Vehicle abnormal jitter detection method and device, electronic equipment, medium and vehicle

Abstract

The invention relates to a vehicle abnormal jitter detection method and device, electronic equipment, a medium and a vehicle. The method comprises the following steps: acquiring a target time sequence corresponding to an original time sequence signal; selecting a plurality of segmentation points in the target time sequence to segment the target time sequence to obtain a plurality of target time subsequences; fitting each target time subsequence based on the correlation between the front and back data in each target time subsequence to obtain a fitting value representing the fitting effect of each target time subsequence; under the condition that the sum of the fitting values of the fitting effects of the target time subsequences is smaller than a preset threshold value, the multiple segmentation points are recognized as abnormal points, and an abnormal point list composed of the multiple abnormal points is obtained; and identifying an abnormal jitter interval according to the time interval of each abnormal point in the abnormal point list. According to the method, the problem of missing detection in abnormal detection of the vehicle state information can be avoided.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a method, device, electronic equipment, medium and vehicle for detecting abnormal vehicle vibration. Background Art

[0002] When developing a new vehicle control strategy, road testing is an essential verification step. By analyzing key vehicle status signals, the implementation effect of the vehicle control strategy can be evaluated.

[0003] When analyzing vehicle status signals, continuous abnormal jitter is a very dangerous condition. For torque-related or speed-related status signals, their continuous abnormal jitter not only affects drivability, but also endangers the driver's safety. Therefore, accurately detecting the continuous abnormal jitter in the vehicle status signal is of great significance. However, the types of working conditions faced by vehicles are complex and diverse, which makes the vehicle status signal have a high degree of randomness. For example, for vehicle status signals such as battery bus actual power, motor torque, and motor speed, their statistical indicators such as mean and variance are functions of time. Therefore, the vehicle status signal is a typical non-stationary time series signal, and abnormality detection of non-stationary time series signals is very difficult.

[0004] In the related art, when using anomaly detection methods based on prediction errors for non-stationary signals, a prediction model is used to predict abnormal points. However, during the training process of the prediction model, the sample data involved in the training data does not cover all possible abnormal working conditions. Therefore, the trained prediction model is only effective under some working conditions, resulting in missed detection problems. Therefore, how to avoid missed detection in vehicle status information anomaly detection is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to solve the above technical problems, the present disclosure provides a method, device, electronic device, medium and vehicle for detecting abnormal vehicle vibration.

[0006] In a first aspect, the present disclosure provides a method for detecting abnormal vehicle vibration, comprising:

[0007] Obtaining a target time series corresponding to an original time series signal; the original time series signal is a time series signal corresponding to a vehicle state signal, and the target time series is a stationary time series obtained by preprocessing the original time series signal;

[0008] Selecting a plurality of segmentation points in the target time series to segment the target time series to obtain a plurality of target time subsequences;

[0009] Fitting each target time subsequence based on the correlation between the preceding and following data in each target time subsequence to obtain a fitting value representing the fitting effect of each target time subsequence;

[0010] When the sum of the fitting values ​​of the fitting effects of the target time subsequences is less than a preset threshold, the plurality of segmentation points are identified as abnormal points, and an abnormal point list consisting of the plurality of abnormal points is obtained;

[0011] The abnormal jitter interval is identified according to the time interval of each abnormal point in the abnormal point list.

[0012] As an optional implementation of the embodiment of the present disclosure, the method further includes:

[0013] When the fitting value of the fitting effect of each target time subsequence is greater than or equal to the preset threshold, randomly selecting a plurality of preset segmentation points in the target time series to segment the target time series to obtain a plurality of preset time subsequences;

[0014] Fitting each preset time subsequence based on the correlation between the preceding and following data in each preset time subsequence to obtain a fitting value representing the fitting effect of each preset time subsequence;

[0015] When the sum of the fitting values ​​of the fitting effects of the preset time subsequences is less than the preset threshold, the plurality of preset segmentation points are identified as abnormal points, and an abnormal point list consisting of the plurality of abnormal points is obtained.

[0016] As an optional implementation of the embodiment of the present disclosure, the step of obtaining a target time series corresponding to the original time series signal includes:

[0017] Get the original time series signal;

[0018] Performing low-pass filtering on the original time series signal to obtain a first time series;

[0019] Perform difference processing on the first time series to obtain a target time series.

[0020] As an optional implementation of the embodiment of the present disclosure, the low-pass filtering of the original time series signal to obtain the first time series includes:

[0021] Performing global spectrum analysis on the original time series signal to determine the cutoff frequency of the low-pass filter;

[0022] A low-pass filter is designed based on the cut-off frequency to remove burrs and redundant peaks in the original time series signal to obtain a first time series.

[0023] As an optional implementation of the embodiment of the present disclosure, the designing of a low-pass filter based on the cutoff frequency to remove burrs and redundant peaks in the original time series signal to obtain a first time series includes:

[0024] According to the cut-off frequency, the sampling rate is designed to be f s , a low-pass filter of order n;

[0025] The first time series after low-pass filtering is calculated according to the difference equation of the low-pass filter:

[0026]

[0027] Among them, Y(k) represents the sequence value at the kth moment, n is the order of the filter, and b 0 ~b n is the input signal coefficient, a 0 ~a n is the output signal coefficient, b 0 ~b n and a 0 ~a n The filter order n, cutoff frequency f c Sure.

[0028] As an optional implementation of the embodiment of the present disclosure, performing differential processing on the first time series to obtain a target time series includes:

[0029] Performing first-order difference processing on the first time series to obtain a first-order difference series;

[0030] or;

[0031] Perform second-order difference processing on the first time series to obtain a second-order difference series.

[0032] As an optional implementation of the embodiment of the present disclosure, the identifying the abnormal jitter interval according to the time interval of each abnormal point in the abnormal point list includes:

[0033] Taking the first point in the abnormal point list as the starting point of the target abnormal jitter interval, and adding the starting point to the first list;

[0034] Starting from the second point in the abnormal point list, the time interval between the current abnormal point and the previous abnormal point is calculated. If the time interval is greater than the preset time interval, the previous abnormal point is determined to be the end point of the target abnormal jitter interval, and the current abnormal point is determined to be the starting point of the next target abnormal jitter interval. The end point is added to the second list, and the judgment logic is repeatedly executed to obtain multiple abnormal jitter intervals.

