Terminal protection method and device, vehicle, electronic equipment and storage medium

Abstract

The application discloses a steering system end protection method and device, a vehicle, an electronic device and a storage medium, wherein the end protection method collects motion signals of the vehicle in an end protection state in real time, the motion signals represent the daily driving habits of a user to a certain extent, and end protection parameters are adjusted based on the motion signals, so as to provide the end protection parameters that fit the driving habits of the user. The application proposes an adaptive adjustment method for the end protection parameters, and the flexibility of parameter adjustment is enhanced by adaptively adjusting the end protection parameters.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle steering protection, and in particular to a steering system end protection method and device, a vehicle, an electronic device and a storage medium. BACKGROUND

[0002] End protection can be simply understood as providing a steering buffer effect to slow down the collision between mechanical devices under the steering system when the user turns the steering wheel to the left or right limit.

[0003] For example, in practice, to facilitate the user's flexible and easy operation of the steering wheel, the electric power steering system outputs a power torque when the user operates the steering wheel, and the power torque output by the electric power steering system is reduced when the steering wheel turns to the left or right limit and either end of the steering rack enters the end protection area.

[0004] The current adjustment method of end protection is commonly used as follows: different end protection parameter values are defined for different steering modes during steering adjustment, and the user can manually switch modes to change the end protection effect according to personal preferences during the use of the vehicle.

[0005] However, since the end protection is bound to the steering mode, in order to select the preferred end protection effect, the corresponding other feel parameters must be accepted.

[0006] In addition, since the number of steering modes is limited, it is impossible to achieve stepless adjustment of the end protection, and the user can only choose from the existing options, and the parameters cannot be adapted to the user's preferences. SUMMARY

[0007] Therefore, it is necessary to provide a steering system end protection method, device, vehicle, electronic device and storage medium to realize the adaptive adjustment of the end protection parameter and provide the user with end protection in line with driving habits.

[0008] A steering system end protection method comprises:

[0009] Based on a preset trigger condition, it is determined whether the vehicle enters an end protection state, and the preset trigger condition is set according to a current end protection parameter;

[0010] Collecting a motion signal of the vehicle in the end protection state;

[0011] According to the motion signal, the current end protection parameter is adjusted to update the preset trigger condition.

[0012] In the embodiments of the present application, after collecting the motion signal of the vehicle in the end protection state, the method further comprises:

[0013] The cumulative number of times the vehicle enters end-of-life protection mode;

[0014] The step of adjusting the current end protection parameters based on the motion signal includes:

[0015] If the number of times the vehicle enters the end protection state exceeds a preset threshold, the current end protection parameters are adjusted based on the motion signal collected each time the vehicle enters the end protection state.

[0016] In this embodiment of the application, adjusting the current end-of-life protection parameters based on the motion signal collected each time the vehicle enters the end-of-life protection state includes:

[0017] Based on a pre-trained classification model, the direction is adjusted by predicting parameters according to the motion signals collected each time the vehicle enters the end-of-life protection state.

[0018] Adjust the direction based on the parameters, and adjust the current end protection parameters.

[0019] In this embodiment of the application, adjusting the current end protection parameter based on the parameter adjustment direction includes:

[0020] The current end protection parameters are adjusted according to the preset adjustment step size, preset adjustment range, and parameter adjustment direction.

[0021] In this embodiment of the application, the step of predicting parameters and adjusting the direction based on a pre-trained classification model and the motion signals collected each time the vehicle enters the end-of-life protection state includes:

[0022] The motion signal collected each time the vehicle enters the end protection state is taken as a working condition sample, and the average value of the features under the same latitude in all working condition samples is calculated.

[0023] Based on the mean, a classification model is used to predict the direction of parameter adjustment.

[0024] In this embodiment of the application, the classification model is built based on the support vector machine model and is trained through the following process:

[0025] The training samples corresponding to different working conditions are preprocessed to obtain a sample structure that meets the requirements of the support vector machine model.

[0026] Based on the preprocessed training samples, the support vector machine model is trained to determine the model parameters of the support vector machine model, thereby determining the candidate classification model;

[0027] Based on the model evaluation metrics, the candidate classification models that meet the criteria are selected as the trained classification models from all the candidate classification models.

