Vehicle electronic gear shifting control method and system based on multiple sensors and self-adaption
Through the adaptive network architecture optimized by multi-sensor data fusion and Gray Wolf algorithm, the problem of insufficient anti-interference and adaptive capabilities of the automotive electronic gear shift system is solved, high-precision and high-reliability shift control are achieved, and the model construction process is simplified.
Patent Information
- Application Number
- CN202510895174.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-30
- Publication Date
- 2025-08-15
AI Technical Summary
The existing automotive electronic shifting systems have poor anti-interference capabilities, insufficient adaptability under dynamic operating conditions, difficulty in fusion of multiple signals, and lack of applicability in traditional models. The model logic needs to be reconstructed and the workload is increased.
Using multi-sensor data fusion and adaptive network architecture, the Gray Wolf algorithm is introduced to optimize the neural network, automatically learn multi-source signal mapping relationships, and update the weights and thresholds of the neural network through the Gray Wolf group intelligent optimization algorithm to achieve high-precision and high-reliability electronic shift control.
It improves the robustness of the electronic gear shift system in a noisy environment, simplifies the complexity of model construction, is suitable for different project needs, reduces repetitive labor, and improves the accuracy and reliability of gear shift control.
Smart Images
Figure CN120487865A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of vehicle shift control, and in particular to a vehicle electronic shift control method and system based on multiple sensors and adaptation. Background Art
[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.
[0003] In the field of modeling and development of automotive electronic shift systems, the current mainstream technical solution is based on the digital modeling of the Electronic Gear Shift Controller (EGSC), using the Matlab / Simulink platform to achieve system-level modeling and closed-loop simulation verification. This technical architecture strictly adheres to the SAE J2399 technical specification and adopts a model development methodology based on the V process to convert shift logic requirements into an executable control algorithm model. In the existing execution control process, the button voltage and 3D Hall effect angle are used as the input of the electronic shift. After passing through the electronic shift model, the output data is transmitted to the TCU, and finally the execution signal is sent to the transmission to perform the shift operation. However, this approach still has the following problems: 1) Poor anti-interference ability: voltage signals are easily affected by electromagnetic noise or hardware aging, leading to misjudgment; 2) Insufficient adaptability under dynamic operating conditions. During long-term vehicle operation, sensors are susceptible to temperature drift, mechanical wear, and electromagnetic interference, leading to signal baseline offsets. Existing fixed threshold or static models lack online learning mechanisms, making it impossible to adjust signal weights in real time and unable to adapt to signal drift or extreme operating conditions (such as voltage anomalies caused by low temperatures).
[0004] 3) Multi-signal fusion is difficult. The nonlinear relationship between the 3D Hall sensor angle signal, ADC voltage signal, and TCU gear position signal is difficult to model using traditional algorithms.
[0005] 4) The shift model needs to be rebuilt according to different project requirements. The traditional use of MATLAB to build a logical model is not compatible and can not be reused. Sometimes it may be necessary to rebuild the model logic, which lacks applicability and increases unnecessary workload. Summary of the Invention
[0006] In order to solve the above problems, the present disclosure proposes a vehicle electronic shift control method and system based on multi-sensor and adaptation. Through the spatiotemporal feature fusion of multi-sensor data and a lightweight adaptive network architecture, the Grey Wolf algorithm is introduced to optimize the network, automatically learn the complex mapping relationship of multi-source signals, improve the robustness in noisy environments, achieve high-precision and high-reliability electronic shift control, and break through the technical bottleneck of traditional solutions.