[0035] As an optional implementation of the embodiment of the present disclosure, the method further includes:

[0036] Calculate the effective length of each abnormal jitter interval according to each starting point and each ending point in the first list and the second list;

[0037] According to the size relationship between the effective length of each abnormal jitter interval and the effective length threshold, determine whether each abnormal jitter interval in the multiple initial abnormal jitter intervals is a continuous abnormal jitter interval, and determine the continuous abnormal jitter interval in the multiple abnormal jitter intervals as a valid abnormal jitter interval; the valid abnormal jitter interval is used to represent the abnormal jitter interval in the multiple abnormal jitter intervals whose effective length is greater than or equal to the effective length threshold;

[0038] Acquire at least one differential sequence corresponding to at least one valid abnormal jitter interval;

[0039] Performing fast Fourier transform processing on the at least one differential sequence to obtain spectrum data corresponding to the at least one differential sequence;

[0040] According to the magnitude relationship between the spectrum data corresponding to the at least one differential sequence and the threshold spectrum data, determining whether each valid abnormal jitter interval belongs to a false detection interval;

[0041] The abnormal jitter intervals whose spectrum data is less than the threshold spectrum data in the valid abnormal jitter intervals are determined as false detection intervals, and the false detection intervals are removed, and the false detection interval judgment logic is repeatedly executed until all valid abnormal jitter intervals are traversed to obtain at least one target abnormal jitter interval.

[0042] In a second aspect, an embodiment of the present disclosure provides a vehicle abnormal vibration detection device, comprising:

[0043] An acquisition module, used to acquire a target time series corresponding to an original time series signal; the original time series signal is a time series signal corresponding to a vehicle state signal, and the target time series is a stationary time series obtained by preprocessing the original time series signal;

[0044] An initialization module, used for selecting a plurality of segmentation points in the target time series to segment the target time series to obtain a plurality of target time subsequences;

[0045] A calculation module, used for fitting each target time subsequence based on the correlation between the preceding and following data in each target time subsequence, to obtain a fitting value representing the fitting effect of each target time subsequence;

[0046] A detection module, configured to identify the plurality of segmentation points as abnormal points when the sum of the fitting values ​​of the fitting effects of the respective target time subsequences is less than a preset threshold, and obtain an abnormal point list consisting of the plurality of abnormal points;

[0047] The identification module is used to identify the abnormal jitter interval according to the time interval of each abnormal point in the abnormal point list.

[0048] As an optional implementation of the embodiment of the present disclosure, the detection module is further used to:

[0049] When the fitting value of the fitting effect of each target time subsequence is greater than or equal to the preset threshold, randomly selecting a plurality of preset segmentation points in the target time series to segment the target time series to obtain a plurality of preset time subsequences;

[0050] Fitting each preset time subsequence based on the correlation between the preceding and following data in each preset time subsequence to obtain a fitting value representing the fitting effect of each preset time subsequence;

[0051] When the sum of the fitting values ​​of the fitting effects of the preset time subsequences is less than the preset threshold, the plurality of preset segmentation points are identified as abnormal points, and an abnormal point list consisting of the plurality of abnormal points is obtained.

[0052] As an optional implementation of the embodiment of the present disclosure, the acquisition module includes:

[0053] An acquisition unit, used for acquiring original time series signals;

[0054] A filtering unit, configured to perform low-pass filtering on the original time series signal to obtain a first time series;

[0055] A processing unit, configured to perform differential processing on the first time series to obtain a target time series;

[0056] As an optional implementation of the embodiment of the present disclosure, the filtering unit is specifically used for:

[0057] Performing global spectrum analysis on the original time series signal to determine the cutoff frequency of the low-pass filter;

[0058] A low-pass filter is designed based on the cut-off frequency to remove burrs and redundant peaks in the original time series signal to obtain a first time series.

[0059] As an optional implementation of the embodiment of the present disclosure, the processing unit is specifically configured to:

[0060] Performing first-order difference processing on the first time series to obtain a first-order difference series;

[0061] or;

[0062] Perform second-order difference processing on the first time series to obtain a second-order difference series.

[0063] As an optional implementation of the embodiment of the present disclosure, the identification module is specifically used to:

[0064] Taking the first point in the abnormal point list as the starting point of the target abnormal jitter interval, and adding the starting point to the first list;

[0065] Starting from the second point in the abnormal point list, the time interval between the current abnormal point and the previous abnormal point is calculated. If the time interval is greater than the preset time interval, the previous abnormal point is determined to be the end point of the target abnormal jitter interval, and the current abnormal point is determined to be the starting point of the next target abnormal jitter interval. The end point is added to the second list, and the judgment logic is repeatedly executed to obtain multiple abnormal jitter intervals.

[0066] As an optional implementation of the embodiment of the present disclosure, the device further includes a filtering module, and the filtering module is specifically used to:

[0067] Calculate the effective length of each abnormal jitter interval according to each starting point and each ending point in the first list and the second list;

[0068] According to the size relationship between the effective length of each abnormal jitter interval and the effective length threshold, determine whether each abnormal jitter interval in the multiple initial abnormal jitter intervals is a continuous abnormal jitter interval, and determine the continuous abnormal jitter interval in the multiple abnormal jitter intervals as a valid abnormal jitter interval; the valid abnormal jitter interval is used to represent the abnormal jitter interval in the multiple abnormal jitter intervals whose effective length is greater than or equal to the effective length threshold;

[0069] Acquire at least one differential sequence corresponding to at least one valid abnormal jitter interval;

[0070] Performing fast Fourier transform processing on the at least one differential sequence to obtain spectrum data corresponding to the at least one differential sequence;

[0071] According to the magnitude relationship between the spectrum data corresponding to the at least one differential sequence and the threshold spectrum data, determining whether each valid abnormal jitter interval belongs to a false detection interval;

[0072] The abnormal jitter intervals whose spectrum data is less than the threshold spectrum data in the valid abnormal jitter intervals are determined as false detection intervals, and the false detection intervals are removed, and the false detection interval judgment logic is repeatedly executed until all valid abnormal jitter intervals are traversed to obtain at least one target abnormal jitter interval.

[0073] As an optional implementation of the embodiment of the present disclosure, the device further includes:

[0074] The output module is used to use the length of each target abnormal jitter interval as the corresponding abnormal jitter duration and output each abnormal jitter duration.

[0075] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: one or more processors;

[0076] a storage device for storing one or more programs,

[0077] When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle abnormal vibration detection method as described in any embodiment of the first aspect.

[0078] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle abnormal vibration detection method as described in any one of the embodiments in the first aspect.

[0079] In a fifth aspect, the disclosed embodiment provides a vehicle, comprising: the electronic device as described in the third aspect.

