Engineering truck brake friction fault assessment method and system

Abstract

The invention provides an engineering vehicle brake friction fault assessment method and system. The method comprises the steps that feature extraction is conducted on friction parameter data, feature extraction is conducted on friction braking data, and feature screening is conducted on a parameter feature set and a braking feature set; merging and compressing the parameter screening feature set and the braking screening feature set respectively; performing feature fusion on the parameter compression feature set and the braking compression feature set; historical training data and corresponding friction fault labels are obtained, a preset evaluation model is trained based on the historical training data and the friction fault labels, the fused feature set is input into the training evaluation model for evaluation, and the corresponding friction fault labels are output; according to the method, irrelevant feature information can be eliminated, interference of repeated information on a fault evaluation process is reduced, and the accuracy of model prediction is effectively improved.

Description

Technical Field

[0001] The invention belongs to the technical field of vehicle fault assessment, and in particular relates to a method and system for assessing brake friction faults of an engineering vehicle. Background Art

[0002] Engineering vehicles are the backbone of a construction project. Their appearance has doubled the progress of the construction project and greatly reduced manpower. The functions of engineering vehicles include transportation, excavation, and repair, and they are widely used in the field of construction engineering. Common engineering vehicles include heavy transport vehicles, large bulldozers, excavators, etc.

[0003] For large and heavy vehicles such as engineering vehicles, when the engineering vehicle brakes, the mutual friction of the rotating elements in the brake is usually used to determine the fault. In order to ensure the safety of personnel, it is very necessary to regularly evaluate the friction of the brakes of the engineering vehicle. The friction evaluation of the existing technology usually collects brake friction data and compares the brake friction braking data with a threshold value to achieve a friction fault assessment of the brake. The above-mentioned evaluation method based on threshold comparison has a low evaluation accuracy and cannot accurately achieve a friction fault assessment of the brake, thereby affecting the braking safety of the engineering vehicle. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for evaluating brake friction faults of an engineering vehicle, which are used to solve the technical problems in the prior art.

[0005] On the one hand, the present invention provides the following technical solution, a method for evaluating brake friction fault of an engineering vehicle, comprising: Collecting friction parameter data of the brake of the engineering vehicle and friction braking data of the brake during braking; Performing feature extraction on the friction parameter data to obtain a parameter feature set, and performing feature extraction on the friction braking data to obtain a braking feature set; Performing feature screening on the parameter feature set and the braking feature set respectively to obtain a parameter screening feature set and a braking screening feature set; Combining and compressing the parameter screening feature set and the brake screening feature set respectively to obtain a parameter compression feature set and a brake compression feature set; Performing feature fusion on the parameter compression feature set and the brake compression feature set to obtain a fused feature set; Acquire historical training data and corresponding friction fault labels, train a preset evaluation model based on the historical training data and the friction fault labels to obtain a training evaluation model, input the fusion feature set into the training evaluation model for evaluation, and output corresponding friction fault labels.

[0006] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention first collects the friction parameter data of the brake of the engineering vehicle and the friction braking data of the brake during braking; then performs feature extraction on the friction parameter data to obtain a parameter feature set, and performs feature extraction on the friction braking data to obtain a braking feature set; then performs feature screening on the parameter feature set and the braking feature set respectively to obtain a parameter screening feature set and a braking screening feature set; then performs merging and compression on the parameter screening feature set and the braking screening feature set respectively to obtain a parameter compression feature set and a braking compression feature set; then performs feature fusion on the parameter compression feature set and the braking compression feature set to obtain a fusion feature set. Collect; then obtain historical training data and corresponding friction fault labels, train the preset evaluation model based on the historical training data and the friction fault labels to obtain a training evaluation model, input the fused feature set into the training evaluation model for evaluation, and output the corresponding friction fault label. The present invention first performs feature extraction on the data set, which can effectively extract feature information that is valuable for the brake fault assessment of engineering vehicles, and screens, compresses and fuses the extracted features, which can effectively eliminate irrelevant feature information, reduce the interference of repeated information on the fault assessment process, and effectively improve the accuracy of model prediction, so as to improve the effectiveness and accuracy of brake friction fault assessment.

