Regenerative braking energy feedback control method based on multi-sensor fusion

Abstract

The invention relates to the technical field of braking energy feedback, in particular to a regenerative braking energy feedback control method based on multi-sensor fusion, and the method comprises the steps: respectively collecting vehicle driving state data and pedal state data in a vehicle driving process, and carrying out the preprocessing of the collected data; performing feature extraction on the preprocessed vehicle driving state data and pedal state data, and constructing a driver intention recognition model with the vehicle driving state data and the pedal state data as input and driver intention as output; and inputting the real-time vehicle driving state data and the real-time pedal state data into the driver intention recognition model to obtain a real-time driver intention, calculating a total braking force demand, and performing distribution control of regenerative braking and mechanical braking. The intervention opportunity and direction of regenerative braking are obtained by recognizing the intention of a driver, and more efficient and more stable energy feedback is achieved.

Description

Background Art

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

[0003] With the popularity of new energy vehicles, regenerative braking technology plays a key role in vehicle energy saving and extended driving range. In order to achieve more efficient and stable energy feedback, this solution proposes a regenerative braking energy feedback method based on multi-sensor fusion. By integrating advanced sensor technology, innovative data fusion algorithms and intelligent control strategies, the performance and reliability of the system are improved. Summary of the invention

[0004] The main purpose of the present invention is to provide a regenerative braking energy feedback control method based on multi-sensor fusion to effectively solve the above-mentioned problems mentioned in the background technology.

[0005] The technical solution of the present invention is as follows:

[0006] A regenerative braking energy feedback control method based on multi-sensor fusion is proposed, which includes the following steps:

[0007] S1, respectively collecting vehicle driving state data and pedal state data during vehicle driving, and preprocessing the collected data;

[0008] S2, extracting features from the preprocessed vehicle driving state data and pedal state data, and constructing a driver intention recognition model whose input is the vehicle driving state data and pedal state data and whose output is the driver intention;

[0009] S3. Input the real-time vehicle driving state data and the real-time pedal state data into the driver intention recognition model to obtain the real-time driver intention, calculate the total braking force demand, and perform distribution control of regenerative braking and mechanical braking.

[0010] A further improvement of the present invention is that the vehicle driving state data in S1 includes the vehicle driving speed and the vehicle longitudinal acceleration; the pedal state data includes the brake pedal opening, the accelerator pedal opening, the brake pedal opening change rate, and the accelerator pedal opening change rate.

[0011] A further improvement of the present invention is that the preprocessing of the collected data in S1 includes the following specific contents: using a unified timestamp to time-align the vehicle driving state data and the pedal state data, and performing a first-order low-pass filtering process on the time-aligned data to remove high-frequency noise; the specific formula of the first-order low-pass filtering process is: f (t) = αs(t) + (1-α)s f (t-Δt); where s f (t) is the data at time t after filtering, α is the filtering coefficient, s(t) is the data at time t before filtering, and Δt is the acquisition time interval.

[0012] A further improvement of the present invention is that the construction of the driver intention recognition model in S2 includes the following specific steps:

[0013] S21, extracting the brake pedal opening, the accelerator pedal opening, the brake pedal opening change rate, and the accelerator pedal opening change rate to form a pedal state feature data set, and at the same time extracting the vehicle driving speed and the vehicle longitudinal acceleration to form a vehicle driving state feature data set, thereby forming a complete driver operation feature data set;

[0014] S22, using the pedal state feature data set and the vehicle driving state feature data as inputs of the machine learning model, constructing a driver intention recognition model, and obtaining the driver intention output under different operations of the driver, wherein the driver intention output includes acceleration, constant speed driving, deceleration gliding, and braking deceleration;

[0015] S23. Obtain the driver intention labels corresponding to the driver under different operations to form a training data set; at the same time, use at least one set of vehicle pedal feature data and driving state feature data as input, and the corresponding labeled driver intention as the prediction target, so as to train the machine learning model until the error between the actual intention and the predicted intention is minimized.

[0016] A further improvement of the present invention is that the machine learning model in S32 and S33 is a support vector machine or a naive Bayes algorithm.

[0017] A further improvement of the present invention is that the total braking force requirement calculation in S3 includes the following specific steps:

[0018] S31, inputting the real-time vehicle driving state data and the real-time pedal state data into a driver intention recognition model to obtain the real-time driver intention;

[0019] S32: When the driver intention recognition model outputs acceleration, the total braking force demand F total = 0; when the driver intention recognition model outputs a constant speed or deceleration coasting, the total braking force demand Ftotal =F resist ; where F resist is the driving resistance; when the output result of the driver intention recognition model is braking deceleration, the total braking force demand F total =kmθ brk , k is the proportional coefficient of brake pedal opening and deceleration, m is the vehicle mass, θ brk is the brake pedal opening;

[0020] S33, according to the total braking force demand F total The calculation results are used to control the distribution of regenerative braking and mechanical braking.

