Electric power steering torque control method, device, electronic equipment and program product

Abstract

The application discloses an electric power steering torque control method and device, electronic equipment and program product. The method comprises the following steps: identifying a target driving scene according to vehicle dynamics data and environment perception data, and determining attention weight parameters of the vehicle dynamics data, the environment perception data and interference data; inputting the vehicle dynamics data, the environment perception data, the interference data and the attention weight parameters into a vehicle dynamics prediction model to obtain a steering wheel expected torque and an ideal yaw rate value; calculating a pre-compensation torque according to the steering wheel expected torque, determining a feedback adjustment torque according to the ideal yaw rate value and an actual yaw rate value of the target vehicle, and calculating an interference compensation torque according to the interference data; determining a target torque according to the pre-compensation torque, the feedback adjustment torque and the interference compensation torque, and driving an electric power steering motor to perform torque control. The application improves the control stability and driving safety of the vehicle, and can be applied to the technical field of vehicle control.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to an electric power steering torque control method, device, electronic equipment, and program product. Background Technology

[0002] The core performance of an electric power steering (EPS) system depends on the accuracy of torque control; the rationality of torque determination directly affects the vehicle's steering response and handling experience under different operating conditions. Existing EPS torque determination schemes have the following drawbacks: 1) Sensor data has a single dimension and insufficient fusion depth: Existing solutions mostly rely on vehicle dynamics sensors such as steering wheel torque sensors and vehicle speed sensors, without fully integrating environmental perception sensor data, or only performing simple data superposition, which cannot cope with complex environmental conditions such as sudden changes in road adhesion coefficient, crosswind interference, and lane departure risk. 2) Fixed weight allocation strategy: Existing multi-source data fusion solutions mostly adopt a fixed weight allocation method, which cannot dynamically adjust the weight ratio of each sensor data according to the driving scenario. When the data of a certain sensor fluctuates due to environmental interference, it will significantly reduce the robustness of torque determination. 3) Significant control lag: Existing solutions mostly adopt feedback torque control, which adjusts the assist torque after detecting the vehicle's dynamic response deviation. In dynamic conditions such as emergency obstacle avoidance and high-speed steering, control lag can easily lead to steering inaccuracy and cannot meet the real-time control requirements in complex environments. 4) Insufficient anti-interference capability: For external and internal interference such as road bumps and motor disturbances, existing solutions mostly adopt single filtering or robust control strategies, without combining multi-source sensor data for accurate identification and targeted compensation of interference sources, resulting in poor torque output stability.

[0003] Therefore, there is an urgent need for an electric power steering torque control scheme that integrates multi-dimensional sensor data, has dynamic weight adaptation capabilities, and takes into account both pre-compensation and feedback adjustment, in order to improve the accuracy and robustness of torque control in complex driving environments. Summary of the Invention

[0004] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0005] Therefore, one objective of this invention is to provide an electric power steering torque control method. This method integrates vehicle dynamics, environmental perception data, and disturbance data across domains, performs attention weight allocation based on driving scenario recognition, and predicts the ideal values ​​of the steering wheel's desired torque and yaw rate. It then calculates the pre-compensation torque, feedback adjustment torque, and disturbance compensation torque to finally obtain the target torque. This achieves real-time and precise control of electric power steering torque in complex environments, improving vehicle handling stability and driving safety.

[0006] Another objective of this invention is to provide an electric power steering torque control device.

[0007] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include: On one hand, embodiments of the present invention provide an electric power steering torque control method, comprising the following steps: Acquire vehicle dynamics data, environmental perception data, and interference data of the target vehicle; The target driving scenario of the target vehicle is identified based on the vehicle dynamics data and environmental perception data, and attention weight parameters of the vehicle dynamics data, environmental perception data and interference data are determined based on the target driving scenario. The vehicle dynamics data, the environmental perception data, the disturbance data, and the attention weight parameters are input into a pre-trained vehicle dynamics prediction model to obtain the ideal values ​​of the steering wheel desired torque and yaw rate. The pre-compensation torque is calculated based on the desired steering wheel torque, the feedback adjustment torque is determined based on the ideal yaw rate and the actual yaw rate of the target vehicle, and the interference compensation torque is calculated based on the interference data. The target torque is determined based on the pre-compensation torque, the feedback adjustment torque, and the interference compensation torque, and the electric power steering motor of the target vehicle is driven to perform torque control based on the target torque.