[0028] A steering system end protection device, comprising:

[0029] The judgment module is used to determine whether the vehicle has entered the end protection state based on a preset trigger condition, wherein the preset trigger condition is set according to the current end protection parameters;

[0030] The acquisition module is used to acquire the motion signals of vehicles under end-of-life protection conditions.

[0031] The adjustment module is used to adjust the current end protection parameters according to the motion signal in order to update the preset triggering conditions.

[0032] In this embodiment of the application, the device further includes a counting module, used for:

[0033] The cumulative number of times the vehicle enters end-of-life protection mode;

[0034] The adjustment module is further used for:

[0035] If the number of times the vehicle enters the end protection state exceeds a preset threshold, the current end protection parameters are adjusted based on the motion signal collected each time the vehicle enters the end protection state.

[0036] In this embodiment of the application, the adjustment module is further used for:

[0037] Based on a pre-trained classification model, the direction is adjusted by predicting parameters according to the motion signals collected each time the vehicle enters the end-of-life protection state.

[0038] Adjust the direction based on the parameters, and adjust the current end protection parameters.

[0039] In this embodiment of the application, the adjustment module is further used for:

[0040] The current end protection parameters are adjusted according to the preset adjustment step size, preset adjustment range, and parameter adjustment direction.

[0041] In this embodiment of the application, the adjustment module is further used for:

[0042] The motion signal collected each time the vehicle enters the end protection state is taken as a working condition sample, and the average value of the features under the same latitude in all working condition samples is calculated.

[0043] Based on the mean, a classification model is used to predict the direction of parameter adjustment.

[0044] In this embodiment, the classification model is built based on a support vector machine model, and the apparatus further includes a model training module for training the classification model through the following process:

[0045] The training samples corresponding to different working conditions are preprocessed to obtain a sample structure that meets the requirements of the support vector machine model.

[0046] Based on the preprocessed training samples, the support vector machine model is trained to determine the model parameters of the support vector machine model, thereby determining the candidate classification model;

[0047] Based on the model evaluation metrics, the candidate classification models that meet the criteria are selected as the trained classification models from all the candidate classification models.

[0048] A vehicle, characterized in that it includes: the aforementioned steering system end protection device.

[0049] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the steering system end protection method described above.

[0050] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the steering system end protection method described above.

[0051] In summary, this application proposes a steering system end-of-life protection method, device, vehicle, electronic device, and storage medium. The end-of-life protection method involves real-time acquisition of vehicle motion signals during end-of-life protection. These motion signals, to some extent, characterize the user's daily driving habits, such as the speed of steering wheel rotation. End-of-life protection parameters are adjusted based on these motion signals to provide end-of-life protection tailored to the user's driving habits. This application proposes an adaptive adjustment method for end-of-life protection parameters, enhancing the flexibility of parameter adjustment through adaptive adjustment. Attached Figure Description

[0052] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart illustrating an end-of-steering system protection method according to an exemplary embodiment of this application;

[0054] Figure 2 This is a flowchart illustrating a steering system end protection method according to another exemplary embodiment of this application;

[0055] Figure 3 This is a flowchart illustrating a steering system end protection method according to another exemplary embodiment of this application;

[0056] Figure 4 This is a flowchart illustrating the classification model training in a steering system end protection method according to another exemplary embodiment of this application;

[0057] Figure 5 This is an exemplary schematic diagram illustrating the use of the 3σ detection method to eliminate outliers in a steering system end protection method according to another exemplary embodiment of this application;

[0058] Figure 6 This is an exemplary schematic diagram illustrating tree model feature selection in a steering system end protection method according to another exemplary embodiment of this application;

[0059] Figure 7 This is a schematic diagram comparing the predicted label and the actual label of a test sample in a steering system end protection method according to another exemplary embodiment of this application;

[0060] Figure 8 This is a schematic diagram of the confusion matrix of a test sample in a steering system end protection method according to another exemplary embodiment of this application;

[0061] Figure 9 This is an overall flowchart illustrating the classification model training in a steering system end protection method according to another exemplary embodiment of this application;

