Dynamic decision control system and method based on vehicle energy consumption optimization

Abstract

The invention relates to the technical field of vehicle engineering, and discloses a dynamic decision control system and method based on vehicle energy consumption optimization, and the method comprises the steps: determining an initial driving strategy based on real-time road surface information and vehicle body state information; the method comprises the following steps: performing simulation prediction based on real-time road surface information and an initial driving strategy to obtain control instability data, motor energy efficiency data and tire slippage data, calculating according to the control instability data to obtain a control instability influence value, calculating according to the motor energy efficiency data to obtain a motor energy efficiency value, calculating according to the tire slippage data to obtain a slippage energy loss value, and calculating according to the slippage energy loss value. And finally, optimizing the initial driving strategy based on the control instability influence value, the motor energy efficiency value, the slip energy loss value and an intelligent optimization algorithm to obtain an optimal driving strategy, so that in the process of optimizing the energy consumption of the vehicle, the reduction of the running stability of the vehicle caused by excessive optimization is avoided, and the safety of the vehicle is improved. And the expected dynamic stability of the vehicle can be kept under complex working conditions.

Description

Technical Field

[0001] The present invention relates to the field of vehicle engineering technology, and more specifically, to a dynamic decision control system based on vehicle energy consumption optimization and a method thereof. Background Art

[0002] Electric vehicles have become an important tool for promoting green development due to their advantages in reducing environmental pollution and alleviating energy crises. However, in the context that the range of electric vehicles is limited by battery capacity, it is particularly important to improve energy utilization efficiency and reduce energy consumption. Distributed four-wheel drive electric vehicles, by virtue of their independent control of each drive motor, can optimize energy consumption and reduce tire slip power loss while ensuring operational stability while meeting the same torque requirements. Therefore, designing a reasonable torque distribution strategy is not only helpful for energy saving, but also of great significance for improving the vehicle's handling stability. However, although the prior art has disclosed many studies related to energy saving, the consideration of vehicle operation stability factors is still relatively insufficient.

[0003] In the prior art, for example, the patent with publication number CN117382641A provides a method, device and medium for optimizing the energy consumption performance of a vehicle. The patent collects the operating status data of the vehicle within a certain period of time and analyzes its distribution characteristics to determine the key data items that affect the energy consumption performance. Based on these data items, it provides driving behavior improvement suggestions or optimized vehicle control strategies to improve energy efficiency. The patent with publication number CN111086501A provides an energy consumption optimization method for a pure electric vehicle. The patent draws an energy consumption contour curve and selects an economic gear curve to clearly divide the economic zone and the dynamic zone, thereby achieving precise matching of the drive motor torque and speed and realizing energy consumption optimization.

[0004] Although the prior art has disclosed many research contents related to energy conservation, the prior art seldom considers that in the process of optimizing the energy consumption of the vehicle, excessive optimization leads to a reduction in the vehicle's operating stability, which results in a decrease in the vehicle's handling performance in actual operation, especially in complex working conditions (such as turning, acceleration or emergency braking), the expected dynamic stability cannot be maintained, thereby increasing safety risks.

[0005] In view of this, the present invention proposes a dynamic decision control system based on vehicle energy consumption optimization and a method thereof to solve the above-mentioned problem. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a dynamic decision control system and method based on vehicle energy consumption optimization.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] In a first aspect, a dynamic decision control method based on vehicle energy consumption optimization is provided, comprising:

[0009] Acquire real-time road surface information and vehicle body status information, determine the initial driving strategy based on the real-time road surface information and vehicle body status information, and perform simulation prediction based on the real-time road surface information and the initial driving strategy to obtain control instability data, motor energy efficiency data, and tire slip data;

[0010] The control instability impact value is calculated based on the control instability data, the motor energy efficiency value is calculated based on the motor energy efficiency data, and the slip energy loss value is calculated based on the tire slip data;

[0011] The initial driving strategy is optimized based on the control instability impact value, motor energy efficiency value, slip energy loss value and intelligent optimization algorithm to obtain the optimal driving strategy.

[0012] Furthermore, the method of simulating and predicting the control instability data, the motor energy efficiency data and the tire slip data based on the real-time road surface information and the initial driving strategy includes:

[0013] Real-time road information and initial driving strategies are input into the pre-built driving prediction model to obtain handling instability data, motor energy efficiency data, and tire slip data.

