Automobile driver vibration comfort evaluation method, equipment, medium and product

Abstract

The invention discloses an automobile driver vibration comfort evaluation method and device, a medium and a product, and relates to the field of driver comfort evaluation, and the method comprises the steps: obtaining electroencephalogram signals of a subject under different working conditions and corresponding comfort overall subjective evaluation scores; the electroencephalogram signals under different working conditions are preprocessed; electroencephalogram signal features of the preprocessed electroencephalogram signals are extracted through wavelet packet transformation; according to the comfort overall subjective evaluation score, performing normalization processing to obtain a questionnaire table; constructing a data set according to the electroencephalogram signal characteristics and the corresponding comfort types under different working conditions; according to the data set, adopting a machine learning model to determine an overall comfort evaluation model; the overall comfort evaluation model is a mapping model between electroencephalogram signal features and subjective evaluation; and according to the overall comfort evaluation model, carrying out vibration comfort evaluation on the automobile driver. According to the invention, deep analysis and comprehensive evaluation of the comfort of the driver in the vibration environment can be realized.

Description

Technical Field

[0001] The present application relates to the field of driver comfort evaluation, and in particular to a method, device, medium and product for evaluating vibration comfort of automobile drivers. Background Art

[0002] Despite the rapid development of the automobile industry, the performance and safety of vehicles have been significantly improved, but the driver's comfort is still an important issue that needs to be addressed. Long-term driving, especially in complex road environments, not only causes visual and auditory fatigue to the driver, but also the impact of vehicle vibration on the body. Vehicle vibration not only affects the driving experience, but also poses a potential threat to the driver's health, such as occupational diseases such as cervical spondylosis and lumbar spondylosis.

[0003] Traditional driver comfort evaluation methods mostly rely on subjective evaluation methods and objective evaluation methods; among them, the subjective evaluation method is based on questionnaires and verbal feedback, and mainly relies on the driver's personal feelings, such as patent CN105334066A; although the subjective evaluation method can directly reflect the driver's real experience during driving, it is highly dependent on individual subjective judgment and is easily affected by various factors such as individual differences, emotional state, and driving experience of the driver, resulting in instability and difficulty in standardization of the evaluation results. In addition, the subjective evaluation method usually lacks objective data support, which makes the accuracy and reliability of the evaluation results questionable, and it is difficult to form a unified and objective evaluation standard, which is not conducive to the quantitative analysis and comparison of driver comfort. In addition, the subjective evaluation method is also affected by environmental conditions, resulting in a lack of accuracy and consistency in the evaluation results, and cannot fully reflect the actual vibration comfort.

[0004] Objective evaluation methods mainly focus on selecting easily accessible surface data, such as the body pressure distribution of the driver (CN209505533U), etc. Objective evaluation methods for vehicle vibration comfort usually use means such as vibration acceleration measurement, vibration spectrum analysis, weighted index method, human dynamics model, and international standards (such as ISO 2631 and VDV method) to quantitatively analyze vehicle vibration in order to objectively and accurately evaluate the impact of vibration on comfort. However, although objective evaluation methods can provide certain objective data support, their evaluation depth is limited and they often cannot fully reflect the true comfort status of the driver during driving. Especially when it comes to complex environmental factors such as vibration and noise, objective evaluation methods are often difficult to accurately evaluate their impact on driver comfort, and thus cannot fully simulate the individual perception differences of drivers, and may ignore the physiological adaptation effects of long-term exposure to vibration. Moreover, in complex driving environments, it is difficult to comprehensively consider the combined effects of multiple factors. In addition, the data collection and processing process of objective evaluation methods may also be restricted by various factors such as equipment accuracy and operation specifications, thus affecting the accuracy and reliability of evaluation results.

