Vehicle driving comfort level prediction method, device and equipment and storage medium

Abstract

The invention relates to the technical field of vehicle comfort evaluation, and discloses a vehicle driving comfort prediction method and device, equipment and a storage medium. The method comprises the following steps: firstly, obtaining subjective evaluation data on a plurality of vibration type indexes and objective measurement data at a plurality of preset measurement point positions; wherein each vibration type index corresponds to at least one target measuring point position in the plurality of preset measuring point positions; inputting the objective measurement data into a first-level scoring prediction model to obtain first-level scoring data of each vibration type index; determining a vibration related index corresponding to the driving comfort index in the plurality of vibration type indexes; inputting the index scoring data of the vibration-related indexes into a second-level scoring prediction model to obtain second-level scoring data of the driving comfort indexes; and integration is carried out based on the second-level score data of the driving comfort index, and the vehicle driving comfort is obtained. Therefore, the efficient and accurate vehicle driving comfort prediction method based on subjective and objective consistency is realized.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle comfort evaluation, and in particular to a method, device, equipment and storage medium for predicting vehicle ride comfort. Background Art

[0002] As the main force in the field of logistics and transportation, the comfort of heavy-duty commercial vehicles is a performance indicator that major manufacturers urgently need to improve, and it is also a core reference factor for customers when purchasing vehicles. A large number of engineering practices have shown that there is no measurement and analysis method that can comprehensively measure and evaluate the various impact quantities on human biological tissues through contact with vehicles.

[0003] For the commercial vehicle comfort optimization process, there are two commonly used vehicle comfort performance evaluation methods: subjective evaluation and objective evaluation. The subjective evaluation is mainly based on the subjective feelings of the human body, while the objective evaluation is based on the actual measurement of vibration parameters as the objective basis for evaluation.

[0004] However, in the related technologies, the evaluation methods for vehicle driving comfort performance are relatively limited, and there is an urgent need to propose a new method to accurately evaluate vehicle comfort performance. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the present application proposes a method, device, equipment and storage medium for predicting vehicle ride comfort. The main technical solutions adopted by the present application include:

[0006] In a first aspect, an embodiment of the present application provides a method for predicting vehicle ride comfort, the method comprising: obtaining subjective evaluation data on multiple vibration type indicators and objective measurement data at multiple preset measuring point positions; wherein each vibration type indicator has a first-level scoring prediction model; the vibration type indicator is an indicator of a preset vibration condition for vehicle ride comfort; each vibration type indicator corresponds to at least one target measuring point position in multiple preset measuring point positions; the objective measurement data at at least one target measuring point position is input into the first-level scoring prediction model for first-level prediction to obtain first-level scoring data for each vibration type indicator; the vibration-related indicator corresponding to the ride comfort indicator is determined among multiple vibration type indicators; the indicator scoring data of the vibration-related indicator is input into the second-level scoring prediction model for prediction to obtain second-level scoring data of the ride comfort indicator; the second-level scoring data based on the ride comfort indicator is integrated to obtain the vehicle ride comfort.

[0007] In a second aspect, an embodiment of the present application provides a device for predicting vehicle ride comfort, the device comprising: a data acquisition module, used to acquire subjective evaluation data on multiple vibration type indicators and objective measurement data at multiple preset measuring point positions; wherein each vibration type indicator has a first-level scoring prediction model; the vibration type indicator is an indicator of a preset vibration condition for vehicle ride comfort; each vibration type indicator corresponds to at least one target measuring point position in multiple preset measuring point positions; a first-level prediction module, used to input the objective measurement data at at least one target measuring point position into the first-level scoring prediction model for first-level prediction, and obtain first-level scoring data for each vibration type indicator; an indicator determination module, used to determine the vibration-related indicator corresponding to the ride comfort indicator among multiple vibration type indicators; a second-level prediction module, used to input the indicator scoring data of the vibration-related indicator into the second-level scoring prediction model for prediction, and obtain second-level scoring data of the ride comfort indicator; a comfort prediction module, used to integrate the second-level scoring data based on the ride comfort indicator to obtain the vehicle ride comfort.

[0008] In a third aspect, the present application further provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0009] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when the computer program is executed by a processor.

[0010] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which implements the steps of any of the above methods when executed by a processor.

[0011] In the above embodiment, firstly, a plurality of vibration type indicators are divided according to the vehicle ride comfort, and the subjective evaluation data on the plurality of vibration type indicators and the objective measurement data at the plurality of preset measuring points are obtained and processed and analyzed. Secondly, the objective measurement is input into the first-level scoring prediction model for first-level prediction and first-level scoring data is obtained, and further, the vibration-related indicators corresponding to the ride comfort indicators are determined again among the plurality of vibration type indicators, and the indicator scoring data of the vibration-related indicators are input into the second-level scoring prediction model for prediction to obtain the second-level scoring data of the ride comfort indicators. Finally, these data are integrated to evaluate the overall ride comfort of the vehicle. Thus, an efficient and accurate method for predicting the vehicle ride comfort based on subjective and objective consistency is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1a A flowchart of a vehicle driving comfort prediction method provided according to an embodiment of the present application;

[0014] Figure 1b A fitting curve diagram of a primary score prediction model provided according to an embodiment of the present application;

[0015] Figure 1c A fitting curve diagram of a primary score prediction model provided according to another embodiment of the present application;

[0016] Figure 1d A fitting curve diagram of a secondary rating prediction model provided according to an embodiment of the present application;

[0017] Figure 1e This is a graph showing error analysis results of a secondary rating prediction model provided according to one embodiment of the present application;

[0018] Figure 1f A framework diagram of an overall score prediction model provided according to an embodiment of the present application;

[0019] Figure 2 A flowchart of a vehicle driving comfort prediction method provided according to an embodiment of the present application;

[0020] Figure 3 A flowchart of a method for determining operating condition scoring data according to an embodiment of the present application;

[0021] Figure 4 A flowchart of a method for obtaining objective measurement data according to an embodiment of the present application;

[0022] Figure 5a A flowchart of a method for obtaining vibration parameter data according to an embodiment of the present application;

[0023] Figure 5b A time domain diagram of an impact strength index provided according to an embodiment of the present application;

[0024] Figure 5c A time domain diagram of a limit impact index provided according to an embodiment of the present application;

[0025] Figure 5dA time domain diagram of a residual vibration index provided according to an embodiment of the present application;

[0026] Figure 6a A flowchart of a method for obtaining vibration parameter data according to another embodiment of the present application;

[0027] Figure 6b A frequency response diagram of a certain vibration type indicator provided according to an embodiment of the present application;

[0028] Figure 6c A frequency response diagram of a certain vibration type indicator provided according to another embodiment of the present application;

[0029] Figure 7 A schematic diagram of a correlation analysis result of subjective evaluation data and objective measurement data of some vibration type indicators provided according to an embodiment of the present application;

[0030] Figure 8 A structural block diagram of a vehicle ride comfort prediction device provided according to an embodiment of the present application;

[0031] Fig. 9 The figure is a diagram of the internal structure of a computer device provided according to one embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0033] As the main force in the field of logistics and transportation, the comfort of heavy-duty commercial vehicles is a performance indicator that major manufacturers urgently need to improve, and it is also a core reference factor for customers when purchasing vehicles. In related technologies, both foreign and domestic automobile manufacturers have increased their efforts in the development of vibration, noise, and comfort to meet customers' requirements for NVH performance.