[0007] According to some embodiments, the present disclosure adopts the following technical solutions: A vehicle electronic shift control method based on multiple sensors and adaptation includes: Obtain the vehicle's multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status, and pre-process them; The pre-processed vehicle multi-channel ADC voltage signal, shift lever angle signal and TCU gear position status are input into the trained and optimized gear position prediction model, and the output is the shift lever target position; Among them, the gear prediction model is optimized by using the gray wolf group intelligent optimization algorithm, including: setting the gray wolf population size, individual position vector dimension and its feasible solution space boundary, using a uniform distribution strategy to generate the initial population position matrix, inputting the position of the gray wolf individual into the neural network weight matrix, and calculating the fitness; establishing a three-level leadership system and follower group based on the fitness ranking, updating the individual position vector according to the group collaboration mechanism, synchronously adjusting the convergence factor and its related parameters, and performing dimension-by-dimensional out-of-bounds detection on the updated position vector. If there is an out-of-bounds, the upper or lower bound of the gray wolf dimension is set to the out-of-bounds value, and iterating continuously until the conditions are met, and the optimal network parameters of the gear prediction model are output.
[0008] According to some embodiments, the present disclosure adopts the following technical solutions: The vehicle electronic shift control system based on multiple sensors and adaptation includes: The data acquisition module is used to obtain the vehicle's multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status, and pre-process them; The prediction module is used to input the pre-processed vehicle multi-channel ADC voltage signals, the shift lever angle signal, and the TCU gear position status into the trained and optimized gear position prediction model, and output the target shift lever position; Among them, the gear prediction model is optimized by using the gray wolf group intelligent optimization algorithm, including: setting the gray wolf population size, individual position vector dimension and its feasible solution space boundary, using a uniform distribution strategy to generate the initial population position matrix, inputting the position of the gray wolf individual into the neural network weight matrix, and calculating the fitness; establishing a three-level leadership system and follower group based on the fitness ranking, updating the individual position vector according to the group collaboration mechanism, synchronously adjusting the convergence factor and its related parameters, and performing dimension-by-dimensional out-of-bounds detection on the updated position vector. If there is an out-of-bounds, the upper or lower bound of the gray wolf dimension is set to the out-of-bounds value, and iterating continuously until the conditions are met, and the optimal network parameters of the gear prediction model are output.
[0009] According to some embodiments, the present disclosure adopts the following technical solutions: A computer program product includes a computer program. When the computer program is executed by a processor, the computer program implements the vehicle electronic shift control method based on multiple sensors and adaptation.
[0010] According to some embodiments, the present disclosure adopts the following technical solutions: A non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the multi-sensor and adaptive vehicle electronic shift control method is implemented.
[0011] According to some embodiments, the present disclosure adopts the following technical solutions: An electronic device includes: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the multi-sensor and adaptive vehicle electronic shift control method.
[0012] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a vehicle electronic shift control method based on multiple sensors and adaptation. The method automatically learns the complex mapping relationship of multi-source signals through a neural network to improve the robustness in a noisy environment. The neural network is optimized through the gray wolf algorithm, that is, the position information of the gray wolf is used as the weight and threshold of the neural network. The gray wolf continuously judges and updates the position of the prey, which is equivalent to continuously updating the threshold and weight of the neural network. After multiple iterations, the global optimal result is finally calculated. The electronic shift switches the driving gear through the shift logic and is trained through the neural network. It only focuses on the input and output of the electronic shift without paying attention to its internal logical judgment, thereby simplifying the complexity of the model construction and being applicable to the different needs of different projects, thereby reducing duplication of work.
[0013] This disclosure utilizes a multi-sensor, adaptive vehicle electronic shift control method that utilizes the Gray Wolf Algorithm (GWA) to optimize neural network models. This algorithm enhances global search capabilities and avoids being trapped in local optima. Its core mechanism is to simulate the social hierarchy (α, β, δ, ω) and hunting behaviors (encirclement, pursuit, and attack) of a wolf pack. Three leader wolves, α, β, and δ, guide the pack's search direction, effectively escaping local optima and finding solutions closer to the global optimum in complex, multi-peaked, high-dimensional spaces (such as the surface of a neural network's loss function). The GWA's collaborative mechanism enables multiple individuals in the pack to explore different areas simultaneously. The α, β, and δ wolves share information to guide convergence, while parallel search accelerates global exploration and the leader wolf mechanism accelerates local exploration. Furthermore, the GWA optimizes neural network hyperparameters (learning rate, number of layers, number of nodes), weight initialization, and feature selection, thereby improving model performance and generalization. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] The accompanying drawings, which constitute a part of the present disclosure, are used to provide a further understanding of the present disclosure. The exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation to the present disclosure.