[0080] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art: obtaining a target time series corresponding to an original time series signal, wherein the original time series signal is a vehicle status signal, and the target time series is a stationary time series obtained after preprocessing the original time series signal; selecting multiple segmentation points in the target time series to segment the target time series to obtain multiple target time subsequences; fitting each target time subsequence based on the correlation between previous and next data in each target time subsequence to obtain a fitting value characterizing the fitting effect of each target time subsequence; when the fitting value of the fitting effect of each target time subsequence is less than a preset threshold, identifying multiple segmentation points as abnormal points to obtain an abnormal point list consisting of multiple abnormal points; and identifying abnormal jitter intervals according to the time intervals of each abnormal point in the abnormal point list. For the non-stationary time series signal of the vehicle, a stationary target time series is obtained after preprocessing. Since the vehicle state signal often contains data under different working conditions, there may be mutations or anomalies between these working conditions. By selecting multiple segmentation points in the target time series to segment the target time series, multiple target time subsequences are obtained, and the fitting value used to characterize the fitting effect of each target time subsequence is calculated. By selecting different segmentation points, the target time subsequence is divided for multiple times, so as to obtain multiple target time subsequences under multiple different segmentation conditions, and multiple fitting values ​​for characterizing the fitting effect of each target time subsequence. When the sum of the fitting values ​​of the fitting effects of each target time subsequence is less than a preset threshold, that is, a group of segmentation points corresponding to the fitting values ​​less than the preset threshold are obtained from multiple fitting values ​​as abnormal points, so that the change points or abnormal points between different working conditions can be accurately identified, avoiding the problem of missed detection in the process of abnormal detection of vehicle state information. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0082] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0083] Figure 1 is a flow chart of a method for detecting abnormal vehicle vibration provided by an embodiment of the present disclosure;

[0084] Figure 2 is a flow chart of another method for detecting abnormal vehicle vibration provided by an embodiment of the present disclosure;

[0085] Figure 3 is a structural schematic diagram of a vehicle abnormal vibration detection device provided by an embodiment of the present disclosure;

[0086] Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0087] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0088] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0089] Relational terms such as “first” and “second” in the description and claims of the present disclosure are merely used to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0090] In the embodiments of the present disclosure, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present disclosure should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way. In addition, in the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "multiple" refers to two or more.

[0091] Glossary:

[0092] FFT: Fast Fourier Transform, fast Fourier transform.

[0093] BIC: Bayesian information criterion. The Bayesian information criterion is a statistical method for selecting the best model from a finite set of models. Under incomplete intelligence, the partially unknown state is estimated using subjective probability, and then the probability of occurrence is corrected using the Bayesian formula. Finally, the expected value and the corrected probability are used to make the best decision.

[0094] For non-stationary signals, when using anomaly detection methods based on statistical information, it is necessary to narrow the range of normal data points, which may lead to false detection problems; when using anomaly detection methods based on prediction errors, the selection of prediction models is very critical, and improper model selection may also cause false detection and missed detection problems.

[0095] In view of the above problems, the present invention obtains a stable target time series after preprocessing for a non-stationary time series signal of a vehicle. Since the vehicle state signal often contains data under different working conditions, there may be mutations or anomalies between these working conditions. By selecting multiple segmentation points in the target time series to segment the target time series, multiple target time subsequences are obtained, and fitting values ​​for characterizing the fitting effects of each target time subsequence are calculated. By selecting different segmentation points multiple times and dividing the target time subsequence multiple times, multiple target time subsequences under multiple different segmentation conditions and multiple fitting values ​​for characterizing the fitting effects of each target time subsequence are obtained. When the sum of the fitting values ​​of the fitting effects of each target time subsequence is less than a preset threshold, that is, multiple segmentation points corresponding to the fitting values ​​less than the preset threshold are obtained from the multiple fitting values ​​as abnormal points, so that the change points or abnormal points between different working conditions can be accurately identified, thereby avoiding the problem of missed detection in the process of detecting abnormal vehicle state information.

[0096] In some embodiments, Figure 1 As shown, a method for detecting abnormal vehicle vibration is provided, comprising the following steps S11-S15:

[0097] S11. Obtain a target time series corresponding to the original time series signal.

[0098] The original time series signal is a time series signal corresponding to the vehicle status signal. For example, the original time series signal may be, but is not limited to, a non-stationary time series signal such as the actual power of the battery bus, the motor torque, and the motor speed.

[0099] The target time series is a stationary time series obtained by preprocessing the original time series signal, wherein the preprocessing includes low-pass filtering and differential processing.

[0100] In some embodiments, Figure 2 As shown, the above step S11 (obtaining the target time series corresponding to the original time series signal) can be implemented by the following steps:

[0101] S111. Obtain original time series signal.

[0102] Specifically, the original time series signal can be collected periodically in real time by the vehicle end, for example, the collection period is 10 milliseconds.

[0103] S112: Perform low-pass filtering on the original time series signal to obtain a first time series.

[0104] Specifically, given that high-frequency noise can be observed in the time series signals such as the actual power of the battery bus, the motor torque, and the motor speed collected at the vehicle end, a low-pass filter is set to pre-process the signal.

[0105] In some embodiments, the above step S112 (performing low-pass filtering on the original time series signal to obtain the first time series) can be implemented by the following steps:

[0106] a. Perform global spectrum analysis on the original time series signal to determine the cutoff frequency of the low-pass filter.

[0107] Specifically, a global spectrum analysis is performed on the original time series signal to determine the cutoff frequency f of the low-pass filter. c .

[0108] For example, taking the actual power signal of the vehicle-side battery bus as an example, the time series signal of the actual power of the battery bus can be expressed as:

[0109] {P t ,t∈T}={P 1 ,P 2 ,P 3 ,…,P t ,…} Formula (1)

[0110] Among them, {P t} represents a time series with a length of t, reflecting the change of the actual power of the battery bus over time.

[0111] Since the analysis process targets a time series signal of finite length, the actual power time series of the battery bus {P N}:

[0112] {P N}={P 1 ,P 2 ,P 3 ,…,P N} Formula (2)

[0113] The time series signal {P N}, and determine the cutoff frequency f of the low-pass filter c For the time series of the actual power of the vehicle battery bus, the cutoff frequency f c Can be set to 30 Hz.

[0114] b. Designing a low-pass filter based on the cutoff frequency to remove burrs and redundant peaks in the original time series signal to obtain a first time series.

[0115] Optionally, the designing of a low-pass filter based on the cutoff frequency to remove burrs and redundant peaks in the original time series signal to obtain a first time series includes:

[0116] According to the cut-off frequency, the sampling rate is designed to be f s , a low-pass filter of order n;

[0117] Calculating a first time series after low-pass filtering according to a differential equation of the low-pass filter;

[0118]

[0119] Among them, Y(k) represents the sequence value at the kth moment, n is the order of the filter, and b 0 ~b n is the input signal coefficient, a 0 ~a n is the output signal coefficient, b 0 ~b n and a 0 ~a n The filter order n, cutoff frequency f c Sure.