[0014] The method of building a driving prediction model includes:

[0015] Acquire a sample data set, wherein the sample data set includes historical road surface information, historical initial driving strategy, historical control instability data, historical motor energy efficiency data, and historical tire slip data;

[0016] Divide the sample data set into a sample training set and a sample test set, and build a regression network;

[0017] The historical road surface information and historical initial driving strategies in the sample training set are used as input data of the regression network, and the historical control instability data, historical motor energy efficiency data and historical tire slip data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting control instability data, motor energy efficiency data and tire slip data.

[0018] The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as a driving prediction model.

[0019] Furthermore, the control instability data includes an actual center of mass sideslip angle and an actual yaw rate. The method for calculating the control instability influence value according to the control instability data includes: ;

[0020] In the formula, is the control instability impact value, is the actual center of mass sideslip angle, is the standard center of mass sideslip angle, is the actual yaw angular velocity, is the standard yaw rate, is the simulation time.

[0021] Furthermore, the motor energy efficiency data includes wheel speed, motor output torque, motor braking torque, motor output efficiency and motor braking efficiency. The method for obtaining the motor output efficiency includes: ;

[0022] In the formula, is the motor output efficiency, is the motor output torque, is the wheel speed, is the motor input voltage, is the motor input current;

[0023] Methods for obtaining motor braking efficiency include: ;

[0024] In the formula, is the motor braking efficiency, is the motor braking torque, Recover voltage for the battery, Recovers current to the battery.

[0025] Furthermore, the method for calculating the motor energy efficiency value according to the motor energy efficiency data includes: ;

[0026] In the formula, is the motor energy efficiency value.

[0027] Furthermore, the tire slip data includes the wheel inertia coefficient, the wheel equivalent radius and the wheel acceleration. The method for calculating the slip energy loss value according to the tire slip data includes: ;

[0028] In the formula, is the slip energy loss value, is the wheel inertia coefficient, is the wheel acceleration, is the equivalent radius of the wheel.

[0029] Furthermore, the intelligent optimization algorithm is a sparrow search algorithm, which optimizes the initial driving strategy and obtains the optimal solution by:

[0030] S301: Randomly generate a group of sparrow individuals, each sparrow individual represents an initial driving strategy, and randomly generate an initial position for each sparrow individual , that is, the initial driving strategy, so that it satisfies: ;

[0031] in, is the control instability impact value corresponding to the initial driving strategy, To control the instability impact threshold;

[0032] S302: Construct the fitness function value of each sparrow individual : ;

[0033] In the formula, is the slip energy loss value corresponding to the initial driving strategy, is the motor energy efficiency value corresponding to the initial driving strategy, , All are weight factors;

[0034] S303: Perform exploration operations on some sparrow individuals and update their target initial driving strategy ; ;

[0035] In the formula, For the A sparrow in The position of the generation, For the A sparrow in The position of the generation, is the maximum number of iterations, is a random angle, It is an exponential function with e as the base, where e is a natural constant;

[0036] S304: Check the updated Is it less than , if not, perform boundary processing;

[0037] S305: Perform a following operation on the remaining sparrow individuals and update their target initial driving strategy ;

[0038] S306: Calculate the fitness function value of each sparrow individual after the update , update the current optimal solution;

[0039] S307: Repeat the above steps S303 to S306 until the preset maximum number of iterations is reached. Stop searching when , and output the initial driving strategy corresponding to the current optimal solution, which is the optimal driving strategy.

[0040] Furthermore, check the updated Is it less than If not, the boundary processing methods include: ;

[0041] In the formula, It refers to the control instability impact value corresponding to the i-th sparrow individual after the t+1 generation update.

[0042] Further, update its target initial driving strategy The methods include: ;

[0043] In the formula, is a random number, is the location of the current optimal solution.