[0008] Furthermore, in one embodiment of the present invention, the vehicle dynamics data includes steering wheel input torque, steering angle, vehicle speed, and yaw rate; the environmental perception data includes road surface adhesion coefficient, crosswind intensity, lane departure, and distance to the vehicle in front; and the disturbance data includes motor disturbance current and suspension vibration acceleration.

[0009] Furthermore, in one embodiment of the present invention, the step of identifying the target driving scenario of the target vehicle based on the vehicle dynamics data and environmental perception data, and determining the attention weight parameters of the vehicle dynamics data, the environmental perception data, and the interference data based on the target driving scenario, specifically includes: The vehicle dynamics data and the environmental perception data are input into a pre-built scene classification decision tree model to obtain the target driving scene; Based on the target driving scenario, a preset weight allocation MAP is queried to obtain the attention weight parameters of the vehicle dynamics data, the environmental perception data, and the interference data.

[0010] Furthermore, in one embodiment of the present invention, the vehicle dynamics prediction model is trained through the following steps: Acquire vehicle dynamics data samples, environmental perception data samples, and disturbance data samples of the test vehicle, and determine the corresponding steering wheel torque label and yaw rate label through manual annotation; The vehicle dynamics data sample, the environmental perception data sample, and the interference data sample are input into a multi-branch LSTM neural network. The hidden states of the vehicle dynamics data sample, the environmental perception data sample, and the interference data sample are calculated by using multiple LSTM branches of the multi-branch LSTM neural network to obtain the first hidden state vector, the second hidden state vector, and the third hidden state vector. Based on the self-attention mechanism, the first hidden state vector, the second hidden state vector, and the third hidden state vector are fused to obtain a fused hidden state vector. The fused hidden state vector is then mapped to the predicted steering wheel torque and the predicted yaw rate through a fully connected layer. The loss value is determined based on the predicted steering wheel torque, the predicted yaw rate, the steering wheel torque label, and the yaw rate label; The parameters of the multi-branch LSTM neural network are updated based on the loss value to obtain the trained vehicle dynamics prediction model.

[0011] Furthermore, in one embodiment of the present invention, the pre-compensated torque is calculated using the following formula:

[0012] in, Indicates pre-compensated torque. Indicates the desired torque of the steering wheel. This indicates the current steering wheel input torque. Indicates the current crosswind intensity. This represents the road surface condition correction factor. This represents the vehicle speed correction factor. Indicates the crosswind correction factor; The interference data includes motor disturbance current and suspension vibration acceleration, and the interference compensation torque is calculated using the following formula:

[0013] in, Indicates the interference compensation torque. This indicates the motor disturbance current. Indicates the suspension vibration acceleration. This represents the preset current interference compensation coefficient. This represents the preset vibration interference compensation coefficient.

[0014] Furthermore, in one embodiment of the present invention, determining the feedback adjustment torque based on the ideal value of the yaw rate and the actual value of the yaw rate of the target vehicle specifically includes: The actual value of the yaw rate is determined based on the vehicle dynamics data, and the current lane deviation of the target vehicle is determined based on the environmental perception data. The yaw rate deviation is determined based on the ideal value of the yaw rate and the actual value of the yaw rate. The feedback proportional coefficient, feedback integral coefficient, and feedback derivative coefficient are determined using a fuzzy PID algorithm based on the yaw rate deviation and the lane offset, and the feedback adjustment torque is determined based on the feedback proportional coefficient, the feedback integral coefficient, and the feedback derivative coefficient.