[0005] In summary, existing comfort evaluation methods ignore the impact of vehicle vibration on driver comfort, psychological state, and driving experience, and fail to fully reflect real driving scenarios; therefore, there is an urgent need to construct a method that can comprehensively consider dynamic vibration factors during vehicle driving and comprehensively evaluate driver comfort in complex road environments. Summary of the Invention

[0006] The purpose of this application is to provide a method, device, medium, and product for evaluating the vibration comfort of automobile drivers, which can achieve in-depth analysis and comprehensive evaluation of driver comfort in a vibration environment.

[0007] To achieve the above purpose, this application provides the following solutions:

[0008] In the first aspect, this application provides a method for evaluating the vibration comfort of automobile drivers, and the method for evaluating the vibration comfort of automobile drivers includes:

[0009] Obtain the electroencephalogram (EEG) signals of the subject under different working conditions and the corresponding overall subjective evaluation scores of comfort; the different working conditions are determined according to the sine excitation signals with different frequencies and root mean square values of acceleration generated by the test shaker; the overall subjective evaluation score of comfort is the comprehensive score based on the comfort element scores at different levels;

[0010] Preprocess the EEG signals under different working conditions;

[0011] Use wavelet packet transform to extract the EEG signal features of the preprocessed EEG signals;

[0012] According to the overall subjective evaluation score of comfort, a normalization process is performed to obtain a questionnaire table; the questionnaire table is used to characterize the comfort type;

[0013] Construct a data set based on the EEG signal characteristics and corresponding comfort types under different working conditions;

[0014] According to the data set, a machine learning model is used to determine an overall comfort evaluation model; the overall comfort evaluation model is a mapping model between EEG signal features and subjective evaluation;

[0015] The vibration comfort of automobile drivers is evaluated based on the overall comfort evaluation model.

[0016] Optionally, obtaining the EEG signals of the subject under different working conditions and the corresponding overall subjective evaluation scores of comfort specifically includes:

[0017] Obtaining the EEG signals of the subjects under different working conditions;

[0018] The comfort factors are decomposed hierarchically to obtain a hierarchical structure;

[0019] The weight of each comfort factor is determined by using the analytic hierarchy process;

[0020] Obtain the subjective evaluation score table of the subjects under different working conditions;

[0021] According to the subjective evaluation score table and the weight of each comfort factor, the overall subjective evaluation score of comfort is determined.

[0022] Optionally, the preprocessing of the EEG signals under different working conditions specifically includes:

[0023] Remove abnormal segments of EEG signals under different working conditions;

[0024] Filtering the EEG signal after removing the abnormal segments;

[0025] Artifacts are removed from the filtered EEG signal to obtain a preprocessed EEG signal.

[0026] Optionally, the method used for artifact removal is independent component analysis.

[0027] Optionally, the extracting EEG signal features of the preprocessed EEG signal using wavelet packet transform specifically includes:

[0028] Wavelet packet transform is used to extract five rhythmic EEG signals from the preprocessed EEG signals;

[0029] The EEG signal characteristics are determined according to the rhythmic wave EEG signal; the EEG signal characteristics include: energy, energy proportion and power spectrum density of the rhythmic wave EEG signal.

[0030] Optionally, the machine learning model is a LightGBM model.

[0031] Optionally, determining the overall comfort evaluation model according to the dataset by using a machine learning model specifically includes:

[0032] Dividing the dataset into a training set and a test set;

[0033] According to the training set, using a 5-fold cross-validation and grid search method to train the machine learning model to determine the overall comfort evaluation model.

[0034] In a second aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for evaluating the vibration comfort of a vehicle driver.

[0035] In a third aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for evaluating the vibration comfort of a vehicle driver is implemented.

[0036] In a fourth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method for evaluating the vibration comfort of a vehicle driver is implemented.