[0007] Preferably, the step of extracting features from the friction parameter data to obtain a parameter feature set includes: The friction parameter data is subjected to a first feature extraction to obtain a data feature set. : ; ; ; ; ; ; ; ; In the formula, Respectively represent the first, second, third, fourth, fifth, sixth, and seventh data features, Indicates Group friction parameter data, Indicates The average value of the friction parameter data of the group, represents the number of groups of friction parameter data, Indicates Standard deviation of group friction parameter data; The friction parameter data is converted into frequency domain to obtain frequency domain data, and the frequency domain data is subjected to a second feature extraction to obtain a frequency feature set. : ; ; ; ; ; ; ; ; In the formula, represents the first, second, third, fourth, fifth, sixth, and seventh frequency characteristics, , Respectively represent The frequency value of the frequency domain data of the group Group frequency domain data, The number of groups representing frequency domain data; Calculate the intimacy between the friction parameter data , the intimacy The friction parameter data greater than the preset value is extracted to obtain the intimate feature set: ; In the formula, , Respectively represent Group, The first data, Indicates The average value of the friction parameter data of the group, Indicates Group, The number of data in the group friction parameter data; The data feature set, the frequency feature set and the intimacy feature set are integrated to obtain a parameter feature set.

[0008] Preferably, the step of extracting features from the friction braking data to obtain a braking feature set comprises: The friction brake data is subjected to wavelet decomposition to obtain a number of wavelet coefficients. ; The wavelet coefficients are updated to obtain updated wavelet coefficients. : ; In the formula, Indicates the preset threshold; Based on the updated wavelet coefficients Performing inverse wavelet transform to obtain reconstructed friction brake data; Extracting the maximum value, minimum value, average value, median value, peak value, variance, and standard deviation of the reconstructed friction brake data to obtain a first feature set; Performing frequency domain conversion on the reconstructed friction braking data to obtain braking frequency domain data, and extracting the center frequency, frequency variance, frequency standard deviation, root mean square frequency, and mean square frequency of the braking frequency domain data to obtain a second feature set; The first feature set and the second feature set are combined to obtain a braking feature set.

[0009] Preferably, the step of performing feature screening on the parameter feature set and the braking feature set respectively to obtain the parameter screening feature set and the braking screening feature set comprises: Calculate the classification index of the parameter feature set and the braking feature set : ; In the formula, Indicates the number of categories of parameter feature set or brake feature set, represents the number of samples of parameter feature set or brake feature set, Indicates the first The number of samples in each category; Traversing all feature dimensions in the parameter feature set and the brake feature set, and arranging them in ascending order according to the size of the feature dimensions, so as to obtain a parameter permutation set and a brake permutation set; Calculate the average values ​​of two adjacent items in the parameter permutation set and the braking permutation set respectively to obtain a parameter average value set and a braking average value set, divide the parameter average value set into large and small values ​​according to each item in the parameter average value set to obtain a plurality of parameter partition sets, and divide the braking average value set into large and small values ​​according to each item in the braking average value set to obtain a plurality of braking partition sets; Calculate the classification index of each parameter partition set and each brake partition set respectively, and determine the classification index and classification index of the parameter partition set and the classification index of the braking partition set and the classification index The second difference of Determine a parameter partition set corresponding to when the first difference is maximum and a braking partition set corresponding to when the second difference is maximum, use the parameter feature set as a parameter main node and use the parameter partition set corresponding to when the first difference is maximum and its corresponding feature dimension as a first parameter sub-node, use the braking feature set as a braking main node and use the braking partition set corresponding to when the second difference is maximum and its corresponding feature dimension as a first braking sub-node; The node partitioning process is iteratively repeated to obtain a parameter partitioning tree and a braking partitioning tree. The parameter partitioning sets corresponding to the first several nodes in the parameter partitioning tree are extracted as parameter screening feature sets according to the parameter screening threshold. The braking partitioning sets corresponding to the first several nodes in the braking partitioning tree are extracted as braking screening feature sets according to the braking screening threshold.