[0015] Furthermore, in one embodiment of the present invention, the target torque is calculated using the following formula:

[0016] in, Indicates the target torque. Indicates pre-compensated torque. This indicates feedback adjustment torque. This indicates the interference compensation torque.

[0017] On the other hand, embodiments of the present invention provide an electric power steering torque control device, comprising: The data acquisition module is used to acquire vehicle dynamics data, environmental perception data, and interference data of the target vehicle. The scene recognition module is used to identify the target driving scene of the target vehicle based on the vehicle dynamics data and environmental perception data, and to determine the attention weight parameters of the vehicle dynamics data, the environmental perception data and the interference data based on the target driving scene. The prediction module is used to input the vehicle dynamics data, the environmental perception data, the interference data, and the attention weight parameters into a pre-trained vehicle dynamics prediction model to obtain the ideal values ​​of the steering wheel expected torque and yaw rate. The calculation module is used to calculate the pre-compensation torque based on the desired torque of the steering wheel, determine the feedback adjustment torque based on the ideal value of the yaw rate and the actual value of the yaw rate of the target vehicle, and calculate the interference compensation torque based on the interference data. The control module is used to determine the target torque based on the pre-compensated torque, the feedback adjustment torque, and the interference compensation torque, and to drive the electric power steering motor of the target vehicle to perform torque control based on the target torque.

[0018] On the other hand, embodiments of the present invention provide an electronic device, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above-described electric power steering torque control method.

[0019] On the other hand, embodiments of the present invention also provide a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described electric power steering torque control method.

[0020] On the other hand, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the above-described electric power steering torque control method.

[0021] The advantages and beneficial effects of the present invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention: This invention acquires vehicle dynamics data, environmental perception data, and interference data of a target vehicle. Based on the vehicle dynamics data and environmental perception data, it identifies the target driving scenario of the target vehicle and determines the attention weight parameters of the vehicle dynamics data, environmental perception data, and interference data according to the target driving scenario. The vehicle dynamics data, environmental perception data, interference data, and attention weight parameters are input into a pre-trained vehicle dynamics prediction model to obtain the desired steering wheel torque and ideal yaw rate values. A pre-compensation torque is calculated based on the desired steering wheel torque. A feedback adjustment torque is determined based on the ideal yaw rate value and the actual yaw rate value of the target vehicle. An interference compensation torque is calculated based on the interference data. The target torque is determined based on the pre-compensation torque, feedback adjustment torque, and interference compensation torque. The electric power steering motor of the target vehicle is then driven to perform torque control based on the target torque. This invention integrates vehicle dynamics, environmental perception data, and interference data across domains. Based on driving scenario recognition, it allocates attention weights and predicts the desired steering wheel torque and ideal yaw rate values, thereby calculating the pre-compensation torque, feedback adjustment torque, and interference compensation torque to ultimately obtain the target torque. This achieves real-time and precise control of electric power steering torque in complex environments, improving vehicle handling stability and driving safety. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments of the present invention are described below. It should be understood that the drawings described below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart illustrating the steps of an electric power steering torque control method provided in an embodiment of the present invention; Figure 2 A structural block diagram of an electric power steering torque control device provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0026] The electric power steering torque control method provided in this invention can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the electric power steering torque control method, but is not limited to the above forms.

[0027] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0028] It should be noted that in various specific embodiments of the present invention, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user parking space location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of the present invention require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to a confirmation page. Only after obtaining the user's separate permission or consent is the necessary user-related data for the normal operation of the embodiments of the present invention acquired.