[0021] The technical effects of the present invention are as follows:

[0022] A regenerative braking energy feedback control method based on multi-sensor fusion is constructed. The present invention collects vehicle driving state data and pedal state data during vehicle driving, pre-processes the collected data, extracts features from the pre-processed vehicle driving state data and pedal state data, constructs a driver intention recognition model with vehicle driving state data and pedal state data as input and driver intention as output, inputs real-time vehicle driving state data and real-time pedal state data into the driver intention recognition model to obtain real-time driver intention, calculates total braking force demand, and performs distribution control of regenerative braking and mechanical braking. By identifying the driver's intention, the timing and direction of regenerative braking intervention are obtained, achieving more efficient and smoother energy feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0024] Figure 1 It is a flow chart of the regenerative braking energy feedback control method based on multi-sensor fusion of the present invention. DETAILED DESCRIPTION

[0025] The present invention aims to propose a regenerative braking energy feedback control method based on multi-sensor fusion, by respectively collecting vehicle driving state data and pedal state data during vehicle driving, preprocessing the collected data; extracting features from the preprocessed vehicle driving state data and pedal state data, constructing a driver intention recognition model with vehicle driving state data and pedal state data as input and driver intention as output; inputting real-time vehicle driving state data and real-time pedal state data into the driver intention recognition model to obtain real-time driver intention, calculate the total braking force demand, and perform distribution control of regenerative braking and mechanical braking. By identifying the driver's intention, the intervention timing and direction of regenerative braking can be obtained, so as to achieve more efficient and smoother energy feedback.

[0026] Embodiment 1:

[0027] This embodiment proposes a regenerative braking energy feedback control method based on multi-sensor fusion, such as Figure 1 As shown, the specific steps include:

[0028] S1, respectively collecting vehicle driving state data and pedal state data during vehicle driving, and preprocessing the collected data;

[0029] S2, extracting features from the preprocessed vehicle driving state data and pedal state data, and constructing a driver intention recognition model whose input is the vehicle driving state data and pedal state data and whose output is the driver intention;

[0030] S3. Input the real-time vehicle driving state data and the real-time pedal state data into the driver intention recognition model to obtain the real-time driver intention, calculate the total braking force demand, and perform distribution control of regenerative braking and mechanical braking.

[0031] In this embodiment, the vehicle driving state data in S1 includes the vehicle driving speed and the vehicle longitudinal acceleration; the pedal state data includes the brake pedal opening, the accelerator pedal opening, the brake pedal opening change rate, and the accelerator pedal opening change rate.

[0032] In this embodiment, the preprocessing of the collected data in S1 includes the following specific contents: using a unified timestamp to time-align the vehicle driving state data and the pedal state data, and performing a first-order low-pass filtering process on the time-aligned data to remove high-frequency noise; the specific formula of the first-order low-pass filtering process is: f (t) = αs(t) + (1-α)s f (t-Δt); where s f (t) is the data at time t after filtering, α is the filtering coefficient, s(t) is the data at time t before filtering, and Δt is the acquisition time interval.

[0033] In this embodiment, the construction of the driver intention recognition model in S2 includes the following specific steps:

[0034] S21, extracting the brake pedal opening, the accelerator pedal opening, the brake pedal opening change rate, and the accelerator pedal opening change rate to form a pedal state feature data set, and at the same time extracting the vehicle driving speed and the vehicle longitudinal acceleration to form a vehicle driving state feature data set, thereby forming a complete driver operation feature data set;

[0035] S22, using the pedal state feature data set and the vehicle driving state feature data as inputs of the machine learning model, constructing a driver intention recognition model, and obtaining the driver intention output under different operations of the driver, wherein the driver intention output includes acceleration, constant speed driving, deceleration gliding, and braking deceleration;

[0036] S23. Obtain the driver intention labels corresponding to the driver under different operations to form a training data set; at the same time, use at least one set of vehicle pedal feature data and driving state feature data as input, and the corresponding labeled driver intention as the prediction target, so as to train the machine learning model until the error between the actual intention and the predicted intention is minimized.

[0037] In this embodiment, the machine learning model in S32 and S33 is a support vector machine or a naive Bayes algorithm.

