A method, device, equipment and medium for evaluating NVH performance attenuation of electric drive system

Abstract

The present application discloses a method, device, equipment and medium for evaluating the NVH performance attenuation of an electric drive system, and relates to the field of NVH performance evaluation of an electric drive system. The method comprises obtaining a sequence value of historical NVH performance; determining a model parameter based on the sequence value; constructing a prediction model based on the model parameter, the prediction model being used to predict the NVH performance attenuation of the electric drive system at a preset time point; extracting a characteristic value based on the prediction model, and establishing an evaluation model based on the characteristic value, the evaluation model being used to evaluate the NVH performance attenuation. The present application realizes the prediction of the NVH performance attenuation trend.

Description

Technical Field

[0001] The present application relates to the field of NVH performance evaluation, and in particular to a method, device, equipment and medium for evaluating NVH performance attenuation of an electric drive system. Background Art

[0002] Electric drive system NVH refers to the noise, vibration and harshness generated by the electric drive system (including motors, controllers, reducers and other components) used in electric vehicles. With the rapid development of electric vehicle technology, the NVH performance of electric drive systems has become an important indicator for measuring the overall quality and ride comfort of vehicles. The NVH performance attenuation of electric drive systems refers to the gradual deterioration of the performance of electric drive systems in terms of noise, vibration and harshness over time and changes in usage conditions.

[0003] As system integration increases, the electric drive system of new energy vehicles may bring more complex NVH performance issues while providing higher efficiency and performance.

[0004] However, existing NVH performance evaluation methods rely on subjective evaluation and lack the prediction of NVH performance attenuation trends, which has certain limitations. Summary of the invention

[0005] The purpose of this application is to provide a method, device, equipment and medium for evaluating the NVH performance attenuation of an electric drive system, which can predict the NVH performance attenuation trend.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for evaluating NVH performance attenuation of an electric drive system, comprising:

[0008] Obtaining the sequence value of the historical NVH performance of the prediction target;

[0009] determining model parameters based on the sequence values;

[0010] Building a prediction model based on the model parameters, the prediction model is used to predict the NVH performance attenuation of the electric drive system at a preset time point;

[0011] Characteristic values ​​are extracted based on the prediction model, and an evaluation model is established according to the characteristic values, wherein the evaluation model is used to evaluate the NVH performance attenuation.

[0012] In a second aspect, the present application provides an electric drive system NVH performance attenuation evaluation device, comprising:

[0013] An acquisition module, used to obtain the sequence value of historical NVH performance;

[0014] A determination module, configured to determine model parameters based on the sequence value;

[0015] A construction module, used to construct a prediction model based on the model parameters, wherein the prediction model is used to predict the NVH performance attenuation of the electric drive system at a preset time point;

[0016] An evaluation module is used to extract characteristic values ​​based on the prediction model and establish an evaluation model according to the characteristic values, wherein the evaluation model is used to evaluate the NVH performance attenuation.

[0017] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-described methods for evaluating NVH performance attenuation of an electric drive system.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for evaluating NVH performance attenuation of an electric drive system.

[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0020] The present application provides a method, device, equipment and medium for evaluating the NVH performance attenuation of an electric drive system. By obtaining the sequence values ​​of historical NVH performance, determining the model parameters according to the sequence values, and constructing a prediction model according to the model parameters, the prediction model is used to predict the NVH performance attenuation of the electric drive system at a preset time point, thereby realizing the prediction of the NVH performance attenuation trend. Based on the prediction model, characteristic values ​​are extracted, and an evaluation model is established according to the characteristic values. The evaluation model is used to evaluate the NVH performance attenuation, providing a scientific basis for the optimization and maintenance of the electric drive system. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 This is an application environment diagram of an electric drive system NVH performance attenuation evaluation method in one embodiment of the present application;

[0023] Figure 2 A schematic flow chart of a method for evaluating NVH performance attenuation of an electric drive system provided in one embodiment of the present application;

[0024] Figure 3 A schematic diagram of a process for obtaining a sequence value of historical NVH performance of a predicted target provided in an embodiment of the present application;

[0025] Figure 4 A schematic diagram of functional modules of a device for evaluating NVH performance attenuation of an electric drive system provided in one embodiment of the present application;

[0026] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0029] It can be understood that the electric drive system NVH performance prediction method provided in the embodiment of the present application is used for the electric drive system of new energy vehicles, and its NVH performance will develop in the future.

