automatically calculated according to the data range and the number of intervals to obtain the interval range of each interval, and the data of each item of information is grouped according to the interval range of the two or more data intervals, and the data falling into each interval is discretized, and each data is represented by the discretized interval representative value, and the interval representative value can be, for example, a level divided according to a preset rule, such as a level divided according to the remaining power.

[0101] (2) Constructing a first variable mathematical model based on the vehicle control information obtained after discretization processing.

[0102] In a specific implementation, the vehicle speed control information, the battery health information, and the remaining power information are combined with the pre-acquired empirical data to construct a data model. For example, the influence of the vehicle speed control information, the battery health information, and the remaining power information on the energy feedback information (e.g., gain effect or loss effect) is integrated into the constructed mathematical model. If there is a gain effect, this information is used as a gain in the model, and if there is a loss effect, this information is used as a loss in the model.

[0103] The constructed mathematical model is, for example, D=Ax+By+Cz, where x, y and z represent vehicle speed control information, battery health information and remaining power information respectively, A, B and C are corresponding coefficients, and D can represent the vehicle's cruising range. Within the parameters of this model, the larger the three are, the farther the vehicle can run. Therefore, in this model, the larger the final value of D is, the better.

[0104] In a specific implementation, the collected driving habit information is processed by a preset process to obtain a second variable mathematical model, including the following steps:

[0105] (1) The collected driving state information and the vehicle power consumption information are associated according to a corresponding relationship to form two or more sets of driving associated information.

[0106] Specifically, different driving state information is associated with corresponding vehicle power consumption information to form driving association information of different driving states and their corresponding vehicle power consumption information. The driving association information is association information of driving state information and vehicle power consumption information.

[0107] (2) performing clustering processing on each group of the driving-related information to obtain two or more categories.

[0108] Specifically, the formed driving association information is clustered using a clustering algorithm according to the driving state information and the vehicle power consumption information, and is divided into two or more categories. For example, the driving relationship information is clustered using a K-means clustering algorithm to obtain two or more categories. The K-means clustering algorithm is an unsupervised learning method that divides the data points in a data set into K categories so that the data points in each category are as similar as possible, while the data points between different categories are as different as possible.

[0109] The K-means algorithm continuously optimizes the cluster centers through an iterative process, minimizing the sum of the squared distances from each data point to its nearest cluster center. Specifically, the algorithm is implemented through the following steps: Initialize cluster centers: Select K initial cluster centers. Assign data points: Assign each data point to the category to which the nearest cluster center belongs. Update cluster centers: Calculate a new cluster center for each category, which is the average of all data points in that category. Repeat iterations: Repeat the above steps of assigning data points and updating cluster centers until the cluster center no longer changes or the maximum number of iterations is reached.

[0110] (3) converting the two or more classifications into two or more data levels according to the vehicle power consumption information, thereby assigning a corresponding data level to each set of the driving-related information formed, and constructing a second variable mathematical model;

[0111] Specifically, the data level of each of the two or more classifications can be converted according to the vehicle power consumption information (power consumption), so that the corresponding driving-related information is assigned a corresponding data level according to the classification to which each group of driving-related information belongs. For example, after the classification is completed, the two or more classifications are converted into two or more data levels according to the power consumption, wherein the smaller the power consumption, the higher the corresponding data level. According to the data level of each group of driving-related information, different information entropy is assigned to each group of driving-related information, so as to construct a second variable mathematical model.

[0112] In a specific implementation, the collected road information is processed by a preset process to obtain a third variable mathematical model, including the following steps:

[0113] The collected road information is clustered to obtain two or more classifications. For example, the road information includes at least one of the charging station location information, the road traffic information, and the destination location information. Clustering is performed according to the road traffic volume to obtain two or more classifications, and then a mathematical model of the vehicle's full vehicle range is constructed based on the two or more classifications, that is, the third variable mathematical model; wherein the charging station location and the destination location are synthesized according to a preset rule as a parameter of the third variable mathematical model, and the road traffic information is used as a parameter of the third variable mathematical model.