[0044] In a second aspect, a dynamic decision control system based on vehicle energy consumption optimization is provided, which is used to implement the above-mentioned dynamic decision control method based on vehicle energy consumption optimization, including:

[0045] Strategy generation module: used to obtain real-time road information and vehicle body status information, determine the initial driving strategy based on the real-time road information and vehicle body status information, and simulate and predict the control instability data, motor energy efficiency data and tire slip data based on the real-time road information and the initial driving strategy;

[0046] Data processing module: used to calculate the control instability impact value according to the control instability data, calculate the motor energy efficiency value according to the motor energy efficiency data, and calculate the slip energy loss value according to the tire slip data;

[0047] Strategy optimization module: used to optimize the initial driving strategy based on the control instability impact value, motor energy efficiency value, slip energy loss value and intelligent optimization algorithm to obtain the optimal driving strategy.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] The present invention first determines an initial driving strategy based on real-time road surface information and vehicle body status information, performs simulation prediction based on the real-time road surface information and the initial driving strategy to obtain control instability data, motor energy efficiency data and tire slip data, then calculates a control instability influence value according to the control instability data, calculates a motor energy efficiency value according to the motor energy efficiency data, and calculates a slip energy loss value according to the tire slip data, and finally optimizes the initial driving strategy based on the control instability influence value, the motor energy efficiency value, the slip energy loss value and an intelligent optimization algorithm to obtain an optimal driving strategy. In this way, in the process of optimizing the energy consumption of the vehicle, a reduction in the vehicle's operating stability caused by over-optimization is avoided, so that the vehicle can maintain the expected dynamic stability under complex working conditions, thereby improving the reliability and safety of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic flow chart of a dynamic decision-making control method based on vehicle energy consumption optimization in the present invention;

[0051] Figure 2 It is a structural schematic diagram of a dynamic decision control system based on vehicle energy consumption optimization in the present invention;

[0052] Figure 3 The figure is a schematic diagram of the structure of an electronic device in the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0054] Example 1

[0055] See also Figure 1 As shown, this embodiment discloses a dynamic decision control method based on vehicle energy consumption optimization, including:

[0056] S10: acquiring real-time road surface information and vehicle body status information, determining an initial driving strategy based on the real-time road surface information and vehicle body status information, and performing simulation prediction based on the real-time road surface information and the initial driving strategy to obtain control instability data, motor energy efficiency data, and tire slip data;

[0057] In this embodiment, real-time road surface information includes but is not limited to road surface slope, road surface type, lane information, and real-time weather conditions. It can be understood that road surface types include asphalt road surface, concrete road surface, muddy road surface, etc. The road surface type affects the adhesion and slip rate of the tire. Lane information includes lane width, lane dividing line type, road curvature, etc., which are used to judge the driving environment of the vehicle, and real-time weather conditions include wetness, real-time wind direction, and real-time visibility.

[0058] It should be added that the vehicle body status information includes but is not limited to real-time speed, real-time acceleration, vehicle body steering angle and vehicle body posture angle. The real-time acceleration is used to analyze the dynamic stability of the vehicle, the vehicle body steering angle reflects the current steering state of the vehicle, and the vehicle body posture angle reflects the spatial posture of the vehicle during driving.

[0059] The method for determining the initial driving strategy based on real-time road surface information and vehicle body state information includes:

[0060] The real-time road surface information and vehicle body status information are input into the driving strategy generation system to obtain the initial driving strategy.

[0061] It should be noted that the driving strategy generation system can be an existing L2 level driving assistance system, or an L3 and above level autonomous driving system. For example, the L2 level driving assistance system can be a Drive Pilot system or a Super Cruise system, while the L3 and above level autonomous driving system can be Tesla Autopilot or Apollo, etc. The initial driving strategy at least includes: adjusting vehicle speed and acceleration instructions, steering control instructions, power distribution instructions, and energy recovery instructions, etc. The power distribution instruction represents the distribution of target torque and speed of each drive motor for distributed drive vehicles, and the energy recovery instruction represents the determination of the energy recovery strength (recovered torque and power) of the motor during braking.

[0062] The method for obtaining control instability data, motor energy efficiency data and tire slip data by simulation prediction based on real-time road surface information and initial driving strategy includes:

[0063] Real-time road information and initial driving strategies are input into the pre-built driving prediction model to obtain handling instability data, motor energy efficiency data, and tire slip data.

[0064] The method of building a driving prediction model includes:

[0065] Acquire a sample data set, wherein the sample data set includes historical road surface information, historical initial driving strategy, historical control instability data, historical motor energy efficiency data, and historical tire slip data;

[0066] Divide the sample data set into a sample training set and a sample test set, and build a regression network;

[0067] The historical road surface information and historical initial driving strategies in the sample training set are used as input data of the regression network, and the historical control instability data, historical motor energy efficiency data and historical tire slip data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting control instability data, motor energy efficiency data and tire slip data.