[0034] Automobile performance evaluation is mainly carried out in three ways: subjective evaluation, objective evaluation and computer simulation. Among them, subjective evaluation is the most effective traditional automobile performance evaluation method and the final evaluation method of automobile performance. Subjective evaluation takes people as the main body. The physiological and psychological conditions of each passenger are different. When riding in the same car, the reaction to the same driving conditions is also different. The evaluation is very different and uncertain. The requirements for evaluators are high and sufficient evaluation training is required. On the other hand, subjective evaluation cannot directly give the connection between "automobile performance" and "automobile structure" parameters, and it is not easy to convert into engineering development language. As an important supplement to subjective evaluation, objective evaluation uses objective parameters as the evaluation basis, which can go beyond subjective judgment to obtain a lot of system information that drivers cannot perceive. However, in actual operation, the computer model has limited ability to predict driving performance. There are differences in the objective evaluation indicators that are currently available and can correspond to subjective evaluation. That is, objective evaluation cannot directly reflect the degree of human perception when bearing vibration, nor can it reflect the subjective acceptance of human vibration performance. Therefore, it still needs to be tested by subjective feeling; and subjective feeling makes it difficult to link the evaluation results with vehicle structure and actual vibration parameters for quantitative evaluation, which is inconvenient to implement structural design.

[0035] In the relevant technologies, the driving comfort is often evaluated by dual standards of objective test data and subjective evaluation of personnel in the process of optimizing the comfort of commercial vehicles. The process is cumbersome and subject to certain limitations. In addition, there is no measurement and analysis method that can comprehensively measure and evaluate various impact quantities acting on the human body through contact with the car. Therefore, in the process of optimizing the smoothness of commercial vehicles, there is still the problem of low rigor in the evaluation of driving comfort. Therefore, the two evaluation methods must be combined to comprehensively and accurately evaluate the vibration performance of the vehicle.

[0036] Based on this, according to an embodiment of the present application, a method, device, equipment and storage medium embodiment for predicting vehicle driving comfort is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] In this embodiment, a method for predicting vehicle driving comfort is provided. Figure 1a is a flow chart of a method for predicting vehicle ride comfort according to an embodiment of the present application, such as Figure 1a As shown, the method comprises the following steps:

[0038] S110, obtaining subjective evaluation data on multiple vibration type indicators and objective measurement data at multiple preset measurement point positions.

[0039] Among them, the vibration type index is an index of the preset vibration conditions for the vehicle's driving comfort. The preset vibration conditions are used to describe the specific vibration dynamic conditions caused by various road conditions and vehicle responses encountered by the vehicle on different road surfaces. For example, the preset vibration conditions can be random vibration, pulse vibration or resonant vibration, etc. Based on this, the description of the vibration type index can be referred to as shown in Table 1 below:

[0040] Table 1 Description of vibration type indicators

[0041]

[0042] The preset measuring point position may refer to a specific position pre-set on the vehicle to be tested that can measure the pulse vibration and random vibration generated by the vehicle to be tested during driving. For example, the point in contact with the human body in the vehicle can be used as the preset measuring point position, such as: seat cushion, seat rail, seat back and body B-pillar and other positions; the position of the key structural components of the vehicle can also be used as the preset measuring point position, such as: wheel center, suspension and body suspension active and passive ends and other positions. Objective measurement data may refer to data directly collected based on scientific instruments, equipment or standardized test methods. For example, the vibration acceleration, velocity or displacement data of the vehicle under different driving conditions can be used as objective measurement data; certain vibration response data of specific measuring points of the vehicle can also be used as objective measurement data; certain dynamic characteristic data of key structural components of the vehicle can also be used as objective measurement data.

[0043] Specifically, when conducting a vehicle ride comfort test, objective measurement data at multiple preset measuring points can be obtained by installing vibration sensors or other measuring equipment at the preset measuring points of the vehicle to be tested to collect vibration parameters generated by the vehicle to be tested during driving, and use these vibration parameters as objective measurement data. It is understandable that when conducting a vehicle ride comfort test, in order to make the test results have subjective and objective consistency, subjective evaluation data also needs to be obtained. Subjective evaluation data may refer to data on vehicle ride comfort intuitively felt by the test personnel in the vehicle through their senses when the vehicle to be tested is driving under different working conditions. Specifically, subjective evaluation data on multiple vibration type indicators can be obtained by allowing experienced drivers and passengers to fill in standardized evaluation forms according to their direct feelings and preset evaluation criteria during actual driving or riding of the test vehicle to obtain subjective evaluation data. For example, a full score of 10 points and a scoring interval of 0.25 points can be adopted, as shown in Table 2:

[0044] Table 2 Subjective evaluation scoring criteria

[0045]

[0046] Optionally, when obtaining subjective evaluation data, testers may receive professional training in advance. During the evaluation process, multiple testers score each vibration type index of the vehicle based on their driving and riding experience, and the results are averaged to obtain subjective evaluation data on multiple vibration type indicators of the vehicle to be tested.

[0047] S120: Inputting objective measurement data at at least one target measuring point into a primary scoring prediction model to perform primary prediction, thereby obtaining primary scoring data for each vibration type index.

[0048] Among them, each vibration type indicator corresponds to a first-level scoring prediction model, and each vibration type indicator corresponds to at least one target measuring point position in multiple preset measuring point positions. Among them, the first-level scoring prediction model can refer to a mathematical model established in order to convert the objectively measured vehicle vibration parameters into quantitative indicators of predictable subjective evaluation data when conducting a vehicle ride comfort test. Based on this, the first-level scoring data can be data used to reflect the degree of influence of each vibration type indicator on driving comfort, that is, the first-level scoring data can be the data obtained by performing a first-level prediction based on objective measurement data for the first-level scoring prediction model for each vibration type indicator when conducting a vehicle ride comfort test.

[0049] Optionally, since the first-level scoring prediction model is a mathematical model established to convert the vehicle vibration parameters obtained by objective measurement into quantitative indicators of predictable subjective evaluation data, when establishing the first-level scoring prediction model, the objective measurement data at multiple preset measuring point positions can be used as independent variables, and the corresponding subjective evaluation data on multiple vibration type indicators can be used as dependent variables to establish a functional relationship model between subjective evaluation data and objective measurement data. It should be understood that since each vibration type indicator corresponds to at least one target measuring point position among multiple preset measuring point positions, when establishing the first-level scoring prediction model, it is also necessary to use a single variable modeling method and a multivariate modeling method according to different situations. Specifically, if a certain vibration type indicator corresponds to only one target measuring point position among multiple preset measuring point positions, when establishing the first-level scoring prediction model, a single variable modeling method of a univariate regression algorithm can be used. Exemplarily, the expression of the univariate nonlinear regression model is shown as follows:

[0050] y=f(x,θ)+ε

[0051] In the formula, y is the dependent variable; x is the independent variable; θ=(θ0,θ1,…,θ p ) T represents the unknown parameter vector; ε is the random error term.

[0052] Furthermore, the final polynomial fitting model formula is shown as follows:

[0053] y=β0+β1x+…+β n x n

[0054] Where β0, β1, …, β n are the coefficients of the polynomial; n is the maximum degree of the polynomial, which can be 2 or 3.

[0055] Optionally, after the primary score prediction model is established, error analysis and correction can be performed on it. For example, the sample fit goodness of fit R 2 Specifically, in the multivariate linear regression equation, the sample goodness of fit R is defined as 2 As shown below:

[0056]

[0057] In the formula, is the estimated value of y; is the mean value of y.

[0058] Similarly, the root mean square error (RMSE) represents the root mean square of the average squared prediction error, which measures the average difference between the predicted value and the true value. This process can be expressed mathematically as follows:

[0059]

[0060] Where, X obs，i is the true value, X model，i is the predicted value and n is the number of samples.

[0061] It is understandable that when the goodness of fit R 2 If it is close to 1 (greater than 0.8 or higher), it means that the model fits the data well. The root mean square error (RMSE) can intuitively express the order of magnitude of the prediction error. The smaller the value, the higher the prediction accuracy.

[0062] For example, for the vertical motion index, the B-pillar (Z direction) is selected as the target measurement point position, and the fitting equation of the first-level score prediction model can be shown as follows:

[0063] Y 垂向运动 =10-9.382x+7.67x 2 -2.327x 3

[0064] Where Y 垂向运动 It is the primary scoring data of the vertical motion index; x is the objective measurement data measured at the measuring point position of the B-pillar (Z direction).