[0037] According to the specific embodiments provided by the present application, the present application has the following technical effects:

[0038] The present application provides a method, device, medium, and product for evaluating the vibration comfort of a vehicle driver. By obtaining the electroencephalogram signals of the subject under different working conditions and the corresponding overall subjective evaluation scores of comfort, and processing them respectively, a dataset including electroencephalogram signal features and subjective evaluations is constructed; and then, according to the dataset, an overall comfort evaluation model for characterizing the relationship between electroencephalogram signal features and subjective evaluations is established, so as to comprehensively consider the dynamic vibration factors during vehicle driving and comprehensively evaluate the driving comfort of the driver in a complex road environment, realizing in-depth analysis and comprehensive evaluation of the driver's comfort in a vibration environment. Description of the Drawings

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0040] Figure 1Schematic diagram of the process of a method for evaluating the vibration comfort of a vehicle driver in an embodiment of the present application;

[0041] Figure 2 Schematic diagram of the principle of a method for evaluating the vibration comfort of a vehicle driver in an embodiment of the present application;

[0042] Figure 3 Flow chart for objective evaluation;

[0043] Figure 4 Flow chart for subjective evaluation;

[0044] Figure 5 Schematic diagram of the hierarchical structure;

[0045] Figure 6 Schematic diagram of the process for determining the overall comfort evaluation model. Specific embodiments

[0046] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0047] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0048] In an exemplary embodiment, as shown in Figure 1 and Figure 2 a method for evaluating the vibration comfort of a vehicle driver is provided, and the method includes the following S101 to S107. Among them:

[0049] S101, obtaining the electroencephalogram signals of the subject under different working conditions and the corresponding overall subjective evaluation scores of comfort; the different working conditions are determined according to the sine excitation signals with different frequencies and root mean square values of acceleration generated by the test shaker; the overall subjective evaluation score of comfort is the comprehensive score based on the comfort elements of different levels;

[0050] S101 specifically includes:

[0051] S11, obtaining the electroencephalogram signals of the subject under different working conditions;

[0052] As shown in Figure 3As shown in the figure, the shaker generates sinusoidal excitation signals with different frequencies and root mean square values of acceleration. The Semi-Dry EEG device used is worn on the scalp surface of the subject to collect EEG signals. The Semi-Dry EEG device has a high sampling frequency (256 Hz - 1000 Hz) and high resolution (24 Bit), and can record 8 EEG channels in real time. During the test, the subject is required to maintain a stable physiological and psychological state, wear earplugs and install the EEG acquisition device. Before the test starts, start the EEG signal acquisition device, turn on the data acquisition instrument and the PC-side control software. After checking that the working status of each channel is normal, start collecting the EEG signals under various working conditions. The frequency range of the sinusoidal excitation signal is selected as 2 - 15 Hz. Among them, the vibration test interval is 1 Hz for 2 - 4 Hz; the vibration test interval is 0.5 Hz for 4 - 15 Hz. The duration of each group of vibration tests is 10 s, and the interval is 30 s; the selected vibration amplitudes are: 0.02 m / s 2 , 0.05 m / s 2 , 0.1 m / s 2 , 0.2 m / s 2 , 0.3 m / s 2 , 0.4 m / s 2 , 0.5 m / s 2 , 0.6 m / s 2 , 0.7 m / s 2 , 0.8 m / s 2 , 0.9 m / s 2 , 0.1 m / s 2 , 1.5 m / s 2 , 2 m / s 2 , 4 m / s 2 , 6 m / s 2 , 8 m / s 2 , 10 m / s 2 , a total of 414 working conditions (18 amplitudes * 23 frequencies).

[0053] As Figure 4 shown, S12 - S15 is the process of subjective evaluation, which can comprehensively consider the relative importance of various factors, and improve the accuracy and scientificity of evaluation through the combination of subjective judgment and mathematical model.

[0054] S12, hierarchically decompose the comfort factors to obtain the hierarchical structure;

[0055] As Figure 5As shown in the figure, by hierarchically decomposing the comfort factors, a hierarchical structure including different comfort dimensions (such as seat comfort, noise, suspension system, etc.) is constructed; the vehicle vibration comfort is composed of three primary factors: seat comfort, noise level, and suspension system; among them, the seat comfort is further divided into material softness / hardness, lumbar support, and adjustment freedom; these three comfort factors form the secondary factors of the vehicle vibration comfort evaluation hierarchy.

[0056] S13. Use the analytic hierarchy process to determine the weight of each comfort factor.