[0030] NVH is the abbreviation of Noise, Vibration and Harshness. It is a concept in the field of engineering technology, especially in the automotive manufacturing industry. NVH characteristics are related to the ride comfort, quietness and overall driving experience of the vehicle. Noise refers to various sounds generated during the operation of the vehicle, including engine noise, tire-road noise, wind resistance noise, etc. These sounds may affect the comfort of passengers. Vibration refers to the vibration phenomenon caused by different reasons in the structure or components of the vehicle, such as vibration caused by engine operation, bumps caused by uneven road surface, etc. Excessive vibration not only affects comfort, but may also pose a threat to the durability and safety of the vehicle. Harshness is a more subjective evaluation index used to describe the degree of discomfort or unpleasantness caused to passengers by the combined effects of noise and vibration. It is related to how "rough" or unacceptable these factors are to people's perception. Manufacturers of automobiles and other vehicles use NVH engineering to analyze, simulate and optimize these factors to improve the overall quality and market competitiveness of their products.

[0031] like Figure 1 As shown, the electric drive system NVH performance attenuation evaluation method provided in the embodiment of the present application can be applied to the hardware environment and / or software environment formed by the terminal 102 and the server. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, or it can be integrated on the server 104, or it can be placed on the cloud or other servers. The terminal 102 can send the acquired sequence values ​​of the historical NVH performance of the prediction target to the server 104, and the server 104 receives the sequence values ​​of the historical NVH performance of the prediction target. For the sequence values ​​to be processed, the server 104 determines the model parameters based on the sequence values, and constructs a prediction model based on the model parameters. The prediction model is used to predict the NVH performance attenuation of the electric drive system at a preset time point, extracts characteristic values ​​based on the prediction model, and establishes an evaluation model based on the characteristic values. The evaluation model is used to evaluate the NVH performance attenuation. The server 104 can feedback the obtained prediction model and evaluation model to the terminal 102. In addition, in some embodiments, the NVH performance attenuation evaluation method can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly process the sequence values ​​of the historical NVH performance of the prediction target to be processed to obtain a prediction model and an evaluation model, or the server 104 can obtain the sequence values ​​of the historical NVH performance of the prediction target to be processed from the data storage system, and process the sequence values ​​to construct a prediction model and an evaluation model.

[0032] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0033] For ease of understanding and explanation, the following Figures 2 to 5 A method, device, equipment and medium for evaluating NVH performance attenuation of an electric drive system provided in an embodiment of the present application are described in detail.

[0034] In an exemplary embodiment, Figure 2 As shown, a method for evaluating the NVH performance attenuation of an electric drive system is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S201 to S204. Among them:

[0035] Step S201, obtaining a sequence value of historical NVH performance of a prediction target;

[0036] Specifically, NVH performance data refers to a series of numerical values ​​and analysis results obtained by comprehensively and quantitatively evaluating the three key indicators of vehicle noise, vibration and harshness in the field of automotive engineering. These data are important parameters for measuring the ride comfort, driving experience and overall quality of a car. During the operation of the electric drive system, in order to accurately monitor its working status, a series of sensors are deployed at the key parts of the electric drive. This series of sensors mainly includes acceleration sensors and sensors specifically used to measure sound pressure and sound power. Key parts include but are not limited to motors, transmission belts and bearings, because these places are the main sources of vibration and noise. Exemplarily, multiple acceleration sensors and multiple sound pressure sensors are installed on the rotor, stator and housing of the electric drive system. Through these sensors, vibration signals and noise signals of the electric drive system during operation at rated power can be collected in real time.

[0037] In another exemplary embodiment of the present application, Figure 3 As shown, the above step S201 is replaced by the following steps S2011 to S2012:

[0038] Step S2011, acquiring NVH performance data based on a durability test of the same electric drive system, wherein the electric drive system is provided with a sensor, wherein the time period corresponding to the NVH performance data includes an initial time period and a decay time period, and the number of cycles preset in the durability test is equivalent to the mileage under actual road conditions;

[0039] Specifically, the sensors preset in the electric drive system can collect NVH (Noise, Vibration, and Harshness) performance data, including the collection of vibration signals and noise signals. In the process of collecting NVH performance data, a time period can be preset first, and an initial time period and an attenuation time period can be selected. The initial time period refers to the stage when the electric drive system starts working and the vibration signal and noise signal just begin to be generated; and the attenuation time period refers to the time period after the NVH performance decays over time.