[0062] Figure 10 This is a block diagram illustrating a steering system end protection device according to an exemplary embodiment of this application;

[0063] Figure 11 This is a vehicle block diagram illustrated according to an exemplary embodiment of this application;

[0064] Figure 12 This is a schematic diagram of an electronic device structure according to an exemplary embodiment of this application. Detailed Implementation

[0065] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. The embodiments described with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0066] Figure 1 This is a flowchart illustrating an end-of-steering system protection method according to an exemplary embodiment of this application, such as... Figure 1 As shown, the steering system end protection method includes the following steps:

[0067] S101 determines whether the vehicle has entered the end protection state based on preset trigger conditions. The preset trigger conditions are set according to the current end protection parameters.

[0068] This application pre-sets trigger conditions for sampling the vehicle's operating conditions. These trigger conditions include a judgment value, which determines whether the vehicle has entered an end-of-life protection state. It's easy to understand that when a user turns the steering wheel, the steering wheel drives the rack to move left and right. When the steering wheel angle enters the judgment range corresponding to the maximum steering wheel rotation angle (this judgment range can be understood as the angle between a certain angle near the steering wheel's limit angle and the maximum steering wheel rotation angle; the aforementioned "certain angle" can be understood as the value at the beginning of the judgment range, i.e., the judgment value), one end of the rack will enter the end-of-life protection range, and the vehicle will be in an end-of-life protection state. In this state, the electric power steering torque is reduced to decrease the steering wheel's turning flexibility, allowing the user to feel resistance when turning the steering wheel, thus reminding the user that the steering wheel is about to reach its limit. This also slows down the steering wheel's rotation speed, slows down the rack's movement speed, and reduces mechanical collisions, achieving the purpose of end-of-life protection.

[0069] Among them, the end protection parameters are used to limit the end protection range. Therefore, the above-mentioned preset triggering conditions can be determined based on the current end protection parameters.

[0070] The end protection parameter can be a parameter corresponding to the rack, such as the position or distance parameter of the rack when it enters the starting end of the end protection range. In this case, the judgment value in the preset trigger condition can be the steering wheel rotation angle corresponding to when the rack enters the end protection range defined by the end protection parameter.

[0071] The end-of-life protection parameter can also be directly set to the steering wheel angle. In this case, the end-of-life protection parameter can be set to the judgment value in the preset trigger conditions.

[0072] In some embodiments, the steering wheel angle can be acquired in real time to determine whether the steering wheel angle exceeds a threshold. If the angle exceeds the threshold, the vehicle is considered to have entered the end-of-life protection state; if the angle does not exceed the threshold, the vehicle is considered not to be in the end-of-life protection state.

[0073] S102, collects the vehicle's motion signal under end protection status.

[0074] Real-time acquisition of vehicle motion signals during end-of-life protection can be understood as acquiring the vehicle's motion signals during the process from when the steering wheel enters the end of the rack to when it leaves the end of the rack, or it can be understood as acquiring the vehicle's motion signals during the process from when one end of the rack enters the end-of-life protection range to when that end leaves the end-of-life protection range. The motion signals can be acquired through sensors or other devices, and this application does not impose any limitations on this method.

[0075] In some embodiments, the motion signal can be a motion signal on the vehicle that represents the user's driving habits. For example, the motion signal may include, but is not limited to, vehicle speed signal and steering wheel rotation signal; the steering wheel rotation signal may include, but is not limited to, steering wheel angle signal, steering wheel speed signal and steering wheel torque signal.

[0076] By analyzing vehicle speed and steering wheel angle signals, it is possible to determine the driver's driving habits, such as the speed and force with which the steering wheel is turned at different speeds, including the speed and force required to "lock" the steering wheel.

[0077] S103, adjust the current end protection parameters according to the motion signal to update the preset trigger conditions.

[0078] Based on the vehicle's motion signals during end-of-life protection, the current end-of-life protection parameters are adjusted. Based on these adjusted parameters, the judgment values ​​in the preset trigger conditions are adjusted to update the preset trigger conditions. This allows for real-time determination of whether the vehicle has entered end-of-life protection mode based on the updated preset trigger conditions. This achieves the goal of adjusting end-of-life protection parameters according to the user's driving habits, providing end-of-life protection tailored to their driving style and offering a better driving experience.