[0068] The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as a driving prediction model. The initial regression network is a deep neural network model.

[0069] It can be understood that the above-mentioned sample data sets are based on experiments conducted by technicians in this field and obtained from public databases, and the handling instability data is used as an example for illustration. The handling instability data includes but is not limited to the actual center of mass sideslip angle and the actual yaw rate. The center of mass sideslip angle refers to the angle between the driving direction of the center of mass of the vehicle and the longitudinal axis of the vehicle, which is usually used to describe the side deviation of the vehicle under the action of lateral force (such as turning or crosswind). The yaw rate refers to the angular velocity of the vehicle rotating around the vertical axis of its center of mass, which is usually used to describe the yaw dynamic behavior of the vehicle. For example, when the road type in the road information is a slippery asphalt road, and the real-time weather conditions are medium visibility and light rain, the initial driving strategy may be to suggest deceleration, increase the steering angle, and reduce the driving torque of the outer wheels, etc., then the corresponding center of mass sideslip angle should be reduced after the vehicle is decelerated, and the yaw rate should also be reduced.

[0070] In this embodiment, the initial driving strategy not only takes into account environmental changes (such as wetness and road curvature), but also combines the current dynamic characteristics of the vehicle (such as real-time speed and body steering angle) to improve vehicle handling performance and energy efficiency. Through simulation and prediction, the actual impact of the initial driving strategy (such as handling instability, motor energy efficiency and tire slip data) is further quantified for subsequent optimization.

[0071] S20: calculating a control instability impact value according to the control instability data, calculating a motor energy efficiency value according to the motor energy efficiency data, and calculating a slip energy loss value according to the tire slip data;

[0072] In an optional embodiment, a method for calculating a control instability influence value according to control instability data includes: ;

[0073] In the formula, is the control instability impact value, is the actual center of mass sideslip angle, is the standard center of mass sideslip angle, is the actual yaw angular velocity, is the standard yaw rate, is the simulation time.

[0074] It should be noted that the actual center of mass sideslip angle and actual yaw rate in the above can be obtained in real time through sensors or gyroscopes on the vehicle. is the simulation time. The simulation time represents the time range for the vehicle to simulate the adjustment according to the initial driving strategy. The simulation time is used to analyze the impact of the initial driving strategy on the vehicle stability and energy efficiency within a specific time. Taking the actual center of mass sideslip angle as an example, the more the actual center of mass sideslip angle deviates from the standard center of mass sideslip angle, the greater the deviation of the vehicle's lateral control may be, which may lead to understeer or oversteer. Similarly, the more the actual yaw angular velocity deviates from the standard yaw angular velocity, the more the vehicle's rotation behavior around the center of mass cannot be controlled as expected. Therefore, it can be seen from the above content that in this embodiment, the greater the control instability impact value, the worse the vehicle's control stability is.

[0075] Generally, motor energy efficiency data includes but is not limited to wheel speed, motor output torque, motor braking torque, motor output efficiency and motor braking efficiency. Motor output torque refers to the mechanical torque output by the motor in driving mode, which is used to drive the vehicle wheels. Motor braking torque refers to the reverse torque output in braking or energy recovery mode, which is used to decelerate and convert mechanical energy into electrical energy. Motor output efficiency refers to the efficiency of the motor in converting input electrical energy into mechanical energy in driving mode. Motor braking efficiency refers to the efficiency of converting mechanical energy into electrical energy in braking mode. It can be understood that wheel speed, motor output torque and motor braking torque can all be directly obtained through the vehicle's sensors and control system, while motor output efficiency and motor braking efficiency are calculated. The calculation method is as follows:

[0076] Methods for obtaining motor output efficiency include: ;

[0077] In the formula, is the motor output efficiency, is the motor output torque, is the wheel speed, is the motor input voltage, is the motor input current.

[0078] Methods for obtaining motor braking efficiency include: ;

[0079] In the formula, is the motor braking efficiency, is the motor braking torque, Recover voltage for the battery, Recovers current to the battery.

[0080] Methods for calculating the motor energy efficiency value based on motor energy efficiency data include: ;

[0081] In the formula, is the motor energy efficiency value.