[0065] The fitting curve and coefficient results of the first-level scoring prediction model of vertical motion index can be referred to Figure 1b After error analysis, the goodness of fit R 2 The result is 0.9156, and the root mean square error RMSE is 0.5855. It can be seen that the fitting equation of its first-level score prediction model has a high prediction accuracy.

[0066] Furthermore, the objective measurement data measured at the B-pillar (Z direction) measuring point position is input into the fitting equation of the primary scoring prediction model of the vertical motion index, so as to obtain the primary scoring data of the vertical motion vibration type index.

[0067] Similarly, if a vibration type indicator corresponds to multiple target measurement point positions in multiple preset measurement point positions, a multivariate modeling method of a ridge regression estimation algorithm can be used when establishing a first-level score prediction model. For example, multivariate linear regression analysis means that there are two or more independent variables in the model, and there is a linear relationship between these independent variables and the dependent variable. As shown in the following formula:

[0068] Y=Xβ+ε

[0069] In the formula, Y is the model dependent variable; X is the independent variable matrix; β is the regression coefficient; ε is the sample error.

[0070] Its least squares estimated coefficient It is expressed as:

[0071]

[0072] Where: X T is the transposed matrix of the independent variable matrix X.

[0073] It can be understood that the objective function of ridge regression is to add a regular term on the basis of the least squares error, so the calculation method of the ridge regression model can be shown as follows:

[0074]

[0075] Where: y i is the response variable of the ith observation; x ij is the value of the jth predictor variable for the ith observation; β0 is the intercept term; β j is the coefficient corresponding to the jth predictor variable; n is the number of samples; p is the number of features; α is the regularization parameter.

[0076] Furthermore, if there is strong collinearity between the feature parameters, it will lead to |X T X|≈0, so that (X T X) -1 The values ​​on the diagonal are large, resulting in This will produce large changes and inaccurate estimated coefficients. In order to improve the accuracy of the estimated coefficients, ridge estimation can be used to eliminate multicollinearity characteristic parameters. The ridge estimation ridge regression coefficient calculation formula for the undetermined parameters can be shown as follows:

[0077] β(k)=(X T X+I p ) -1 X T Y

[0078] Where k is the ridge trace parameter; I p is the unit matrix of order; p is the number of modeling samples.

[0079] It is important to understand that in order to improve the matrix X T When the characteristic root of X tends to 0, the ridge trace parameter k is introduced into the calculation formula to make the estimated coefficient reach the optimal value as much as possible. The estimated coefficient β is taken as a function of k. When k changes in the range of [0, 1], k is the horizontal coordinate and β(k) is the vertical coordinate. The corresponding graph in the plane rectangular coordinate is the ridge trace. The ridge trace can intuitively reflect the role and relationship of each characteristic parameter on the subjective score prediction. With the help of ridge trace analysis, the main characteristic parameters that affect the subjective score estimation model can be effectively selected, and the estimation model can be finally determined.

[0080] For example, for the pitch index, the X direction and Z direction of the guide rail measuring point are selected as the target measuring point positions, and the fitting curve and coefficient results of the first-level scoring prediction model established can be referred to Figure 1c , where it can be seen that the fitting curve 101 is relatively close to the original data curve 103 used for fitting, that is, the fitting effect is good. The fitting equation of the first-level score prediction model can be shown as follows:

[0081] Y 俯仰 =9.097-0.177x 导轨 -2.519z 导轨

[0082] Where Y 俯仰 Represents the first-level scoring data of the pitch index; x 导轨 Represents the objective measurement data measured at the X-axis measuring point position of the guide rail measuring point; z 导轨 Represents the objective measurement data measured at the Z-axis measuring point position of the guide rail measuring point.

[0083] Furthermore, the objective measurement data measured at the X-direction measuring point position of the guide rail measuring point and the objective measurement data measured at the Z-direction measuring point position of the guide rail measuring point are input into the fitting equation of the primary scoring prediction model of the pitch index, so as to obtain the primary scoring data of the pitch vibration type index.

[0084] Similarly, the first-level score prediction model established for all vibration type indicators can be shown in Table 3:

[0085] Table 3. The first-level score prediction model established based on a certain vehicle model

[0086]

[0087] Furthermore, the objective measurement data at the target measuring point position is input into the established first-level scoring prediction model for first-level prediction, and the first-level scoring data of each vibration type index can be obtained.

[0088] S130. Determine a vibration-related index corresponding to the driving comfort index from among a plurality of vibration type indexes.

[0089] Among them, the driving comfort index can be a quantitative standard index used to evaluate the comfort experience provided by the vehicle to the driver and passengers during driving. Exemplarily, the driving comfort index can be the degree of comfort felt by the driver and passengers when the vehicle to be tested travels over different road conditions, such as: primary comfort index, secondary comfort index and impact comfort index. Vibration-related indexes can be a series of parameter indicators used to further describe the ride comfort of the vehicle. Specifically, vibration-related indexes can reflect the vehicle's response to various road surface irregularities and how these responses affect the comfort of the driver and passengers. Exemplarily, the vibration-related index of the primary comfort index in the driving comfort index can be vertical movement, body shaking, softness, pitching and forward and backward movement; the vibration-related index of the secondary comfort index in the driving comfort index can be bumpy feeling and crushing vibration feeling; the vibration-related index of the impact comfort index in the driving comfort index can be impact intensity, residual vibration, and limit impact.

[0090] S140, inputting the index scoring data of the vibration-related index into the secondary scoring prediction model for prediction to obtain the secondary scoring data of the driving comfort index.

[0091] Similarly, the secondary scoring prediction model can refer to a mathematical model established to convert the objectively measured vehicle vibration parameters into quantitative indicators that can predict subjective evaluation data when conducting a vehicle ride comfort test. Based on this, the secondary scoring data can be a higher-level scoring data obtained by further summarizing and analyzing the primary scoring data, which can reflect the overall comfort performance of the vehicle in specific aspects (such as primary comfort index, secondary comfort index, impact comfort index, etc.).

[0092] It can be understood that since there are multiple vibration-related indicators when establishing the secondary scoring prediction model, when establishing the secondary scoring prediction model, the primary scoring data of multiple vibration-related indicators can be used as independent variables according to the vibration-related indicators, and the multivariate modeling method of the ridge regression estimation algorithm can be used to establish a functional relationship model between the subjective evaluation data and the objective measurement data.

[0093] For example, the secondary scoring prediction model for the primary comfort index of vehicle driving can use the primary scoring prediction model of the vibration type indexes of vertical movement, body shaking, softness, pitching and front and rear swaying. After the primary prediction, the primary scoring data of the above five vibration type indexes are used as independent variables to establish the secondary scoring prediction model. The fitting curve and coefficient results of the secondary scoring prediction model of the primary comfort index can be referred to Figure 1d , where it can be seen that the fitting curve 105 is relatively close to the original data curve 107 used for fitting, that is, the fitting effect is good. The fitting equation of its secondary score prediction model can be shown as follows:

[0094] Y 初级舒适性 =-0.635+0.128×y1+0.323×y2+0.291×y3+0.211×y4+0.156×y5

[0095] In the formula, y1 represents the first-level scoring data of the vertical motion index; y2 represents the first-level scoring data of the body shaking index; y3 represents the first-level scoring data of the softness index; y4 represents the first-level scoring data of the pitch index; y5 represents the first-level scoring data of the front and rear movement index.

[0096] Optionally, the prediction error of the secondary score prediction model of the primary comfort index is calculated. Figure 1e is the error analysis result, please refer to Figure 1e ,It can be obtained that the maximum prediction error of the secondary rating prediction model is only 4.81%, the prediction error is very small, and the prediction effect is good.