[0040] Optionally, in order to accurately obtain vibration signals and noise signals, a variety of sensors are arranged at key parts of the electric drive system, illustratively, there are speed sensors, sound pressure sensors and sound power sensors. These sensors can collect vibration signals and noise signals during the operation of the electric drive system in real time. Among them, the acceleration sensor is mainly used to measure the acceleration of the object, which can be used to evaluate the magnitude and frequency of the vibration, and the sound pressure and sound power sensors are used to measure the intensity and energy of the sound to further understand the characteristics of the noise. Through the real-time collection of the above sensors, we can comprehensively monitor and evaluate the NVH performance of the electric drive system, thereby providing strong data support for optimizing the performance of the electric drive system. At the same time, these data can also be used to analyze and solve the vibration and noise problems that may occur in the operation of the electric drive system, so as to improve the reliability and comfort of the electric drive system.

[0041] Specifically, the purpose of durability testing is to simulate the wear and aging process that the electric drive system experiences during actual use in order to predict its performance over its entire life cycle. By repeatedly performing a series of standardized test cycles in a laboratory environment, the aging of the electric drive system can be accelerated, thereby quickly obtaining its NVH performance data after long-term operation.

[0042] It is understood that in order to ensure the accuracy and representativeness of the durability test, an equivalent relationship between the number of cycles and the actual road mileage is established. This relationship is based on the study of the performance degradation rate of the electric drive system under different working conditions. Specifically, each test cycle includes but is not limited to the following categories:

[0043] City Road Cycle: Simulates daily commuting with frequent starting and stopping procedures and low-speed driving conditions commonly found in heavy traffic.

[0044] High Speed ​​Cycle: The vehicle is driven at a relatively high speed, simulating the conditions a driver would experience on a long road trip.

[0045] Hill Cycle: Contains steep uphill and downhill driving to simulate mountain road driving. The vehicle needs to overcome gravity and provide enough power to cope with the uphill driving, while properly managing the braking force on the downhill to prevent the brake system from overheating.

[0046] Each test cycle is equivalent to a certain actual mileage, ensuring that 1,000 cycles are equivalent to 300,000 kilometers of driving distance. This setting of equivalent mileage not only saves time and resources, but also provides a test environment similar to actual road conditions.

[0047] Step S2012: pre-process the NVH performance data to obtain the sequence value of the historical NVH performance.

[0048] Specifically, the original NVH performance data often contains a wide range of frequency components, such as noise signals from the surrounding environment and other interference sources. In order to improve the noise quality, a bandpass filter is used to pre-process the data to remove irrelevant frequency components and retain key signal frequency bands. In this embodiment, the frequency range of the filter is set at 10Hz to 1kHz, which covers the main vibration signals and noise signals in the NVH characteristics of the electric drive system. After filtering, the signal is usually represented in the frequency domain. The signal is converted from a frequency domain signal to a time domain signal using an inverse Fourier transform (IFT) to facilitate subsequent feature extraction and analysis. The signal is normalized so that the signal amplitude is adjusted to the same range to eliminate the impact of amplitude differences on subsequent analysis.

[0049] Time domain features such as mean, standard deviation, maximum, minimum and energy are extracted from the signal. The mean of the signal reflects the average level of the signal, the standard deviation measures the fluctuation of the signal strength, the maximum value identifies the maximum amplitude of the signal, the minimum value identifies the minimum amplitude of the signal, and the energy represents the total energy of the signal in a specified time period. The mean, standard deviation, maximum, minimum and energy of each signal segment together constitute the characteristics of the signal. For the frequency bands of vibration signals and noise signals, the short-time Fourier transform (STFT) is used to analyze the local spectral characteristics of the signal, such as the main frequency and frequency bandwidth. The short-time Fourier transform is a time-frequency analysis tool that can reflect the frequency composition of the signal that changes over time. The wavelet transform method is used to extract the local features of the signal in the time and frequency dimensions. All the features extracted above are integrated into a feature vector. Each element in the feature vector corresponds to a specific feature value. For example, if 10 time domain features and 10 frequency domain features are extracted, the length of the feature vector is 10.