[0079] For example, the following effects can be achieved: For drivers who turn the steering wheel quickly and with considerable force when turning it to its left or right limits, the end-of-range protection parameters can be reduced to allow for more flexible steering wheel operation. For drivers who turn the steering wheel slowly and with less force, the end-of-range protection parameters can be increased to expand the end-of-range protection range and better protect the mechanical components under the steering system.

[0080] In summary, the steering system end-of-life protection method provided in this application collects vehicle motion signals in real time during the end-of-life protection state. These motion signals, to a certain extent, characterize the user's daily driving habits, such as the speed of steering wheel rotation. End-of-life protection parameters are adjusted based on these motion signals to provide end-of-life protection tailored to the user's driving habits. This application proposes an adaptive adjustment method for end-of-life protection parameters, which enhances the flexibility of parameter adjustment.

[0081] Based on the above embodiments, this application embodiment further includes the following step after "collecting the vehicle's motion signal under the end protection state" in step S102: accumulating the number of times the vehicle enters the end protection state.

[0082] Correspondingly, step S103 "adjusting the current end protection parameters according to the motion signal" in the above embodiment may further include the following steps:

[0083] If the number of times a vehicle enters the end protection state exceeds a preset threshold, the current end protection parameters are adjusted based on the motion signals collected each time the vehicle enters the end protection state.

[0084] In this embodiment of the application, the aforementioned preset threshold can be understood as the threshold for entering the "adjust current end protection parameters" step.

[0085] During the process of a vehicle entering and leaving the end protection state, the vehicle's motion signal is collected. After the collection is completed, the number of times the vehicle enters the end protection state can be accumulated by adding one to the total number of times the vehicle enters the end protection state. When the number of times the vehicle enters the end protection state exceeds a preset threshold, the adjustment of the current end protection parameters is initiated.

[0086] This application uses the aforementioned preset threshold to constrain the number of times the end protection parameters are adjusted, thereby reducing workload and pressure on the vehicle's computing and control units. At the same time, based on the limitation of the aforementioned preset threshold, multiple sets of motion signals can be accumulated from multiple end protection states and used as multiple operating condition samples. Based on multiple operating condition samples, the user's driving habits can be better analyzed, thereby enhancing the effectiveness of adjusting the end protection parameters.

[0087] Based on the above embodiments, such as Figure 2 As shown, in the above embodiment, "adjusting the current end-of-life protection parameters based on the motion signals collected each time the vehicle enters the end-of-life protection state" further includes the following steps:

[0088] S201, based on a pre-trained classification model, predicts parameters and adjusts the direction according to the motion signals collected each time the vehicle enters the end-of-life protection state.

[0089] Using a pre-trained classification model, the direction of parameter adjustment is predicted based on the motion signals collected each time the vehicle enters the end-of-life protection state.

[0090] For example, the classification model predicts classification labels based on the motion signals collected each time the vehicle enters the end-of-life protection state: 1 indicates a decrease in the current end-of-life protection parameters, 2 indicates maintaining the current end-of-life protection parameters, and 3 indicates an increase in the current end-of-life protection parameters. The direction of parameter adjustment is determined based on these labels.

[0091] S202, Adjust the current end protection parameters based on parameter adjustment direction.

[0092] This application uses a classification model to process the features of collected motion signals and predict the adjustment direction. It achieves this by analyzing and predicting the driver's driving habits based on the motion signals of the vehicle each time it enters the end-of-life protection state, thereby obtaining an end-of-life protection parameter adjustment direction that aligns with those habits. The embodiments of this application utilize a classification model to categorize user preferences under the current end-of-life protection parameters, thereby achieving directional adaptive adjustment of the end-of-life protection parameters and enhancing the flexibility of end-of-life protection.

[0093] Furthermore, the current end protection parameters are adjusted according to the preset adjustment step size, preset adjustment range, and parameter adjustment direction.