[0029] Reference Figure 1 This invention provides an electric power steering torque control method, which specifically includes the following steps: S101. Acquire vehicle dynamics data, environmental perception data, and interference data of the target vehicle; S102. Identify the target driving scenario of the target vehicle based on vehicle dynamics data and environmental perception data, and determine the attention weight parameters of vehicle dynamics data, environmental perception data and interference data based on the target driving scenario. S103. Input the vehicle dynamics data, environmental perception data, disturbance data and attention weight parameters into the pre-trained vehicle dynamics prediction model to obtain the ideal values ​​of the steering wheel expected torque and yaw rate. S104. Calculate the pre-compensation torque based on the desired steering wheel torque, determine the feedback adjustment torque based on the ideal yaw rate and the actual yaw rate of the target vehicle, and calculate the interference compensation torque based on the interference data. S105. Determine the target torque based on the pre-compensation torque, feedback adjustment torque, and interference compensation torque, and drive the electric power steering motor of the target vehicle for torque control based on the target torque.

[0030] This invention integrates vehicle dynamics, environmental perception data, and interference data across domains. Based on driving scenario recognition, it performs attention weight allocation and predicts the ideal values ​​of steering wheel torque and yaw rate. In this way, it calculates pre-compensation torque, feedback adjustment torque, and interference compensation torque to finally obtain the target torque. This achieves real-time and precise control of electric power steering torque in complex environments, improving vehicle handling stability and driving safety.

[0031] As an optional implementation, vehicle dynamics data includes steering wheel input torque, steering angle, vehicle speed, and yaw rate; environmental perception data includes road surface adhesion coefficient, crosswind intensity, lane departure, and distance to the vehicle in front; and disturbance data includes motor disturbance current and suspension vibration acceleration.

[0032] Specifically, the vehicle in this embodiment of the invention is equipped with a multi-source sensor array, including a vehicle dynamics sensor group, an environmental perception sensor group, and an interference detection sensor group. The vehicle dynamics sensor group includes a steering wheel torque sensor, a steering angle sensor, a vehicle speed sensor, and a yaw rate sensor, used to acquire vehicle steering and driving dynamic parameters. The environmental perception sensor group includes a forward-facing camera, a millimeter-wave radar, a road surface adhesion coefficient sensor, and a crosswind sensor, used to acquire lane position, distance to the vehicle in front, road surface condition, and crosswind intensity. The interference detection sensor group includes a motor current sensor and a suspension vibration sensor, used to acquire EPS motor disturbance and road bump interference parameters.

[0033] In some optional embodiments, the present invention preprocesses vehicle dynamics data, environmental perception data, and interference data. For example, it uses an FPGA chip to achieve high-speed data synchronization and optimization processing, and outputs a standardized data source through timestamp alignment, 3σ criterion for outlier removal, and Kalman filtering for noise reduction.

[0034] As a further optional implementation, the target driving scenario of the target vehicle is identified based on vehicle dynamics data and environmental perception data, and attention weight parameters for vehicle dynamics data, environmental perception data, and interference data are determined based on the target driving scenario. Specifically, this includes: S1021. Input vehicle dynamics data and environmental perception data into a pre-built scene classification decision tree model to obtain the target driving scene; S1022. Based on the target driving scenario, query the preset weight allocation MAP to obtain the attention weight parameters of vehicle dynamics data, environmental perception data, and interference data.

[0035] Specifically, based on environmental perception data and vehicle dynamics data, driving scenarios are divided into five categories: cruising on regular paved roads, driving on low-adhesion roads, crosswind interference, high-speed emergency lane change, and low-speed vehicle maneuvering. Then, a preset weight allocation MAP is queried to obtain the attention weight parameters of vehicle dynamics data, environmental perception data, and interference data.

[0036] In some optional embodiments, scene classification is achieved through a decision tree algorithm. For example, the judgment rules are as follows: when the vehicle speed is >60km / h, the road surface adhesion coefficient is ≥0.6, and the crosswind intensity is <3m / s, it is judged as cruising on a regular paved road; when the road surface adhesion coefficient is <0.3, it is judged as driving on a low-adhesion road; when the crosswind intensity is ≥5m / s, it is judged as a crosswind interference scene; when the vehicle speed is >80km / h, the steering angle change rate is >30° / s, and the lane deviation is >0.2m, it is judged as a high-speed emergency lane change; when the vehicle speed is <5km / h, it is judged as a low-speed maneuver.