[0120] Specifically, a low-pass filter is used to filter the time series signal {P N} Perform low-pass filtering and design the sampling rate to be f according to the cutoff frequency determined in step a. s , a low-pass filter of order n is used to remove the time series signal {P N}. The difference equation of the low-pass filter can be used to calculate the sequence after low-pass filtering, that is, the first time series {Y N}, the calculation process of the sequence value Y(k) at the kth moment is as follows:

[0121]

[0122] In formula (3), n is the order of the filter, b is 0 ~b n is the input signal coefficient, a 0 ~a n is the output signal coefficient, b 0 ~b n and a 0 ~a n The filter order n, cutoff frequency f cFor a clearer description, the following embodiments of the present disclosure uniformly use the following set to represent the first time series after low-pass filtering:

[0123] {Y N}={Y 1 ,Y 2 ,Y 3 ,…,Y N} Formula (4)

[0124] S113: Perform differential processing on the first time series to obtain a target time series.

[0125] Specifically, the first time series {Y N} to perform difference processing and remove the first time series {Y N}The trend component in .

[0126] In some embodiments, the above step S113 (performing differential processing on the first time series to obtain a target time series) can be implemented in the following manner:

[0127] Performing first-order difference processing on the first time series to obtain a first-order difference series;

[0128] or;

[0129] Perform second-order difference processing on the first time series to obtain a second-order difference series.

[0130] Specifically, the order of differential processing needs to be determined according to the characteristics of the signal. In practical applications, feature selection is performed based on the effect of anomaly detection, and the first-order difference or second-order difference is selected as the feature of the isolation forest algorithm.

[0131] Among them, the calculation formulas for the first-order difference sequence and sequence elements are as follows:

[0132]

[0133] The calculation formulas for the second-order difference sequence and sequence elements are as follows:

[0134]

[0135] For example, for the time series of the actual power of the vehicle battery bus, what needs to be paid attention to is the rate of change of the instantaneous rate of change of power, that is, the second-order difference of the actual power of the battery bus. That is, when there is a sudden change in the rate of change of the instantaneous rate of change of power, it is considered that the vehicle has continuous abnormal shaking. For the time series of the actual speed of the vehicle motor, it is necessary to pay attention to the instantaneous rate of change of the motor speed, that is, the angular acceleration, and analyze whether there is a sudden change in the first-order difference of the actual speed of the motor. If there is a sudden change, it is considered that the vehicle has abnormal shaking. In the subsequent embodiments of the present disclosure, the set in formula (7) is uniformly used to represent the target time series after detrending:

[0136] {D R}={D 1 ,D 2 ,D 3 ,…,D R} Formula (7)

[0137] In addition, it should be noted that when using the difference method to construct anomaly detection features, it is not recommended to do differences higher than the second order. The reason is that a high-order difference sequence will lose too much information and approach a horizontal line.

[0138] S12: Select multiple segmentation points in the target time series to segment the target time series to obtain multiple target time subsequences.

[0139] Specifically, a plurality of separation points are randomly selected in the target time series to segment the target time series, thereby obtaining a plurality of target time subsequences, wherein the segmentation points between the target time subsequences are the initial abnormal points to be identified.

[0140] For example, when the abnormal points to be identified are initially determined, the target time series can be segmented at preset intervals to obtain multiple target time subsequences. The preset intervals can be set according to actual application scenarios and are not specifically limited here.

[0141] S13. Fitting each target time subsequence based on the correlation between the preceding and following data in each target time subsequence to obtain a fitting value representing the fitting effect of each target time subsequence.

[0142] Specifically, each target time subsequence is fitted based on the correlation between the preceding and following data in each target time subsequence, and a fitting value representing the fitting effect of each time subsequence is obtained.

[0143] The change point detection algorithm is used to identify the mutation of the generation parameters of the sequence data. The Bayesian change point detection algorithm is one of the change point detection algorithms. In the embodiment of the present disclosure, the process of obtaining the abnormal point list is described by taking the Bayesian change point detection algorithm as an example.

[0144] Among them, the target time series is the difference series after the difference processing. The fitting results of each target time subsequence are represented by the Bayesian information volume BIC. The first target fitting result is the sum of the BIC values ​​of each target time subsequence.

[0145] Specifically, the target time series is first divided into preset time intervals to obtain multiple target time subsequences and multiple initial abnormal points to be identified. Each target time subsequence is fitted by a piecewise linear regression method, a linear regression model is constructed for different target time subsequences, and the fitting results of each target time subsequence are calculated to obtain a first target fitting result representing the sum of the fitting results of each target time subsequence.

[0146] Based on the Bayesian information criterion, the Bayesian information corresponding to each target time subsequence is calculated. The Bayesian information is calculated using the following formula (8):

[0147] BIC=-2*ln(L)+k*ln(N-2) Formula (8)

[0148] Where k is the number of model parameters, and for the linear regression model, k is 2; N-2 represents the total number of data points in the difference sequence, ln(L) is the log-likelihood function value of the model, and L represents the likelihood function value.

[0149] With the target time subsequence {D i ,D i+1 ,D i+2 ,…,D i+R} as an example, the calculation formula of the likelihood function value of the target time subsequence is as follows:

[0150] L(β 0 ,β 1 )=f(D i β 0 ,β 1 )*f(D i+1 β 0 ,β 1 )*f(D i+2 β 0 ,β 1 )*…f(D i+R β 0 ,β 1 ) Formula (9)

[0151] Among them, f(D i β 0 ,β 1 ) is the data of the target time subseries {D i ,D i+1 ,D i+2 ,…,D i+R}In the model parameters (β 0 ,β 1 ) can be calculated using the probability density function of the normal distribution. The specific calculation formula is as follows:

[0152]

[0153] Where μ is the data of the target time subsequence {D i ,D i+1 ,D i+2 ,…,D i+R}, σ 2 is the data of the target time subseries {D i ,D i+1 ,D i+2 ,…,D i+R} variance.

[0154] For example, the target time series is divided into equal intervals, that is, the difference series {D N-2}, and obtain multiple preset time subsequences. For each preset time subsequence, a linear regression model h(β 0 ,β 1 ) to fit the data points in the preset time subsequence, and use the least squares method to optimize the slope β of the linear regression model 1 With intercept β 0 , complete the fitting of the local time series. Then calculate the BIC value of each target time subsequence and get the sum of the BIC values ​​of each target time subsequence.

[0155] S14. When the sum of the fitting values ​​of the fitting effects of the target time subsequences is less than a preset threshold, the plurality of segmentation points are identified as abnormal points, and an abnormal point list consisting of the plurality of abnormal points is obtained.

