Automobile ride comfort evaluation method and device, computer device and storage medium

Abstract

The application relates to a vehicle ride comfort evaluation method and device, computer equipment, a storage medium and a computer program product. A test database is acquired. Data in the test database is filtered to obtain target data. The effectiveness index and the repeatability index of the target data are calculated. In the case where the effectiveness index and the repeatability index of the target data both meet preset conditions, the test type corresponding to each target data in the evaluation database is determined. The evaluation index of a vehicle to be evaluated is calculated according to the test type, and the evaluation result of the vehicle to be evaluated is determined. Through preprocessing of the test data of the vehicle to be evaluated, the availability and accuracy of the test data are improved. The test type identification model is trained by using a database generated by a large number of historical tests, the test type of the test data of the vehicle to be evaluated is automatically determined, and then the evaluation index of the vehicle to be evaluated is calculated, so that the efficiency of the evaluation index calculation and the accuracy of the obtained evaluation result are improved.

Description

Technical Field

[0001] This application relates to the field of ride comfort testing technology, and in particular to a method, apparatus, computer equipment, storage medium and computer program product for evaluating vehicle ride comfort. Background Technology

[0002] Automotive testing plays a crucial role in the automotive development process, permeating the entire process. Whether designing a new model or producing a product already in production, automotive testing is essential. Through numerous rigorous vehicle performance tests, the rationality of the vehicle design can be verified, problems can be analyzed and improved, and through multiple iterations, vehicle performance can be ensured to meet design requirements. Furthermore, it provides a basis for mass production by conducting type approval tests on new models, and it accumulates a wealth of automotive technical parameters, providing theoretical support and practical guidance for new model design and product improvement. Automotive testing is a vital means of ensuring product performance, improving product quality, and enhancing market competitiveness. Ride comfort, as one of the important factors affecting driving comfort, directly impacts the user's driving experience.

[0003] In related technologies, test data is manually input and processed based on the type of test data selected by the user to determine the vehicle's ride comfort assessment results. However, because the test data is manually input and directly used in the ride comfort assessment, the accuracy of the assessment results can be affected. Furthermore, the human judgment in determining the type of test data is highly subjective, impacting the objectivity and reliability of the assessment results. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can quickly and accurately evaluate vehicle ride comfort in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for evaluating vehicle ride comfort. The method includes:

[0006] Obtain the test database generated from the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data obtained through all test channels.

[0007] The test data obtained through each test channel is filtered to obtain the target data for each test channel;

[0008] Calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, construct an evaluation database of the vehicle to be evaluated based on the target data.

[0009] Input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each channel in the evaluation database.

[0010] The evaluation indicators for the vehicle to be evaluated are calculated based on the test type, and the evaluation results of the vehicle to be evaluated are determined based on the evaluation indicators.

[0011] In one embodiment, the test data acquired by the test channel has a corresponding test vehicle speed, and the test data acquired by each test channel at each test vehicle speed is taken as a set of test data; accordingly, the test data acquired through each test channel is filtered to obtain the target data of each test channel, including:

[0012] The filtering order of each set of test data in the experimental database is determined according to the preset order;

[0013] Based on the filtering order of each set of test data, all test data are filtered sequentially to obtain the target data for each set of test data.

[0014] Among them, filtering refers to performing outlier removal and noise filtering on any set of test data in the experimental database in sequence.

[0015] In one embodiment, the preset order includes a preset channel order and a preset test speed order; correspondingly, based on the preset order, the filtering order of each set of test data in the test database is determined, including:

[0016] Test data corresponding to the same test speed are treated as a single dataset. All datasets are sorted according to a preset test speed order to obtain the first sorting result.

[0017] For any dataset, sort all test data in any dataset according to the preset channel order to obtain a second sorting result;

[0018] Based on the first and second sorting results, the filtering order of each group of test data in the experimental database is determined.

[0019] In one embodiment, the repeatability index of the target data for each test channel is calculated, including:

[0020] For any set of test data for each test channel, calculate the peak factor of each test data in the set of test data;

[0021] Calculate the difference between the maximum and minimum values ​​of all peak factors, and use the difference as a repeatability indicator for any set of test data.

[0022] In one embodiment, before inputting the target data for each test channel in the evaluation database into the preset recognition model, the method further includes:

[0023] The target data of each test channel in the database to be evaluated is normalized to obtain the normalized result corresponding to each group of data in the database to be evaluated. The normalized result is used to input into the preset recognition model.

[0024] In one embodiment, the vehicle to be evaluated has a pre-test location, the test points of which include the seat and foot area; accordingly, evaluation indicators for the vehicle to be evaluated are calculated according to the test type, and the evaluation result of the vehicle to be evaluated is determined by the evaluation indicators, including:

[0025] In the case of a random ride comfort test, the longitudinal test channel, the lateral test channel, the vertical test channel, and the vertical test channel of the foot test point at the pre-test position are taken as the target channels.

[0026] Based on the target data of the target channel, calculate the random ride comfort evaluation index of the pre-test position. The random ride comfort evaluation index is used to indicate the degree to which the human body feels the energy generated by vehicle vibration at the pre-test position.

[0027] Based on the preset range of the random ride comfort evaluation index, the human comfort level of the pre-test location is determined. The correspondence between the preset range and the human comfort level is determined based on the test data generated from the ride comfort tests of several vehicles and the corresponding manual annotation results.