[0094] When the parameter adjustment direction is to increase or decrease the current end protection parameter, one or more adjustment steps are increased or decreased based on the current end protection parameter according to a preset adjustment step size. Adjusting the end protection parameter based on the adjustment step size enhances the adjustment efficiency of the end protection parameter. The adjustment step size and preset adjustment range can be set as needed, and this application does not impose any limitations on them.

[0095] In this embodiment of the application, the adjusted end protection parameters should not exceed the preset adjustment range. The preset adjustment range is the maximum range that the end protection parameters can be adjusted. By setting this adjustment range, the minimum conversion diameter of the vehicle is not sacrificed when adjusting the end protection parameters, or the end protection parameters are not lost after adjustment.

[0096] Based on the above embodiments, such as Figure 3 As shown, step S201 above, "based on the pre-trained classification model, predicting parameters and adjusting the direction according to the motion signals collected each time the vehicle enters the end-of-life protection state," further includes the following steps:

[0097] S301 will collect motion signals as a working condition sample each time the vehicle enters the end protection state, and calculate the average value of the features at the same latitude in all working condition samples.

[0098] Taking the motion signal, which includes vehicle speed signal, steering wheel angle signal, steering wheel speed signal and steering wheel torque signal, as an example, the motion signal collected by the vehicle during each process from entering the end protection state to the end of the end protection state is taken as a working condition sample. Each working condition sample may include features corresponding to vehicle speed, steering wheel angle, steering wheel speed and steering wheel torque.

[0099] As a feasible implementation method, the average vehicle speed under the end-of-life protection state is obtained based on the vehicle speed signal; the maximum steering wheel angle under the end-of-life protection state is obtained based on the steering wheel angle signal; the maximum steering wheel speed under the end-of-life protection state is obtained based on the steering wheel speed; and the maximum steering wheel torque under the end-of-life protection state is obtained based on the steering wheel torque. The maximum steering wheel angle, maximum steering wheel speed, maximum steering wheel torque, and average vehicle speed are used as features of the operating condition sample.

[0100] When initiating an adjustment of the end-of-line protection parameters, the direction of the adjustment is predicted using all operating condition samples collected under the current end-of-line protection state corresponding to the current end-of-line protection parameters. The average value of the features of the same dimension in all the above operating condition samples is calculated.

[0101] S302, based on the mean, uses a classification model to predict parameters and adjust the direction.

[0102] In the embodiments of this application, the above classification model is constructed using support vector machines (SVM). Support vector machines (SVM) are a binary classification model, and their basic model is a linear classifier with the largest margin defined on the feature space.

[0103] The mean is predicted using a classification model based on SVM to obtain the classification result, which is the direction of adjustment of the end protection parameter. Then, the current end protection parameter is adjusted to increase, decrease, or remain unchanged based on the classification result.

[0104] Based on the above embodiments, such as Figure 4 As shown, the classification model is trained through the following process in the embodiments of this application.

[0105] S401 preprocesses the training samples corresponding to different working conditions to obtain a sample structure that meets the requirements of the support vector machine model.

[0106] The construction and training of the classification model can be carried out during the research and development stage. At this stage, different triggering conditions can be set according to different end protection parameters, and data from various working conditions can be automatically sampled to obtain training samples corresponding to different working conditions, which can be used as the original material for model training.

[0107] Before training begins, the samples are preprocessed, which may include steps such as cleaning up missing rows and eliminating outliers.

[0108] In some embodiments, outlier elimination can be achieved using methods such as 3σ detection. Figure 5 This is an exemplary schematic diagram illustrating the use of the 3σ detection method to eliminate outliers.

[0109] In some embodiments, to obtain a sample structure that meets the requirements of the Support Vector Machine (SVM) model, dimensionality reduction of the sample features is necessary. For example, a tree-based feature selection algorithm can be used to process and select features from the original data, thereby forming the sample structure required for solving the SVM model. Figure 6 An exemplary diagram illustrating the selection of features for a tree model.

[0110] S402, Based on the preprocessed training samples, train the support vector machine model, determine the model parameters of the support vector machine model, and thus determine the candidate classification model.

[0111] Using training samples and their labels, an SVM model is trained to learn the classification of the direction of end-protection parameter adjustment. The model parameters are solved in the function space to determine the candidate classification model.