[0082] It should be noted that in the above formula The same is the simulation time, , For example, The larger the value, the higher the motor drive efficiency and the better the energy utilization rate. The larger the value, the higher the energy recovery efficiency of the motor and the stronger the energy recovery capability during braking. Therefore, it can be seen from the above content that in this embodiment, the larger the motor energy efficiency value, the lower the energy consumption of the motor when it is working.

[0083] In this embodiment, the tire slip data includes but is not limited to the wheel inertia coefficient, the wheel equivalent radius and the wheel acceleration. The wheel inertia coefficient refers to the moment of inertia of the wheel when it rotates around its rotation axis. The wheel equivalent radius refers to the equivalent radius of a circle when the wheel's complex geometric characteristics are simplified during the actual rolling process. It can be understood that the wheel inertia coefficient and the wheel equivalent radius are closely related to the physical structure and design parameters of the wheel itself, and the wheel inertia coefficient and the wheel equivalent radius can be stored in a database in advance.

[0084] Methods for calculating the slip energy loss value based on tire slip data include: ;

[0085] In the formula, is the slip energy loss value, is the wheel inertia coefficient, is the wheel acceleration, is the equivalent radius of the wheel.

[0086] It should be added that the slip energy loss value represents the energy loss caused by wheel slip. The slip energy loss value reflects the energy consumption between the tire and the ground during wheel slip, which is usually manifested as reduced efficiency. It can be understood that the larger the slip energy loss value, the higher the energy consumption of the vehicle.

[0087] This embodiment first obtains real-time road surface information and vehicle body status information and generates simulation predictions in combination with the initial driving strategy to obtain handling instability data, motor energy efficiency data and tire slip data. These data provide a complete and reliable basis for subsequent performance calculations. These data are used to calculate the handling instability impact value, motor energy efficiency value and slip energy loss value respectively, which can achieve multi-dimensional quantitative evaluation of the performance of the initial driving strategy, thereby providing a clear basis for the optimization of the initial driving strategy.

[0088] S30: Optimize the initial driving strategy based on the control instability impact value, motor energy efficiency value, slip energy loss value and intelligent optimization algorithm to obtain the optimal driving strategy.

[0089] The intelligent optimization algorithm can be a sparrow search algorithm to optimize the initial driving strategy. The methods for obtaining the optimal solution include:

[0090] S301: Randomly generate a group of sparrow individuals, each sparrow individual represents an initial driving strategy, and randomly generate an initial position for each sparrow individual , that is, the initial driving strategy, so that it satisfies: ;

[0091] in, is the control instability impact value corresponding to the initial driving strategy, To control the instability impact threshold.

[0092] S302: Construct the fitness function value of each sparrow individual : ;

[0093] In the formula, is the slip energy loss value corresponding to the initial driving strategy, is the motor energy efficiency value corresponding to the initial driving strategy, , All are weight factors;

[0094] It should be noted that the initial driving strategy generated by this embodiment takes the slip energy loss value and the motor energy efficiency value as optimization targets, and takes these two items as key constraints. The fitness function is constructed by calculating the difference between the slip energy loss value and the motor energy efficiency value to further quantify the combined impact of the two. This embodiment ensures that all sparrow individuals meet the handling stability requirements by strictly limiting the impact value of handling instability, and effectively avoids vehicle loss of control due to improper driving strategies. On this basis, the fitness function balances and optimizes the slip energy loss and motor energy efficiency, so that the optimal driving strategy finally generated not only has stability and low energy consumption characteristics, but also has high practicality and reliability, thereby significantly improving the overall performance of the vehicle in actual operation.

[0095] S303: Perform exploration operations on some sparrow individuals and update their target initial driving strategy ; ;

[0096] In the formula, For the A sparrow in The position of the generation, For the A sparrow in The position of the generation, is the maximum number of iterations, is a random angle, It is an exponential function with e as base, where e is a natural constant.

[0097] Among them, through exploration operations, some sparrow individuals are moved randomly to better cover the solution space, find potential optimal solutions, increase the diversity of solutions, prevent sparrow individuals from falling into local optimality, and provide more solution paths for the group.

[0098] S304: Check the updated Is it less than , if not, perform boundary processing;

[0099] This embodiment ensures that all sparrow individuals still meet the constraint conditions of the control instability impact value after updating, performs boundary processing on solutions that do not meet the conditions, and ensures that all solutions are within the range of feasible solutions to ensure the effectiveness of subsequent optimization operations.