[0038] In this embodiment, the total braking force requirement calculation in S3 includes the following specific steps:

[0039] S31, inputting the real-time vehicle driving state data and the real-time pedal state data into a driver intention recognition model to obtain the real-time driver intention;

[0040] S32: When the driver intention recognition model outputs acceleration, the total braking force demand F total = 0; when the driver intention recognition model outputs a constant speed or deceleration coasting, the total braking force demand F total =F resist ; where F resist is the driving resistance; when the output result of the driver intention recognition model is braking deceleration, the total braking force demand F total =kmθ brk , k is the proportional coefficient of brake pedal opening and deceleration, m is the vehicle mass, θ brk is the brake pedal opening;

[0041] S33, according to the total braking force demand F total The calculation results are used to control the distribution of regenerative braking and mechanical braking.

[0042] Embodiment 2:

[0043] 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-mentioned regenerative braking energy feedback control method based on multi-sensor fusion by calling the computer program stored in the memory.

[0044] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 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 regenerative braking energy feedback control method based on multi-sensor fusion provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface for data input and output. This embodiment will not be described in detail here.

[0045] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), and it can also be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0046] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0047] The present invention is described with reference to flowcharts and block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process or block in the flowchart and block diagram, as well as the combination of processes and blocks in the flowchart or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 Process or multiple processes and boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 Process or multiple processes and boxes Figure 1 The steps for the functions specified in one or more boxes.

[0049] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A regenerative braking energy feedback control method based on multi-sensor fusion, characterized in that: The specific steps include: S1, respectively collecting vehicle driving state data and pedal state data during vehicle driving, and preprocessing the collected data; S2, extracting features from the preprocessed vehicle driving state data and pedal state data, and constructing a driver intention recognition model whose input is the vehicle driving state data and pedal state data and whose output is the driver intention; S3. Input the real-time vehicle driving state data and the real-time pedal state data into the driver intention recognition model to obtain the real-time driver intention, calculate the total braking force demand, and perform distribution control of regenerative braking and mechanical braking.

2. The regenerative braking energy feedback control method based on multi-sensor fusion according to claim 1 is characterized in that: The vehicle driving state data in S1 includes the vehicle driving speed and the vehicle longitudinal acceleration; the pedal state data includes the brake pedal opening, the accelerator pedal opening, the brake pedal opening change rate, and the accelerator pedal opening change rate.

3. The regenerative braking energy feedback control method based on multi-sensor fusion according to claim 2 is characterized in that: The preprocessing of the collected data in S1 includes the following specific contents: using a unified timestamp to time-align the vehicle driving state data and the pedal state data, and performing a first-order low-pass filter on the time-aligned data to remove high-frequency noise; the specific formula of the first-order low-pass filter is: f (t) = αs(t) + (1-α)s f (t-Δt); where s f (t) is the data at time t after filtering, α is the filtering coefficient, s(t) is the data at time t before filtering, and Δt is the acquisition time interval.

4. The regenerative braking energy feedback control method based on multi-sensor fusion according to claim 3 is characterized in that: The construction of the driver intention recognition model in S2 includes the following specific steps: S21, extracting the brake pedal opening, the accelerator pedal opening, the brake pedal opening change rate, and the accelerator pedal opening change rate to form a pedal state feature data set, and at the same time extracting the vehicle driving speed and the vehicle longitudinal acceleration to form a vehicle driving state feature data set, thereby forming a complete driver operation feature data set; S22, using the pedal state feature data set and the vehicle driving state feature data as inputs of the machine learning model, constructing a driver intention recognition model, and obtaining the driver intention output under different operations of the driver, wherein the driver intention output includes acceleration, constant speed driving, deceleration gliding, and braking deceleration; S23. Obtain the driver intention labels corresponding to the driver under different operations to form a training data set; at the same time, use at least one set of vehicle pedal feature data and driving state feature data as input, and the corresponding labeled driver intention as the prediction target, so as to train the machine learning model until the error between the actual intention and the predicted intention is minimized.

5. The regenerative braking energy feedback control method based on multi-sensor fusion according to claim 4 is characterized in that: The machine learning model in S32 and S33 is a support vector machine or a naive Bayes algorithm.

6. The regenerative braking energy feedback control method based on multi-sensor fusion according to claim 5 is characterized in that: The total braking force requirement calculation in S3 includes the following specific steps: S31, inputting the real-time vehicle driving state data and the real-time pedal state data into a driver intention recognition model to obtain the real-time driver intention; S32: When the driver intention recognition model outputs acceleration, the total braking force demand F total = 0; when the driver intention recognition model outputs a constant speed or deceleration coasting, the total braking force demand F total =F resist ; where F resist is the driving resistance; when the output result of the driver intention recognition model is braking deceleration, the total braking force demand F total =kmθ brk , k is the proportional coefficient of brake pedal opening and deceleration, m is the vehicle mass, θ brk is the brake pedal opening; S33, according to the total braking force demand F total The calculation results are used to control the distribution of regenerative braking and mechanical braking.

Images