[0015] Figure 1 This is a structural diagram of a vehicle electronic shift control system based on multiple sensors and adaptation according to an embodiment of the present disclosure; Figure 2 This is a diagram of the prediction model architecture in the vehicle electronic shift control method based on multiple sensors and adaptation according to an embodiment of the present disclosure; Figure 3 This is a diagram of the implementation process of the vehicle electronic shift control method based on multiple sensors and adaptation according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0016] The present disclosure will be further described below with reference to the accompanying drawings and embodiments.
[0017] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present disclosure belongs.
[0018] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.
[0019] Example 1 In one embodiment of the present disclosure, a vehicle electronic shift control method based on multiple sensors and adaptation is provided, comprising the following steps: Step 1: Obtain the vehicle's multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status, and pre-process them; Step 2: Input the pre-processed vehicle multi-channel ADC voltage signals, shift lever angle signals, and TCU gear position status into the trained and optimized gear position prediction model, and output the target shift lever position; Among them, the gear prediction model is optimized by using the gray wolf group intelligent optimization algorithm, including: setting the gray wolf population size, individual position vector dimension and its feasible solution space boundary, using a uniform distribution strategy to generate the initial population position matrix, inputting the position of the gray wolf individual into the neural network weight matrix, and calculating the fitness; establishing a three-level leadership system and follower group based on the fitness ranking, updating the individual position vector according to the group collaboration mechanism, synchronously adjusting the convergence factor and its related parameters, and performing dimension-by-dimensional out-of-bounds detection on the updated position vector. If there is an out-of-bounds, the upper or lower bound of the gray wolf dimension is set to the out-of-bounds value, and iterating continuously until the conditions are met, and the optimal network parameters of the gear prediction model are output.
[0020] As an embodiment, the disclosed multi-sensor and adaptive vehicle electronic shift control method uses a neural network to automatically learn the complex mapping relationships of multiple source signals, improving robustness in noisy environments. The neural network is optimized using the gray wolf algorithm, which uses the gray wolf's position information as the neural network's weights and thresholds. The gray wolf continuously determines and updates the location of its prey, which is equivalent to continuously updating the neural network's thresholds and weights, achieving high-precision and high-reliability electronic shift control. The specific implementation process is as follows: Step 1: Obtain the vehicle's multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status, and pre-process them; Specifically, configure GPIO and external interrupts, initialize ADC, set reference voltage, sampling time and resolution, start ADC conversion by triggering interrupt, and obtain raw ADC value through polling or DMA; collect shift lever angle signal through 3D Hall sensor and call the TCU gear status of the current transmission control unit.
[0021] Among them, the multi-channel ADC voltage signal is a three-channel ADC voltage signal, including the shift lever contact point voltage; the shift lever angle signal is a shift lever angle signal collected by the 3D Hall sensor, including the X / Y / Z axis angles, which is used to detect the spatial position of the shift lever.
[0022] Furthermore, the vehicle's multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status are subjected to Kalman filtering denoising preprocessing; the preprocessed vehicle multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status are used as inputs to the prediction model, and the output is the shift lever target position signal.
[0023] Step 2: Input the preprocessed vehicle multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status into the trained and optimized gear prediction model, and output the shift lever target position, including: inputting the preprocessed signals into the core processing unit, which is an embedded microcontroller with an integrated ADC module and a CAN communication interface, and an embedded gear prediction algorithm. The gear prediction algorithm processes multiple signals through the gear prediction model and outputs the shift lever target position signal.