[0112] Furthermore, to improve classification accuracy, optimization algorithms can be used to further optimize the model parameters. The Gorilla Optimization (GTO) algorithm can be selected as an optimization algorithm.

[0113] S403: Select qualified candidate classification models from all candidate classification models based on model evaluation metrics as trained classification models.

[0114] Calculate the model evaluation index of the candidate classification model, such as the value of the index AUC, to evaluate the classification performance of the candidate classification model. The classification model that meets the index among all classification models is selected as the trained classification model.

[0115] For example, by using the Gorilla Optimization Algorithm to iteratively optimize model parameters, the AUC value of the model can be calculated after each round of optimization. The AUC value is then compared with a preset AUC threshold to determine whether the model's classification accuracy meets the requirements. If the requirements are not met, the hyperparameters of the Gorilla Optimization Algorithm are readjusted, and parameter optimization continues. The hyperparameters may include, but are not limited to, the population size and the number of evolutions. If the requirements are met, the iteration is terminated.

[0116] In some embodiments, when it is necessary to check the performance of the classification model during model training and model evaluation, the predicted labels of the samples can be visually compared with the true labels, or the classification performance can be visualized using a confusion matrix, to help developers judge the quality of the classification model.

[0117] For example, the selected classification model can be tested using test samples: the selected classification model is used to predict labels on the test samples, and the predicted labels are compared with the true labels of the test samples to intuitively judge the performance of the classification model. Figure 7The image shows a comparison between the predicted and true labels of the test samples. Furthermore, the prediction results for the test samples can be visualized using a confusion matrix (e.g., ...). Figure 8 The diagram shows the confusion matrix corresponding to the test samples. The diagram shows the number of true classes and the number of predicted classes, as well as the precision and recall corresponding to the test samples, to help developers judge the quality of the output model.

[0118] This application obtains the final classification model through the above training process, and then implants the classification model into mass-produced vehicles. This allows the vehicles to perform end-of-life protection self-adjustment based on the model after collecting samples of the user's daily driving conditions. This further enables "unobtrusive" self-adjustment during user operation, subtly adjusting the end-of-life protection parameters to the user's desired effect.

[0119] To clearly illustrate the classification model training process in the end-protection method proposed in this application, the following is combined with... Figure 9 An exemplary description of the overall process is provided. Figure 9 This is a flowchart for training a classification model.

[0120] S901 sets the judgment value in the trigger condition based on the factory-set end protection value; sets two boundary values ​​for the adjustment range of the end protection parameters; and sets the AUC threshold.

[0121] S902, based on the triggering condition, determine whether the vehicle has entered the end protection state; if yes, proceed to step S903; otherwise, return to step S901.

[0122] S903 collects the vehicle's motion signal under the end protection state, and records the maximum steering wheel angle, maximum speed, maximum torque and average vehicle speed under the end protection state corresponding to the current end protection parameters based on the collected motion signal, and uses it as a set of data samples to obtain multiple sets of data samples.

[0123] S904 performs preprocessing on multiple sets of data samples.

[0124] S905 is a classification model built on the SVM model, which uses preprocessed multi-group sample data to train the model parameters.

[0125] S906 uses the Gorilla Optimization algorithm to optimize model parameters.

[0126] S907, calculate the AUC value of the model after parameter optimization.

[0127] S908, determine whether the AUC value exceeds the AUC threshold; if yes, proceed to step S910, otherwise proceed to step S909.

[0128] S909, adjust the population size and evolution number in the gorilla optimization algorithm, and return to step S906.

[0129] S910, classifying models whose AUC values ​​exceed the AUC threshold are identified as well-trained classification models.

[0130] In summary, this application collects vehicle motion signals in real time during end-of-life protection. These motion signals, to some extent, characterize the user's daily driving habits, such as the speed of steering wheel rotation. End-of-life protection parameters are adjusted based on these motion signals to provide users with end-of-life protection tailored to their driving habits. The adaptive adjustment method for end-of-life protection parameters proposed in this application predicts the adjustment direction of the parameters using a trained classification model. This allows for self-calibration of parameters after mass production, enhancing the flexibility and efficiency of parameter adjustment. Predicting the adjustment direction based on motion signals under different operating conditions makes the adjustment of end-of-life protection parameters more consistent with individual users' daily driving habits, enabling adaptive adjustments for each user and enhancing the user's experience in vehicle steering.