[0050] In this embodiment, the signal is divided into multiple segments of 1 second in length, with an overlap of 0.5 seconds between each segment to maintain a balance between time resolution and frequency resolution. The Hanning window is used to reduce boundary effects, which helps to smooth the edges of the signal and avoid artifacts introduced by sudden signal truncation. For each time window, the feature extraction step and the feature vector formation step need to be repeated to generate a feature vector. As the time window moves, a series of feature vectors are obtained. The above feature vectors are arranged in chronological order to form a feature vector sequence, which can be regarded as a feature representation of the signal changing over time, that is, a sequence value of the historical NVH performance.

[0051] Step S202, determining model parameters based on the sequence value.

[0052] Before step S202, it is necessary to determine the stability of the sequence values ​​of historical NVH performance. If it is stable, the original sequence composed of the sequence values ​​of historical NVH performance is a stable sequence; if it is not stable, differential processing is performed based on the sequence values ​​in the original sequence until a stable sequence is obtained, wherein the number of differential processing is the differential order of the prediction model.

[0053] Specifically, stationarity mainly refers to the stability of the statistical characteristics of time series data. Stationarity means that the statistical characteristics of the time series data, such as the mean, variance, and autocovariance function, remain unchanged throughout the observation period and will not change significantly over time. Before performing a sequence analysis on the sequence values ​​of historical NVH performance, it is first necessary to determine whether these sequence values ​​meet the conditions of stationarity. Because if the sequence data is non-stationary, its statistical characteristics will change over time, which will lead to the instability of the nature of the sequence data, thereby affecting the prediction ability of the model.

[0054] It can be understood that when the sequence value is judged to be non-stationary, the sequence data is transformed by differential processing until a stationary time data sequence is obtained. The differential operation is used to calculate the difference between adjacent items in the sequence. In this way, the trend and seasonal effects in the data are eliminated, making the time series data more stable.

[0055] For example, a first difference can be calculated by the following formula:

[0056] ;

[0057] in, is the differenced sequence value, is the current value of the original sequence, It is the previous value of the original sequence.

[0058] It can be understood that if the sequence still exhibits non-stationary characteristics after a single difference, a higher-order difference is usually required, such as a second difference. The second difference can be understood as a second difference of the first difference sequence, and so on, that is, multiple differences are performed on the sequence until the sequence exhibits stationarity. The number of times the sequence values ​​are differentiated will affect the order of the forecasting model. In time series analysis, the number of differences can be used as the difference order in the autoregressive integrated moving average (ARIMA) model.

[0059] For example, if two differencing steps are required to make the series stationary, then the order of differencing for the forecasting model is 2.

[0060] In one embodiment, based on the obtained stationary sequence, the number of autoregressive terms p and the number of moving average terms q of the model are determined by AIC and BIC order determination methods. A prediction model is constructed based on the number of autoregressive terms p, the number of moving average terms q and the difference order d.

[0061] Specifically, the two order determination methods of AIC (Akaike Information Criterion) and BIC (Bayesian Information Criterion) are used to determine the number of autoregressive terms p and the number of moving average terms q, so as to further improve the accuracy of the prediction results. First, a set of stable sequence data needs to be obtained. If the original data is not stable, it needs to be differentiated to make it stable, and the differential order d is recorded. Then, a reasonable range is selected for the number of autoregressive terms p and the number of moving average terms q. For example, the range of the number of autoregressive terms p and the number of moving average terms q is from 0 to 4 respectively. The ARIMA model is fitted through all possible (p, d, q) combinations, and the AIC value and BIC value of each model are calculated. The smaller the AIC value and BIC value, the better the model. By comparing the AIC and BIC values ​​of different models, the smallest AIC value and BIC value are selected to establish the optimal (p, d, q) combination, that is, to establish the optimal ARIMA (p, d, q) model.