[0100] S305: Perform a following operation on the remaining sparrow individuals and update their target initial driving strategy ;

[0101] The above-mentioned following operation means that the remaining sparrow individuals will follow the direction of the current optimal solution for update. By continuously following the optimal solution, the follower individuals have the opportunity to gradually approach the optimal solution, thereby improving the overall fitness of the population.

[0102] S306: Calculate the fitness function value of each sparrow individual after the update , update the current optimal solution;

[0103] After updating the target initial driving strategy of the individual sparrow, the fitness of each individual sparrow is recalculated to determine its pros and cons under the new initial driving strategy. Through this operation, the algorithm can evaluate the effect of each update and select the optimal initial driving strategy.

[0104] S307: Repeat the above steps S303 to S306 until the preset maximum number of iterations is reached. Stop searching when , and output the initial driving strategy corresponding to the current optimal solution, which is the optimal driving strategy.

[0105] Check for updated Is it less than If not, the boundary processing methods include: ;

[0106] In the formula, It refers to the control instability impact value corresponding to the i-th sparrow individual after the t+1 generation update.

[0107] It should be added that the above steps are and This ensures that the initial driving strategy that exceeds the preset control instability threshold is forced to be corrected to a feasible range, ensuring that all solutions in the optimization process can be actually applied and avoiding infeasible solutions.

[0108] Update its target initial driving strategy The methods include: ;

[0109] In the formula, is a random number, is the location of the current optimal solution.

[0110] In this embodiment, the above steps indicate that the individual sparrows follow and update based on the current optimal solution. In this way, the individual sparrows will gradually move closer to the optimal solution and converge to a better solution.

[0111] This embodiment first determines an initial driving strategy based on real-time road surface information and vehicle body status information, performs simulation prediction based on the real-time road surface information and the initial driving strategy to obtain control instability data, motor energy efficiency data and tire slip data, then calculates a control instability impact value based on the control instability data, calculates a motor energy efficiency value based on the motor energy efficiency data, and calculates a slip energy loss value based on the tire slip data, and finally optimizes the initial driving strategy based on the control instability impact value, the motor energy efficiency value, the slip energy loss value and the intelligent optimization algorithm to obtain the optimal driving strategy. In this way, in the process of optimizing the vehicle's energy consumption, over-optimization that leads to a reduction in vehicle operating stability is avoided, so that the vehicle can maintain the expected dynamic stability under complex working conditions, thereby improving the reliability and safety of the vehicle.

[0112] Example 2

[0113] See also Figure 2As shown, based on the same inventive concept, this embodiment discloses a dynamic decision control system based on vehicle energy consumption optimization. For details not provided in this embodiment, please refer to the description of the relevant parts in Embodiment 1. The system includes:

[0114] Strategy generation module: used to obtain real-time road information and vehicle body status information, determine the initial driving strategy based on the real-time road information and vehicle body status information, and simulate and predict the control instability data, motor energy efficiency data and tire slip data based on the real-time road information and the initial driving strategy;

[0115] The method for determining the initial driving strategy based on real-time road surface information and vehicle body state information includes:

[0116] The real-time road surface information and vehicle body status information are input into the driving strategy generation system to obtain the initial driving strategy.

[0117] The method for obtaining control instability data, motor energy efficiency data and tire slip data by simulation prediction based on real-time road surface information and initial driving strategy includes:

[0118] Real-time road information and initial driving strategies are input into the pre-built driving prediction model to obtain handling instability data, motor energy efficiency data, and tire slip data.

[0119] The method of building a driving prediction model includes:

[0120] Acquire a sample data set, wherein the sample data set includes historical road surface information, historical initial driving strategy, historical control instability data, historical motor energy efficiency data, and historical tire slip data;

[0121] Divide the sample data set into a sample training set and a sample test set, and build a regression network;

[0122] The historical road surface information and historical initial driving strategies in the sample training set are used as input data of the regression network, and the historical control instability data, historical motor energy efficiency data and historical tire slip data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting the initial driving strategy.

[0123] The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as a driving prediction model. The initial regression network is a deep neural network model.