[0131] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0132] Figure 10 This is a block diagram illustrating an end-of-steering system protection device according to an exemplary embodiment of this application, such as... Figure 10 As shown, the device 1000 includes: a judgment module 1001, a data acquisition module 1002, and an adjustment module 1003.

[0133] The judgment module 1001 is used to determine whether the vehicle has entered the end protection state based on preset trigger conditions. The preset trigger conditions are set according to the current end protection parameters.

[0134] Acquisition module 1002 is used to acquire vehicle motion signals under end protection conditions;

[0135] The adjustment module 1003 is used to adjust the current end protection parameters according to the motion signal in order to update the preset triggering conditions.

[0136] In this embodiment of the application, the device further includes a counting module, used for:

[0137] The cumulative number of times the vehicle enters end-of-life protection mode;

[0138] Adjust the module for further use in:

[0139] If the number of times a vehicle enters the end protection state exceeds a preset threshold, the current end protection parameters are adjusted based on the motion signals collected each time the vehicle enters the end protection state.

[0140] In this embodiment of the application, the adjustment module is further used for:

[0141] Based on a pre-trained classification model, the direction is adjusted by predicting parameters according to the motion signals collected each time the vehicle enters the end-of-life protection state.

[0142] Adjust the current end protection parameters based on the parameter adjustment direction.

[0143] In this embodiment of the application, the adjustment module is further used for:

[0144] Adjust the current end protection parameters according to the preset adjustment step size, preset adjustment range, and parameter adjustment direction.

[0145] In this embodiment of the application, the adjustment module is further used for:

[0146] The motion signal collected each time the vehicle enters the end protection state is taken as a working condition sample, and the average value of the features at the same latitude in all working condition samples is calculated.

[0147] Based on the mean, the direction is adjusted by predicting parameters using a classification model.

[0148] In this embodiment, the classification model is built based on a support vector machine model, and the device further includes a model training module for training the classification model through the following process:

[0149] The training samples corresponding to different working conditions are preprocessed to obtain a sample structure that meets the requirements of the support vector machine model.

[0150] Based on the preprocessed training samples, the support vector machine model is trained to determine the model parameters of the support vector machine model, thereby determining the candidate classification model;

[0151] Based on the model evaluation metrics, select qualified candidate classification models from all candidate classification models as the trained classification models.

[0152] In summary, the steering system end-of-life protection device of this application collects vehicle motion signals in real time during end-of-life protection. These motion signals, to a certain extent, characterize the user's daily driving habits, such as the speed of steering wheel rotation. End-of-life protection parameters are adjusted based on these motion signals to provide end-of-life protection tailored to the user's driving habits. By using a trained classification model to predict the adjustment direction of the end-of-life protection parameters, self-adjusting parameter calibration can be achieved after mass production of the vehicle, enhancing the flexibility and efficiency of parameter adjustment. Predicting the parameter adjustment direction based on motion signals under different operating conditions makes the adjustment of end-of-life protection parameters more consistent with the individual user's daily driving habits, enabling adaptive adjustments for each user and enhancing the user's steering experience while driving.

[0153] To achieve the above embodiments, this application also proposes a vehicle 1100, which is equipped with the above-mentioned steering system end protection device 1000.

[0154] In summary, the vehicle proposed in this application's embodiments collects motion signals of the vehicle in real time during end-of-life protection. These motion signals, to a certain extent, characterize the user's daily driving habits, such as the speed of steering wheel rotation. End-of-life protection parameters are adjusted based on these motion signals to provide end-of-life protection tailored to the user's driving habits. This application uses a trained classification model to predict the adjustment direction of end-of-life protection parameters, enabling self-calibration of parameters after mass production, enhancing the flexibility and efficiency of parameter adjustment. Predicting the adjustment direction based on motion signals under different operating conditions makes the adjustment of end-of-life protection parameters more consistent with the individual user's daily driving habits, allowing for adaptive adjustments for each user and enhancing the user's experience in vehicle steering.