[0057] The analytic hierarchy process for subjective evaluation scoring of vehicle comfort is a multi-level and multi-criterion decision analysis method. The analytic hierarchy process determines the relative importance weights of various factors through a pairwise comparison matrix. The specific steps are as follows:

[0058] ① Construct a pairwise comparison matrix: First, for the scaling rule, use the 1-9 scaling method to define the relative importance of two comfort factors. Assign a value of 1 when the two factors are equally important, a value of 3 when one factor is slightly more important than the other, a value of 5 when one factor is significantly more important than the other, a value of 7 when one factor is strongly more important than the other, and a value of 9 when one factor is extremely more important than the other. 2, 4, 6, 8 are intermediate values, and their importance levels are also within the assigned range. Then, the specific matrix expression form is as follows: Suppose there are n comfort factors, construct an n×n matrix, A = [a ij , where a ij represents the importance of the i-th factor relative to the j-th factor.

[0059] ② Calculate the weight vector: First, perform normalization processing, that is, normalize each column of the matrix; then, take the row average, that is, take the average value of each row of the normalized matrix to obtain the weight vector.

[0060] ③ Consistency test.

[0061] To better understand the analytic hierarchy process, taking the three primary factors of vehicle vibration comfort as an example, construct a pairwise comparison matrix and calculate the weight vector. The first comfort factor is the suspension system, the second comfort factor is seat comfort, and the third comfort factor is noise level. The first comfort factor, seat comfort, is significantly more important than the second comfort factor, noise level, with an importance assignment of 5. The first comfort factor, seat comfort, is strongly more important than the third comfort factor, noise level, with an importance assignment of 7. The second comfort factor, seat comfort, is slightly more important than the third comfort factor, noise level, with an importance assignment of 3. Therefore, the pairwise comparison matrix is A:

[0062]

[0063] Calculate its weight matrix. First, normalize the pairwise comparison matrix to get B:

[0064]

[0065] According to the above calculation process, it can be determined that the weight of the suspension system is 0.7, the weight of seat comfort is 0.2, and the weight of noise level is 0.1. Similarly, it can be determined that the weights of the secondary comfort factors of material softness / hardness, lumbar support, and adjustment freedom are 0.6, 0.3, and 0.1 respectively. The calculation process of the overall evaluation score of vehicle vibration comfort is described as follows. First, score each bottom-level sub-factor (usually using a 1-10 scale). For example, the material softness / hardness is scored 8 points, the lumbar support is scored 7 points, the adjustment freedom is scored 8 points; the suspension system is scored 9 points; the noise level is scored 7 points.

[0066] The overall score is as follows:

[0067] 0.7×9 + 0.2×(0.6×8 + 0.3×7 + 0.1×8) + 0.1×7 = 9.5;

[0068] S14. Obtain the subjective evaluation score table of the subject under different working conditions; the determination process of the subjective evaluation score table is as follows:

[0069] The test shaker generates sinusoidal excitation signals with different frequencies and root mean square values of acceleration. The tester fills in the overall comfort evaluation score according to his own feelings, and the range is limited between 0-10 points; among them, 0 points means very uncomfortable, 10 points means very comfortable, and the higher the score, the higher the comfort level.

[0070] S15. Determine the overall subjective evaluation score of comfort according to the subjective evaluation score table and the weight of each comfort factor.

[0071] S102. Preprocess the electroencephalogram (EEG) signals under different working conditions;

[0072] S102 specifically includes:

[0073] S21. Remove abnormal segments from the EEG signals under different working conditions;

[0074] As a specific embodiment, abnormal signals such as poor electrode contact or equipment failure are detected manually to avoid interference in analysis and improve accuracy; among them, load the EEG signal and view the time-domain waveforms of each channel, focusing on regions of sudden amplitude change and high-frequency noise. Poor electrode contact is manifested as a sudden decrease or zeroing of the signal amplitude (flat line); equipment interference is manifested as periodic high-frequency noise (such as 50Hz power frequency interference). Manually mark the abnormal time segments and intercept them.