[0062] The formula of AIC is expressed as:

[0063] AIC=2k-2ln(L);

[0064] The formula for BIC is:

[0065] BIC = kln(n)-2ln(L);

[0066] Among them, k represents the number of parameters in the model; n represents the number of samples; and L represents the maximum likelihood estimate of the model.

[0067] Optionally, when performing time series analysis, the autocorrelation coefficient and partial autocorrelation coefficient corresponding to different p and q can be generated according to the value range of the number of autoregressive terms p and the number of sliding average terms q. Time series are analyzed based on autocorrelation coefficients and partial autocorrelation coefficients. For the autocorrelation coefficient, the average value of the time series must be calculated first. For any two observations in the time series data separated by k time units, and , calculate its covariance, the covariance calculation formula is:

[0068] ;

[0069] in, represents the observed value at time point t; represents the observed value k time units before time t; represents the mean of all observations at time point t; represents the mean of all observations at time point tk.

[0070] The autocorrelation coefficient is obtained from the covariance formula:

[0071] ;

[0072] in, express For each lag period k, a multiple regression model is constructed, where is the dependent variable, as independent variable.

[0073] The partial autocorrelation coefficient can be expressed as:

[0074]

[0075] in, Indicates that in the removal and Under the influence , The size of the correlation.

[0076] Specifically, the sequence values ​​in the sample set are substituted into the autocorrelation coefficient and partial autocorrelation coefficient to obtain a series of p and q values, where p and q represent the order parameters in the autoregressive model (AR) and the moving average model (MA), respectively. Each specific p value and q value corresponds to a function value of the autocorrelation coefficient and the partial autocorrelation coefficient. After obtaining the autocorrelation coefficient and partial autocorrelation coefficient corresponding to different p and q, the final p and q can be determined by using the information criterion to construct an autoregressive model (AR), a moving average model (MA) or an ARIMA model.

[0077] Step S203: constructing a prediction model based on the model parameters, where the prediction model is used to predict the NVH performance degradation of the electric drive system at a preset time point.

[0078] Specifically, a prediction model is constructed based on the number of autoregressive terms p, the number of sliding average terms q and the difference order d, and characteristic values ​​characterizing the NVH performance degradation are extracted from the residuals of the prediction model. The above characteristic values ​​include standard deviation, skewness and kurtosis. The characteristic values ​​are used to predict the NVH performance degradation of the electric drive system at a preset time point.

[0079] For example, a time series data set is preset, and a suitable ARIMA (p, d, q) model is determined. The original time series is first differentiated to obtain a new sequence, and the new sequence is used to fit the ARIMA model. For each observation point, the ARIMA model is used for prediction. The difference between the observed value and the predicted value is calculated as the residual, and the characteristic values ​​that characterize the attenuation of NVH performance are extracted from the residual. The characteristic values ​​include standard deviation, skewness and kurtosis.

[0080] The prediction model is expressed as:

[0081] = ;

[0082] in,{ , t=1, 2, …, n} represents the time series, d represents the difference order of the prediction model, represents the p-order autoregressive process coefficient, represents the error term coefficient of the q-order moving average process, B represents the backoff operator, represents the error term of the data at time point t.

[0083] For example, the parameters of the ARIMA model are set to (1, 1, 2), that is, the values ​​of the forecast model order, the number of autoregressive terms, and the number of moving average terms are: d=1, p=1, q=2, respectively. and The value of depends on the best fitting parameters obtained through time series analysis. For the ARIMA (1, 1, 2) model, =0.2, = 0.3 or 0.5, B=1, the above values ​​can be used to obtain the evaluation function of the time series, which is expressed as follows:

[0084] = .

[0085] The above prediction model can predict the standard deviation, skewness and kurtosis values ​​corresponding to different moments to characterize the key features of NVH performance degradation. For example, the standard deviation (σ_res=0.02g), skewness (S_res=0.05) and kurtosis (K_res=3.0) are extracted at time 0, and the standard deviation, skewness and kurtosis values ​​at other moments are shown in Table 1. Through the analysis of these characteristic values, the NVH performance degradation of the electric drive system at different time points can be predicted more accurately.

[0086] Step S204: extracting characteristic values ​​based on the prediction model, and establishing an evaluation model according to the characteristic values, wherein the evaluation model is used to evaluate the attenuation of NVH performance.