[0037] Attention weight parameters for different driving scenarios are pre-calibrated through experiments to form a weight allocation map. For example: when cruising on a regular paved road, the weight of dynamic data is 0.6, the weight of environmental data is 0.3, and the weight of interference data is 0.1; when driving on a low-friction road, the weight of dynamic data is 0.4, the weight of environmental data is 0.5, and the weight of interference data is 0.1; when encountering crosswind interference, the weight of dynamic data is 0.3, the weight of environmental data is 0.6, and the weight of interference data is 0.1; when making an emergency lane change at high speed, the weight of dynamic data is 0.5, the weight of environmental data is 0.4, and the weight of interference data is 0.1; when maneuvering at low speed, the weight of dynamic data is 0.7, the weight of environmental data is 0.2, and the weight of interference data is 0.1.

[0038] Vehicle dynamics data, environmental perception data, disturbance data, and determined attention weight parameters are input into a pre-trained vehicle dynamics prediction model to predict steering demand 0.3-0.5 seconds in advance, thereby obtaining the ideal values ​​of steering wheel torque and yaw rate.

[0039] As an optional implementation, the vehicle dynamics prediction model is trained through the following steps: S201. Obtain vehicle dynamics data samples, environmental perception data samples, and interference data samples of the test vehicle, and determine the corresponding steering wheel torque label and yaw rate label through manual annotation. S202. Input the vehicle dynamics data samples, environmental perception data samples, and interference data samples into the multi-branch LSTM neural network. S203. The hidden states of the vehicle dynamics data sample, the environmental perception data sample, and the interference data sample are calculated by using multiple LSTM branches of the multi-branch LSTM neural network to obtain the first hidden state vector, the second hidden state vector, and the third hidden state vector. S204. Based on the self-attention mechanism, feature fusion is performed on the first hidden state vector, the second hidden state vector and the third hidden state vector to obtain the fused hidden state vector, and the fused hidden state vector is mapped to the predicted steering wheel torque and the predicted yaw rate through a fully connected layer. S205. Determine the loss value based on the predicted steering wheel torque, predicted yaw rate, steering wheel torque label, and yaw rate label. S206. Update the parameters of the multi-branch LSTM neural network based on the loss value to obtain the trained vehicle dynamics prediction model.

[0040] Specifically, vehicle dynamics data samples, environmental perception data samples, and interference data samples of the test vehicle are acquired. The corresponding steering wheel torque and yaw rate labels are determined through manual annotation. These data samples are then input into a multi-branch LSTM neural network. Multiple LSTM branches of the network calculate the hidden states of each data sample, yielding a first, second, and third hidden state vector. Based on a self-attention mechanism, these vectors are fused to obtain a fused hidden state vector. This fused hidden state vector is then mapped to predicted steering wheel torque and predicted yaw rate through a fully connected layer. A loss value is determined based on the predicted steering wheel torque, predicted yaw rate, steering wheel torque label, and yaw rate label. The parameters of the multi-branch LSTM neural network are updated based on this loss value, completing one iteration of training. Training stops when the number of iterations reaches a preset threshold or the loss value falls below the preset threshold, resulting in a trained vehicle dynamics prediction model.

[0041] It is understood that the embodiments of the present invention input real-time collected vehicle dynamics data, environmental perception data, interference data, and attention weight parameters determined based on the market price of the vehicle into a pre-trained vehicle dynamics prediction model. By fixing the attention weight parameters through prior knowledge, the prediction accuracy of the model is improved.

[0042] As a further optional implementation, the pre-compensation torque is calculated using the following formula:

[0043] in, Indicates pre-compensated torque. Indicates the desired torque of the steering wheel. This indicates the current steering wheel input torque. Indicates the current crosswind intensity. This represents the road surface condition correction factor. This represents the vehicle speed correction factor. Indicates the crosswind correction factor; The interference data includes motor disturbance current and suspension vibration acceleration. The interference compensation torque is calculated using the following formula:

[0044] in, Indicates the interference compensation torque. This indicates the motor disturbance current. Indicates the suspension vibration acceleration. This represents the preset current interference compensation coefficient. This represents the preset vibration interference compensation coefficient.