[0075] S22. Filter the EEG signals after removing the abnormal segments;

[0076] As a specific embodiment, noise is removed by low-pass, high-pass, band-pass, and notch filters to retain the useful signals, improve the signal quality, and ensure the effective extraction of electroencephalogram (EEG) activities in specific frequency bands;

[0077] S23, artifact removal is performed on the filtered EEG signals to obtain the preprocessed EEG signals.

[0078] As a specific embodiment, artifacts caused by external factors such as eye movements and electromyograms are identified; among them, algorithms such as Independent Component Analysis (FastICA) are used to remove the artifacts, thereby improving the authenticity of the signals and the accuracy of the analysis results.

[0079] The detailed steps of using the FastICA algorithm to remove eye movement and muscle artifacts are as follows:

[0080] ① Data preprocessing: Remove the mean value of the EEG signals to eliminate baseline shift and achieve centering processing; reduce the data dimension by PCA and eliminate the correlation between channels to accelerate convergence and achieve whitening processing;

[0081] ② FastICA decomposition: First, determine the objective function; FastICA separates the source signals by maximizing the non-Gaussianity of the components (such as negentropy, kurtosis), and then updates the mixing matrix and independent components using the FastICA algorithm until convergence; finally, a series of independent components are obtained, and each component corresponds to a potential source (such as EEG, electrooculogram (EOG), electromyogram (EMG));

[0082] ③ Artifact component identification: Identify the artifact components through the time-domain characteristics of the artifacts (the amplitude of the EOG component suddenly increases and is synchronized with blinking; the EMG component shows high-frequency irregular fluctuations), frequency-domain characteristics (EOG is concentrated in 0.1 - 5 Hz, EMG covers the high-frequency band above 20 Hz), and spatial distribution (EOG has a high weight in the frontal channels; EMG is significant in the temporal or neck channels);

[0083] ④ Artifact removal and signal reconstruction: Set the independent components marked as EOG and EMG to zero, and then perform inverse transformation and reconstruction, that is, use the inverse transformation of the mixing matrix to project the remaining EEG components back to the original channel space to obtain the EEG signals after artifact removal.

[0084] S103, Wavelet packet transform is used to extract the EEG signal features of the preprocessed EEG signals;

[0085] S103 specifically includes:

[0086] S31, Wavelet packet transform is used to extract five rhythm wave EEG signals from the preprocessed EEG signals; the five rhythm wave EEG signals are: delta wave (0.5 - 4 Hz), theta wave (4 - 8 Hz), alpha wave (8 - 12 Hz), beta wave (12 - 30 Hz), gamma wave (30 - 100 Hz);

[0087] S32. Determine the EEG signal characteristics according to the rhythmic EEG signal; the EEG signal characteristics include: the energy, energy proportion, and power spectral density of the rhythmic EEG signal.

[0088] The energy of the rhythmic EEG signal is obtained by summing the squared amplitude values of the discrete points of the five types of rhythmic EEG signals, where n represents the length of the five types of rhythmic EEG signals.

[0089] Among them, use to determine the energy of each rhythmic EEG signal.

[0090] Use the formula E t = E δ + E θ + E α + E β + E γ to determine the total energy E t ;

[0091] Use to determine the energy proportion of each rhythmic EEG signal.

[0092] Use the formula to determine the power spectral density of each rhythmic EEG signal.

[0093] Among them, E is the energy, x represents the amplitude of the rhythmic EEG signal, i represents the i-th rhythmic EEG signal, P represents the energy proportion of the rhythmic EEG signal, X(w) is the discrete Fourier transform of the time-domain signal of the five types of rhythmic EEG signals to obtain the frequency-domain signal, N represents the length of the frequency-domain signal, PSD represents the power spectral density of various rhythmic EEG signals, and the subscripts δ, θ, α, β, and γ respectively represent the δ wave (0.5 - 4 Hz), θ wave (4 - 8 Hz), α wave (8 - 12 Hz), β wave (12 - 30 Hz), and γ wave (30 - 100 Hz).