[0028] Secondly, this application also provides a vehicle ride comfort evaluation device. The device includes:

[0029] The data acquisition module is used to acquire the test database generated by the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data acquired through all test channels.

[0030] The first preprocessing module is used to filter the test data obtained through each test channel to obtain the target data for each test channel.

[0031] The second preprocessing module is used to calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, an evaluation database of the vehicle to be evaluated is constructed based on the target data.

[0032] The type determination module is used to input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each channel in the evaluation database.

[0033] The evaluation determination module is used to calculate the evaluation indicators of the vehicle to be evaluated based on the test type, and to determine the evaluation result of the vehicle to be evaluated based on the evaluation indicators.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0035] Obtain the test database generated from the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data obtained through all test channels.

[0036] The test data obtained through each test channel is filtered to obtain the target data for each test channel;

[0037] Calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, construct an evaluation database of the vehicle to be evaluated based on the target data.

[0038] Input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each channel in the evaluation database.

[0039] The evaluation indicators for the vehicle to be evaluated are calculated based on the test type, and the evaluation results of the vehicle to be evaluated are determined based on the evaluation indicators.

[0040] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0041] Obtain the test database generated from the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data obtained through all test channels.

[0042] The test data obtained through each test channel is filtered to obtain the target data for each test channel;

[0043] Calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, construct an evaluation database of the vehicle to be evaluated based on the target data.

[0044] Input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each channel in the evaluation database.

[0045] The evaluation indicators for the vehicle to be evaluated are calculated based on the test type, and the evaluation results of the vehicle to be evaluated are determined based on the evaluation indicators.

[0046] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0047] Obtain the test database generated from the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data obtained through all test channels.

[0048] The test data obtained through each test channel is filtered to obtain the target data for each test channel;

[0049] Calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, construct an evaluation database of the vehicle to be evaluated based on the target data.

[0050] Input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each channel in the evaluation database.

[0051] The evaluation indicators for the vehicle to be evaluated are calculated based on the test type, and the evaluation results of the vehicle to be evaluated are determined based on the evaluation indicators.

[0052] The aforementioned vehicle ride comfort evaluation method, apparatus, computer equipment, storage medium, and computer program product acquire a test database generated from vehicle ride comfort tests of the vehicle to be evaluated. The test database includes test data acquired through all test channels. The test data acquired through each test channel is filtered to obtain target data for each test channel. The validity and repeatability indices of the target data for each test channel are calculated. If both the validity and repeatability indices of the target data meet preset conditions, an evaluation database for the vehicle to be evaluated is constructed based on the target data. The target data for each test channel in the evaluation database is input into a preset recognition model to determine the corresponding test type for the target data in each channel of the evaluation database. Evaluation indices for the vehicle to be evaluated are calculated based on the test type, and the evaluation result for the vehicle to be evaluated is determined through these evaluation indices. By preprocessing the test data of the vehicle to be evaluated, the usability and accuracy of the test data are improved. The test type recognition model is trained using a database generated from a large number of historical tests, enabling automatic identification of the test type of the test data of the vehicle to be evaluated, thereby calculating the evaluation indices for the vehicle to be evaluated, improving the efficiency of evaluation index calculation and the accuracy of the obtained evaluation results. Attached Figure Description

[0053] Figure 1This is a diagram illustrating the application environment of a vehicle ride comfort evaluation method in one embodiment.

[0054] Figure 2 This is a flowchart illustrating a vehicle ride comfort evaluation method in one embodiment;

[0055] Figure 3 This is a flowchart illustrating the vehicle ride comfort assessment method in another embodiment;

[0056] Figure 4 Here is a raw waveform diagram of the test data in one embodiment;

[0057] Figure 5 This is a median-filtered plot of the test data in one embodiment;

[0058] Figure 6 This is a low-pass filter plot of a median filter plot in one embodiment;

[0059] Figure 7 This is a flowchart illustrating the vehicle ride comfort assessment method in yet another embodiment;

[0060] Figure 8 This is a structural block diagram of a vehicle ride comfort evaluation device in one embodiment;

[0061] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] The vehicle ride comfort evaluation method provided in this application can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. Terminal 102 acquires vehicle ride comfort test data and sends it to server 104. Server 104 evaluates the ride comfort of the vehicle to be evaluated based on the acquired vehicle ride comfort test data. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers.

[0064] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0065] In one embodiment, such as Figure 2 As shown, the vehicle ride comfort test involves at least N test points, each with three test channels: longitudinal, lateral, and vertical. A method for evaluating vehicle ride comfort is provided, which can be applied to… Figure 1 Taking the server in the example, the following steps are included:

[0066] Step 202: Obtain the test database generated from the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data obtained through all test channels.

[0067] It should be noted that the test data for the vehicle ride comfort test in this embodiment is obtained through the data acquisition sensor of the data acquisition instrument. The data acquisition instrument has multiple test channels, and each test channel is connected to three locations at each test point, collecting data in three directions to form the test channel for each test point. The test data collected through the test channels can be discrete signals or continuous signals, and this embodiment does not specifically limit this. In one embodiment, the physical quantities involved in the ride comfort test scheme of the vehicle to be evaluated include the test vehicle speed; N driving and riding positions; three test points for each driving and riding position (foot, seat, and backrest, respectively); each test point has longitudinal (X), lateral (Y), and vertical (Z) test channels; thus, there are a total of 9*N test channels, that is, the data acquisition instrument collects test data for 9*N points of the vehicle to be evaluated through multiple test channels.