[0087] The extracted eigenvalues ​​are used to establish an evaluation model, and the support vector machine method is used to establish an NVH attenuation level evaluation model to evaluate the attenuation characteristics. The evaluation model is expressed as:

[0088] = + ;

[0089] in, represents the attenuation level value evaluated at time point t+h at time point t; Represents the mean of time series data; represents the estimated values ​​of the decaying series of the parameters of the prediction model; Represents the error term of the data at time point t+hj.

[0090] It can be understood that according to the NVH attenuation level evaluation model, the vibration acceleration root mean square and sound pressure peak values ​​every 1 hour between time 0 and time 1000 can be obtained, where the vibration acceleration root mean square value is used to represent the vibration value, and the sound pressure peak value is used to represent the noise value. The vibration acceleration root mean square value and the sound pressure peak value at the beginning and end are directly measured and obtained by the instrument. The specific data are shown in Table 1.

[0091] Table 1

[0092]

[0093] By observing the changes in the data in Table 1, it can be seen that the root mean square (RMS) of the acceleration shows a gradual downward trend as time goes by. This trend clearly indicates that the force or intensity of the vibration is weakening. Considering this change, we can speculate that this may be due to wear between mechanical parts or other types of performance degradation. Further analysis shows that the steady reduction in the peak sound pressure may mean that the sound insulation ability of the electric drive system is gradually increasing, or the source of noise generation is gradually weakening. The standard deviation of the residuals is also gradually decreasing, indicating that the prediction and evaluation accuracy of the model is improving. In addition, the skewness of the residuals has changed from a slight positive skew to a negative skew, indicating that the operating condition of the system may have changed to some extent. The kurtosis of the residuals has decreased from 3.00 to 1.80, indicating that the distribution shape has gradually changed from sharp to flat, which may be an obvious sign that the system performance has gradually changed from drastic changes to stable and gentle.

[0094] Based on the same inventive concept, the embodiment of the present application also provides a device for implementing the above-mentioned electric drive system NVH performance attenuation evaluation. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the device embodiments of one or more electric drive system NVH performance attenuation evaluation methods provided below can be referred to the above limitations on the electric drive system NVH performance attenuation evaluation methods, which will not be repeated here.

[0095] In an exemplary embodiment, Figure 4 As shown, a device for evaluating NVH performance attenuation of an electric drive system is provided, comprising:

[0096] An acquisition module 410 is used to acquire a sequence value of historical NVH performance of a prediction target;

[0097] A determination module 420, configured to determine a model parameter based on the sequence value;

[0098] A construction module 430 is used to construct a prediction model based on the model parameters, wherein the prediction model is used to predict the NVH performance attenuation of the electric drive system at a preset time point;

[0099] The evaluation module 440 is used to extract characteristic values ​​based on the prediction model, and establish an evaluation model according to the characteristic values, wherein the evaluation model is used to evaluate the NVH performance attenuation.

[0100] As an optional implementation, the acquisition module 410 is specifically configured to:

[0101] NVH performance data is obtained based on a durability test of the same electric drive system, in which a sensor is provided, wherein the time period corresponding to the NVH performance data includes an initial time period and a decay time period, and the number of cycles preset in the durability test is equivalent to the mileage under actual road conditions;

[0102] The NVH performance data is preprocessed to obtain the sequence value of historical NVH performance.

[0103] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store sequence values ​​of the historical NVH performance of the predicted target. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes the NVH performance attenuation evaluation method of the electric drive system.

[0104] Those skilled in the art will understand that Figure 5 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.