[0124] Data processing module: used to calculate the control instability impact value according to the control instability data, calculate the motor energy efficiency value according to the motor energy efficiency data, and calculate the slip energy loss value according to the tire slip data;

[0125] In an optional embodiment, a method for calculating a control instability influence value according to control instability data includes: ;

[0126] In the formula, is the control instability impact value, is the actual center of mass sideslip angle, is the standard center of mass sideslip angle, is the actual yaw angular velocity, is the standard yaw rate, is the simulation time.

[0127] Generally, motor energy efficiency data includes but is not limited to wheel speed, motor output torque, motor braking torque, motor output efficiency and motor braking efficiency. Motor output torque refers to the mechanical torque output by the motor in driving mode, which is used to drive the vehicle wheels. Motor braking torque refers to the reverse torque output in braking or energy recovery mode, which is used to decelerate and convert mechanical energy into electrical energy. Motor output efficiency refers to the efficiency of the motor in converting input electrical energy into mechanical energy in driving mode. Motor braking efficiency refers to the efficiency of converting mechanical energy into electrical energy in braking mode. It can be understood that wheel speed, motor output torque and motor braking torque can all be directly obtained through the vehicle's sensors and control system, while motor output efficiency and motor braking efficiency are calculated. The calculation method is as follows:

[0128] Methods for obtaining motor output efficiency include: ;

[0129] In the formula, is the motor output efficiency, is the motor output torque, is the wheel speed, is the motor input voltage, is the motor input current.

[0130] Methods for obtaining motor braking efficiency include: ;

[0131] In the formula, is the motor braking efficiency, is the motor braking torque, Recover voltage for the battery, Recovers current to the battery.

[0132] Methods for calculating the motor energy efficiency value based on motor energy efficiency data include: ;

[0133] In the formula, is the motor energy efficiency value.

[0134] Methods for calculating the slip energy loss value based on tire slip data include: ;

[0135] In the formula, is the slip energy loss value, is the wheel inertia coefficient, is the wheel acceleration, is the equivalent radius of the wheel.

[0136] Strategy optimization module: used to optimize the initial driving strategy based on the control instability impact value, motor energy efficiency value, slip energy loss value and intelligent optimization algorithm to obtain the optimal driving strategy.

[0137] Example 3

[0138] like Figure 3 As shown, this embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a dynamic decision-making control method based on vehicle energy consumption optimization provided by the above methods is implemented.

[0139] Since the electronic device introduced in this embodiment is an electronic device used to implement a dynamic decision-making control method based on vehicle energy consumption optimization in the embodiment of the present application, based on the dynamic decision-making control method based on vehicle energy consumption optimization introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is no longer introduced in detail. As long as technical personnel in this field implement the electronic device used in the dynamic decision-making control method based on vehicle energy consumption optimization in the embodiment of the present application, it belongs to the scope of protection of this application.

[0140] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0141] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0142] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0143] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0144] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0145] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0146] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0147] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0148] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A dynamic decision control method based on vehicle energy consumption optimization, characterized in that: include: Acquire real-time road surface information and vehicle body status information, determine the initial driving strategy based on the real-time road surface information and vehicle body status information, and perform simulation prediction based on the real-time road surface information and the initial driving strategy to obtain control instability data, motor energy efficiency data, and tire slip data; The control instability impact value is calculated based on the control instability data, the motor energy efficiency value is calculated based on the motor energy efficiency data, and the slip energy loss value is calculated based on the tire slip data; The initial driving strategy is optimized based on the control instability impact value, motor energy efficiency value, slip energy loss value and intelligent optimization algorithm to obtain the optimal driving strategy.

2. The dynamic decision control method based on vehicle energy consumption optimization according to claim 1 is characterized in that: The method for obtaining control instability data, motor energy efficiency data and tire slip data by simulation prediction based on real-time road surface information and initial driving strategy includes: Input real-time road information and initial driving strategy into the pre-built driving prediction model to obtain handling instability data, motor energy efficiency data, and tire slip data; The method of building a driving prediction model includes: Acquire a sample data set, wherein the sample data set includes historical road surface information, historical initial driving strategy, historical control instability data, historical motor energy efficiency data, and historical tire slip data; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical road surface information and historical initial driving strategies in the sample training set are used as input data of the regression network, and the historical control instability data, historical motor energy efficiency data and historical tire slip data in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting control instability data, motor energy efficiency data and tire slip data. The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as a driving prediction model.