[0156] The preset threshold value may be set according to the actual situation of the fitting value and is not specifically limited here.

[0157] Specifically, when the sum of the fitting values ​​of the fitting effects of each target time subsequence is less than a preset threshold, multiple segmentation points are identified as abnormal points, and an abnormal point list consisting of the multiple abnormal points is obtained.

[0158] It should be noted that different preset thresholds can be set to divide the target time subsequence multiple times, so as to obtain more initial abnormal points and avoid missed detection problems.

[0159] In some embodiments, when the fitting value of the fitting effect of each target time subsequence is greater than or equal to the preset threshold, a plurality of preset segmentation points are randomly selected in the target time series to segment the target time series to obtain a plurality of preset time subsequences;

[0160] Fitting each preset time subsequence based on the correlation between the preceding and following data in each preset time subsequence to obtain a fitting value representing the fitting effect of each preset time subsequence;

[0161] When the sum of the fitting values ​​of the fitting effects of the preset time subsequences is less than the preset threshold, the plurality of preset segmentation points are identified as abnormal points, and an abnormal point list consisting of the plurality of abnormal points is obtained.

[0162] Specifically, when the fitting value of the fitting effect of each target time subsequence is greater than or equal to the preset threshold, a plurality of abnormal points to be identified are randomly selected again in the target time series, a plurality of preset time subsequences are determined, and the fitting results of each preset time subsequence are calculated to obtain a second target fitting result representing the sum of the fitting results of each preset time subsequence. When the sum of the fitting values ​​of the fitting effects of each preset time subsequence is less than the preset threshold, the plurality of preset segmentation points are identified as abnormal points. Otherwise, the steps (fitting each preset time subsequence based on the correlation between the previous and next data in each preset time subsequence to obtain a fitting value characterizing the fitting effect of each preset time subsequence; when the sum of the fitting values ​​of the fitting effects of each preset time subsequence is less than the preset threshold, the plurality of preset segmentation points are identified as abnormal points to obtain an abnormal point list consisting of a plurality of abnormal points) are repeatedly executed. It can be understood that the step of selecting abnormal points to be identified and the step of calculating the fitting result are performed for a preset number of times, and a plurality of abnormal points to be identified corresponding to the minimum value of the target fitting result are determined as abnormal points in the first target fitting result and the plurality of second target fitting results, to obtain an abnormal point list consisting of detected abnormal points.

[0163] In some embodiments, the above steps can be implemented as follows:

[0164] a. randomly selecting a plurality of abnormal points to be identified in the target time series, determining a plurality of preset time subsequences according to the plurality of abnormal points to be identified, and calculating the fitting results of each preset time subsequence.

[0165] b. According to the fitting results of the respective preset time subsequences, a second target fitting result representing the sum of the fitting results of the respective preset time subsequences is calculated.

[0166] It should be noted that in the step ab, the multiple randomly selected abnormal points to be identified are different from the multiple initial abnormal points to be identified in the above step S12.

[0167] c. Execute the steps of selecting the abnormal points to be identified and calculating the fitting results for a preset number of times, and determine the multiple abnormal points to be identified corresponding to the minimum value of the target fitting result in the preset number of times as abnormal points.

[0168] The preset number of times can be set according to the actual application scenario and is not specifically limited here. For example, the preset number of times can be 10 times, 15 times, 20 times, etc.

[0169] Specifically, the smaller the sum of the Bayesian information, the better the fitting effect of each linear segment, that is, the more accurate the position of the segmentation point in the piecewise linear fitting algorithm. Try to obtain different initial segmentation point positions through brute force or dynamic programming algorithms, and then calculate the total Bayesian information according to the Bayesian information corresponding to each preset time subsequence to search for the optimal piecewise linear fitting result and optimize the segmentation point position. These segmentation points represent significant change points in the data, that is, the anomalies to be identified.

[0170] d. Arrange the abnormal points in the target time series in ascending order according to the index of the target time series to obtain an abnormal point list.

[0171] Specifically, all the identified abnormal points are sorted into the original sequence {D R} in ascending order, and finally obtain a list of all abnormal points detected by the sliding window algorithm {X M}.

[0172] Since the vehicle status signal often contains data under different working conditions, there may be mutations or anomalies between these working conditions. By selecting multiple segmentation points in the target time series to segment the target time series, multiple target time subsequences are obtained, and the fitting values ​​used to characterize the fitting effect of each target time subsequence are calculated. By selecting different segmentation points, the target time subsequence is divided multiple times, so as to obtain multiple target time subsequences under multiple different segmentation conditions and multiple fitting values ​​used to characterize the fitting effect of each target time subsequence. When the sum of the fitting values ​​of the fitting effects of each target time subsequence is less than a preset threshold, that is, a group of segmentation points corresponding to the fitting values ​​less than the preset threshold are obtained from the multiple fitting values ​​as abnormal points, so that the change points or abnormal points between different working conditions can be accurately identified, avoiding the problem of missed detection in the process of abnormal detection of vehicle status information.

[0173] S15. Identify abnormal jitter intervals according to the time intervals of the abnormal points in the abnormal point list.

[0174] In some embodiments, the above step S15 (identifying the abnormal jitter interval according to the time interval of each abnormal point in the abnormal point list) can be implemented as follows:

[0175] (1) The first point in the abnormal point list is used as the starting point of the target abnormal jitter interval, and the starting point is added to the first list.

[0176] For example, the outlier list {X M The first point in} is taken as the first abnormal jitter interval Ω 1 and adds the starting point to the first list.

[0177] (2) Starting from the second point in the abnormal point list, calculate the time interval between the current abnormal point and the previous abnormal point. If the time interval is greater than the preset time interval, determine the previous abnormal point as the end point of the target abnormal jitter interval, and determine the current abnormal point as the starting point of the next target abnormal jitter interval. Add the end point to the second list, repeat the judgment logic, and obtain multiple abnormal jitter intervals.

[0178] For example, from the list of outliers {X M}, calculate the interval between the current outlier point X(i) and the previous outlier point X(i-1). If the interval between the two exceeds the threshold θ interval , then determine the current abnormal jitter interval Ω j It has ended and needs to be truncated, so the previous abnormal point X(i-1) is used as the current abnormal jitter interval Ω j The end point of the m}, and at the same time, the current abnormal point X(i) is used as the starting point of the next abnormal jitter interval and added to the starting point list {S m}. Repeat the judgment logic to obtain multiple abnormal jitter intervals.