[0010] Preferably, the step of merging and compressing the parameter screening feature set and the brake screening feature set to obtain a parameter compression feature set and a brake compression feature set comprises: Segmenting the parameter screening feature set and the brake screening feature set according to the positions of the peaks and the troughs to obtain a plurality of parameter segmentation feature sets and a plurality of brake segmentation feature sets; A first distance matrix is ​​constructed based on the parameter segmentation feature set and the brake segmentation feature set. With the second distance matrix : ; ; In the formula, , , , Respectively represent the first distance matrix Line Column, No. Line Column, No. Line Column, No. Line The elements of the column, , , , Respectively represent the first Line Column, No. Line Column, No. Line Column, No. Line The elements of the column, represents the Euclidean distance calculation, Respectively represent The parameter segmentation feature set elements, Indicates The parameter segmentation feature set elements, Respectively represent The brake segmentation feature set elements, Indicates The brake segmentation feature set elements; Calculate the first similarity between each two parameter segmentation feature sets based on the distance matrix And the second similarity between every two brake segmentation feature sets : ; ; If the first similarity between the two parameter segmentation feature sets is not less than the preset similarity, the time series of the two parameter segmentation feature sets is determined, the parameter segmentation feature set with the earlier time series is retained and the parameter segmentation feature set with the later time series is eliminated; if the first similarity between the two parameter segmentation feature sets is less than the preset similarity, the corresponding two parameter segmentation feature sets are retained to obtain a retained parameter set; If the second similarity between the two braking segmentation feature sets is not less than the preset similarity, the time series of the two braking segmentation feature sets are determined, the braking segmentation feature set with the earlier time series is retained and the braking segmentation feature set with the later time series is eliminated; if the second similarity between the two braking segmentation feature sets is less than the preset similarity, the corresponding two braking segmentation feature sets are retained to obtain a retained braking set; Several reserved parameter sets are spliced ​​together according to a time series, and several reserved brake sets are spliced ​​together to obtain a parameter compression feature set and a brake compression feature set.

[0011] Preferably, the step of fusing the parameter compression feature set with the brake compression feature set to obtain a fused feature set comprises: Determining a first brake state corresponding to each set of data in the parameter compression feature set and a second brake state corresponding to each set of data in the brake compression feature set; Determining a first characteristic distance of the parameter compression characteristic set based on the brake state and a second characteristic distance in the brake compression characteristic set : ; ; In the formula, Indicates that the first brake state is The total number of samples under Indicates that the first brake state is The parameter compression feature set under Group data, The first Features, Indicates the second brake status is The total number of samples under Indicates the second brake status is The brake compression characteristics under Group data, The first Features Based on the first characteristic distance Calculate the first compensation coefficient And based on the second characteristic distance Calculate the second compensation coefficient : ; ; In the formula, , Respectively indicate the first brake state is , The following parameters compress all samples in the feature set The mean of the features, Respectively indicate the state of the second brake , The first of all samples in the lower brake compression feature set The mean of the features; Based on the first compensation coefficient With the second compensation coefficient Determine the fusion feature set.

[0012] Preferably, the first compensation coefficient With the second compensation coefficient The steps of determining the fusion feature set include: Based on the first compensation coefficient Calculate the first important factor Based on the second compensation coefficient Calculate the second most important factor : ; ; ; ; In the formula, , Represent the first impact factor and the second impact factor respectively. , The state numbers respectively represent the first brake state and the second brake state; Arrange the first important factor of each feature in the parameter compression feature set in ascending order, and assign ascending weights to each feature in the parameter compression feature set according to the arrangement relationship of the features in the parameter compression feature set to obtain a plurality of parameter assignment weights, and perform weighted fusion on the parameter compression feature set based on the parameter assignment weights to obtain a first fused data set; Arrange the second most important factor of each feature in the brake compression feature set in ascending order, and assign ascending weights to each feature in the brake compression feature set according to the arrangement relationship of the features in the brake compression feature set to obtain a plurality of brake assignment weights, and perform weighted fusion on the brake compression feature set based on the brake assignment weights to obtain a second fused data set; Based on the first fusion dataset Fusion with the second dataset Determine the fusion feature set : ; In the formula, represents the fusion weight.