[0097] Furthermore, by inputting the index scoring data of the vibration-related index into the fitting equation of the secondary scoring prediction model of the primary comfort index, the secondary scoring data of the primary comfort index, which is a driving comfort index, can be obtained.

[0098] S150: Integrate the secondary scoring data based on the driving comfort index to obtain the vehicle driving comfort.

[0099] Among them, the vehicle ride comfort can be used to reflect the overall feeling of the comfort experience provided by the vehicle to the driver and passengers during driving. For example, the predicted data after the unified analysis of subjective and objective factors can be used as the vehicle ride comfort data. Specifically, the hierarchical modeling method can also be used to take the secondary scoring data of the ride comfort index as the independent variable, and also establish a deeper functional relationship model between the subjective evaluation data and the objective measurement data, integrate the secondary scoring data of the ride comfort index, and finally obtain the vehicle ride comfort scoring data.

[0100] Optionally, a stepwise regression hierarchical modeling method can be used to establish an overall score prediction model and perform stepwise prediction to finally obtain the vehicle ride comfort score data. Specifically, firstly, based on the objective measurement data (X1, X2, ...X 10 ) to establish a first-level score prediction model (y1, y2, ...y 10 ), perform a first-level prediction to obtain the first-level scoring data; then, according to the vibration-related indicators, take the first-level scoring data of multiple vibration-related indicators as independent variables to establish a second-level scoring prediction model (y Ⅰ ,y Ⅱ ,y Ⅲ ), perform secondary prediction to obtain secondary scoring data; finally, establish an overall scoring prediction model (y) based on the secondary scoring data of the secondary scoring prediction model and perform overall prediction to obtain vehicle ride comfort scoring data (Y). For example, Figure 1f As shown, an overall score prediction model is established and step-by-step prediction is performed to finally obtain the vehicle ride comfort score data.

[0101] In the above implementation, first, multiple vibration type indicators are divided according to the vehicle ride comfort, and the subjective evaluation data on the multiple vibration type indicators and the objective measurement data at multiple preset measuring points are obtained and processed and analyzed. Secondly, the objective measurement is input into the first-level scoring prediction model for first-level prediction and first-level scoring data is obtained. Further, the vibration-related indicators corresponding to the ride comfort indicators are determined again among the multiple vibration type indicators, and the indicator scoring data of the vibration-related indicators are input into the second-level scoring prediction model for prediction to obtain the second-level scoring data of the ride comfort indicators. Finally, these data are integrated to evaluate the overall ride comfort of the vehicle. At this point, an efficient and accurate method for predicting vehicle ride comfort based on subjective and objective consistency is achieved.

[0102] In some embodiments, the driving comfort index corresponds to the first preset working condition, the second preset working condition and the third preset working condition, and the driving comfort index includes a primary comfort index, a secondary comfort index and an impact comfort index. The secondary scoring data based on the driving comfort index is integrated to obtain the vehicle driving comfort. Please refer to the attached Figure 2 ,include:

[0103] S210. Determine working condition scoring data of a first preset working condition according to the secondary scoring data of the primary comfort index and the secondary scoring data of the secondary comfort index.

[0104] Among them, the driving comfort index can be a quantitative standard index used to evaluate the comfort experience provided by the vehicle to the driver and passengers during driving. The primary comfort index, secondary comfort index and impact comfort index can be classified indicators of different levels used to further evaluate the comfort experience provided by the vehicle to the driver and passengers during driving. For example, the primary comfort index can be a first-order smoothness index used to examine the smoothness of the vehicle body movement; the secondary comfort index can be a second-order smoothness index used to evaluate the vibration of the vehicle body and its components; the impact comfort index can be a single impact index used to evaluate the comfort of the axle or wheel alone.

[0105] It is understandable that, since the vehicle is traveling under different working conditions, the corresponding driving comfort of the vehicle will also be different. Specifically, different driving comfort indicators can be respectively corresponded to the first preset working condition, the second preset working condition and the third preset working condition. Among them, the first preset working condition, the second preset working condition and the third preset working condition can be three specific driving conditions or test scenarios defined when evaluating the driving comfort of the vehicle. Exemplarily, the first preset working condition may refer to the working condition of the vehicle driving on a random uneven road surface, that is, a random road condition; the second preset working condition may refer to the driving condition when the vehicle passes through a road obstacle with obvious impact such as a speed bump, that is, a speed bump impact condition; the third preset working condition may refer to the driving condition when the vehicle encounters a road bump or depression that may cause the suspension system to reach its travel limit during driving, that is, a limited impact condition. It is understandable that when conducting a vehicle driving comfort test, the road condition type can be selected from the road conditions that the tested vehicle model often passes through. Exemplarily, it can be shown in the following table:

[0106] Table 4 Road conditions selected based on a vehicle model

[0107]

[0108] It needs to be understood that, among them, performance road cement pavement, second ring asphalt repair pavement (40km / h), second ring asphalt repair pavement (60km / h), high ring cement pavement, fourth phase smooth asphalt pavement and Belgian road belong to the operating conditions when vehicles are driving on randomly uneven roads, that is, they belong to random road conditions; speed bumps belong to the driving conditions when vehicles pass through road obstacles with obvious impact such as speed bumps, that is, they belong to speed bump impact conditions; long wave road belongs to the driving conditions when the vehicle encounters road bumps or depressions that may cause the suspension system to reach its travel limit during driving, that is, it belongs to limited impact conditions.

[0109] Further, according to the index score data of the vibration-related index, the secondary score prediction model is input to perform prediction, and after the secondary score data of the ride comfort index is obtained, the working condition score data of the first preset working condition is determined according to the secondary score data of the primary comfort index and the secondary score data of the secondary comfort index. Exemplarily, for the first preset working condition, the secondary score data of the primary comfort index and the secondary score data of the secondary comfort index are used as independent variables, and the working condition score prediction model of the first preset working condition is established using the ridge regression method, and the fitting equation of the working condition score prediction model can be shown as follows:

[0110] Y 第一工况 =-0.032+0.501Y 初级舒适性 +0.501Y 次级舒适性

[0111] Where Y 初级舒适性 Represents the secondary scoring data of the primary comfort index; Y 次级舒适性 Secondary rating data representing secondary comfort indicators.

[0112] Furthermore, under the six random road conditions of the first preset working condition, objective measurement data are obtained to obtain secondary scoring data of the primary comfort index and secondary scoring data of the secondary comfort index, which are then input into the fitting equation of the working condition scoring prediction model to obtain the working condition scoring data of the first preset working condition.

[0113] S220. Determine working condition scoring data of a second preset working condition and working condition scoring data of a third preset working condition according to the primary scoring data of the vibration-related index of the impact comfort index.

[0114] It should be understood that since the impact comfort index can be a single impact index used to evaluate the comfort of the axle or wheel separately, and the vibration-related index of the impact comfort index can be an impact strength index, a residual vibration index, and a limited impact index. Furthermore, the impact strength index, the residual vibration index, and the limited impact index can correspond to the speed bump impact condition and the limited impact condition. Therefore, when determining the working condition scoring data of the second preset working condition and the working condition scoring data of the third preset working condition, it is necessary to integrate and analyze the primary scoring data of the vibration-related index of the impact comfort index to obtain the working condition scoring data of the second preset working condition and the working condition scoring data of the third preset working condition.

[0115] S230, integrating the working condition scoring data of the first preset working condition, the working condition scoring data of the second preset working condition, and the working condition scoring data of the third preset working condition to obtain the vehicle driving comfort.