[0068] All data in the test database are obtained from vehicle ride comfort tests, which include vehicle simulation test data in a MATLAB simulation environment and actual vehicle track tests. This embodiment does not specifically limit the number of road surface unevenness levels involved in random ride comfort tests and the bump heights involved in pulse ride comfort tests. For example, in one embodiment, the road surface unevenness levels in random ride comfort simulation and actual vehicle testing can include 5 levels, and the bump heights in pulse ride comfort simulation and actual vehicle testing can include 5 different sizes.

[0069] Step 204: Filter the test data obtained through each test channel to obtain the target data for each test channel;

[0070] In real-world vehicle testing, ride comfort data often contains noise and numerous outliers. Therefore, preprocessing is necessary to ensure data accuracy in practical applications. For test data acquired through test channels, whether discrete or continuous signals, pre-defined filters can be used to filter out data that could negatively impact accuracy.

[0071] Target data refers to the accurate data obtained after filtering the test data. In a specific embodiment, if the test data is an acceleration signal obtained through a test channel and is a continuous signal, then after filtering, a signal with the same trend as the original acceleration signal but smoother will be obtained, which is convenient for calculating the smoothness evaluation index.

[0072] Step 206: Calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, construct an evaluation database of the vehicle to be evaluated based on the target data.

[0073] The validity index is used to indicate whether data is valid. In this embodiment, the validity index is used to determine whether the target data can be used to evaluate the ride comfort of a vehicle. In a specific embodiment, the validity index is determined with reference to the test parameter deviation limits specified in the preset rules and practical experience. The repeatability index determines whether the data is valid data that can be used to evaluate the ride comfort of a vehicle based on the principle of data repeatability. It is understood that when an experiment is repeated multiple times under the same conditions, the experimental data obtained have a high degree of similarity. For example, when repeatedly testing a person's height, the multiple data obtained are treated as a group. Under normal circumstances, the repeatability rate of the data obtained multiple times in this group should be extremely high. If there is abnormal data that differs significantly from other values, this abnormal data will affect the repeatability rate of the data in the group, thus indicating that there may be an error in the measurement of this group of data. Therefore, the smaller the repeatability index, the more accurate the data.

[0074] Step 208: Input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each channel in the evaluation database;

[0075] The preset recognition model is obtained through extensive vehicle ride comfort tests and human experience testing by test drivers. Its purpose is to determine the corresponding test category based on the changing trends of characteristic physical quantities in the test data. These characteristic physical quantities are selected from the physical quantities included in the test data to best characterize the test type and distinguish the test scheme of that type from other types. In selecting these characteristic physical quantities, a systematic analysis and in-depth study of ride comfort testing methods are conducted to determine the characteristic physical quantities for each test scheme, laying the foundation for subsequent test scheme identification. In a specific embodiment, since the vehicle evaluation test involves impulsive ride comfort tests and random ride comfort tests, the impulsive ride comfort test involves the vehicle passing over a bump at a certain speed. When passing the bump, the absolute value of the Z-axis acceleration at the measuring point suddenly increases, while random ride comfort tests assume that the change in road surface unevenness is a stationary random process, and the absolute value of the Z-axis acceleration at the measuring point does not change abruptly. Furthermore, vehicle speed also affects the vibration at the measuring point. Therefore, the driver's seat and foot Z-axis acceleration signals and the vehicle speed signal can be selected as characteristic physical quantities.

[0076] Specifically, simulation test data for four vehicle models and accumulated real-vehicle test data for 27 vehicle models were used in the MATLAB simulation environment. Random ride comfort simulation and real-vehicle measured road surface unevenness levels included AE level, while pulse ride comfort simulation and real-vehicle tested bump heights included five different sizes. For each condition, three representative drivers were selected to obtain their subjective feelings. The simulation test data and real-vehicle test data for each test channel were filtered and preprocessed, then normalized to obtain normalized results. Manual annotation was performed according to the test type corresponding to each test data point, and then the initial recognition model was trained. The initial recognition model can be a neural network model. It should be noted that when training the recognition model, only the feature physical quantities can be used for model training.

[0077] Step 210: Calculate the evaluation index of the vehicle to be evaluated according to the test type, and determine the evaluation result of the vehicle to be evaluated through the evaluation index.

[0078] The test types include random ride comfort tests and impulsive ride comfort tests. The test type is determined before the ride comfort test is conducted on the vehicle. The evaluation indicators to be calculated are different for different types of ride comfort tests. For example, based on the test data obtained from the random ride comfort test, the evaluation indicators to be calculated may include the weighted root mean square value of acceleration, human body absorbed power, and fatigue reduction efficiency limit. Based on the test data obtained from the impulsive ride comfort test, the maximum value of the absolute value of axial acceleration, the axial peak coefficient, and the vibration dose value of the test channel need to be calculated.