[0114] Specifically, a clustering algorithm is used to classify the charging station location information, road traffic information and destination location information, thereby forming a mathematical model of G=Mp+Nq. Among them, the charging station location information and the destination location information are combined into a parameter p. The larger the value of the parameter p, the longer the vehicle's cruising range. For example, the charging station location information and the destination location information are weighted according to their respective corresponding preset weights to obtain the weighted parameter p, that is, p=aP1+bP2, P1 and P2 are the charging station location information and the destination location information respectively; a and b are the weights corresponding to the charging station location information and the destination location information respectively. q represents the road traffic flow information, which is divided into different levels according to the size of the traffic flow, and is arranged in reverse or forward order according to the level according to demand. M and N are the coefficients corresponding to p and q respectively, and G represents the vehicle's cruising range.

[0115] Figure 3 The figure shows a schematic diagram of the process of processing the collected data. Figure 3 As shown, the collected data is first classified into vehicle control information, driving habit information and road information, and then semantic information conversion is performed, and the optimal mathematical model is constructed through cluster analysis or discrete processing.

[0116] The establishing unit 130 is used to establish an energy recovery strategy mathematical model based on the first variable mathematical model, the second variable mathematical model and the third variable mathematical model obtained after the preset processing.

[0117] The first variable mathematical model, the second variable mathematical model and the third variable mathematical model obtained above are used as variables x1, x2 and x3 of the energy recovery strategy mathematical model y=f(x1, x2, x3) to establish the energy recovery strategy mathematical model. x1, x2 and x3 respectively represent the influence of the three groups of information, namely, vehicle control information, driving habit information and road information, on the optimal energy recovery strategy, and the definition domains of the three groups of information are determined by historical expert experience values.

[0118] In a specific implementation, the energy recovery strategy mathematical model y=f(x1, x2, x3)=aX1+bX2+cX3, where f(x) is a function of constructing a mathematical model using empirical data, and a, b, and c are weighted coefficients of the first variable mathematical model, the second variable mathematical model, and the third variable mathematical model, respectively, which can be calibrated in advance through testing. For example, based on the various performances of the energy recovery strategy in the vehicle test, the data calibrated through multiple tests can dynamically adjust these parameters according to the vehicle requirements.

[0119] The solving unit 140 is used to optimize and solve the established energy recovery strategy mathematical model through an optimization algorithm to obtain a predicted optimal energy recovery strategy for the electric vehicle.

[0120] The predicted optimal energy recovery strategy is the predicted optimal energy recovery strategy that currently achieves the longest cruising range and energy. In a specific embodiment, the established mathematical model of the energy recovery strategy is optimized and solved by a particle swarm algorithm to obtain the predicted optimal energy recovery strategy for the electric vehicle. Specifically, the optimal Y value of the mathematical model of the energy recovery strategy is optimized and solved by a particle swarm algorithm. The Y value is the optimal energy recovery strategy. The optimal solution of the mathematical model of the energy recovery strategy, that is, the optimal Y value, is obtained by solving the mathematical model. The energy recovery strategy corresponding to the optimal solution is the optimal energy recovery strategy. For example, different Y value ranges correspond to different energy recovery strategies. The optimal energy recovery strategy can be determined based on the range of the optimal Y value solved.

[0121] The particle swarm algorithm process is as follows:

[0122] (1) Assuming a population size, randomly initialize the speed and position of each solution in the search space;

[0123] (2) Calculate the value of the fitness function and obtain the historical optimal position of all particles in the population and the global optimal position of the population;

[0124] (3) Determine whether the global optimal position meets the set end conditions. For example, if the optimal position meets the conditions of optimal battery, optimal power, longest distance, fastest speed, good driving experience and fastest charging position, then the optimal solution process of the algorithm is terminated. This position is the demand value of the optimal energy recovery strategy.

[0125] (4) If it is determined that the global optimal position does not meet the set end condition, the optimal value is further sought, that is, the speed and position of each particle are updated so that each particle iterates the latest speed and position of each particle according to the historical optimal energy recovery strategy and the global optimal energy recovery strategy; in this update, some out-of-bounds particles need to be adjusted, such as the reverse energy recovery strategy, excessive feedback current, strategy that violates the braking demand, etc., which do not conform to the historical experience value and need data adjustment;

[0126] (5) After the iterative update is completed, the fitness function values ​​of all particles are evaluated to obtain a new optimal energy recovery strategy;

[0127] (6) updating the optimal energy recovery strategy of the particle history;

[0128] (7) Update the global optimal energy recovery strategy of the group; then determine whether the global optimal energy recovery strategy meets the set end condition. If so, end the iteration; otherwise, repeat the above iterative steps (3) to (7) until the optimal energy recovery strategy is found.