[0045] Specifically, embodiments of the present invention can address control lag issues in complex scenarios by calculating pre-compensated torque. This represents the pavement condition correction factor, with a value range of 0.8-1.2; This represents the vehicle speed correction factor, with a value ranging from 0.5 to 1.0. This represents the crosswind correction factor, with a value ranging from 0.3 to 0.6. The disturbance compensation torque is estimated from the motor disturbance current and suspension vibration acceleration, where... This represents the preset current interference compensation coefficient. This represents the preset vibration interference compensation coefficient, the specific value of which can be obtained through experimental calibration.

[0046] As a further optional implementation, the feedback adjustment torque is determined based on the ideal yaw rate and the actual yaw rate of the target vehicle, specifically including: S1041. Determine the actual value of the yaw rate based on vehicle dynamics data, and determine the current lane deviation of the target vehicle based on environmental perception data. S1042. Determine the yaw rate deviation based on the ideal value and the actual value of the yaw rate. S1043. Based on the yaw rate deviation and lane departure, the feedback proportional coefficient, feedback integral coefficient, and feedback derivative coefficient are determined using a fuzzy PID algorithm, and the feedback adjustment torque is determined based on the feedback proportional coefficient, feedback integral coefficient, and feedback derivative coefficient.

[0047] Specifically, in this embodiment of the invention, the feedback adjustment torque is calculated based on the yaw rate deviation and lane offset. When the yaw rate deviation is greater than 0.05 rad / s or the absolute value of the lane offset is greater than 0.1 m, feedback adjustment is initiated. The yaw rate deviation and lane offset are input into the PID controller of the fuzzy PID algorithm to obtain the feedback proportional coefficient, feedback integral coefficient, and feedback derivative coefficient of the PID controller. Then, the feedback adjustment torque is calculated based on the feedback proportional coefficient, feedback integral coefficient, feedback derivative coefficient, and PID control formula.

[0048] As an optional implementation, the target torque is calculated using the following formula:

[0049] in, Indicates the target torque. Indicates pre-compensated torque. This indicates feedback adjustment torque. This indicates the interference compensation torque.

[0050] Specifically, the target torque is obtained by integrating the pre-compensation torque, feedback adjustment torque, and disturbance compensation torque, and a vector control algorithm is used to drive the EPS motor for torque control.

[0051] The method steps of the embodiments of the present invention have been described above. It can be understood that the embodiments of the present invention integrate vehicle dynamics, environmental perception data, and interference data across domains, allocate attention weights based on driving scene recognition, and predict the ideal values ​​of the steering wheel's desired torque and yaw rate, thereby calculating the pre-compensation torque, feedback adjustment torque, and interference compensation torque to finally obtain the target torque. This achieves real-time and precise control of electric power steering torque in complex environments, improving vehicle handling stability and driving safety.

[0052] Compared with the prior art, the embodiments of the present invention have the following advantages: 1) Significantly improved fusion depth and robustness: By integrating three types of sensor data across domains and adopting dynamic scene adaptive weight allocation, compared with the existing fixed weight fusion scheme, the error of torque control in complex environments is reduced, and it can effectively cope with extreme working conditions such as sudden changes in road adhesion coefficient and crosswind interference. 2) Significantly improved control lag: A pre-compensation-feedback dual closed-loop control architecture is constructed to predict steering demand in advance and output pre-compensation torque. Compared with traditional feedback control, this reduces steering response delay and improves handling stability under dynamic conditions such as high-speed emergency lane changes. 3) Strong anti-interference capability: The targeted interference compensation mechanism accurately identifies and compensates for the effects of motor disturbances and road bumps, reducing the fluctuation range of torque output and improving driving comfort; 4) Wide compatibility: It can be directly integrated into the existing EPS system without major changes to the hardware structure. It is compatible with different vehicle models (sedans, SUVs, commercial vehicles) and different intelligent driving levels (L2-L4), and has broad industrialization prospects.