[0116] It can be understood that after the above steps, the ridge regression model is again performed based on the six working condition scoring data of the first preset working condition, one working condition scoring data of the second preset working condition, and one working condition scoring data of the third preset working condition, and the prediction model of the final vehicle ride comfort can be obtained. Further, the objective measurement data collected under different preset working conditions are input as independent variables into the prediction model of the final vehicle ride comfort to obtain the vehicle ride comfort. Exemplarily, the fitting equation of the established prediction model of vehicle ride comfort can be shown as follows:

[0117] Y 整体舒适度 =-2.91+0.11Y 第一工况 -0.04Y 第二工况 +0.12Y 第三工况 +0.2Y 第四工况

[0118] +0.19Y 第五工况 +0.61Y 第六工况 +0.42Y 第七工况 -0.12Y 第八工况

[0119] Where Y 第一工况 , Y 第二工况、 …Y 第八工况 Indicates the working condition scoring data corresponding to 8 preset working conditions.

[0120] In the above implementation, by establishing a model based on different road conditions, the ride comfort score of the whole vehicle can be directly fitted based on the objective measurement data of vehicle smoothness measured under the preset working conditions. This reduces the subjective evaluation differences of testers, reduces the time cost of enterprises in subjective and objective evaluation tests, and improves the efficiency of vehicle research and development.

[0121] In some embodiments, the plurality of vibration type indicators include a residual vibration indicator, an impact strength indicator, and a limit impact indicator, and the vibration-related indicators of the impact comfort indicator include a residual vibration indicator, an impact strength indicator, and a limit impact indicator. The working condition scoring data of the second preset working condition and the working condition scoring data of the third preset working condition are determined according to the first-level scoring data of the vibration-related indicators of the impact comfort indicator. Please refer to the attached Figure 3 ,include:

[0122] S310. Determine working condition scoring data of a second preset working condition according to the primary scoring data of the residual vibration index and the primary scoring data of the impact strength index.

[0123] For example, for the second preset working condition, the first-level scoring data of the impact strength index in the impact comfort index and the first-level scoring data of the residual vibration index in the impact comfort index can be used as independent variables, and the ridge regression method is used to establish a working condition scoring prediction model for the second preset working condition. The fitting equation of the working condition scoring prediction model can be shown as follows:

[0124] Y 第二工况 =1.334+0.419y 冲击强度 +0.391y 余振

[0125] In the formula, y 冲击强度 Represents the first-level scoring data of the impact strength index; 余振 Represents the first-level scoring data of the residual vibration indicator.

[0126] Furthermore, under a random road condition of the second preset working condition, objective measurement data is obtained to obtain the first-level scoring data of the impact strength index and the first-level scoring data of the residual vibration index, and they are input into the fitting equation of the working condition scoring prediction model to obtain the working condition scoring data of the second preset working condition.

[0127] S320. Determine working condition scoring data of a third preset working condition according to the first-level scoring data of the limit impact index.

[0128] Similarly, for the third preset working condition, the first-level scoring data of the limit impact index in the impact comfort index can be used as an independent variable, and a working condition scoring prediction model for the third preset working condition can be established using a single variable modeling method. The fitting equation of the working condition scoring prediction model can be shown as follows:

[0129] Y 第三工况 =10-0.173z+0.0021z 2

[0130] Where z represents the objective measurement data measured at the Z-direction measuring point position at the guide rail measuring point.

[0131] Furthermore, under a random road condition of the third preset working condition, objective measurement data measured at the Z-direction measuring point position of the vehicle at the guide rail measuring point is obtained, and is input into the fitting equation of the working condition score prediction model to obtain the working condition score data of the third preset working condition.

[0132] In the above implementation, by establishing a model based on different road conditions, the comfort score of the whole vehicle can be directly fitted based on the objective measurement data of vehicle ride comfort measured under the preset working conditions. This shortens the test process, thereby reducing the time cost of the enterprise in subjective and objective evaluation tests and improving vehicle R&D efficiency.

[0133] In some embodiments, vibration sensors are respectively mounted at multiple preset measuring points, and the vibration sensors are used to detect vibration signals on each vibration type indicator when the vehicle is driving under different working conditions. Figure 4 , obtain objective measurement data at any preset measuring point by:

[0134] S410 . For each vibration type index, determine vibration time series data of the vehicle at any preset measuring point based on the vibration signal detected by the vibration sensor.

[0135] Among them, vibration time series data can refer to vibration signals recorded in a time series, which can be used to reflect the vibration conditions caused by the vehicle driving under different working conditions. Specifically, for each vibration type index, a vibration sensor mounted at different preset measuring points of the vehicle to be tested can detect the vibration state of the vehicle driving under different working conditions and convert it into an electrical signal. Furthermore, the vibration sensor data time curve at the preset measuring point position is recorded by a data acquisition device, and the vibration time series data of the vehicle at any preset measuring point position is obtained.

[0136] S420: Analyze the vibration time series data to obtain vibration parameter data of the vehicle at any preset measuring point.

[0137] Among them, the vibration parameter data is parameter data reflecting the vibration conditions of the vehicle under different working conditions obtained by quantitatively describing the vibration conditions of the vehicle on each vibration type index. Exemplarily, the vibration parameter data may include the maximum amplitude data of the vibration signal generated by the vehicle under different working conditions; it may also include the maximum instantaneous vibration data obtained by analyzing and processing the maximum amplitude data; it may also include the root mean square value data obtained by analyzing and processing the vibration time series data. It can be understood that when the vehicle is driving, the basic input of the vehicle vibration is the road surface roughness, and the road surface roughness input mainly includes pulse input and random input. Among them, the random input vibration is used to evaluate the impact of the random vibration generated when the car passes on a random uneven road surface on comfort. The pulse input vibration is used to evaluate the impact of the pulse vibration generated when the car passes obstacles such as potholes and speed bumps on comfort. Therefore, when analyzing the vibration time series data, it is also necessary to process the situation separately.

[0138] Specifically, for random input vibration, the single-axis RMS value at different frequencies can be used for evaluation and analysis. Exemplarily, for random input driving conditions, the vibration direction can be divided into x, y, and z axes, wherein the x axis represents the front-to-back direction, the y axis represents the left-to-right direction, and the z axis represents the vertical direction. Further, the RMS values ​​of the three axes of x, y, and z at different frequencies can be calculated for further subsequent application. It can be understood that since the main influencing conditions of the primary comfort index and the secondary comfort index are the random vibrations generated when the car passes on a random uneven road surface, the vibration parameter analysis method for random input vibration can be used to further analyze the vibration frequency data. Specifically, since the reasons affecting primary comfort are mainly caused by low-frequency body motion results, when analyzing the vibration of the primary comfort index, a relatively low frequency range can be taken for analysis. Since the reasons affecting primary comfort are usually related to the mode of the vehicle suspension or the mode of the floor, when analyzing the vibration of the secondary comfort index, a relatively high frequency range can be analyzed.

[0139] Furthermore, for pulse input vibration, the root mean square value evaluation method can be run to analyze the peak value or impulse response of the vibration using the integral time constant to reflect the characteristics of transient vibration or accidental impact. For example, the vibration amplitude is defined as the maximum transient vibration value (MTVV), that is, a w The maximum value of vibration in the time history (t0) is defined as follows:

[0140]

[0141] MTVV=max[a w (t0)]

[0142] In the formula, a w (t0) is the instantaneous frequency-weighted acceleration; τ is the running average integration time; t is time; t0 is the instantaneous time.

[0143] Optionally, the peak-to-peak value data of the vibration timing curve can also be used for evaluation and analysis. Specifically, the difference between the maximum and minimum values ​​of the signal waveform is calculated using a function or algorithm in the analysis tool to obtain the change in signal amplitude for further subsequent application.

[0144] Optionally, for the input analysis of the residual vibration of the vehicle, an auxiliary evaluation method may be used, for example, such as the fourth-order root mean square value method or the running root mean square method. The fourth-order root mean square value method requires the calculation of the fourth-order vibration dose value (VDV value), and the calculation formula is as follows:

[0145]

[0146] Where T is the vibration measurement time and aw(t) is the instantaneous frequency-weighted acceleration.