[0094] S104. According to the overall subjective evaluation score of comfort, perform normalization processing to obtain a questionnaire form; the questionnaire form is used to characterize the comfort type.

[0095] The normalization processing is to reduce the individual differences existing in the subjective scoring and make the results of the overall comfort evaluation model comparable. Specifically, this application proposes a label discretization method based on individual differences, which discretizes the subjective overall comfort score into three different comfort types: comfortable, average, and uncomfortable, and uses a questionnaire form to characterize them. Assume that the overall vibration comfort scores of all testers are 0 - 4 for uncomfortable, 4 - 6 for average, and 6 - 10 for comfortable.

[0096] S105. Construct a dataset according to the EEG signal characteristics and corresponding comfort types under different working conditions;

[0097] S106. According to the dataset, use a machine learning model (ML) to determine the overall comfort evaluation model as shown; the overall comfort evaluation model is a mapping model between EEG signal characteristics and subjective evaluation; Figure 6 The dataset is divided into a training set and a test set, which contain 70% and 30% of the labeled data respectively.

[0098] To solve the time-consuming problem and obtain better performance, the machine learning model in this application uses the LightGBM model for driver vibration comfort;

[0099] Among them, the LightGBM model is a distributed and efficient boosting algorithm that adopts two novel techniques: gradient-based side sampling (GOSS) and exclusive feature bundling (EFB);

[0100] Use 5-fold cross-validation and grid search methods to select the best hyperparameters for each machine learning model. Each model is trained and validated five times with different best hyperparameters. The test set is only used to test the evaluation performance of all models to avoid "data leakage".

[0101] The detailed steps for constructing the LightGBM model are as follows:

[0102] 1) Data preprocessing:

[0103] ① Missing value handling: Eliminate abnormal or missing EEG signal characteristics.

[0104] ② Standardization: Perform Z-score normalization on the EEG signal characteristics to eliminate the dimension difference.

[0105] ③ Label encoding: Convert the classification labels (uncomfortable, average, comfortable) into numerical values (0, 1, 2).

[0106] 2) EEG signal feature optimization:

[0107] Redundancy elimination: Remove highly correlated features through correlation analysis (such as Pearson coefficient) to reduce the risk of overfitting.

[0108] 3) Dataset construction:

[0109] ① Stratified division: Divide the training set and the test set according to a ratio (such as 7:3) to maintain class balance.

[0110] ② Cross-validation: Use 5-fold cross-validation to optimize the hyperparameters and ensure the stability of the model.

[0111] ② Cross-validation: Use 5-fold cross-validation to optimize the hyperparameters and ensure the stability of the model.

[0112] 4) Model construction and training:

[0113] ① Parameter configuration: The objective function is for multi-classification tasks, the number of classes is 3, the learning rate is 0.05, the number of leaves is 31, and the regularization parameter is 0.1.

[0114] ② Class balance: Adjust the sample weights through class_weight to alleviate data skew.

[0115] 5) Hyperparameter tuning:

[0116] ① Bayesian optimization / Grid search: Optimize key parameters (such as the number of leaves, learning rate).

[0117] ② Evaluation metrics: Guided by multi-classification log loss and macro-average F1-score.

[0118] 6) Model evaluation and interpretation:

[0119] ① Performance metrics: Calculate the confusion matrix, accuracy, F1-score, and classification report.

[0120] ② Feature importance: Visualize the contribution of features such as rhythm wave energy / energy ratio / PSD to classification.

[0121] ③ SHAP (SHapley Additive exPlanations) interpretation: Quantify the direction and strength of the impact of each feature on the prediction result (e.g., high theta energy is associated with "comfort").

[0122] 7) Model application:

[0123] ① Deployment for prediction: Encapsulated as an API, input real-time EEG features, and output the comfort state.

[0124] ② Model saving: Persist the trained LightGBM model (in.txt or.pkl format).