3. The dynamic decision control method based on vehicle energy consumption optimization according to claim 1 is characterized in that: The control instability data includes an actual center of mass sideslip angle and an actual yaw rate. The method for calculating the control instability influence value according to the control instability data includes: ; In the formula, is the control instability impact value, is the actual center of mass sideslip angle, is the standard center of mass sideslip angle, is the actual yaw angular velocity, is the standard yaw rate, is the simulation time.

4. The dynamic decision control method based on vehicle energy consumption optimization according to claim 1 is characterized in that: The motor energy efficiency data includes wheel speed, motor output torque, motor braking torque, motor output efficiency and motor braking efficiency. The method for obtaining the motor output efficiency includes: ; In the formula, is the motor output efficiency, is the motor output torque, is the wheel speed, is the motor input voltage, is the motor input current; Methods for obtaining motor braking efficiency include: ; In the formula, is the motor braking efficiency, is the motor braking torque, Recover voltage for the battery, Recovers current to the battery.

5. The dynamic decision control method based on vehicle energy consumption optimization according to claim 4 is characterized in that: The method for calculating the motor energy efficiency value according to the motor energy efficiency data includes: ; In the formula, is the motor energy efficiency value.

6. The dynamic decision control method based on vehicle energy consumption optimization according to claim 4 is characterized in that: The tire slip data includes wheel inertia coefficient, wheel equivalent radius and wheel acceleration. The method for calculating the slip energy loss value according to the tire slip data includes: ; In the formula, is the slip energy loss value, is the wheel inertia coefficient, is the wheel acceleration, is the equivalent radius of the wheel.

7. The dynamic decision control method based on vehicle energy consumption optimization according to claim 6 is characterized in that: The intelligent optimization algorithm is a sparrow search algorithm, which optimizes the initial driving strategy and obtains the optimal solution by: S301: Randomly generate a group of sparrow individuals, each sparrow individual represents an initial driving strategy, and randomly generate an initial position for each sparrow individual , that is, the initial driving strategy, so that it satisfies: ; in, is the control instability impact value corresponding to the initial driving strategy, To control the instability impact threshold; S302: Construct the fitness function value of each sparrow individual : ; In the formula, is the slip energy loss value corresponding to the initial driving strategy, is the motor energy efficiency value corresponding to the initial driving strategy, , All are weight factors; S303: Perform exploration operations on some sparrow individuals and update their target initial driving strategy ; ; In the formula, For the A sparrow in the The position of the generation, For the A sparrow in the The position of the generation, is the maximum number of iterations, is a random angle, It is an exponential function with e as the base, where e is a natural constant; S304: Check the updated Is it less than , if not, perform boundary processing; S305: Perform a following operation on the remaining sparrow individuals and update their target initial driving strategy ; S306: Calculate the fitness function value of each sparrow individual after the update , update the current optimal solution; S307: Repeat the above steps S303 to S306 until the preset maximum number of iterations is reached. Stop searching when , and output the initial driving strategy corresponding to the current optimal solution, which is the optimal driving strategy.

8. The dynamic decision control method based on vehicle energy consumption optimization according to claim 7 is characterized in that: The check updated Is it less than If not, the boundary processing methods include: ; In the formula, It refers to the control instability impact value corresponding to the i-th sparrow individual after the t+1 generation update.

9. The dynamic decision control method based on vehicle energy consumption optimization according to claim 7 is characterized in that: The target initial driving strategy is updated The methods include: ; In the formula, is a random number, is the location of the current optimal solution.

10. A dynamic decision control system based on vehicle energy consumption optimization, which is used to implement a dynamic decision control method based on vehicle energy consumption optimization as claimed in any one of claims 1 to 9, characterized in that: include: Strategy generation module: used to obtain real-time road information and vehicle body status information, determine the initial driving strategy based on the real-time road information and vehicle body status information, and simulate and predict the control instability data, motor energy efficiency data and tire slip data based on the real-time road information and the initial driving strategy; Data processing module: used to calculate the control instability impact value according to the control instability data, calculate the motor energy efficiency value according to the motor energy efficiency data, and calculate the slip energy loss value according to the tire slip data; Strategy optimization module: used to optimize the initial driving strategy based on the control instability impact value, motor energy efficiency value, slip energy loss value and intelligent optimization algorithm to obtain the optimal driving strategy.

Images