[0155] To implement the above embodiments, this application also proposes an electronic device 1200, such as... Figure 12 As shown, the electronic device 1200 may specifically include: a memory 1201, a processor 1202, and a computer program stored on the memory 1201 and executable on the processor 1202. When the processor 1202 executes the program, it implements the steps of the end protection method for the steering system as described in the above embodiment.

[0156] In summary, this application proposes an electronic device that collects motion signals of a vehicle in real time during end-of-life protection. These motion signals, to some extent, characterize the user's daily driving habits, such as the speed of steering wheel rotation. End-of-life protection parameters are adjusted based on these motion signals to provide end-of-life protection tailored to the user's driving habits. This application uses a trained classification model to predict the adjustment direction of end-of-life protection parameters, enabling self-calibration of parameters after mass production, thus enhancing the flexibility and efficiency of parameter adjustment. Predicting the adjustment direction based on motion signals under different operating conditions makes the adjustment of end-of-life protection parameters more consistent with the individual user's daily driving habits, allowing for adaptive adjustments for each user and enhancing the user's experience in vehicle steering.

[0157] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0158] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0159] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for end-of-steering system protection, characterized in that, include: Based on preset trigger conditions, it is determined whether the vehicle has entered the end protection state. The preset trigger conditions are set according to the current end protection parameters. Collect vehicle motion signals under end-of-life protection conditions; Based on the motion signal, adjust the current end protection parameters to update the preset triggering conditions; After acquiring the vehicle's motion signal under the end-protection state, the method further includes: The cumulative number of times the vehicle enters end-of-life protection mode; The step of adjusting the current end protection parameters based on the motion signal includes: If the number of times the vehicle enters the end protection state exceeds a preset threshold, the current end protection parameters are adjusted based on the motion signal collected each time the vehicle enters the end protection state.

2. The method according to claim 1, characterized in that, The step of adjusting the current end-of-life protection parameters based on the motion signals collected each time the vehicle enters the end-of-life protection state includes: Based on a pre-trained classification model, the direction is adjusted by predicting parameters according to the motion signals collected each time the vehicle enters the end-of-life protection state. Adjust the direction based on the parameters, and adjust the current end protection parameters.

3. The method according to claim 2, characterized in that, The adjustment of the current end protection parameters based on the parameter adjustment direction includes: The current end protection parameters are adjusted according to the preset adjustment step size, preset adjustment range, and parameter adjustment direction.

4. The method according to claim 2, characterized in that, The method of adjusting the direction based on the pre-trained classification model and the motion signals collected each time the vehicle enters the end-of-life protection state includes: The motion signal collected each time the vehicle enters the end protection state is taken as a working condition sample, and the average value of the features at the same latitude in all the working condition samples is calculated. Based on the mean, a classification model is used to predict the direction of parameter adjustment.

5. The method according to claim 2, characterized in that, The classification model is built based on the support vector machine model and is trained through the following process: The training samples corresponding to different working conditions are preprocessed to obtain a sample structure that meets the requirements of the support vector machine model. Based on the preprocessed training samples, the support vector machine model is trained to determine the model parameters of the support vector machine model, thereby determining the candidate classification model; Based on the model evaluation metrics, the candidate classification models that meet the criteria are selected from all the candidate classification models as the trained classification models.

6. A steering system end protection device, characterized in that, include: The judgment module is used to determine whether the vehicle has entered the end protection state based on a preset trigger condition, wherein the preset trigger condition is set according to the current end protection parameters; The acquisition module is used to acquire the motion signals of vehicles under end-of-life protection conditions. An adjustment module is used to adjust the current end protection parameters according to the motion signal in order to update the preset triggering conditions; The device also includes a counting module, used to: after collecting the vehicle's motion signal in the end protection state, accumulate the number of times the vehicle enters the end protection state; The adjustment module is further configured to: adjust the current end protection parameters based on the motion signal collected each time the vehicle enters the end protection state, in response to the number of times the vehicle enters the end protection state exceeding a preset threshold.

7. A vehicle, characterized in that, include: The end protection device as described in claim 6.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the steering system end protection method as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the steps of the steering system end protection method as described in any one of claims 1-5.

Images