[0129] Figure 4 The particle swarm algorithm process is shown. The above particle swarm algorithm can be combined with Figure 4 To understand.

[0130] The control unit 150 is used to control the electric vehicle according to the obtained predicted optimal energy recovery strategy.

[0131] Specifically, the obtained optimal energy recovery strategy is fed back to the VCU controller of the electric vehicle to complete the optimal energy recovery strategy control of the entire vehicle, thereby improving the driving experience and increasing the cruising range and driving safety of the entire vehicle.

[0132] The optimal energy recovery strategy is to reasonably distribute the braking force of the front and rear axles while ensuring safe and smooth braking of the vehicle, with the maximum energy recovery rate as the goal, so that more braking force on the drive shaft is distributed to motor braking, so as to achieve perfect coordination between friction braking and motor braking, ensure safety and maximize energy utilization, and achieve stability and durability of the vehicle's operating endurance.

[0133] The energy recovery strategy includes: a first energy recovery strategy, a second energy recovery strategy and a third energy recovery strategy.

[0134] The first energy recovery strategy, i.e., the ideal braking force distribution control strategy, controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the magnitude of the braking force and / or whether it is an emergency braking. If the braking force is greater than a preset threshold, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if the braking force is less than or equal to the preset threshold and it is an emergency braking, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if the braking force is less than or equal to the preset threshold and it is not an emergency braking, the electric vehicle is controlled to perform motor regenerative braking.

[0135] Figure 5a The first energy recovery strategy braking force distribution flow chart is shown. Figure 5a As shown, the brake pedal opening is collected to determine the braking force. If the braking force is greater than the preset threshold, the vehicle controller VCU sends a motor regenerative braking and mechanical braking combined signal for braking; if the braking force is less than or equal to the preset threshold, it is further determined whether it is an emergency braking signal. If it is an emergency braking signal, that is, an emergency brake is encountered, the vehicle controller VCU sends a motor regenerative braking and mechanical braking combined signal for braking. If it is not an emergency braking signal, the vehicle controller VCU sends a motor regenerative braking signal for braking.

[0136] When the vehicle is lightly braked, it does not require too much braking force, and only the regenerative braking of the front axle can meet the braking requirements; if an emergency braking situation occurs, the braking intensity increases, and the motor braking alone can no longer meet the braking requirements. Friction braking force needs to be added, and the braking is coordinated with each other. In this case, if the braking force allocated to the front axle can be fully borne by the motor, then the electric brake force is fully involved. If the electric brake force does not meet the above requirements, mechanical braking force is required to provide the remaining braking force required by the front axle. The ideal braking force distribution control strategy can reduce the braking distance of the car and can recover the braking energy to a large extent.

[0137] The second energy recovery strategy, i.e., the maximum braking force distribution control strategy, controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to whether it is emergency braking. If it is emergency braking, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if it is not emergency braking, the electric vehicle is controlled to perform motor regenerative braking.

[0138] Figure 5b The second energy recovery strategy braking force distribution flow chart is shown. Figure 5bAs shown, it is determined whether it is an emergency braking signal. If it is determined to be an emergency braking signal, that is, an emergency brake is encountered, the vehicle controller VCU sends a motor regenerative braking and mechanical braking combined signal for braking. If it is not determined to be an emergency braking signal, the vehicle controller VCU sends a motor regenerative braking signal for braking. The maximum braking capacity allocation strategy is to use the motor braking method as much as possible when the wheel is not locked, so as to maximize the feedback energy.

[0139] The third energy recovery strategy, i.e., the parallel braking control strategy, controls the front and rear wheels of the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the motor temperature and state. If the motor temperature exceeds a preset temperature threshold or the motor is on the verge of failure, the front and rear wheels of the vehicle are controlled to perform mechanical braking; if the motor temperature does not exceed the preset temperature threshold and the motor is not on the verge of failure, the front wheels of the vehicle are controlled to perform a combination of motor regenerative braking and mechanical braking, and the rear wheels of the vehicle are controlled to perform mechanical braking.

