Machine Learning-Based Regenerative Braking Energy Feedback Control Method

Abstract

This invention relates to the field of regenerative braking energy feedback technology, and particularly to a machine learning-based regenerative braking energy feedback control method. The method includes: collecting vehicle driving style characteristic data, road condition characteristic data, and energy consumption level data at n consecutive time points during historical vehicle operation; calculating the mean of the vehicle driving style characteristic data, importing it into a correlation evaluation strategy to output the correlation with the energy consumption level data and sorting it in descending order, outputting key characteristic data of the vehicle driving style; inputting the key characteristic data of the vehicle driving style into an energy consumption level prediction model construction strategy to construct an energy consumption level prediction model with the key characteristic data of driving style and road condition data as input, and the energy consumption level at m future time points as output; when the energy consumption level predicted by the energy consumption level prediction model is higher than the safe energy consumption range, adjusting the feature weights of the neural network model, thereby adjusting the vehicle driving style and controlling the characteristic data affecting the energy consumption level.

Description

Technical Field

[0001] This invention relates to the field of regenerative braking energy feedback technology, and more particularly to a machine learning-based regenerative braking energy feedback control method. Background Technology

[0002] The development of regenerative braking energy feedback control technology is heavily influenced by the global energy crisis and environmental protection requirements. With the rapid expansion of the electric vehicle (EV) and hybrid electric vehicle (HEV) markets, improving the energy efficiency and driving range of these vehicles has become a key research focus. Regenerative braking technology, by converting the kinetic energy of vehicle braking into electrical energy stored in batteries, can effectively improve energy utilization, reduce dependence on fossil fuels, and lower vehicle operating costs and environmental impact.

[0003] In the development and optimization of regenerative braking systems, the introduction of machine learning technology is key to improving the system's intelligence and efficiency. Machine learning models can predict the vehicle's operating status and energy recovery potential, dynamically adjusting the regenerative braking strategy based on real-time road conditions, vehicle speed, battery status, and other factors to maximize energy recovery efficiency. Predictive maintenance using machine learning involves analyzing braking system data to identify potential faults and performance degradation, enabling preventative maintenance and reducing unexpected downtime and repair costs.

[0004] Problems with existing technologies: There is currently no solution that uses driver driving habits and style data to determine the timing and direction of regenerative braking intervention, making the braking process smoother and energy recovery more efficient. Summary of the Invention

[0005] The main objective of this invention is to provide a machine learning-based regenerative braking energy feedback control method, which effectively solves the problems mentioned in the background art.

[0006] The technical solution of the present invention is as follows:

[0007] A machine learning-based regenerative braking energy feedback control method is proposed, which includes the following steps:

[0008] S1. Collect vehicle driving style characteristic data, road condition characteristic data, and energy consumption level data at n consecutive time points during the historical vehicle driving process;

[0009] S2. Calculate the average and rate of change of brake pedal opening, accelerator pedal opening, steering wheel angle, speed during acceleration to braking, and speed during braking to acceleration at n consecutive time points during the historical vehicle driving process. Import these values ​​into the correlation evaluation strategy to determine their correlation with energy consumption level data and sort them in descending order. Output the key characteristic data of vehicle driving style.

[0010] S3. Input key characteristic data of vehicle driving style into the energy consumption level prediction model construction strategy to construct an energy consumption level prediction model with key characteristic data of driving style and road condition data as input and energy consumption level of the next m time nodes as output.

[0011] S4. When the energy consumption level predicted by the energy consumption level prediction model is higher than the safe energy consumption range, adjust the feature weights of the neural network model, and then adjust the vehicle driving style to control the feature data that affect the energy consumption level.

[0012] A further improvement of the present invention is that the vehicle driving style characteristic data in S1 includes brake pedal opening, accelerator pedal opening, steering wheel angle, speed of acceleration to braking process, standard speed of acceleration to braking process, speed of braking to acceleration process, and standard speed of braking to acceleration process; the road condition characteristic data includes suburban road condition data, urban road condition data, and highway road condition data.

[0013] A further improvement of the present invention is that the relevance strategy in S2 includes the following specific contents:

[0014] S21. Extract features from the average and rate of change of brake pedal opening, average and rate of change of accelerator pedal opening, average and rate of change of steering wheel angle, average speed during acceleration to braking process, and average speed during braking to acceleration process at n consecutive time points during the historical vehicle driving process.

[0015] S22. Construct a correlation analysis model, which is a three-layer neural network model. The neural network model includes an input layer, a hidden layer, and an output layer. Each node corresponds to a vehicle driving style feature data. The correlation is used as the output, and the output value is between 0 and 1.

[0016] S23. Sort the correlations output by the correlation analysis model in descending order, and output the vehicle driving style data with a correlation greater than 0.4 with the energy consumption level as the key feature data of vehicle driving style.

[0017] A further improvement of the present invention is that the energy consumption level prediction model construction strategy in S3 includes the following specific contents: 70% of the feature data is used as a training set to input the neural network model for training to obtain an initial neural network model, and 30% of the feature data is used as a test set to test the initial neural network model, and the optimal initial neural network model that meets the accuracy of the historical vehicle energy consumption level change curve data is output as the neural network model.