[0079] In one specific embodiment, the physical quantities of the ride comfort test scheme include: vehicle speed V, N driving and riding positions, three measuring points for each driving and riding position (footrest, seat, and backrest), and each measuring point having longitudinal (X), lateral (Y), and vertical (Z) channels, for a total of 3*N measuring points and 9*N test channels, where N is a positive integer greater than 1. After preprocessing the test data acquired from each channel and confirming the validity of the test data, the test type is determined, and then the evaluation index is calculated.

[0080] For example, the test type is the pulse ride comfort test. Based on the data from three measuring points (seat, backrest, and footrest) and nine test channels at each position, the pulse ride comfort index is calculated. The following is an example of the measurement data of the driver's position at a certain vehicle speed: The absolute value of axial acceleration is calculated based on the vehicle pulse ride comfort test data, and the maximum value of the absolute value of the vehicle axial acceleration is calculated.

[0081]

[0082] In the formula: This represents the test data in the i-th row and j-th column of the m-th data set when the vehicle speed is v. This represents the maximum absolute value of the j-th column of the test signal in the m-th group of data when the vehicle speed is v, where j = 1, 2, 3…9.

[0083] The root mean square value of axial weighted acceleration was calculated based on the vehicle pulse ride comfort test data. The calculation method is the same as that used for the root mean square value of axial weighted acceleration in random ride comfort.

[0084] Calculate the axial peak factor:

[0085]

[0086] In the formula: This represents the peak value coefficient of the j-th column in the m-th data set when the vehicle speed is v.

[0087] Based on the vehicle pulse ride comfort test data, the vibration dose value VDV (unit: m / s^1.75) for each channel is calculated using the following formula:

[0088]

[0089] In the formula: is the weighted acceleration time history, in m / s²; T is the action time (the time from when the front wheel of the car contacts the bump to when the car passes the bump and the impact response disappears), in seconds (s).

[0090] At this point, the maximum absolute value of acceleration, peak value, and vibration dose value at the driver's position have been calculated. Then, the same calculation is performed on the data at other positions to obtain the calculation results for each measurement position.

[0091] Based on the actual vehicle speed, the calculation results at the same speed are averaged to obtain the average of the maximum absolute value of acceleration for each channel at each measurement location. Mean value of kurtosis coefficient and the mean value of vibration dose ;

[0092] For the seat Z-axis acceleration at each measuring point, the evaluation method in Table 1 below is used:

[0093] Table 1 Acceleration Evaluation Methods

[0094]

[0095] For example, in the case of a randomized ride comfort test, after calculating the weighted root mean square value of acceleration, human body absorbed power, and fatigue reduction efficiency limit according to the formula, the evaluation results are determined according to Tables 2, 3, and 4 respectively.

[0096] Table 2 Evaluation Criteria for Weighted Root Mean Square Acceleration Values

[0097]

[0098] Table 3. Evaluation Criteria for Human Absorption Power

[0099]

[0100] Table 4 Evaluation Criteria for Fatigue-Induced Efficiency Reduction Time

[0101]

[0102] Using the weighting coefficients determined by the aforementioned database, the evaluation results of the weighted root mean square value of acceleration, human body absorbed power, and fatigue-induced reduction in work efficiency are weighted to obtain the final evaluation result Rv:

[0103] Rv=k1*Sa+ k2*Sp+ k3*ST

[0104] In the formula, The weighting coefficients for the three indicators are shown in Table 5 below.

[0105] Table 5. Final Evaluation Criteria

[0106]

[0107] The method provided in the above embodiments involves obtaining a test database generated from the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data obtained through all test channels. The test data obtained through each test channel is filtered to obtain target data for each test channel. The validity index and repeatability index of the target data for each test channel are calculated. If both the validity index and repeatability index of the target data meet preset conditions, an evaluation database for the vehicle to be evaluated is constructed based on the target data. The target data for each test channel in the evaluation database is input into a preset recognition model to determine the corresponding test type for the target data of each channel in the evaluation database. Evaluation indicators for the vehicle to be evaluated are calculated according to the test type, and the evaluation result of the vehicle to be evaluated is determined through the evaluation indicators. By preprocessing the test data of the vehicle to be evaluated, the usability and accuracy of the test data are improved. The test type recognition model is trained using a database generated from a large number of historical tests to automatically identify the test type of the test data of the vehicle to be evaluated, thereby calculating the evaluation indicators for the vehicle to be evaluated, improving the efficiency of the evaluation indicator calculation and the accuracy of the obtained evaluation results.

[0108] In one embodiment, the test data acquired by the test channel has a corresponding test vehicle speed, and the test data acquired by each test channel at each test vehicle speed is taken as a set of test data; accordingly, see Figure 3 The test data acquired through each test channel is filtered to obtain the target data for each test channel, including:

[0109] Step 302: Determine the filtering order of each set of test data in the test database according to the preset order;

[0110] Step 304: Based on the filtering order of each set of test data, filter all test data sequentially to obtain the target data for each set of test data;

[0111] Among them, filtering refers to performing outlier removal and noise filtering on any set of test data in the experimental database in sequence.

[0112] Since the data is obtained from sensors by a data acquisition device (e.g., the data acquisition device has n channels), the order of the channels may be changed during the actual acquisition process, resulting in a different acquisition order than the order in which the computer processes the experimental data. Therefore, it is necessary to preset the order to adjust the order of the original acquired experimental data and determine the subsequent processing order of each set of test data in the experimental database.