[0053] Reference Figure 2 This invention provides an electric power steering torque control device, comprising: The data acquisition module is used to acquire vehicle dynamics data, environmental perception data, and interference data of the target vehicle. The scene recognition module is used to identify the target driving scene of the target vehicle based on vehicle dynamics data and environmental perception data, and to determine the attention weight parameters of vehicle dynamics data, environmental perception data and interference data based on the target driving scene. The prediction module is used to input vehicle dynamics data, environmental perception data, disturbance data, and attention weight parameters into a pre-trained vehicle dynamics prediction model to obtain the ideal values ​​of steering wheel torque and yaw rate. The calculation module is used to calculate the pre-compensation torque based on the desired steering wheel torque, determine the feedback adjustment torque based on the ideal yaw rate and the actual yaw rate of the target vehicle, and calculate the interference compensation torque based on the interference data. The control module is used to determine the target torque based on the pre-compensated torque, feedback adjustment torque, and disturbance compensation torque, and to drive the electric power steering motor of the target vehicle for torque control based on the target torque.

[0054] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0055] Reference Figure 3 This invention provides an electronic device, comprising: At least one processor; At least one memory for storing at least one program; When the above-mentioned at least one program is executed by the above-mentioned at least one processor, the above-mentioned at least one processor implements the above-mentioned electric power steering torque control method.

[0056] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0057] This invention also provides a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described electric power steering torque control method.

[0058] This invention provides a computer-readable storage medium that can execute an electric power steering torque control method provided in the method embodiments of this invention. It can execute any combination of the implementation steps of the method embodiments and has the corresponding functions and beneficial effects of the method.

[0059] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described electric power steering torque control method.

[0060] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0061] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0062] The embodiments described in this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0063] The terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0064] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0065] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0066] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0067] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0068] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0069] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0070] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0071] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0072] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for controlling torque in electric power steering, characterized in that, Includes the following steps: Acquire vehicle dynamics data, environmental perception data, and interference data of the target vehicle; The target driving scenario of the target vehicle is identified based on the vehicle dynamics data and environmental perception data, and attention weight parameters of the vehicle dynamics data, environmental perception data and interference data are determined based on the target driving scenario. The vehicle dynamics data, the environmental perception data, the disturbance data, and the attention weight parameters are input into a pre-trained vehicle dynamics prediction model to obtain the ideal values ​​of the steering wheel desired torque and yaw rate. The pre-compensation torque is calculated based on the desired steering wheel torque, the feedback adjustment torque is determined based on the ideal yaw rate and the actual yaw rate of the target vehicle, and the interference compensation torque is calculated based on the interference data. The target torque is determined based on the pre-compensation torque, the feedback adjustment torque, and the interference compensation torque, and the electric power steering motor of the target vehicle is driven to perform torque control based on the target torque.

2. The electric power steering torque control method according to claim 1, characterized in that, The vehicle dynamics data includes steering wheel input torque, steering angle, vehicle speed, and yaw rate; the environmental perception data includes road surface adhesion coefficient, crosswind intensity, lane departure, and distance to the vehicle in front; and the disturbance data includes motor disturbance current and suspension vibration acceleration.

3. The electric power steering torque control method according to claim 1, characterized in that, The step of identifying the target driving scenario of the target vehicle based on the vehicle dynamics data and environmental perception data, and determining the attention weight parameters of the vehicle dynamics data, the environmental perception data, and the interference data based on the target driving scenario, specifically includes: The vehicle dynamics data and the environmental perception data are input into a pre-built scene classification decision tree model to obtain the target driving scene; Based on the target driving scenario, a preset weight allocation MAP is queried to obtain the attention weight parameters of the vehicle dynamics data, the environmental perception data, and the interference data.