[0140] Figure 5c The third energy recovery strategy braking force distribution flow chart is shown. Figure 5c As shown, the motor temperature and state are judged. When receiving the status information of motor overheating or imminent failure, the vehicle controller VCU sends the front and rear wheel mechanical brake signals for braking; if the motor overheating and imminent failure status information is not received, the vehicle controller VCU sends the front wheel motor regenerative braking and mechanical braking combined signal, and the rear wheel mechanical braking signal for braking. That is, when receiving the status information of motor overheating or imminent failure, the VCU will control the vehicle control to provide energy recovery by mechanical braking, and the motor's braking energy recovery is used as an auxiliary control demand.

[0141] Regenerative braking and mechanical braking are used together on the front axle, while friction braking is used entirely on the rear axle. Parallel braking is only assisted by motor braking, and the main braking force is still provided by friction braking. This braking method is suitable for when the vehicle motor is overheated or on the verge of failure.

[0142] In order to clearly illustrate the technical solution of the present invention, the execution process of the electric vehicle energy recovery method provided by the present invention is described below with reference to a specific embodiment.

[0143] Figure 6 FIG. 1 is a schematic diagram of a specific embodiment of the electric vehicle energy recovery method provided by the present invention. Figure 6As shown in the figure, firstly, the vehicle speed, remaining power, battery health status, power consumption status and driving status are collected through sensors in various parts of the vehicle, and then the charging station, road traffic and destination information are obtained according to the vehicle navigation. The collected data is classified or discretized, and then a mathematical model for calculating the optimal energy recovery strategy is constructed. The mathematical model is optimized by the particle swarm algorithm to obtain the optimal energy recovery strategy, and the obtained optimal energy recovery strategy is fed back to the VCU for the logic control of the whole vehicle, thereby improving the driving experience and improving the vehicle's cruising range and driving safety.

[0144] The present invention also provides a storage medium corresponding to the electric vehicle energy recovery method, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the aforementioned methods are implemented.

[0145] The present invention also provides an electric vehicle controller corresponding to the electric vehicle energy recovery method, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the aforementioned methods when executing the computer program.

[0146] The present invention also provides an electric vehicle controller corresponding to the electric vehicle energy recovery device, comprising any of the electric vehicle energy recovery devices described above.

[0147] The present invention also provides a computer program product corresponding to the electric vehicle controller method, comprising a computer program, and when the computer program is executed by a processor, the steps of any of the aforementioned methods are implemented.

[0148] Accordingly, the solution provided by the present invention uniformly controls and processes the information of the control system, battery system and road system during vehicle driving, and solves the current optimal energy recovery strategy based on the driver's driving habits and the location information of the charging station, optimizes the battery life, improves the vehicle's range, and eliminates the mileage anxiety of electric vehicle driving. In addition, the driving information of the whole vehicle and the road information are combined and connected with each other, which can not only avoid the vehicle from breaking down due to low power, but also reduce the frequency of the driver adjusting the energy recovery level according to the power, improve driving safety, and enhance the safety and robustness of the control system operation.

[0149] According to the technical solution of the present invention, the vehicle speed, remaining power, battery health status, power consumption status and driving status information are combined with road traffic and charging station location information for discretization processing, and the vehicle's optimal energy recovery strategy is determined by a multi-objective particle swarm algorithm to optimize the battery life, achieve stability and durability of the vehicle's operating endurance, improve the reliability, convenience and comfort of vehicle driving, ensure the overall safety of vehicle driving, and improve the power and economy of the vehicle.

[0150] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on a computer-readable medium or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present invention and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hard wiring, or a combination of any of these. In addition, each functional unit may be integrated into a processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit.

[0151] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0152] The units described as separate components may or may not be physically separated, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed in multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0153] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0154] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the claims of the present invention.

Claims

1. An electric vehicle energy recovery method, characterized in that: include: collecting vehicle control information, driving habit information and road information of the vehicle; Preset processing is performed on the collected vehicle control information, driving habit information and road information to obtain a first variable mathematical model, a second variable mathematical model and a third variable mathematical model respectively; Establishing an energy recovery strategy mathematical model based on the first variable mathematical model, the second variable mathematical model and the third variable mathematical model obtained after performing the preset processing; Optimizing and solving the established mathematical model of the energy recovery strategy through an optimization algorithm to obtain a predicted optimal energy recovery strategy for the electric vehicle; The electric vehicle is controlled according to the obtained predicted optimal energy recovery strategy.

2. The method according to claim 1, characterized in that The collected vehicle control information is processed by a preset method to obtain a first variable mathematical model, including: Using a preset discrete algorithm to discretize the collected vehicle control information; A first variable mathematical model is constructed based on the vehicle control information obtained after discretization processing.