[0018] A further improvement of this invention is that the output formula of a specific neuron in the neural network model is: in The output of the p-term neuron in layer i+1. Let j be the connection weight between neuron j in layer i and neuron p in layer i+1. The output of neuron j in layer i is... σ represents the bias in a linear relationship, and σ is the sigmoid activation function.

[0019] The technical effects of this invention are as follows:

[0020] A machine learning-based regenerative braking energy feedback control method is constructed. This invention collects vehicle driving style characteristic data, road condition characteristic data, and energy consumption level data at n consecutive time points during historical vehicle driving. It calculates the average and rate of change of brake pedal opening, accelerator pedal opening, and steering wheel angle at n consecutive time points during historical vehicle driving, as well as the average speed during the acceleration-to-braking and braking-to-acceleration processes. These values ​​are then imported into a correlation evaluation strategy to output the correlation with energy consumption level data and sorted in descending order, outputting key characteristic data of vehicle driving style. This key characteristic data is then input into an energy consumption level prediction model construction strategy to construct an energy consumption level prediction model that takes the key characteristic data of driving style and road condition data as input and the energy consumption level at m future time points as output. When the energy consumption level predicted by the energy consumption level prediction model is higher than the safe energy consumption range, the feature weights of the neural network model are adjusted, thereby adjusting the vehicle driving style and controlling the characteristic data affecting energy consumption level. By using data on the driver's driving habits and style, the timing and direction of regenerative braking intervention can be determined, making the braking process smoother and energy recovery more efficient. Attached Figure Description

[0021] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0022] Figure 1 This is a schematic flowchart of the machine learning-based regenerative braking energy feedback control method of the present invention. Detailed Implementation

[0023] This invention aims to propose a machine learning-based regenerative braking energy feedback control method. It collects vehicle driving style characteristic data, road condition characteristic data, and energy consumption level data at n consecutive time points during historical vehicle driving. It calculates the average and rate of change of brake pedal opening, accelerator pedal opening, and steering wheel angle at these n consecutive time points, as well as the average speed during acceleration-to-braking and braking-to-acceleration processes. These values ​​are then imported into a correlation evaluation strategy to assess their correlation with energy consumption level data and sorted in descending order, outputting key characteristic data of vehicle driving style. This key characteristic data is then input into an energy consumption level prediction model construction strategy to build an energy consumption level prediction model that takes the key characteristic data of driving style and road condition data as input and outputs the energy consumption level at m future time points. When the energy consumption level predicted by the prediction model is higher than the safe energy consumption range, the feature weights of the neural network model are adjusted, thereby adjusting the vehicle driving style and controlling the characteristic data affecting energy consumption levels. By using data on the driver's driving habits and style, the timing and direction of regenerative braking intervention can be determined, making the braking process smoother and energy recovery more efficient.

[0024] Example 1:

[0025] This embodiment proposes a regenerative braking energy feedback control method based on machine learning, such as... Figure 1 As shown, the specific steps include the following:

[0026] S1. Collect vehicle driving style characteristic data, road condition characteristic data, and energy consumption level data at n consecutive time points during the historical vehicle driving process;

[0027] S2. Calculate the average and rate of change of brake pedal opening, accelerator pedal opening, steering wheel angle, speed during acceleration to braking, and speed during braking to acceleration at n consecutive time points during the historical vehicle driving process. Import these values ​​into the correlation evaluation strategy to determine their correlation with energy consumption level data and sort them in descending order. Output the key characteristic data of vehicle driving style.

[0028] S3. Input key characteristic data of vehicle driving style into the energy consumption level prediction model construction strategy to construct an energy consumption level prediction model with key characteristic data of driving style and road condition data as input and energy consumption level of the next m time nodes as output.

[0029] S4. When the energy consumption level predicted by the energy consumption level prediction model is higher than the safe energy consumption range, adjust the feature weights of the neural network model, and then adjust the vehicle driving style to control the feature data that affect the energy consumption level.

[0030] In this embodiment, the vehicle driving style characteristic data in S1 includes brake pedal opening, accelerator pedal opening, steering wheel angle, speed during acceleration-to-braking process, standard speed during acceleration-to-braking process, speed during braking-to-acceleration process, and standard speed during braking-to-acceleration process; the road condition characteristic data includes suburban road condition data, urban road condition data, and highway road condition data. These data reflect the driver's driving habits.

[0031] In this embodiment, data collected based on different road environments (suburbs, cities, highways) are crucial for understanding changes in vehicle energy consumption, as different road conditions significantly impact energy consumption. Real-time monitoring and recording of vehicle energy consumption is a key indicator for evaluating regenerative braking effectiveness and optimizing strategies.

[0032] In this embodiment, the relevance strategy in S2 includes the following specific contents:

[0033] S21. Extract features from the average and rate of change of brake pedal opening, average and rate of change of accelerator pedal opening, average and rate of change of steering wheel angle, average speed during acceleration to braking process, and average speed during braking to acceleration process at n consecutive time points during the historical vehicle driving process.