[0113] During data acquisition, outliers often exist in the data due to environmental clutter and sensor operating conditions. The presence of outliers has a significant negative impact on subsequent data processing, easily causing data abrupt changes and filter divergence. Identifying and removing outliers is a crucial step in data preprocessing, significantly affecting the accuracy and stability of subsequent data processing. In one embodiment, median filtering is used to effectively remove outliers. The basic principle of median filtering is to reorder the data within a window and use the data located at the center point of the window as the output of the median filter. To balance the effectiveness of outlier removal with the degree of data distortion, a median filter window length of 5 is chosen. (See also...) Figure 4 and Figure 5 As shown, Figure 4 This is the original data. Figure 5 This is the data after median filtering.

[0114] During data acquisition, some high-frequency noise signals inevitably get in. To minimize the impact of high-frequency noise on data reliability, digital filtering techniques are typically used to remove noise signals from the data, improving accuracy and reliability, and making the experimental data more representative. In one embodiment, a low-pass filter with a cutoff frequency of 200Hz is used to reduce high-frequency noise in the signal. See [link to documentation]. Figure 6 As shown, Figure 6 This is the data obtained by low-pass filtering the median-filtered data.

[0115] The method provided in the above embodiments automatically sorts multiple sets of data in the test database using preset sequences, thereby accelerating the data processing speed of the test data and improving the automation level of the vehicle ride comfort evaluation process. Additionally, the test data is filtered to remove useless or interfering data, shortening the vehicle ride comfort evaluation cycle.

[0116] In one embodiment, the preset sequence includes a preset channel sequence and a preset test speed sequence; correspondingly, see [link to relevant documentation]. Figure 7 According to a preset order, the filtering order of each set of test data in the experimental database is determined, including:

[0117] Step 702: Take the test data corresponding to the same test vehicle speed as a dataset, sort all datasets according to the preset test vehicle speed order, and obtain the first sorting result;

[0118] Step 704: For any dataset, sort all test data in any dataset according to the preset channel order to obtain a second sorting result;

[0119] Step 706: Determine the filtering order of each group of test data in the experimental database based on the first sorting result and the second sorting result.

[0120] Before sorting the large amount of data in the test database, it is necessary to understand the relationship between the data. In this embodiment of the invention, each test channel collects data under a certain test vehicle speed. At each collection moment, each test channel will collect data once. Therefore, all the data collected by each test channel under a certain test vehicle speed is taken as a group of data. According to the order of the test channels and the order of the test vehicle speed, the multiple groups of data in the test database are sorted.

[0121] All data in the dataset were collected at the same test speed, such as 20, 30, 40, 50, and 60 km / h. The datasets corresponding to each test speed were sorted according to the order of the test speeds, and then multiple sets of data in a dataset were sorted according to the order of the test channels. In one embodiment, the preset test channel order for data processing is (occupant 1 seat X, occupant 1 seat Y, occupant 1 seat Z, occupant 1 backrest X, occupant 1 backrest Y, occupant 1 backrest Z, occupant 1 foot X, occupant 1 foot Y, occupant 1 foot Z, driver seat X, driver seat Y, driver seat Z, driver backrest X, driver backrest Y, driver backrest Z, driver foot X, driver foot Y, driver foot Z), while the actual test channel order for data collection is (driver seat X, driver seat Y, driver seat Z, driver backrest X, driver backrest Y, driver backrest Z, driver foot X, driver foot Y, driver foot Z, occupant 1 seat X, occupant 1 seat Y, occupant 1 seat Z, occupant 1 backrest X, occupant 1 backrest Y, occupant 1 backrest Z, occupant 1 foot X, occupant 1 foot Y, occupant 1 foot Z), meaning the first sorting result can be determined through the preset channel order.

[0122] In one embodiment, if the preset test speed order is from low to high, the sorted test results are shown in Table 6, where V1 <V2。

[0123] Table 6 Filtering order of test data

[0124]

[0125] It should be noted that the first sorting can be performed according to the preset channel order, and the second sorting can be performed according to the preset test speed order. The results obtained by the two methods are the same. Therefore, this application does not make specific limitations on this.

[0126] In the method provided in the above embodiments, multiple sets of data in the test database are automatically sorted by preset multiple sequences, which speeds up the data processing speed of test data and improves the automation level of the vehicle ride comfort evaluation process.

[0127] In one embodiment, calculating the repeatability index of the target data for each test channel includes:

[0128] For any set of test data for each test channel, calculating the crest factor of each test data in any set of test data;

[0129] Calculating the difference between the maximum value and the minimum value of all the crest factors, and taking the difference as the repeatability index of any set of test data.

[0130] Among them, the crest factor refers to the ratio of the peak value to the effective value of a periodic waveform. In this actual example, the target data obtained after median filtering and low-pass filtering of each set of test data can be approximated as a periodic signal. Therefore, the repeatability of the data can be judged by the crest factor. By the difference between the maximum value and the minimum value of the crest factor, it is judged whether the data meets the repeatability requirements. It should be noted that when the number of repetitions included in each set of test data is different, the criteria for judging repeatability using the difference are also different. For example, using the relationship between the standard deviation R of the 95th percentile distribution and the number of repetitions n, different numbers of repetitions n have different standard deviations. Let Q represent the arithmetic mean of the crest factors at the same vehicle speed, and ∆Q be the difference between the maximum value and the minimum value of the crest factor; when ∆Q < R, it is considered that the repeatability of the test results is good and the data can be used; when ∆Q > R, it is considered that the repeatability of the test results is not good, the data cannot be used or the number of tests should be increased.