3. The method according to claim 1, characterized in that The driving habit information includes: at least one of driving state information and vehicle power consumption information; the collected driving habit information is processed by preset processing to obtain a second variable mathematical model, including: Associating the collected driving state information and the vehicle power consumption information according to a corresponding relationship to form two or more sets of driving associated information; Performing clustering processing on each group of the driving association information to obtain two or more categories; The two or more classifications are converted into two or more data levels according to the vehicle power consumption information, and a second variable mathematical model is constructed.

4. The method according to claim 1, characterized in that The road information includes at least one of charging station location information, road traffic information and destination location information; the collected road information is processed in a preset manner to obtain a third variable mathematical model, including: Performing clustering processing on the collected road information to obtain two or more classifications, and constructing a third variable mathematical model based on the two or more classifications; The charging station location and the destination location are synthesized according to a preset rule as a parameter of the third variable mathematical model, and the road traffic information is used as a parameter of the third variable mathematical model.

5. The method according to any one of claims 1 to 4, characterized in that: The energy recovery strategy mathematical model established is optimized and solved by an optimization algorithm to obtain the predicted optimal energy recovery strategy of the electric vehicle, including: The established mathematical model of the energy recovery strategy is optimized and solved by a particle swarm algorithm to obtain the predicted optimal energy recovery strategy of the electric vehicle.

6. The method according to any one of claims 1 to 4, characterized in that: The energy recovery strategy includes: a first energy recovery strategy, a second energy recovery strategy and a third energy recovery strategy; The first energy recovery strategy controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the braking force and / or whether it is emergency braking; and / or, The second energy recovery strategy controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to whether it is emergency braking; and / or, The third energy recovery strategy controls the front and rear wheels of the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the motor temperature and state.

7. The method according to claim 6, characterized in that The first energy recovery strategy controls the vehicle to perform motor regenerative braking and / or mechanical braking according to the braking force and / or whether it is emergency braking, including: If the braking force is greater than a preset threshold, controlling the electric vehicle to perform a combination of motor regenerative braking and mechanical braking; If the braking force is less than or equal to a preset threshold and it is an emergency brake, controlling the electric vehicle to perform a combination of motor regenerative braking and mechanical braking; If the braking force is less than or equal to a preset threshold and it is not emergency braking, controlling the electric vehicle to perform motor regenerative braking; and / or, The second energy recovery strategy controls the electric vehicle to perform motor regenerative braking and / or mechanical braking according to whether it is emergency braking, including: If it is an emergency braking, the electric vehicle is controlled to perform a combination of motor regenerative braking and mechanical braking; if it is not an emergency braking, the electric vehicle is controlled to perform motor regenerative braking; and / or, The third energy recovery strategy controls the front and rear wheels of the electric vehicle to perform motor regenerative braking and / or mechanical braking according to the motor temperature and state, including: If the motor temperature exceeds a preset temperature threshold or the motor is on the verge of failure, the front and rear wheels of the vehicle are controlled to perform mechanical braking; If the motor temperature does not exceed the preset temperature threshold and the motor is not on the verge of failure, the front wheels of the vehicle are controlled to perform a combination of motor regenerative braking and mechanical braking, and the rear wheels of the vehicle are controlled to perform mechanical braking.

8. An electric vehicle energy recovery control device, characterized in that: include: A collection unit, used to collect vehicle control information, driving habit information and road information of the vehicle; a processing unit, configured to perform preset processing on the vehicle control information, driving habit information and road information collected by the collecting unit, and obtain a first variable mathematical model, a second variable mathematical model and a third variable mathematical model respectively; An establishing unit, configured to establish an energy recovery strategy mathematical model based on the first variable mathematical model, the second variable mathematical model and the third variable mathematical model obtained after performing the preset processing; A solving unit, used for optimizing and solving the established energy recovery strategy mathematical model through an optimization algorithm to obtain a predicted optimal energy recovery strategy for the electric vehicle; A control unit is used to control the electric vehicle according to the obtained predicted optimal energy recovery strategy.

9. A storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the steps of any method described in claims 1-7 are implemented.

10. An electric vehicle controller, characterized in that: It comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any method described in claims 1-7 are implemented, including the electric vehicle energy recovery device described in claim 8.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the steps of any one of the methods of claims 1 to 7 when being executed by a processor.

Images