[0034] S22. Construct a correlation analysis model, which is a three-layer neural network model. The neural network model includes an input layer, a hidden layer, and an output layer. Each node corresponds to a vehicle driving style feature data. The correlation is used as the output, and the output value is between 0 and 1.

[0035] S23. Sort the correlations output by the correlation analysis model in descending order, and output the vehicle driving style data with a correlation greater than 0.4 with the energy consumption level as the key feature data of vehicle driving style.

[0036] In this embodiment, the energy consumption level prediction model construction strategy in S3 includes the following specific contents: 70% of the feature data is used as a training set to input the neural network model for training to obtain an initial neural network model, 30% of the feature data is used as a test set to test the initial neural network model, and the optimal initial neural network model that meets the accuracy of the historical vehicle energy consumption level change curve data is output as the neural network model.

[0037] In this embodiment, the output formula of a specific neuron in the neural network model is: in The output of the p-term neuron in layer i+1. Let j be the connection weight between neuron j in layer i and neuron p in layer i+1. The output of neuron j in layer i is... σ represents the bias in a linear relationship, and σ is the sigmoid activation function.

[0038] In this embodiment, when the predictive model indicates that the energy consumption level may exceed the safe range, the system will adjust the driving style by adjusting the feature weights in the neural network model. This means that the frequency and manner of using the brake pedal and accelerator pedal, as well as the steering wheel angle, are adjusted through machine learning to optimize energy consumption.

[0039] This method combines traditional driving data analysis with modern machine learning techniques, aiming to reduce energy consumption and improve energy recovery efficiency by optimizing driving style.

[0040] Example 2:

[0041] This embodiment provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-described machine learning-based regenerative braking energy feedback control method by calling the computer program stored in the memory.

[0042] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the machine learning-based regenerative braking energy feedback control method provided in the above-described embodiment. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Further details are omitted here.

[0043] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this disclosure can be embodied in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0044] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0045] This invention is described with reference to flowchart illustrations and block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and block diagrams, as well as combinations of blocks in the flowchart illustrations and block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0046] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and boxes Figure 1 The steps of the function specified in one or more boxes.

[0047] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A regenerative braking energy feedback control method based on machine learning, characterized in that: The specific steps include the following: S1. Collect vehicle driving style characteristic data, road condition characteristic data, and energy consumption level data at n consecutive time points during the historical vehicle driving process; S2. Calculate the average and rate of change of brake pedal opening, accelerator pedal opening, steering wheel angle, speed during acceleration to braking, and speed during braking to acceleration at n consecutive time points during the historical vehicle driving process. Import these values ​​into the correlation evaluation strategy to determine their correlation with energy consumption level data and sort them in descending order. Output the key characteristic data of vehicle driving style. S3. Input key characteristic data of vehicle driving style into the energy consumption level prediction model construction strategy to construct an energy consumption level prediction model with key characteristic data of driving style and road condition data as input and energy consumption level of the next m time nodes as output. S4. When the energy consumption level predicted by the energy consumption level prediction model is higher than the safe energy consumption range, adjust the feature weights of the neural network model, and then adjust the vehicle driving style to control the feature data that affect the energy consumption level.

2. The regenerative braking energy feedback control method based on machine learning according to claim 1, characterized in that: The vehicle driving style characteristic data in S1 includes brake pedal opening, accelerator pedal opening, steering wheel angle, speed during acceleration to braking, standard speed during acceleration to braking, speed during braking to acceleration, and standard speed during braking to acceleration. Road condition data includes suburban road condition data, urban road condition data, and highway road condition data.

3. The regenerative braking energy feedback control method based on machine learning according to claim 2, characterized in that: The relevance strategy in S2 includes the following specific contents: S21. Extract features from the average and rate of change of brake pedal opening, average and rate of change of accelerator pedal opening, average and rate of change of steering wheel angle, average speed during acceleration to braking process, and average speed during braking to acceleration process at n consecutive time points during the historical vehicle driving process. S22. Construct a correlation analysis model, which is a three-layer neural network model. The neural network model includes an input layer, a hidden layer, and an output layer. Each node corresponds to a vehicle driving style feature data. The correlation is used as the output, and the output value is between 0 and 1. S23. Sort the correlations output by the correlation analysis model in descending order, and output the vehicle driving style data with a correlation greater than 0.4 with the energy consumption level as the key feature data of vehicle driving style.

4. The regenerative braking energy feedback control method based on machine learning according to claim 3, characterized in that: The energy consumption level prediction model construction strategy in S3 includes the following specific contents: 70% of the feature data is used as the training set to input the neural network model for training to obtain the initial neural network model, and 30% of the feature data is used as the test set to test the initial neural network model. The optimal initial neural network model that meets the accuracy of the historical vehicle energy consumption level change curve data is output as the neural network model.

5. The regenerative braking energy feedback control method based on machine learning according to claim 4, characterized in that: The output formula for a specific neuron in the neural network model is: in The output of the p-term neuron in layer i+1. Let j be the connection weight between neuron j in layer i and neuron p in layer i+1. The output of neuron j in layer i is... σ represents the bias in a linear relationship, and σ is the sigmoid activation function.

Images