[0024] Specifically, the gear prediction model is a neural network architecture, including an input layer, a hidden layer and an output layer. The input layer includes 5 nodes, which correspond to three ADC voltages, the shift lever angle signal and the TCU gear status code; the hidden layer is optimized by the gray wolf group intelligent optimization algorithm, and the parameters are adjusted according to the optimization effect. The output layer has 6 nodes, which are the gear position signals.
[0025] Furthermore, the Grey Wolf Optimizer (GWO) is a swarm intelligence optimization algorithm inspired by the hunting behavior of gray wolf groups in nature. It solves the optimization problem by simulating the social hierarchy and cooperative hunting mechanism of gray wolves. The entire wolf pack is divided into the optimal gray wolf groups according to their fitness values. α , suboptimal gray wolf β , third-best Timberwolves θ and other wolves ω Four levels.
[0026] The gray wolf group intelligent optimization algorithm simulates the gray wolf hunting behavior, which is divided into three stages: ① Tracking and encircling the prey: Approaching the prey and narrowing the encirclement, that is, performing calculations and reasoning based on the relationship between the input three-way ADC voltage signal, the shift lever angle signal, the TCU gear position signal, and the output shift lever target position signal.
[0027] ② Harass the prey: Force the prey to move by constantly adjusting its position, that is, by constantly updating parameters to obtain the optimal solution of input corresponding to output.
[0028] ③ Attack the prey: Attack the prey when it stops moving. This means that after continuously updating the parameters, the output corresponding to the input remains close to the optimal solution.
[0029] Furthermore, the mathematical model of the gray wolf group intelligent optimization algorithm is as follows: ① Gray Wolf position update: (1) (2) in, is the prey position (current optimal solution), 、 is the coefficient vector, controlling exploration and development, t is the current number of iterations, is the distance between the prey and the gray wolf.
[0030] ② The positions of α, β, and δ jointly guide the position updates of other gray wolves: (3) in, = - * , = - * , = - *
[0031] ③ Coefficient vectors A and C (4) (5) in, It decreases linearly from 2 to 0, controlling global search and local development; is a random vector between 0 and 1.
[0032] Furthermore, the specific process of optimizing the neural network by the Grey Wolf Optimizer (GWO) is as follows: A. Parameter initialization phase: Set the size of the gray wolf population N, define the dimension d of the individual position vector and the boundary of its feasible solution space [lb, ub], and determine the maximum evolutionary number T_max. Use a uniform distribution strategy to generate the initial population position matrix X∈R^(N×d); B. Neural Network Parameter Mapping and Fitness Evaluation: The spatial coordinates of the gray wolf individuals are input into the neural network weight matrix. The network output error is calculated through forward propagation, and the fitness is calculated to quantitatively evaluate performance. C. Social hierarchy evolution mechanism: A three-level leadership system of α, β, and δ and a follower group of ω are established based on fitness ranking. The individual position vector is updated according to the group collaboration mechanism described in formula (3), and the convergence factor a and its associated parameters A and C are adjusted synchronously. D. Solution space boundary constraint processing: perform boundary crossing detection on the updated position vector dimension by dimension. If there is any boundary crossing, set the upper or lower bound of the gray wolf dimension to the boundary crossing value. E. Iteration termination judgment: If it is less than the maximum number of iterations, repeat steps B-E and continue to the next iteration until the condition is met; otherwise, end the algorithm.
[0033] The Grey Wolf Optimizer (GWO) algorithm disclosed in the present invention has the advantages of having few parameters, being easy to implement, balancing global exploration and local development capabilities, and having a fast convergence speed.