[0013] In a second aspect, the present invention provides the following technical solution: a brake friction fault assessment system for an engineering vehicle, the system comprising: A collection module, used for collecting friction parameter data of the brake of the engineering vehicle and friction braking data of the brake during braking; An extraction module, used for performing feature extraction on the friction parameter data to obtain a parameter feature set, and performing feature extraction on the friction braking data to obtain a braking feature set; A screening module, used for performing feature screening on the parameter feature set and the braking feature set respectively, so as to obtain a parameter screening feature set and a braking screening feature set; A compression module, used for merging and compressing the parameter screening feature set and the brake screening feature set respectively, so as to obtain a parameter compression feature set and a brake compression feature set; A fusion module, used for fusing the parameter compression feature set with the brake compression feature set to obtain a fused feature set; An evaluation module is used to obtain historical training data and corresponding friction fault labels, train a preset evaluation model based on the historical training data and the friction fault labels to obtain a training evaluation model, input the fusion feature set into the training evaluation model for evaluation, and output the corresponding friction fault labels.

[0014] In a third aspect, the present invention provides the following technical solution: a computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned engineering vehicle brake friction fault assessment method when executing the computer program.

[0015] In a fourth aspect, the present invention provides the following technical solution: a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-mentioned engineering vehicle brake friction fault assessment method. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flow chart of a method for evaluating brake friction faults of an engineering vehicle provided in Embodiment 1 of the present invention; Figure 2 A structural block diagram of a brake friction fault assessment system for an engineering vehicle provided in Embodiment 2 of the present invention; Figure 3 A schematic diagram of the hardware structure of a computer provided in another embodiment of the present invention.

[0018] The embodiments of the present invention will be further described below with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the embodiments of the present invention, and should not be construed as limiting the present invention.

[0020] In the description of the embodiments of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0021] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0022] In the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0023] Embodiment 1 In the first embodiment of the present invention, Figure 1 As shown, a method for evaluating friction fault of brakes of an engineering vehicle comprises: S1, collecting friction parameter data of the brake of the engineering vehicle and friction braking data of the brake during braking; Specifically, the friction parameter data includes the friction coefficient of the brake rotating element, the strength of the brake rotating element, the brake size parameters, the braking torque, the braking runout, the gap between the rotating elements, the residual pressure, the wear degree parameters, etc. The friction parameter data can be obtained through the sensors installed on the brake, and the friction braking data is specifically the audio data of the engineering vehicle during the braking process.

[0024] S2, performing feature extraction on the friction parameter data to obtain a parameter feature set, and performing feature extraction on the friction braking data to obtain a braking feature set; Wherein, the step of extracting features from the friction parameter data to obtain a parameter feature set comprises: S211, performing a first feature extraction on the friction parameter data to obtain a data feature set : ; ; ; ; ; ; ; ; In the formula, Respectively represent the first, second, third, fourth, fifth, sixth, and seventh data features, Indicates Group friction parameter data, Indicates The average value of the friction parameter data of the group, represents the number of groups of friction parameter data, Indicates Standard deviation of group friction parameter data; Specifically, the above data are time domain data of friction parameter data.

[0025] S212, performing frequency domain conversion on the friction parameter data to obtain frequency domain data, and performing a second feature extraction on the frequency domain data to obtain a frequency feature set : ; ; ; ; ; ; ; ; In the formula, represents the first, second, third, fourth, fifth, sixth, and seventh frequency characteristics, , Respectively represent The frequency value of the frequency domain data of the group Group frequency domain data, The number of groups representing frequency domain data; Specifically, the above data are frequency domain data of friction parameter data.

[0026] S213, calculating the intimacy between the friction parameter data , the intimacy The friction parameter data greater than the preset value is extracted to obtain the intimate feature set: ; In the formula, , Respectively represent Group, The first data, Indicates The average value of the friction parameter data of the group, Indicates Group, The number of data in the group friction parameter data; Specifically, the above data is the dependency and intimacy data between devices.

[0027] S214, combining the data feature set, the frequency feature set and the intimacy feature set to obtain a parameter feature set.

[0028] Wherein, the step of extracting features from the friction braking data to obtain a braking feature set comprises: S221, performing wavelet decomposition on the friction braking data to obtain a number of wavelet coefficients .

[0029] S222, updating the wavelet coefficients to obtain updated wavelet coefficients : ; In the formula, Indicates the preset threshold.

[0030] S223, based on the updated wavelet coefficients Performing inverse wavelet transform to obtain reconstructed friction brake data; Specifically, the above steps S221-S223 are wavelet transform algorithms in the prior art, and therefore are not described in detail here. However, it should be noted that in step S22 of this embodiment, the original wavelet coefficients are updated to avoid data signal distortion caused by reconstruction while also reducing the error of the reconstructed noisy signal.