[0179] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art: obtaining a target time series corresponding to an original time series signal, wherein the original time series signal is a vehicle status signal, and the target time series is a stationary time series obtained after preprocessing the original time series signal; selecting multiple segmentation points in the target time series to segment the target time series to obtain multiple target time subsequences; fitting each target time subsequence based on the correlation between previous and next data in each target time subsequence to obtain a fitting value characterizing the fitting effect of each target time subsequence; when the fitting value of the fitting effect of each target time subsequence is less than a preset threshold, identifying multiple segmentation points as abnormal points to obtain an abnormal point list consisting of multiple abnormal points; and identifying abnormal jitter intervals according to the time intervals of each abnormal point in the abnormal point list. For the non-stationary time series signal of the vehicle, a stationary target time series is obtained after preprocessing. Since the vehicle state signal often contains data under different working conditions, there may be mutations or anomalies between these working conditions. By selecting multiple segmentation points in the target time series to segment the target time series, multiple target time subsequences are obtained, and the fitting value used to characterize the fitting effect of each target time subsequence is calculated. By selecting different segmentation points multiple times and dividing the target time subsequence multiple times, multiple target time subsequences under multiple different segmentation conditions and multiple fitting values ​​used to characterize the fitting effect of each target time subsequence are obtained. When the sum of the fitting values ​​of the fitting effects of each target time subsequence is less than a preset threshold, that is, a group of segmentation points whose fitting values ​​are less than the preset threshold are obtained from multiple fitting values ​​as abnormal points, so that the change points or abnormal points between different working conditions can be accurately identified, avoiding the problem of missed detection in the process of abnormal detection of vehicle state information.

[0180] In related technologies, when using anomaly detection methods based on statistical information, it is necessary to narrow the range of normal data points, which may lead to false detection problems; while for anomaly detection based on prediction errors, the selection of prediction models is extremely critical, and improper model selection may also cause false detection problems.

[0181] Based on the false detection problem that occurs in the current vehicle abnormality detection process, the embodiment of the present disclosure further discloses the following steps to avoid the false detection problem. That is, based on the fast Fourier transform algorithm, multiple abnormal jitter intervals are filtered to obtain at least one target abnormal jitter interval. The specific implementation method is as follows:

[0182] A. Calculate the effective length of each abnormal jitter interval according to each starting point and each ending point in the first list and the second list; determine whether each abnormal jitter interval in the multiple initial abnormal jitter intervals is a continuous abnormal jitter interval according to the relationship between the effective length of each abnormal jitter interval and the effective length threshold, and determine the continuous abnormal jitter interval in the multiple abnormal jitter intervals as a valid abnormal jitter interval.

[0183] The effective abnormal jitter interval is used to represent an abnormal jitter interval whose effective length is greater than or equal to an effective length threshold among the multiple abnormal jitter intervals.

[0184] Exemplarily, according to the starting point list of the abnormal jitter interval obtained in the previous step {S m} and the list of end points {E m}Calculate the abnormal jitter interval Ω 1 ~Ω m length, if the current abnormal jitter interval Ω j The length is less than the effective length threshold, and it is determined that the interval is not a continuous abnormal jitter interval, so it is directly selected from the starting point list {S m} and the list of end points {E m}Remove this pair of starting point and ending point to obtain at least one valid abnormal jitter interval.

[0185] B. Obtain at least one differential sequence corresponding to the at least one valid abnormal jitter interval.

[0186] C. Perform fast Fourier transform processing on the at least one differential sequence to obtain spectrum data corresponding to the at least one differential sequence.

[0187] Exemplarily, take out the current abnormal jitter interval Ω j The corresponding local difference sequence [D(S(j)), D(S(j)+1), …, D(E(j)-1), D(E(j))], applies the fast Fourier transform algorithm FFT to the local difference sequence to obtain the current abnormal jitter interval Ω j spectral data.

[0188] D. Determine whether each valid abnormal jitter interval belongs to a false detection interval according to the size relationship between the spectrum data corresponding to the at least one differential sequence and the threshold spectrum data; determine the abnormal jitter interval whose spectrum data is smaller than the threshold spectrum data in each valid abnormal jitter interval as a false detection interval, remove the false detection interval, and repeatedly execute the false detection interval judgment logic until all valid abnormal jitter intervals are traversed to obtain at least one target abnormal jitter interval.

[0189] Exemplarily, the search spectrum peak A max and peak frequency fmax , if the spectrum peak A max Less than the amplitude threshold θ Amplitude , determine the current abnormal jitter interval Ω j The interval that belongs to the false detection is then selected from the starting point list {S m} and the list of end points {E m}Remove this set of starting points S(j) and ending points E(j); repeat the previous step of calculating the local spectrum and this step of removing the false detection interval until all abnormal jitter intervals are traversed.

[0190] The vehicle abnormal jitter detection method provided by the present invention uses a fast Fourier transform algorithm to filter the false detection intervals in multiple abnormal jitter intervals to obtain the final target abnormal jitter interval, thereby avoiding the false detection problem that occurs during the abnormal detection of vehicle status information, thereby accurately detecting the continuous abnormal jitter in the vehicle status signal.

[0191] In some embodiments, after executing the above steps, the following method may also be executed:

[0192] The length of each target abnormal jitter interval is used as the corresponding abnormal jitter duration, and each abnormal jitter duration is output.

[0193] Specifically, according to the filtered starting point list {S w} and the list of end points {E w}, regenerate the abnormal jitter interval Ω 1 ~Ω w , calculate the length of each abnormal jitter interval as the duration of the abnormal jitter, and output each abnormal jitter duration, and then complete the visualization of the results. Thus, it helps R&D personnel to timely discover potential problems in the control strategy and ensure the stability of the vehicle control strategy.

[0194] In some embodiments, reference Figure 4 As shown, a vehicle abnormal vibration detection device 300 is provided, comprising:

[0195] An acquisition module 310 is used to acquire a target time series corresponding to an original time series signal; the original time series signal is a time series signal corresponding to a vehicle state signal, and the target time series is a stationary time series obtained by preprocessing the original time series signal;

[0196] An initialization module 320 is used to select a plurality of segmentation points in the target time series to segment the target time series to obtain a plurality of target time subsequences;

[0197] A calculation module 330 is used to fit each target time subsequence based on the correlation between the preceding and following data in each target time subsequence, and obtain a fitting value representing the fitting effect of each target time subsequence;

[0198] A detection module 340 is configured to identify the plurality of segmentation points as abnormal points when the sum of the fitting values ​​of the fitting effects of the target time subsequences is less than a preset threshold, and obtain an abnormal point list consisting of the plurality of abnormal points;

[0199] The identification module 350 is used to identify the abnormal jitter interval according to the time interval of each abnormal point in the abnormal point list.