[0034] The neural network automatically learns the complex mapping relationship of multi-source signals to improve robustness in noisy environments. The neural network is optimized using the gray wolf algorithm, which uses the gray wolf's position information as the weight and threshold of the neural network. The gray wolf continuously judges and updates the position of its prey, which is equivalent to continuously updating the threshold and weight of the neural network. After multiple iterations, the global optimal result is finally calculated and used for parameter training of the neural network.
[0035] Furthermore, the prediction model outputs the gear shift target position, which is combined with the gear position signal to achieve closed-loop feedback to avoid gear shift conflicts. The specific process of achieving closed-loop feedback includes: 1. The input layer integrates the real-time TCU gear status: The TCU current gear signal (such as P / R / N / D) is encoded into a 4-dimensional one-hot vector. Together with the ADC voltage and Hall effect angle, it forms a multi-dimensional input vector for the neural network, enabling the model to dynamically perceive the actual state of the transmission.
[0036] 2. Conflict Detection and Probabilistic Suppression
[0037] Example 2 In one embodiment of the present disclosure, a vehicle electronic shift control system based on multiple sensors and adaptation is provided, comprising: The data acquisition module is used to obtain the vehicle's multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status, and pre-process them; The prediction module is used to input the pre-processed vehicle multi-channel ADC voltage signals, the shift lever angle signal, and the TCU gear position status into the trained and optimized gear position prediction model, and output the target shift lever position; Among them, the gear prediction model is optimized by using the gray wolf group intelligent optimization algorithm, including: setting the gray wolf population size, individual position vector dimension and its feasible solution space boundary, using a uniform distribution strategy to generate the initial population position matrix, inputting the position of the gray wolf individual into the neural network weight matrix, and calculating the fitness; establishing a three-level leadership system and follower group based on the fitness ranking, updating the individual position vector according to the group collaboration mechanism, synchronously adjusting the convergence factor and its related parameters, and performing dimension-by-dimensional out-of-bounds detection on the updated position vector. If there is an out-of-bounds, the upper or lower bound of the gray wolf dimension is set to the out-of-bounds value, and iterating continuously until the conditions are met, and the optimal network parameters of the gear prediction model are output.
[0038] Example 3 In one embodiment of the present disclosure, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the multi-sensor and adaptive based vehicle electronic shift control method is implemented.
[0039] Example 4 In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, which is used to store computer instructions. When the computer instructions are executed by a processor, the multi-sensor and adaptive vehicle electronic shift control method is implemented.
[0040] Example 5 In one embodiment of the present disclosure, an electronic device is provided, comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the multi-sensor and adaptive vehicle electronic shift control method.
[0041] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / 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 flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0042] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0043] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Those skilled in the art should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.
Claims
1. A vehicle electronic shift control method based on multiple sensors and adaptation, characterized in that: include: Obtain the vehicle's multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status, and pre-process them; The pre-processed vehicle multi-channel ADC voltage signal, shift lever angle signal and TCU gear position status are input into the trained and optimized gear position prediction model, and the output is the shift lever target position; Among them, the gear prediction model is optimized by using the gray wolf group intelligent optimization algorithm, including: setting the gray wolf population size, individual position vector dimension and its feasible solution space boundary, using a uniform distribution strategy to generate the initial population position matrix, inputting the position of the gray wolf individual into the neural network weight matrix, and calculating the fitness; establishing a three-level leadership system and follower group based on the fitness ranking, updating the individual position vector according to the group collaboration mechanism, synchronously adjusting the convergence factor and its related parameters, and performing dimension-by-dimensional out-of-bounds detection on the updated position vector. If there is an out-of-bounds, the upper or lower bound of the gray wolf dimension is set to the out-of-bounds value, and iterating continuously until the conditions are met, and the optimal network parameters of the gear prediction model are output.
2. The vehicle electronic shift control method based on multi-sensor and adaptation according to claim 1, characterized in that: Acquire the vehicle's multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status, including: configuring GPIO and external interrupts, initializing the ADC, setting the reference voltage, sampling time, and resolution, starting ADC conversion by triggering interrupts, and obtaining raw ADC values through polling or DMA; using a 3D Hall sensor to collect the shift lever angle signal and retrieve the TCU gear status of the current transmission control unit.