[0131] In the method provided by the above embodiment, the repeatability of the test data is judged through an algorithm, so as to determine more accurate and effective test data, avoid being affected by human subjective factors during manual judgment, improve the credibility of the test evaluation results, and shorten the automotive performance tuning cycle.

[0132] In one embodiment, before inputting the target data of each test channel in the evaluation database into the preset recognition model, it further includes:

[0133] Normalizing the target data of each test channel in the to-be-evaluated database to obtain the normalization result corresponding to each set of data in the to-be-evaluated database, and the normalization result is used to be input into the preset recognition model.

[0134] The automotive ride comfort test plan corresponds to one or more test conditions. Under different test conditions, the amplitudes of the measured point responses are different, but the test curves have the same changing trend. In order to quickly identify the test type, it is necessary to normalize the test data to eliminate the influence brought by the amplitudes, means, coefficient of variation, etc. of different test data, so that the characteristic physical quantities have the same magnitude and trend. The data normalization method adopted is as follows;

[0135]

[0136] In the formula, The data is after normalization; For observation values; The average of the observed values; The minimum value observed; This represents the maximum value of the observed values.

[0137] In the method provided in the above embodiments, normalizing the characteristic physical quantities can more quickly obtain the test type, realize automatic judgment of the test type, and improve the evaluation efficiency and accuracy of the evaluation results of vehicle ride comfort assessment.

[0138] In one embodiment, the vehicle to be evaluated has a pre-test location, the test points of which include the seat and foot area; accordingly, evaluation indicators for the vehicle to be evaluated are calculated according to the test type, and the evaluation result of the vehicle to be evaluated is determined by the evaluation indicators, including:

[0139] In the case of a random ride comfort test, the longitudinal test channel, the lateral test channel, the vertical test channel, and the vertical test channel of the foot test point at the pre-test position are taken as the target channels.

[0140] Based on the target data of the target channel, calculate the random ride comfort evaluation index of the pre-test position. The random ride comfort evaluation index is used to indicate the degree to which the human body feels the energy generated by vehicle vibration at the pre-test position.

[0141] Based on the preset range of random ride comfort evaluation indicators, the human comfort level at the pre-test location is determined. The correspondence between the preset range and the human comfort level is determined based on test data generated from ride comfort tests of several vehicles and the corresponding manual annotation results.

[0142] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0143] Based on the same inventive concept, this application also provides a vehicle ride comfort evaluation device for implementing the vehicle ride comfort evaluation method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more vehicle ride comfort evaluation device embodiments provided below can be found in the limitations of the vehicle ride comfort evaluation method described above, and will not be repeated here.

[0144] In one embodiment, such as Figure 8 As shown, a vehicle ride comfort evaluation device is provided, comprising: a data acquisition module 801, a first preprocessing module 802, a second preprocessing module 803, a type determination module 804, and an evaluation determination module 805, wherein:

[0145] The data acquisition module 801 is used to acquire the test database generated by the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data acquired through all test channels.

[0146] The first preprocessing module 802 is used to filter the test data obtained through each test channel to obtain the target data of each test channel.

[0147] The second preprocessing module 803 is used to calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, an evaluation database of the vehicle to be evaluated is constructed based on the target data.

[0148] The type determination module 804 is used to input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each channel in the evaluation database.

[0149] The evaluation determination module 805 is used to calculate the evaluation index of the vehicle to be evaluated based on the test type, and to determine the evaluation result of the vehicle to be evaluated based on the evaluation index.

[0150] In one embodiment, the first preprocessing module 802 is further configured to:

[0151] The filtering order of each set of test data in the experimental database is determined according to the preset order;

[0152] Based on the filtering order of each set of test data, all test data are filtered sequentially to obtain the target data for each set of test data.

[0153] Among them, filtering refers to performing outlier removal and noise filtering on any set of test data in the experimental database in sequence.

[0154] In one embodiment, the first preprocessing module 802 is further configured to:

[0155] Test data corresponding to the same test speed are treated as a single dataset. All datasets are sorted according to a preset test speed order to obtain the first sorting result.

[0156] For any dataset, sort all test data in any dataset according to the preset channel order to obtain a second sorting result;

[0157] Based on the first and second sorting results, the filtering order of each group of test data in the experimental database is determined.

[0158] In one embodiment, the second preprocessing module 803 is further configured to:

[0159] For any set of test data for each test channel, calculate the peak factor of each test data in the set of test data;

[0160] Calculate the difference between the maximum and minimum values ​​of all peak factors, and use the difference as a repeatability indicator for any set of test data.

[0161] In one embodiment, the vehicle ride comfort assessment device further includes a third preprocessing module for:

[0162] The target data of each test channel in the database to be evaluated is normalized to obtain the normalized result corresponding to each group of data in the database to be evaluated. The normalized result is used to input into the preset recognition model.