4. The electric power steering torque control method according to claim 1, characterized in that, The vehicle dynamics prediction model is trained through the following steps: Acquire vehicle dynamics data samples, environmental perception data samples, and disturbance data samples of the test vehicle, and determine the corresponding steering wheel torque label and yaw rate label through manual annotation; The vehicle dynamics data sample, the environmental perception data sample, and the interference data sample are input into a multi-branch LSTM neural network. The hidden states of the vehicle dynamics data sample, the environmental perception data sample, and the interference data sample are calculated by using multiple LSTM branches of the multi-branch LSTM neural network to obtain the first hidden state vector, the second hidden state vector, and the third hidden state vector. Based on the self-attention mechanism, the first hidden state vector, the second hidden state vector, and the third hidden state vector are fused to obtain a fused hidden state vector. The fused hidden state vector is then mapped to the predicted steering wheel torque and the predicted yaw rate through a fully connected layer. The loss value is determined based on the predicted steering wheel torque, the predicted yaw rate, the steering wheel torque label, and the yaw rate label; The parameters of the multi-branch LSTM neural network are updated based on the loss value to obtain the trained vehicle dynamics prediction model.

5. The electric power steering torque control method according to claim 1, characterized in that, The pre-compensation torque is calculated using the following formula: in, Indicates pre-compensated torque. Indicates the desired torque of the steering wheel. This indicates the current steering wheel input torque. Indicates the current crosswind intensity. This represents the road surface condition correction factor. This represents the vehicle speed correction factor. Indicates the crosswind correction factor; The interference data includes motor disturbance current and suspension vibration acceleration, and the interference compensation torque is calculated using the following formula: in, Indicates the interference compensation torque. This indicates the motor disturbance current. Indicates the suspension vibration acceleration. This represents the preset current interference compensation coefficient. This represents the preset vibration interference compensation coefficient.

6. The electric power steering torque control method according to claim 1, characterized in that, The step of determining the feedback adjustment torque based on the ideal yaw rate and the actual yaw rate of the target vehicle specifically includes: The actual value of the yaw rate is determined based on the vehicle dynamics data, and the current lane deviation of the target vehicle is determined based on the environmental perception data. The yaw rate deviation is determined based on the ideal value of the yaw rate and the actual value of the yaw rate. The feedback proportional coefficient, feedback integral coefficient, and feedback derivative coefficient are determined using a fuzzy PID algorithm based on the yaw rate deviation and the lane offset, and the feedback adjustment torque is determined based on the feedback proportional coefficient, the feedback integral coefficient, and the feedback derivative coefficient.

7. A method for controlling electric power steering torque according to any one of claims 1 to 6, characterized in that, The target torque is calculated using the following formula: in, Indicates the target torque. Indicates pre-compensated torque. This indicates feedback adjustment torque. This indicates the interference compensation torque.

8. An electric power steering torque control device, characterized in that, include: The data acquisition module is used to acquire vehicle dynamics data, environmental perception data, and interference data of the target vehicle. The scene recognition module is used to identify the target driving scene of the target vehicle based on the vehicle dynamics data and environmental perception data, and to determine the attention weight parameters of the vehicle dynamics data, the environmental perception data and the interference data based on the target driving scene. The prediction module is used to input the vehicle dynamics data, the environmental perception data, the interference data, and the attention weight parameters into a pre-trained vehicle dynamics prediction model to obtain the ideal values ​​of the steering wheel expected torque and yaw rate. The calculation module is used to calculate the pre-compensation torque based on the desired torque of the steering wheel, determine the feedback adjustment torque based on the ideal value of the yaw rate and the actual value of the yaw rate of the target vehicle, and calculate the interference compensation torque based on the interference data. The control module is used to determine the target torque based on the pre-compensated torque, the feedback adjustment torque, and the interference compensation torque, and to drive the electric power steering motor of the target vehicle to perform torque control based on the target torque.

9. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements an electric power steering torque control method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements an electric power steering torque control method as described in any one of claims 1 to 7.

Images