3. The vehicle electronic shift control method based on multi-sensor and adaptation according to claim 1, characterized in that: The preprocessing process includes: using Kalman filtering for denoising and inputting the preprocessed signal into the core processing unit. The core processing unit is an embedded microcontroller with an integrated ADC module and CAN communication interface, and an embedded gear prediction algorithm. The gear prediction algorithm processes multiple signals through a gear prediction model and outputs a gear lever target position signal.
4. The vehicle electronic shift control method based on multi-sensor and adaptation according to claim 1, characterized in that: The gear prediction model is a neural network architecture, consisting of an input layer, a hidden layer, and an output layer. The input layer includes 5 nodes, which correspond to three ADC voltages, the shift lever angle signal, and the TCU gear status code. The hidden layer is optimized using the gray wolf group intelligent optimization algorithm, and the parameters are adjusted according to the optimization effect. The output layer has 6 nodes, which are the gear position signals.
5. The vehicle electronic shift control method based on multi-sensor and adaptation according to claim 1, characterized in that: A three-level leadership system and follower group are established based on fitness ranking, including: the entire wolf pack is divided into four levels according to fitness value: optimal gray wolf, second-best gray wolf, third-best gray wolf and other wolves. The three stages of gray wolf hunting behavior are: ① Tracking and encircling the prey: Approaching the prey and narrowing the encirclement, i.e., performing calculations and reasoning based on the relationship between the input ADC voltage signal, the sensor angle signal, the gear position signal fed back by the TCU, and the output shift lever target position signal; ② Harassing the prey: Forcing the prey to move by constantly adjusting its position, that is, by constantly updating parameters to obtain the optimal solution for the input corresponding to the output; ③ Attack the prey: Attack when the prey stops moving, that is, when the output corresponding to the input is always close to the optimal solution after continuously updating the parameters, output is performed.
6. The vehicle electronic shift control method based on multiple sensors and adaptation as claimed in claim 5, characterized in that: The gray wolf's location information is used as the weight and threshold of the neural network. The gray wolf continuously judges and updates the location of its prey, that is, continuously updates the threshold and weight of the neural network. After multiple iterations, the global optimal result is finally calculated.
7. The vehicle electronic shift control system based on multiple sensors and adaptation is characterized by: include: The data acquisition module is used to obtain the vehicle's multi-channel ADC voltage signals, shift lever angle signals, and TCU gear status, and pre-process them; The prediction module is used to input the pre-processed vehicle multi-channel ADC voltage signals, the shift lever angle signal, and the TCU gear position status into the trained and optimized gear position prediction model, and output the target shift lever position; Among them, the gear prediction model is optimized by using the gray wolf group intelligent optimization algorithm, including: setting the gray wolf population size, individual position vector dimension and its feasible solution space boundary, using a uniform distribution strategy to generate the initial population position matrix, inputting the position of the gray wolf individual into the neural network weight matrix, and calculating the fitness; establishing a three-level leadership system and follower group based on the fitness ranking, updating the individual position vector according to the group collaboration mechanism, synchronously adjusting the convergence factor and its related parameters, and performing dimension-by-dimensional out-of-bounds detection on the updated position vector. If there is an out-of-bounds, the upper or lower bound of the gray wolf dimension is set to the out-of-bounds value, and iterating continuously until the conditions are met, and the optimal network parameters of the gear prediction model are output.
8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the vehicle electronic shift control method based on multiple sensors and adaptation is implemented as described in any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the vehicle electronic shift control method based on multi-sensor and adaptation as described in any one of claims 1 to 6 is implemented.
10. An electronic device, characterized in that: include: A processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the vehicle electronic shift control method based on multi-sensor and adaptation as described in any one of claims 1-6.