[0105] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0106] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0109] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0110] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0111] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for evaluating NVH performance attenuation of an electric drive system, characterized in that: The electric drive system NVH performance attenuation evaluation method includes: Obtaining the sequence value of the historical NVH performance of the prediction target; determining model parameters based on the sequence values; A prediction model is constructed based on the model parameters, and characteristic values ​​characterizing NVH performance degradation are extracted from the residual of the prediction model, wherein the characteristic values ​​are used to predict NVH performance degradation of the electric drive system at a preset time point, wherein the characteristic values ​​include standard deviation, skewness and kurtosis; Establishing an evaluation model according to the characteristic value, wherein the evaluation model is used to evaluate the attenuation of the NVH performance; The evaluation model is expressed as: = + ； in, represents the attenuation level value evaluated at time point t+h at time point t; Represents the mean of time series data; represents the estimated values ​​of the decaying series of the parameters of the prediction model; represents the error term of the data at the time point t+hj; according to the evaluation model, the root mean square value of the vibration acceleration and the peak value of the sound pressure every 1 hour between the time 0 and the time 1000 can be obtained, wherein the value of the root mean square value of the vibration acceleration is used to represent the vibration value, and the peak value of the sound pressure is used to represent the noise value; The obtaining of the sequence value of the historical NVH performance of the prediction target specifically includes: Acquiring NVH performance data based on a durability test of the same electric drive system, wherein the electric drive system is provided with a sensor, wherein the time period corresponding to the NVH performance data includes an initial time period and a decay time period, and the number of cycles preset in the durability test is equivalent to the mileage under actual road conditions; Preprocessing the NVH performance data to obtain a sequence value of the historical NVH performance; Before determining the model parameters based on the sequence value, the NVH performance of the electric drive system is attenuated The assessment method also includes: Performing a stability determination on the sequence values ​​of the historical NVH performance; If it is stable, the original sequence formed by the sequence values ​​of the historical NVH performance is a stable sequence; if it is not stable Stable, performing differential processing based on the sequence values ​​in the original sequence until a stable sequence is obtained, wherein the number of differential processing is the differential order of the prediction model; The determining of the model parameters based on the sequence value specifically includes: Based on the obtained stationary sequence, the number of autoregressive terms and the number of moving average terms of the prediction model are determined by AIC and BIC order determination methods; The model parameters include the number of autoregressive terms, the number of moving average terms and the difference order.

2. An electric drive system NVH performance attenuation evaluation device, characterized in that: The electric drive system NVH performance attenuation evaluation device comprises: An acquisition module, used to obtain a sequence value of the historical NVH performance of the prediction target; A determination module, configured to determine model parameters based on the sequence value; A construction module, used to construct a prediction model based on the model parameters, extract characteristic values ​​characterizing NVH performance degradation from the residual of the prediction model, and the characteristic values ​​are used to predict the NVH performance degradation of the electric drive system at a preset time point, wherein the characteristic values ​​include standard deviation, skewness and kurtosis; An evaluation module, used for establishing an evaluation model according to the characteristic value, wherein the evaluation model is used for evaluating the attenuation of the NVH performance; The evaluation model is expressed as: = + ； in, represents the attenuation level value evaluated at time point t+h at time point t; Represents the mean of time series data; represents the estimated values ​​of the decaying series of the parameters of the prediction model; represents the error term of the data at the time point t+hj; according to the evaluation model, the root mean square value of the vibration acceleration and the peak value of the sound pressure every 1 hour between the time 0 and the time 1000 can be obtained, wherein the value of the root mean square value of the vibration acceleration is used to represent the vibration value, and the peak value of the sound pressure is used to represent the noise value; The acquisition module is specifically used for: Acquiring NVH performance data based on a durability test of the same electric drive system, wherein the electric drive system is provided with a sensor, wherein the time period corresponding to the NVH performance data includes an initial time period and a decay time period, and the number of cycles preset in the durability test is equivalent to the mileage under actual road conditions; Preprocessing the NVH performance data to obtain a sequence value of the historical NVH performance; Before determining the model parameters based on the sequence value, the NVH performance of the electric drive system is attenuated The evaluation unit is also used for: Performing a stability determination on the sequence values ​​of the historical NVH performance; If it is stable, the original sequence formed by the sequence values ​​of the historical NVH performance is a stable sequence; if it is not stable Stable, performing differential processing based on the sequence values ​​in the original sequence until a stable sequence is obtained, wherein the number of differential processing is the differential order of the prediction model; The determining module is specifically used for: Based on the obtained stationary sequence, the number of autoregressive terms and the number of moving average terms of the prediction model are determined by AIC and BIC order determination methods; The model parameters include the number of autoregressive terms, the number of moving average terms and the difference order.

3. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for evaluating the NVH performance attenuation of an electric drive system as described in claim 1.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating NVH performance attenuation of an electric drive system as claimed in claim 1 are implemented.

Images