[0031] S224, extracting the maximum value, minimum value, average value, median value, peak value, variance, and standard deviation of the reconstructed friction braking data to obtain a first feature set; Specifically, the above data are time domain data.

[0032] S225, performing frequency domain conversion on the reconstructed friction braking data to obtain braking frequency domain data, and extracting the center frequency, frequency variance, frequency standard deviation, root mean square frequency, and mean square frequency of the braking frequency domain data to obtain a second feature set; Specifically, the above data is frequency domain data.

[0033] S226: Integrate the first feature set and the second feature set to obtain a braking feature set.

[0034] S3, performing feature screening on the parameter feature set and the braking feature set respectively to obtain a parameter screening feature set and a braking screening feature set; Wherein, the step S3 comprises: S31, calculating the classification index of the parameter feature set and the braking feature set : ; In the formula, Indicates the number of categories of parameter feature set or brake feature set, represents the number of samples of parameter feature set or brake feature set, Indicates the first The number of samples of each category.

[0035] S32, traversing all feature dimensions in the parameter feature set and the brake feature set, and arranging them in ascending order according to the size of the feature dimensions, so as to obtain a parameter permutation set and a brake permutation set.

[0036] S33, respectively calculating the average values ​​of two adjacent items in the parameter permutation set and the braking permutation set to obtain a parameter average value set and a braking average value set, dividing the parameter average value set into large and small according to each item in the parameter average value to obtain a plurality of parameter partition sets, and dividing the braking average value set into large and small according to each item in the braking average value set to obtain a plurality of braking partition sets; Specifically, after determining the parameter average value set and the braking average value set, the parameter average value set and the braking average value set are first divided according to each item in the parameter average value. The set that is not less than one of the parameter average values ​​is used as the left branch of the tree structure, and the set that is less than one of the parameter average values ​​is used as the right branch of the tree structure. The parameter partition set and the braking partition set can be obtained according to each branch data.

[0037] S34, respectively calculating the classification index of each parameter partition set and each brake partition set, and determining the classification index of the parameter partition set and the classification index of the brake partition set. and the classification index of the braking partition set and the classification index The second difference.

[0038] S35, determining the parameter partition set corresponding to the maximum first difference and the braking partition set corresponding to the maximum second difference, taking the parameter feature set as the parameter main node and the parameter partition set corresponding to the maximum first difference and its corresponding feature dimension as the first parameter sub-node, taking the braking feature set as the braking main node and the braking partition set corresponding to the maximum second difference and its corresponding feature dimension as the first braking sub-node; Specifically, after determining the maximum value of the first difference and the maximum value of the second difference, the corresponding braking partition set and parameter partition set are extracted. It should be noted that the braking partition set and parameter partition set extracted here respectively include two branches, and when selecting the first parameter sub-node, the branch on the left is specifically selected. Therefore, when selecting the first braking sub-node, the branch on the left is also selected.

[0039] S36, iteratively repeating the node partitioning process to obtain a parameter partitioning tree and a braking partitioning tree, extracting a parameter partitioning set corresponding to the first several nodes in the parameter partitioning tree as a parameter screening feature set according to a parameter screening threshold, and extracting a braking partitioning set corresponding to the first several nodes in the braking partitioning tree as a braking screening feature set according to a braking screening threshold; Specifically, after determining the child node, the braking partition set and parameter partition set corresponding to the child node are removed from the parameter feature set and the braking feature set, and the data set after removal is used as the main node and the process of steps S33-S35 is repeated, and the subsequently obtained node is used as the next node of the first parameter sub-node and the first braking sub-node, thereby obtaining a parameter partition tree and a braking partition tree. For the parameter partition tree and the braking partition tree, the child nodes in the front row mean that the greater the degree of influence on the brake friction fault, therefore, the braking partition sets and parameter partition sets corresponding to the first few child nodes are selected as the parameter screening feature set and the braking screening feature set, and at the same time, in the present application, the parameter screening threshold is 8 and the braking screening threshold is 6.