[0147] Optionally, the attenuation time can be used to evaluate and analyze the residual vibration input of the vehicle. For example, the time from the start of the vibration impact to the moment when the vibration decays to a certain threshold can be calculated, and this time can be used as the attenuation time data for further subsequent applications.

[0148] S430: Using the vibration parameter data at any preset measuring point as the objective measurement data at any preset measuring point.

[0149] It is understandable that for different preset measuring point positions, it is necessary to consider the importance of the preset measuring point positions in contributing to vehicle comfort and their sensitivity to different types of vibration responses. Specifically, appropriate vibration parameter data is selected according to different road surface input types, and the vibration parameter data is used as objective measurement data at the preset measuring point positions.

[0150] In the above-mentioned implementation mode, in combination with the vehicle's dynamic model and data analysis results, the vibration time series data is analyzed in different situations and different vibration parameter data are obtained by selecting different methods to process, and further special evaluations are performed on specific driving conditions (such as random uneven roads, speed bumps, long-wave roads, etc.), so that comfort problems can be more accurately identified and solved, and the comfort performance of the vehicle under different driving conditions can be more accurately evaluated.

[0151] In some embodiments, the driving comfort index includes an impact comfort index; the vibration time series data is analyzed to obtain the vibration parameter data of the vehicle at any preset measuring point. Figure 5a ,include:

[0152] S510 , with respect to the impact comfort index, performing time domain analysis processing on the vibration time series data to obtain vibration peak value data of the vehicle at any preset measuring point position.

[0153] The vibration peak value data may refer to the maximum amplitude data of the vibration signal generated by the vehicle under different working conditions. Specifically, the vibration time series data captured by the vibration sensor at a preset measuring point when the vehicle is under different working conditions may be recorded by a data acquisition device, and the vibration peak value data at the preset measuring point may be extracted by further analyzing the time curve of the vibration time series data in the time domain.

[0154] S520: Using the vibration peak value data as vibration parameter data of the vehicle at any preset measuring point.

[0155] It is understandable that since the main influencing condition of the impact comfort index is the pulse vibration generated when the car passes over obstacles such as potholes and speed bumps, the vibration peak data obtained by the vibration parameter analysis method for pulse input vibration can be used as the vibration parameter data of the vehicle at any preset measuring point under the impact comfort index. For example, Figure 5b It is a time domain diagram of the impact intensity index in the impact comfort index. For the impact intensity index, its peak value-absolute maximum value can be used as the vibration parameter data of the vehicle at any preset measuring point position; Figure 5c It is a time domain diagram of the limit impact index in the impact comfort index. For the limit impact index, the peak-to-peak value of its acceleration time domain signal can be used as the vibration parameter data of the vehicle at any preset measuring point position; Figure 5d It is a time domain diagram of the residual vibration index in the impact comfort index. For the residual vibration index, the attenuation time data obtained in the time domain diagram of the residual vibration index can be used as the vibration parameter data of the vehicle at any preset measuring point.

[0156] In the above implementation, for the impact comfort index, the vibration peak value data is used as the vibration parameter data of the vehicle at any preset measuring point, providing a simple and direct method for quantifying the vibration parameter data. By determining the main influencing factors of each index according to the situation and adopting the most appropriate vibration parameter data processing method, the accuracy of the objective measurement data and the reliability of the evaluation results are improved, and the prediction accuracy of the comfort performance of the vehicle under different driving conditions is further improved.

[0157] In some embodiments, the driving comfort index includes a primary comfort index and a secondary comfort index; the vibration time series data is analyzed to obtain the vibration parameter data of the vehicle at any preset measuring point position; please refer to the attached Figure 6a , also includes:

[0158] S610: For the primary comfort index and the secondary comfort index, the vibration time series data is converted into the time-frequency domain to obtain the vibration frequency data of the vehicle at any preset measuring point.

[0159] Among them, the vibration frequency data can be a parameter used to describe the frequency characteristics of vibration occurrence, reflecting the distribution of vibration events in time. Specifically, for the primary comfort index and the secondary comfort index, the vibration time series data is Fourier transformed and converted into the sum of complex exponential signals at different frequencies, and its power spectrum density is further calculated to obtain the distribution of vibration energy at different frequencies, that is, the vibration frequency data.

[0160] S620: Determine a target frequency interval in a frequency range corresponding to the vibration frequency data.

[0161] Among them, the target frequency range is a frequency range that can reflect the vibration of the vehicle and meets the preset conditions. It should be understood that since the main influencing conditions of the primary comfort index and the secondary comfort index are the random vibrations generated when the car passes over a random uneven road surface, the vibration parameter analysis method for random input vibration can be used to further analyze the vibration frequency data. Specifically, for the primary comfort index, since the reason affecting the primary comfort is mainly caused by the low-frequency body movement results, when analyzing its vibration frequency data, a relatively low frequency range can be used as the target frequency range of the primary comfort index. Exemplarily, the frequency range of 0Hz to 5Hz can be used as the target frequency range of the primary comfort index. For the secondary comfort index, since the reason affecting the primary comfort is usually related to the mode of the vehicle suspension or the mode of the floor, when analyzing its vibration frequency data, a relatively high frequency range can be used as the target frequency range of the secondary comfort index. Exemplarily, the frequency ranges of 4Hz to 15Hz, 5Hz to 25Hz, 25Hz to 100Hz, 6Hz to 23Hz and 10Hz to 30Hz can be used as the target frequency range of the primary comfort index, and the spectrum thereof can be segmented.

[0162] S630: Calculate the vibration frequency data according to the target frequency range to obtain vibration root mean square value data of the vehicle at any preset measuring point.

[0163] Specifically, the vibration direction can be divided into x, y, and z axes, where the x axis represents the front-to-back direction, the y axis represents the left-to-right direction, and the z axis represents the vertical direction. Furthermore, the three axial RMS values ​​of the x, y, and z axes can be further single-axis weighted acceleration root mean square values. Calculation of . For example, Figure 6b It is a frequency response diagram of a certain vibration type index in the primary comfort index. The vibration frequency data of the vehicle at any preset measuring point can be calculated according to the target frequency range, and the vibration root mean square value data at any preset measuring point can be obtained; Figure 6c It is a frequency response diagram of a vibration type index in the secondary comfort index. Similarly, the vibration frequency data of the vehicle at any preset measuring point can be calculated according to the target frequency range, and the vibration root mean square value data at any preset measuring point can be obtained.

[0164] S640: Use the vibration root mean square value data as vibration parameter data of the vehicle at any preset measuring point.

[0165] Likewise, vibration root mean square value data obtained by calculating vibration frequency data of the vehicle at any preset measuring point according to the target frequency interval may be used as vibration parameter data of the vehicle at any preset measuring point.

[0166] In the above-mentioned implementation mode, for the primary comfort index and the secondary comfort index, their vibration root mean square value data are used as the vibration parameter data of the vehicle at any preset measuring point position, and the vibration characteristics of different frequency components are analyzed and processed in more detail, and the key frequency components that have the greatest impact on the comfort of the vehicle are identified. The main influencing factors of each indicator are further determined by different situations and the most appropriate vibration parameter data processing method is adopted, thereby improving the accuracy of objective measurement data and the reliability of evaluation results, and further improving the prediction accuracy of the comfort performance of the vehicle under different driving conditions.

[0167] In some embodiments, the vibration type indicator is any one of vertical movement, body shaking, softness, pitching, forward and backward movement, bumpy feeling and crushing vibration. The position of at least one target measuring point is determined by:

[0168] For each vibration type indicator, a correlation analysis is performed based on the subjective evaluation data of each vibration type indicator and the objective measurement data at multiple preset measuring point positions, and the preset measuring point positions whose correlation analysis results meet the preset correlation conditions are determined as at least one target measuring point position corresponding to each vibration type indicator.