[0125] S107 Evaluate the vibration comfort of vehicle drivers according to the overall comfort evaluation model.

[0126] Specifically, obtain the EEG signals of drivers in complex road driving environments, preprocess and extract features from the EEG signals; furthermore, use the overall comfort evaluation model to evaluate the vibration comfort of vehicle drivers.

[0127] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for evaluating the vibration comfort of a vehicle driver.

[0128] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0129] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0130] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0131] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memories (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0132] In the embodiments provided in the present application, the databases involved can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. In the embodiments provided in the present application, the processors involved can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0133] In the present application, all actions of obtaining signals, information, or data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the location is located and obtaining authorization from the owner of the corresponding device.

[0134] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0135] In this text, specific examples are used to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. An evaluation method for the vibration comfort of vehicle drivers, characterized in that, The method for evaluating the vibration comfort of automobile drivers includes: Obtaining the electroencephalogram (EEG) signals of the subjects under different working conditions and the corresponding overall subjective evaluation scores of comfort; the different working conditions are determined according to the sine excitation signals with different frequencies and root mean square values of acceleration generated by the test shaker; the overall subjective evaluation score of comfort is the comprehensive score based on the comfort factor scores at different levels; Preprocessing the EEG signals under different working conditions; Using wavelet packet transform to extract the EEG signal features of the preprocessed EEG signals; Performing normalization processing according to the overall subjective evaluation scores of comfort to obtain a questionnaire; the questionnaire is used to characterize the comfort type; Constructing a data set according to the EEG signal features and the corresponding comfort types under different working conditions; Using a machine learning model according to the data set to determine an overall comfort evaluation model; the overall comfort evaluation model is a mapping model between EEG signal features and subjective evaluations; Performing the evaluation of the vibration comfort of automobile drivers according to the overall comfort evaluation model.

2. The method for evaluating the vibration comfort of a vehicle driver according to claim 1, wherein The obtaining of the EEG signals of the subjects under different working conditions and the corresponding overall subjective evaluation scores of comfort specifically includes: Obtaining the EEG signals of the subjects under different working conditions; Performing hierarchical decomposition on the comfort factors to obtain a hierarchical structure; Using the analytic hierarchy process to determine the weight of each comfort factor; Obtaining the subjective evaluation score table of the subjects under different working conditions; Determining the overall subjective evaluation score of comfort according to the subjective evaluation score table and the weight of each comfort factor.

3. The method for evaluating the vibration comfort of a vehicle driver according to claim 1, characterized in that, The preprocessing of the EEG signals under different working conditions specifically includes: Removing abnormal segments from the EEG signals under different working conditions; Performing filtering processing on the EEG signals after removing abnormal segments; Removing artifacts from the filtered EEG signals to obtain the preprocessed EEG signals.

4. The method for evaluating the vibration comfort of a vehicle driver according to claim 3, characterized in that, The method for removing artifacts is independent component analysis.

5. The method for evaluating the vibration comfort of a vehicle driver according to claim 1, characterized in that, The using of wavelet packet transform to extract the EEG signal features of the preprocessed EEG signals specifically includes: Using wavelet packet transform to extract five rhythm wave EEG signals from the preprocessed EEG signals; Determining the EEG signal features according to the rhythm wave EEG signals; the EEG signal features include: the energy, energy ratio, and power spectral density of the rhythm wave EEG signals.

6. The method for evaluating the vibration comfort of a vehicle driver according to claim 1, wherein, The machine learning model is a LightGBM model.

7. The method for evaluating the vibration comfort of a vehicle driver according to claim 1, wherein, The using of a machine learning model according to the data set to determine an overall comfort evaluation model specifically includes: Dividing the data set into a training set and a test set; Training the machine learning model according to the training set by using 5-fold cross-validation and grid search methods to determine the overall comfort evaluation model.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the method for evaluating the vibration comfort of automobile drivers according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for evaluating the vibration comfort of automobile drivers according to any one of claims 1-7.

10. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for evaluating the vibration comfort of automobile drivers according to any one of claims 1-7.

Images