[0200] As an optional implementation of the embodiment of the present disclosure, the detection module is specifically used to:

[0201] Randomly selecting a plurality of abnormal points to be identified in the target time series, determining a plurality of preset time subsequences according to the plurality of abnormal points to be identified, and calculating a fitting result of each preset time subsequence;

[0202] Calculating, according to the fitting results of the respective preset time subsequences, a second target fitting result representing the sum of the fitting results of the respective preset time subsequences;

[0203] The steps of selecting the abnormal points to be identified and calculating the fitting results are performed a preset number of times, and a plurality of abnormal points to be identified corresponding to the minimum value of the target fitting result in the preset number of times are determined as abnormal points;

[0204] According to the index of the target time series, each abnormal point in the target time series is arranged in ascending order to obtain an abnormal point list.

[0205] As an optional implementation of the embodiment of the present disclosure, the acquisition module 310 includes:

[0206] An acquisition unit, used for acquiring original time series signals;

[0207] A filtering unit, configured to perform low-pass filtering on the original time series signal to obtain a first time series;

[0208] A processing unit, configured to perform differential processing on the first time series to obtain a target time series;

[0209] As an optional implementation of the embodiment of the present disclosure, the filtering unit is specifically used for:

[0210] Performing global spectrum analysis on the original time series signal to determine the cutoff frequency of the low-pass filter;

[0211] A low-pass filter is designed based on the cut-off frequency to remove burrs and redundant peaks in the original time series signal to obtain a first time series.

[0212] As an optional implementation of the embodiment of the present disclosure, the processing unit is specifically configured to:

[0213] Performing first-order difference processing on the first time series to obtain a first-order difference series;

[0214] or;

[0215] Perform second-order difference processing on the first time series to obtain a second-order difference series.

[0216] As an optional implementation of the embodiment of the present disclosure, the identification module is specifically used to:

[0217] Taking the first point in the abnormal point list as the starting point of the target abnormal jitter interval, and adding the starting point to the first list;

[0218] Starting from the second point in the abnormal point list, the time interval between the current abnormal point and the previous abnormal point is calculated. If the time interval is greater than the preset time interval, the previous abnormal point is determined to be the end point of the target abnormal jitter interval, and the current abnormal point is determined to be the starting point of the next target abnormal jitter interval. The end point is added to the second list, and the judgment logic is repeatedly executed to obtain multiple abnormal jitter intervals.

[0219] As an optional implementation of the embodiment of the present disclosure, the device further includes a filtering module, and the filtering module is specifically used to:

[0220] Calculate the effective length of each abnormal jitter interval according to each starting point and each ending point in the first list and the second list;

[0221] According to the size relationship between the effective length of each abnormal jitter interval and the effective length threshold, determine whether each abnormal jitter interval in the multiple initial abnormal jitter intervals is a continuous abnormal jitter interval, and determine the continuous abnormal jitter interval in the multiple abnormal jitter intervals as a valid abnormal jitter interval; the valid abnormal jitter interval is used to represent the abnormal jitter interval in the multiple abnormal jitter intervals whose effective length is greater than or equal to the effective length threshold;

[0222] Acquire at least one differential sequence corresponding to at least one valid abnormal jitter interval;

[0223] Performing fast Fourier transform processing on the at least one differential sequence to obtain spectrum data corresponding to the at least one differential sequence;

[0224] According to the magnitude relationship between the spectrum data corresponding to the at least one differential sequence and the threshold spectrum data, determining whether each valid abnormal jitter interval belongs to a false detection interval;

[0225] The abnormal jitter intervals whose spectrum data is less than the threshold spectrum data in the valid abnormal jitter intervals are determined as false detection intervals, and the false detection intervals are removed, and the false detection interval judgment logic is repeatedly executed until all valid abnormal jitter intervals are traversed to obtain at least one target abnormal jitter interval.

[0226] As an optional implementation of the embodiment of the present disclosure, the device further includes:

[0227] The output module is used to use the length of each target abnormal jitter interval as the corresponding abnormal jitter duration and output each abnormal jitter duration.

[0228] The vehicle abnormal jitter detection device provided by the present disclosure obtains a target time series corresponding to an original time series signal, wherein the original time series signal is a vehicle state signal, and the target time series is a stationary time series obtained after preprocessing the original time series signal. Multiple segmentation points are selected in the target time series to segment the target time series to obtain multiple target time subsequences, and each target time subsequence is fitted based on the correlation between the previous and next data in each target time subsequence to obtain a fitting value characterizing the fitting effect of each target time subsequence. When the fitting value of the fitting effect of each target time subsequence is less than a preset threshold, multiple segmentation points are identified as abnormal points to obtain an abnormal point list consisting of multiple abnormal points, and the abnormal jitter interval is identified according to the time interval of each abnormal point in the abnormal point list. For the non-stationary time series signal of the vehicle, a stationary target time series is obtained after preprocessing. Since the vehicle state signal often contains data under different working conditions, there may be mutations or anomalies between these working conditions. By selecting multiple segmentation points in the target time series to segment the target time series, multiple target time subsequences are obtained, and the fitting value used to characterize the fitting effect of each target time subsequence is calculated. By selecting different segmentation points multiple times and dividing the target time subsequence multiple times, multiple target time subsequences under multiple different segmentation conditions and multiple fitting values ​​used to characterize the fitting effect of each target time subsequence are obtained. When the sum of the fitting values ​​of the fitting effects of each target time subsequence is less than a preset threshold, that is, a group of segmentation points whose fitting values ​​are less than the preset threshold are obtained from multiple fitting values ​​as abnormal points, so that the change points or abnormal points between different working conditions can be accurately identified, avoiding the problem of missed detection in the process of abnormal detection of vehicle state information.

[0229] For the specific definition of the abnormal vehicle jitter detection device, please refer to the definition of the abnormal vehicle jitter detection method above, which will not be repeated here. Each module in the above-mentioned abnormal vehicle jitter detection device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor of the electronic device in the form of hardware, or can be stored in the processor of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0230] The present disclosure also provides an electronic device, Figure 4 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 4 As shown, the electronic device provided in this embodiment includes: a memory 41 and a processor 42, the memory 41 is used to store a computer program; the processor 42 is used to execute the steps executed in any embodiment of the fault identification method of the image acquisition device provided by the above method embodiment when calling the computer program. The electronic 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 electronic device is used to provide computing and control capabilities. The memory of the electronic 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. When the computer program is executed by the processor, a method for identifying a fault of an image acquisition device is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0231] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the computer device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0232] In some embodiments, the vehicle abnormal vibration detection device provided by the present disclosure can be implemented in the form of a computer program. Figure 4 The memory of the electronic device may store various program modules constituting the vehicle abnormal vibration detection device of the electronic device, for example, Figure 3The acquisition module 310, initialization module 320, calculation module 330, detection module 340, and identification module 350 shown in the figure. The computer program composed of various program modules enables the processor to execute the steps of the fault identification method of the image acquisition device of the electronic device of each embodiment of the present disclosure described in this specification.