[0163] In one embodiment, the evaluation and determination module 805 is further configured to:

[0164] In the case of a random ride comfort test, the longitudinal test channel, the lateral test channel, the vertical test channel, and the vertical test channel of the foot test point at the pre-test position are taken as the target channels.

[0165] Based on the target data of the target channel, calculate the random ride comfort evaluation index of the pre-test position. The random ride comfort evaluation index is used to indicate the degree to which the human body feels the energy generated by vehicle vibration at the pre-test position.

[0166] Based on the preset range of the random ride comfort evaluation index, the human comfort level of the pre-test location is determined. The correspondence between the preset range and the human comfort level is determined based on the test data generated from the ride comfort tests of several vehicles and the corresponding manual annotation results.

[0167] The modules in the aforementioned vehicle ride comfort evaluation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0168] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores test data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for evaluating vehicle ride comfort.

[0169] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0170] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0171] Obtain the test database generated from the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data obtained through all test channels.

[0172] The test data obtained through each test channel is filtered to obtain the target data for each test channel;

[0173] Calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, construct an evaluation database of the vehicle to be evaluated based on the target data.

[0174] Input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each channel in the evaluation database.

[0175] The evaluation indicators for the vehicle to be evaluated are calculated based on the test type, and the evaluation results of the vehicle to be evaluated are determined based on the evaluation indicators.

[0176] In one embodiment, the test data acquired by the test channel has a corresponding test vehicle speed, and the test data acquired by each test channel at each test vehicle speed is taken as a set of test data; accordingly, when the processor executes the computer program, it also implements the following steps:

[0177] The filtering order of each set of test data in the experimental database is determined according to the preset order;

[0178] Based on the filtering order of each set of test data, all test data are filtered sequentially to obtain the target data for each set of test data.

[0179] Among them, filtering refers to performing outlier removal and noise filtering on any set of test data in the experimental database in sequence.

[0180] In one embodiment, the preset sequence includes a preset channel sequence and a preset test speed sequence; correspondingly, when the processor executes the computer program, it also performs the following steps:

[0181] Test data corresponding to the same test speed are treated as a single dataset. All datasets are sorted according to a preset test speed order to obtain the first sorting result.

[0182] For any dataset, sort all test data in any dataset according to the preset channel order to obtain a second sorting result;

[0183] Based on the first and second sorting results, the filtering order of each group of test data in the experimental database is determined.

[0184] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0185] For any set of test data for each test channel, calculate the peak factor of each test data in the set of test data;

[0186] Calculate the difference between the maximum and minimum values ​​of all peak factors, and use the difference as a repeatability indicator for any set of test data.

[0187] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0188] The target data of each test channel in the database to be evaluated is normalized to obtain the normalized result corresponding to each group of data in the database to be evaluated. The normalized result is used to input into the preset recognition model.

[0189] In one embodiment, the vehicle to be evaluated has a pre-test location, where test points include the seat and foot area; accordingly, the processor, when executing the computer program, also implements the following steps:

[0190] In the case of a random ride comfort test, the longitudinal test channel, the lateral test channel, the vertical test channel, and the vertical test channel of the foot test point at the pre-test position are taken as the target channels.

[0191] Based on the target data of the target channel, calculate the random ride comfort evaluation index of the pre-test position. The random ride comfort evaluation index is used to indicate the degree to which the human body feels the energy generated by vehicle vibration at the pre-test position.

[0192] Based on the preset range of the random ride comfort evaluation index, the human comfort level of the pre-test location is determined. The correspondence between the preset range and the human comfort level is determined based on the test data generated from the ride comfort tests of several vehicles and the corresponding manual annotation results.

[0193] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0194] Obtain the test database generated from the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data obtained through all test channels.

[0195] The test data obtained through each test channel is filtered to obtain the target data for each test channel;

[0196] Calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, construct an evaluation database of the vehicle to be evaluated based on the target data.

[0197] Input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each channel in the evaluation database.

[0198] The evaluation indicators for the vehicle to be evaluated are calculated based on the test type, and the evaluation results of the vehicle to be evaluated are determined based on the evaluation indicators.

[0199] In one embodiment, the test data acquired by the test channel has a corresponding test vehicle speed, and the test data acquired by each test channel at each test vehicle speed is taken as a set of test data; accordingly, when the computer program is executed by the processor, it also implements the following steps:

[0200] The filtering order of each set of test data in the experimental database is determined according to the preset order;

[0201] Based on the filtering order of each set of test data, all test data are filtered sequentially to obtain the target data for each set of test data.

[0202] Among them, filtering refers to performing outlier removal and noise filtering on any set of test data in the experimental database in sequence.

[0203] In one embodiment, the preset sequence includes a preset channel sequence and a preset test speed sequence; correspondingly, when the computer program is executed by the processor, it also performs the following steps:

[0204] Test data corresponding to the same test speed are treated as a single dataset. All datasets are sorted according to a preset test speed order to obtain the first sorting result.

[0205] For any dataset, sort all test data in any dataset according to the preset channel order to obtain a second sorting result;

[0206] Based on the first and second sorting results, the filtering order of each group of test data in the experimental database is determined.

[0207] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0208] For any set of test data for each test channel, calculate the peak factor of each test data in the set of test data;

[0209] Calculate the difference between the maximum and minimum values ​​of all peak factors, and use the difference as a repeatability indicator for any set of test data.