[0169] Among them, the preset correlation condition may refer to a series of standards or thresholds set before performing the correlation analysis between the subjective evaluation data and the objective measurement data, which are used to determine whether the correlation between the subjective feelings and the objective measurement results is strong enough, so as to determine which objective measurement data can effectively reflect the subjective evaluation. Specifically, the correlation analysis may be performed using the Pearson correlation. It is understandable that when the Pearson correlation coefficient r is 0.8≤|r|≤1, the correlation between the samples is extremely strong, that is, the correlation between the subjective feelings and the objective measurement results is strong, so the correlation of 95% can be used as the preset correlation condition.

[0170] Furthermore, for each vibration type indicator, a correlation analysis is performed based on the subjective evaluation data of each vibration type indicator and the objective measurement data at multiple preset measurement points. Please refer to the analysis results. Figure 7 ,from Figure 7 It can be seen that for the vibration type indicator of vertical movement, the correlation result between the objective measurement data and the subjective evaluation data at the preset measuring point position of the B-pillar (right) is the highest, which means that for the vibration type indicator of vertical movement, the preset measuring point position of the B-pillar (right) can be selected as the target measuring point position.

[0171] In the above-mentioned implementation mode, by performing correlation analysis on the subjective evaluation data and the objective measurement data, it is determined which objective measurement data can effectively reflect the subjective evaluation. On the one hand, the points with small correlation are eliminated, and the target measurement point positions with strong correlation with the subjective evaluation data are selected to measure the three-level indicators of smoothness evaluation, so as to simplify the test difficulty and improve the efficiency of subsequent data processing; on the other hand, the correlation degree of the corresponding variable factors is measured, and reliable objective data is established as the proxy data of subjective feelings, thereby realizing an efficient and accurate prediction method of vehicle ride comfort based on subjective and objective consistency.

[0172] The embodiment of the present specification also provides a method for predicting vehicle driving comfort, the method comprising the following steps:

[0173] S802, obtaining subjective evaluation data on multiple vibration type indicators. Each vibration type indicator has a first-level scoring prediction model. The vibration type indicator is an indicator of a preset vibration condition for vehicle driving comfort, which can be any one of vertical movement, body shaking, softness, pitching, front and rear movement, bumpy feeling and crushing vibration.

[0174] S804. Each vibration type index corresponds to at least one target measuring point position in a plurality of preset measuring point positions. A vibration sensor is respectively mounted at the plurality of preset measuring point positions, and the vibration sensor is used to detect the vibration signal on each vibration type index when the vehicle is traveling under different working conditions. For each vibration type index, the vibration time series data of the vehicle at any preset measuring point position is determined based on the vibration signal detected by the vibration sensor.

[0175] S806. The driving comfort index includes an impact comfort index. For the impact comfort index, the vibration time series data is analyzed and processed in the time domain to obtain the vibration peak value data of the vehicle at any preset measuring point.

[0176] S808: Using the vibration peak value data as vibration parameter data of the vehicle at any preset measuring point, wherein the vibration parameter data is obtained by quantitatively describing the vibration condition of the vehicle at each vibration type index.

[0177] S810, the driving comfort index includes a primary comfort index and a secondary comfort index. For the primary comfort index and the secondary comfort index, the vibration time series data is converted into a time-frequency domain to obtain the vibration frequency data of the vehicle at any preset measuring point.

[0178] S812: Determine a target frequency interval in the frequency range corresponding to the vibration frequency data, wherein the target frequency interval is a frequency range that meets preset conditions and can reflect the vibration of the vehicle.

[0179] S814. Calculate the vibration frequency data according to the target frequency range to obtain vibration root mean square value data of the vehicle at any preset measuring point.

[0180] S816: Use the vibration root mean square value data as vibration parameter data of the vehicle at any preset measuring point, wherein the vibration parameter data is obtained by quantitatively describing the vibration condition of the vehicle at each vibration type index.

[0181] S818. Use the vibration parameter data at any preset measuring point as the objective measurement data at any preset measuring point.

[0182] S820. For each vibration type indicator, a correlation analysis is performed based on the subjective evaluation data of each vibration type indicator and the objective measurement data at a plurality of preset measuring point positions, and a preset measuring point position whose correlation analysis results satisfy preset correlation conditions is determined as at least one target measuring point position corresponding to each vibration type indicator.

[0183] S822: Input the objective measurement data at at least one target measuring point into a primary scoring prediction model to perform primary prediction, and obtain primary scoring data for each vibration type indicator.

[0184] S824. Determine a vibration-related index corresponding to the driving comfort index from among the plurality of vibration type indexes.

[0185] S826. Input the index scoring data of the vibration-related index into the secondary scoring prediction model for prediction to obtain the secondary scoring data of the driving comfort index.

[0186] S828: The driving comfort index corresponds to a first preset working condition, a second preset working condition, and a third preset working condition, and the driving comfort index includes a primary comfort index, a secondary comfort index, and an impact comfort index. The working condition scoring data of the first preset working condition is determined according to the secondary scoring data of the primary comfort index and the secondary scoring data of the secondary comfort index.

[0187] S830: The plurality of vibration type indicators include a residual vibration indicator, an impact strength indicator, and a position limiting impact indicator; the vibration related indicators of the impact comfort indicator include a residual vibration indicator, an impact strength indicator, and a position limiting impact indicator; and the working condition scoring data of the second preset working condition is determined according to the primary scoring data of the residual vibration indicator and the primary scoring data of the impact strength indicator.

[0188] S832. Determine the working condition scoring data of the third preset working condition according to the first-level scoring data of the limit impact index.

[0189] S834. Integrate the working condition scoring data of the first preset working condition, the working condition scoring data of the second preset working condition, and the working condition scoring data of the third preset working condition to obtain the vehicle driving comfort.

[0190] It should be understood that, although the various steps in the above flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above flowchart may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0191] The embodiment of this specification also provides a vehicle driving comfort prediction device 800, such as Figure 8 As shown, it includes: a data acquisition module 810, a primary prediction module 820, an index determination module 830, a secondary prediction module 840 and a comfort prediction module 850. Among them:

[0192] The data acquisition module 810 is used to acquire subjective evaluation data on multiple vibration type indicators and objective measurement data at multiple preset measuring point positions. Each vibration type indicator has a first-level scoring prediction model. The vibration type indicator is an indicator of a preset vibration condition for the vehicle's driving comfort. Each vibration type indicator corresponds to at least one target measuring point position in the multiple preset measuring point positions.

[0193] The primary prediction module 820 is used to input the objective measurement data at at least one target measurement point into the primary scoring prediction model to perform primary prediction and obtain primary scoring data for each vibration type indicator.

[0194] The index determination module 830 is used to determine a vibration-related index corresponding to the driving comfort index from among a plurality of vibration type indices.

[0195] The secondary prediction module 840 is used to input the index scoring data of the vibration-related index into the secondary scoring prediction model for prediction, so as to obtain the secondary scoring data of the driving comfort index.

[0196] The comfort prediction module 850 is used to integrate the secondary scoring data based on the driving comfort index to obtain the vehicle driving comfort.

[0197] In some embodiments, the driving comfort index corresponds to a first preset working condition, a second preset working condition and a third preset working condition, and the driving comfort index includes a primary comfort index, a secondary comfort index and an impact comfort index. The comfort prediction module 850 is also used to determine the working condition scoring data of the first preset working condition based on the secondary scoring data of the primary comfort index and the secondary scoring data of the secondary comfort index. The working condition scoring data of the second preset working condition and the working condition scoring data of the third preset working condition are determined based on the primary scoring data of the vibration-related index of the impact comfort index. The working condition scoring data of the first preset working condition, the working condition scoring data of the second preset working condition and the working condition scoring data of the third preset working condition are integrated to obtain the vehicle driving comfort.