[0233] The embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the fault identification method for the image acquisition device provided by the above method embodiment is implemented.

[0234] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0235] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0236] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0237] Computer readable media include permanent and non-permanent, removable and non-removable storage media. Storage media can be implemented by any method or technology to store information, and the information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0238] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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 process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0239] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for detecting abnormal vehicle vibration, It is characterized in that include: Obtaining a target time series corresponding to an original time series signal; the original time series signal is a time series signal corresponding to a vehicle state signal, and the target time series is a stationary time series obtained by preprocessing the original time series signal; Selecting a plurality of segmentation points in the target time series to segment the target time series to obtain a plurality of target time subsequences; Fitting each target time subsequence based on the correlation between the preceding and following data in each target time subsequence to obtain a fitting value representing the fitting effect of each target time subsequence; When the sum of the fitting values ​​of the fitting effects of the target time subsequences is less than a preset threshold, the plurality of segmentation points are identified as abnormal points, and an abnormal point list consisting of the plurality of abnormal points is obtained; The abnormal jitter interval is identified according to the time interval of each abnormal point in the abnormal point list.

2. The method according to claim 1, It is characterized in that The method further comprises: When the fitting value of the fitting effect of each target time subsequence is greater than or equal to the preset threshold, randomly selecting a plurality of preset segmentation points in the target time series to segment the target time series to obtain a plurality of preset time subsequences; Fitting each preset time subsequence based on the correlation between the preceding and following data in each preset time subsequence to obtain a fitting value representing the fitting effect of each preset time subsequence; When the sum of the fitting values ​​of the fitting effects of the preset time subsequences is less than the preset threshold, the plurality of preset segmentation points are identified as abnormal points, and an abnormal point list consisting of the plurality of abnormal points is obtained.

3. The method according to claim 1, It is characterized in that The step of obtaining a target time series corresponding to the original time series signal includes: Get the original time series signal; Performing low-pass filtering on the original time series signal to obtain a first time series; Perform difference processing on the first time series to obtain a target time series.

4. The method according to claim 3, It is characterized in that The low-pass filtering of the original time series signal to obtain a first time series includes: Performing global spectrum analysis on the original time series signal to determine the cutoff frequency of the low-pass filter; A low-pass filter is designed based on the cut-off frequency to remove burrs and redundant peaks in the original time series signal to obtain a first time series.

5. The method according to claim 4, It is characterized in that The step of designing a low-pass filter based on the cutoff frequency to remove burrs and redundant peaks in the original time series signal to obtain a first time series includes: According to the cut-off frequency, the sampling rate is designed to be f s , a low-pass filter of order n; The first time series after low-pass filtering is calculated according to the difference equation of the low-pass filter: Among them, Y(k) represents the sequence value at the kth moment, n is the order of the filter, and b 0 ~b n is the input signal coefficient, a 0 ~a n is the output signal coefficient, b 0 ~b n and a 0 ~a n The filter order n, cutoff frequency f c Sure.

6. The method according to claim 3, It is characterized in that The performing differential processing on the first time series to obtain a target time series includes: Performing first-order difference processing on the first time series to obtain a first-order difference series; or; Perform second-order difference processing on the first time series to obtain a second-order difference series.

7. The method according to claim 1, It is characterized in that The identifying the abnormal jitter interval according to the time interval of each abnormal point in the abnormal point list includes: Taking the first point in the abnormal point list as the starting point of the target abnormal jitter interval, and adding the starting point to the first list; Starting from the second point in the abnormal point list, the time interval between the current abnormal point and the previous abnormal point is calculated. If the time interval is greater than the preset time interval, the previous abnormal point is determined to be the end point of the target abnormal jitter interval, and the current abnormal point is determined to be the starting point of the next target abnormal jitter interval. The end point is added to the second list, and the judgment logic is repeatedly executed to obtain multiple abnormal jitter intervals.

8. The method according to claim 7, It is characterized in that The method further comprises: Calculate the effective length of each abnormal jitter interval according to each starting point and each ending point in the first list and the second list; According to the size relationship between the effective length of each abnormal jitter interval and the effective length threshold, determine whether each abnormal jitter interval in the multiple initial abnormal jitter intervals is a continuous abnormal jitter interval, and determine the continuous abnormal jitter interval in the multiple abnormal jitter intervals as a valid abnormal jitter interval; the valid abnormal jitter interval is used to represent the abnormal jitter interval in the multiple abnormal jitter intervals whose effective length is greater than or equal to the effective length threshold; Acquire at least one differential sequence corresponding to at least one valid abnormal jitter interval; Performing fast Fourier transform processing on the at least one differential sequence to obtain spectrum data corresponding to the at least one differential sequence; According to the magnitude relationship between the spectrum data corresponding to the at least one differential sequence and the threshold spectrum data, determining whether each valid abnormal jitter interval belongs to a false detection interval; The abnormal jitter intervals whose spectrum data is less than the threshold spectrum data in the valid abnormal jitter intervals are determined as false detection intervals, and the false detection intervals are removed, and the false detection interval judgment logic is repeatedly executed until all valid abnormal jitter intervals are traversed to obtain at least one target abnormal jitter interval.

9. The method according to claim 1, It is characterized in that The method further comprises: The length of each target abnormal jitter interval is used as the corresponding abnormal jitter duration, and each abnormal jitter duration is output.

10. A vehicle abnormal vibration detection device, It is characterized in that include: An acquisition module, used to acquire a target time series corresponding to an original time series signal; the original time series signal is a time series signal corresponding to a vehicle state signal, and the target time series is a stationary time series obtained by preprocessing the original time series signal; An initialization module, used for selecting a plurality of segmentation points in the target time series to segment the target time series to obtain a plurality of target time subsequences; A calculation module, used for fitting each target time subsequence based on the correlation between the preceding and following data in each target time subsequence, to obtain a fitting value representing the fitting effect of each target time subsequence; A detection module, configured to identify the plurality of segmentation points as abnormal points when the sum of the fitting values ​​of the fitting effects of the respective target time subsequences is less than a preset threshold, and obtain an abnormal point list consisting of the plurality of abnormal points; The identification module is used to identify the abnormal jitter interval according to the time interval of each abnormal point in the abnormal point list.

11. An electronic device, It is characterized in that include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle abnormal vibration detection method as described in any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the vehicle abnormal vibration detection method as claimed in any one of claims 1 to 9 is implemented.

13. A vehicle, It is characterized in that include: The electronic device as claimed in claim 11.

Images