[0210] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0211] The target data of each test channel in the database to be evaluated is normalized to obtain the normalized result corresponding to each group of data in the database to be evaluated. The normalized result is used to input into the preset recognition model.

[0212] In one embodiment, the vehicle to be evaluated has a pre-test location, where test points include the seat and foot area; accordingly, when the computer program is executed by the processor, it also performs the following steps:

[0213] In the case of a random ride comfort test, the longitudinal test channel, the lateral test channel, the vertical test channel, and the vertical test channel of the foot test point at the pre-test position are taken as the target channels.

[0214] Based on the target data of the target channel, calculate the random ride comfort evaluation index of the pre-test position. The random ride comfort evaluation index is used to indicate the degree to which the human body feels the energy generated by vehicle vibration at the pre-test position.

[0215] Based on the preset range of the random ride comfort evaluation index, the human comfort level of the pre-test location is determined. The correspondence between the preset range and the human comfort level is determined based on the test data generated from the ride comfort tests of several vehicles and the corresponding manual annotation results.

[0216] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements all the steps in the above-described vehicle ride comfort assessment method.

[0217] 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. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0218] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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, they should be considered to be within the scope of this specification.

[0219] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for evaluating vehicle ride comfort, characterized in that, The vehicle ride comfort test involves at least N test points, each test point having three test channels: longitudinal, lateral, and vertical; the method includes: Obtain a test database generated from the vehicle ride comfort test of the vehicle to be evaluated, the test database including test data obtained through all test channels; The test data obtained through each test channel is filtered to obtain the target data for each test channel; Calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, construct the evaluation database of the vehicle to be evaluated based on the target data. Input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each test channel in the evaluation database; The evaluation index of the vehicle to be evaluated is calculated based on the test type, and the evaluation result of the vehicle to be evaluated is determined through the evaluation index.

2. The method according to claim 1, characterized in that, The test data acquired by the test channel has a corresponding test vehicle speed, and the test data acquired by each test channel at each test vehicle speed is taken as a set of test data; accordingly, the filtering process of the test data acquired through each test channel to obtain the target data of each test channel includes: The filtering order of each set of test data in the test database is determined according to a preset order; Based on the filtering order of each set of test data, all test data are filtered sequentially to obtain the target data for each set of test data. Among them, filtering processing refers to performing outlier removal and noise filtering processing on any set of test data in the test database in sequence.

3. The method according to claim 2, characterized in that, The preset order includes a preset channel order and a preset test speed order; correspondingly, determining the filtering order of each set of test data in the test database according to the preset order includes: Test data corresponding to the same test speed are treated as a single dataset. All datasets are sorted according to the preset test speed order to obtain the first sorting result. For any dataset, all test data in the dataset are sorted according to the preset channel order to obtain a second sorting result; Based on the first sorting result and the second sorting result, the filtering order of each group of test data in the experimental database is determined.

4. The method according to claim 2, characterized in that, The repeatability metrics for calculating the target data for each test channel include: For any set of test data for each test channel, calculate the peak factor of each test data in the set of test data; Calculate the difference between the maximum and minimum values ​​of all peak factors, and use the difference as a repeatability indicator for any set of test data.

5. The method according to claim 1, characterized in that, Before inputting the target data of each test channel in the evaluation database into the preset recognition model, the following steps are also included: The target data of each test channel in the evaluation database is normalized to obtain the normalization result corresponding to each group of data in the evaluation database. The normalization result is used to input into the preset recognition model.

6. The method according to claim 1, characterized in that, The vehicle to be evaluated has a pre-test location, and the test points at the pre-test location include the seat and foot area; accordingly, the evaluation index of the vehicle to be evaluated is calculated according to the test type, and the evaluation result of the vehicle to be evaluated is determined through the evaluation index, including: When the test type is a random ride comfort test, the longitudinal test channel, the lateral test channel, the vertical test channel, and the vertical test channel of the foot test point at the pre-test position are taken as the target channels. Based on the target data of the target channel, a random ride comfort evaluation index is calculated for the pre-test position. The random ride comfort evaluation index is used to indicate the degree to which the human body perceives the energy generated by vehicle vibration at the pre-test position. Based on the preset range of the random ride comfort evaluation index, the human comfort level of the pre-test location is determined. The correspondence between the preset range and the human comfort level is determined based on the test data generated from the ride comfort tests of several vehicles and the corresponding manual annotation results.

7. A vehicle ride comfort evaluation device, characterized in that, The device includes: The data acquisition module is used to acquire the test database generated by the vehicle ride comfort test of the vehicle to be evaluated. The test database includes test data acquired through all test channels. The first preprocessing module is used to filter the test data obtained through each test channel to obtain the target data for each test channel. The second preprocessing module is used to calculate the validity index and repeatability index of the target data for each test channel. If the validity index and repeatability index of the target data meet the preset conditions, the evaluation database of the vehicle to be evaluated is constructed based on the target data. The type determination module is used to input the target data of each test channel in the evaluation database into the preset recognition model to determine the corresponding test type of the target data of each test channel in the evaluation database. The evaluation determination module is used to calculate the evaluation index of the vehicle to be evaluated based on the test type, and determine the evaluation result of the vehicle to be evaluated based on the evaluation index.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images