[0198] In some embodiments, the plurality of vibration type indicators include a residual vibration indicator, an impact strength indicator, and a position limiting impact indicator, and the vibration related indicators of the impact comfort indicator include a residual vibration indicator, an impact strength indicator, and a position limiting impact indicator. The comfort prediction module 850 is further used to determine the working condition scoring data of the second preset working condition based on the primary scoring data of the residual vibration indicator and the primary scoring data of the impact strength indicator. The working condition scoring data of the third preset working condition is determined based on the primary scoring data of the position limiting impact indicator.

[0199] The specific definition of a vehicle ride comfort prediction device can be found in the definition of a vehicle ride comfort prediction method mentioned above, which will not be repeated here. Each module in the above-mentioned vehicle ride comfort prediction device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0200] The vehicle ride comfort prediction device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0201] The embodiment of the present application also provides a computer device, which may be a terminal, and its internal structure diagram may be as follows: Fig. 9As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for predicting vehicle driving comfort is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball or a touch pad set on the computer device housing, or an external keyboard, touch pad or mouse, etc.

[0202] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0203] The embodiment of the present application also provides a computer-readable storage medium, and the above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or is implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc. Further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0204] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application. The above embodiment illustrates a method, device, device and storage medium for predicting vehicle ride comfort, which can be implemented by a computer chip or entity, or by a product with a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device or a combination of any of these devices. For the convenience of description, the above device is described in terms of functions and is described separately in various units. Of course, when implementing this application, the functions of each unit can be implemented in the same one or more software and / or hardware.

[0205] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present application is described with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each flow and / or box in the flow chart and / or block diagram and the combination of the flow chart and / or box in the flow chart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of a computer or other programmable data processing device produce a device for realizing the function specified in one flow chart or multiple flows and / or one box or multiple boxes of a block chart.

[0206] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0207] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0208] In the description of this specification, the description of reference terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, the terms "first" and "second" are used only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. It should also be noted that the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such a process, method, commodity or device. In the absence of further restrictions, the elements defined by the sentence "including a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements. The various embodiments in this specification are described in a progressive manner, and the same and similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. Since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0209] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0210] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for predicting vehicle driving comfort, characterized in that: The method comprises: Obtaining subjective evaluation data on a plurality of vibration type indicators and objective measurement data at a plurality of preset measuring point positions; wherein each vibration type indicator has a first-level scoring prediction model; the vibration type indicator is an indicator of a preset vibration condition for vehicle ride comfort; each vibration type indicator corresponds to at least one target measuring point position in the plurality of preset measuring point positions; Inputting the objective measurement data at the at least one target measuring point into the primary scoring prediction model for primary prediction to obtain primary scoring data for each vibration type indicator; Determining a vibration-related index corresponding to a driving comfort index from among the plurality of vibration type indexes; Inputting the index scoring data of the vibration-related index into the secondary scoring prediction model for prediction to obtain the secondary scoring data of the driving comfort index; The secondary scoring data based on the driving comfort index is integrated to obtain the vehicle driving comfort.

2. The method according to claim 1, characterized in that: The driving comfort index corresponds to a first preset working condition, a second preset working condition and a third preset working condition, and the driving comfort index includes a primary comfort index, a secondary comfort index and an impact comfort index; The secondary scoring data based on the driving comfort index is integrated to obtain the vehicle driving comfort, including: Determining the working condition scoring data of the first preset working condition according to the secondary scoring data of the primary comfort index and the secondary scoring data of the secondary comfort index; Determining the working condition scoring data of the second preset working condition and the working condition scoring data of the third preset working condition according to the primary scoring data of the vibration-related index of the impact comfort index; The vehicle driving comfort is obtained by integrating the operating condition scoring data of the first preset operating condition, the operating condition scoring data of the second preset operating condition and the operating condition scoring data of the third preset operating condition.

3. The method according to claim 2, characterized in that The multiple vibration type indicators include a residual vibration indicator, an impact strength indicator and a limit impact indicator, and the vibration-related indicators of the impact comfort indicator include the residual vibration indicator, the impact strength indicator and the limit impact indicator; The determining the working condition scoring data of the second preset working condition and the working condition scoring data of the third preset working condition according to the primary scoring data of the vibration related index of the impact comfort index comprises: Determining the working condition scoring data of the second preset working condition according to the first-level scoring data of the residual vibration index and the first-level scoring data of the impact strength index; The working condition scoring data of the third preset working condition is determined according to the first-level scoring data of the limit impact index.

4. The method according to claim 1, characterized in that: Vibration sensors are respectively mounted at the positions of the plurality of preset measuring points, and the vibration sensors are used to detect vibration signals on each vibration type index when the vehicle is traveling under different working conditions; Obtain objective measurement data at any preset measuring point by: For each of the vibration type indicators, determining the vibration time series data of the vehicle at any of the preset measuring points based on the vibration signal detected by the vibration sensor; Analyze the vibration time series data to obtain vibration parameter data of the vehicle at any of the preset measuring points; wherein the vibration parameter data is obtained by quantitatively describing the vibration condition of the vehicle at each vibration type index; The vibration parameter data at any preset measuring point position is used as the objective measurement data at any preset measuring point position.

5. The method according to claim 4, characterized in that The driving comfort index includes an impact comfort index; the vibration time series data is analyzed to obtain vibration parameter data of the vehicle at any preset measuring point; including: According to the impact comfort index, the vibration time series data is subjected to time domain analysis processing to obtain vibration peak value data of the vehicle at any preset measuring point position; The vibration peak value data is used as the vibration parameter data of the vehicle at any preset measuring point position.

6. The method according to claim 4, characterized in that The driving comfort index includes a primary comfort index and a secondary comfort index; the vibration time series data is analyzed to obtain vibration parameter data of the vehicle at any preset measuring point; including: For the primary comfort index and the secondary comfort index, the vibration time series data is converted into a time-frequency domain to obtain vibration frequency data of the vehicle at any preset measuring point; Determining a target frequency interval in the frequency range corresponding to the vibration frequency data; wherein the target frequency interval is a frequency range that meets preset conditions and can reflect the vibration condition of the vehicle; Calculating the vibration frequency data according to the target frequency range to obtain vibration root mean square value data of the vehicle at any preset measuring point; The vibration root mean square value data is used as the vibration parameter data of the vehicle at any preset measuring point position.

7. The method according to claim 1, characterized in that The vibration type index is any one of vertical movement, body shaking, soft feeling, pitching, forward and backward movement, bumpy feeling and crushing vibration feeling; The position of at least one target measuring point is determined by: For each vibration type indicator, a correlation analysis is performed based on the subjective evaluation data of each vibration type indicator and the objective measurement data at the multiple preset measuring point positions, and the preset measuring point position whose correlation analysis result meets the preset correlation conditions is determined as at least one target measuring point position corresponding to each vibration type indicator.

8. A vehicle driving comfort prediction device, characterized in that: The device comprises: A data acquisition module, used to acquire subjective evaluation data on a plurality of vibration type indicators and objective measurement data at a plurality of preset measuring point positions; wherein each vibration type indicator has a first-level scoring prediction model; the vibration type indicator is an indicator of a preset vibration condition for vehicle ride comfort; each vibration type indicator corresponds to at least one target measuring point position in the plurality of preset measuring point positions; A primary prediction module, used for inputting the objective measurement data at the at least one target measuring point position into the primary scoring prediction model to perform primary prediction, and obtain primary scoring data of each vibration type index; An index determination module, used to determine a vibration-related index corresponding to a driving comfort index from among the plurality of vibration type indices; A secondary prediction module, used for inputting the index scoring data of the vibration-related index into the secondary scoring prediction model for prediction, so as to obtain the secondary scoring data of the driving comfort index; The comfort prediction module is used to integrate the secondary scoring data based on the driving comfort index to obtain the vehicle driving comfort.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images