[0040] S4, merging and compressing the parameter screening feature set and the brake screening feature set respectively to obtain a parameter compression feature set and a brake compression feature set; Wherein, the step S4 comprises: S41, segmenting the parameter screening feature set and the braking screening feature set according to the positions of the peaks and troughs to obtain a plurality of parameter segmentation feature sets and a plurality of braking segmentation feature sets.

[0041] S42, constructing a first distance matrix based on the parameter segmentation feature set and the braking segmentation feature set With the second distance matrix : ; ; In the formula, , , , Respectively represent the first distance matrix Line Column, No. Line Column, No. Line Column, No. Line The elements of the column, , , , Respectively represent the first Line Column, No. Line Column, No. Line Column, No. Line The elements of the column, represents the Euclidean distance calculation, Respectively represent The parameter segmentation feature set elements, Indicates The parameter segmentation feature set elements, Respectively represent The brake segmentation feature set elements, Indicates The brake segmentation feature set elements.

[0042] S43, calculating the first similarity between every two parameter segmentation feature sets based on the distance matrix And the second similarity between every two brake segmentation feature sets : ; .

[0043] S44. If the first similarity between the two parameter segmentation feature sets is not less than the preset similarity, the time series of the two parameter segmentation feature sets is determined, the parameter segmentation feature set with the earlier time series is retained and the parameter segmentation feature set with the later time series is eliminated; if the first similarity between the two parameter segmentation feature sets is less than the preset similarity, the corresponding two parameter segmentation feature sets are retained to obtain a retained parameter set.

[0044] S45. If the second similarity between the two braking segmentation feature sets is not less than the preset similarity, the time series of the two braking segmentation feature sets is determined, the braking segmentation feature set with the earlier time series is retained and the braking segmentation feature set with the later time series is eliminated; if the second similarity between the two braking segmentation feature sets is less than the preset similarity, the corresponding two braking segmentation feature sets are retained to obtain a retained braking set.

[0045] S46, splicing a plurality of reserved parameter sets and splicing a plurality of reserved brake sets in time series to obtain a parameter compression feature set and a brake compression feature set.

[0046] S5, fusing the parameter compression feature set with the brake compression feature set to obtain a fused feature set; Wherein, the step S5 comprises: S51, determining a first brake state corresponding to each set of data in the parameter compression feature set and a second brake state corresponding to each set of data in the brake compression feature set; Specifically, the first brake state and the second brake state specifically represent the actual state of the brake, and the state is related to multiple parameters. Therefore, for one state, it usually corresponds to several groups of data, and the first brake state and the second brake state partially overlap.

[0047] S52: Determine a first characteristic distance of the parameter compression feature set based on the brake state and a second characteristic distance in the brake compression characteristic set : ; ; In the formula, Indicates that the first brake state is The total number of samples under Indicates that the first brake state is The parameter compression feature set under Group data, The first Features, Indicates the second brake status is The total number of samples under Indicates the second brake status is The brake compression characteristics under Group data, The first Features.

[0048] S53, based on the first characteristic distance Calculate the first compensation coefficient And based on the second characteristic distance Calculate the second compensation coefficient : ; ; In the formula, , Respectively indicate the first brake state is , The following parameters compress all samples in the feature set The mean of the features, Respectively indicate the state of the second brake , The first of all samples in the lower brake compression feature set The mean of the features.

[0049] S54, based on the first compensation coefficient With the second compensation coefficient Determine a fusion feature set; Wherein, the step S54 comprises: S541: Based on the first compensation coefficient Calculate the first important factor Based on the second compensation coefficient Calculate the second most important factor : ; ; ; ; In the formula, , Represent the first impact factor and the second impact factor respectively. , The state numbers respectively represent the first brake state and the second brake state.

[0050] S542, arranging the first important factor of each feature in the parameter compression feature set in ascending order, and assigning ascending weights to each feature in the parameter compression feature set according to the arrangement relationship of the features in the parameter compression feature set to obtain a plurality of parameter assignment weights, and performing weighted fusion on the parameter compression feature set based on the parameter assignment weights to obtain a first fused data set; S543, arranging the second important factor of each feature in the brake compression feature set in ascending order, and assigning ascending weights according to the arrangement relationship of each feature in the brake compression feature set to obtain a plurality of brake assignment weights, and performing weighted fusion on the brake compression feature set based on the brake assignment weights to obtain a second fused data set; Specifically, for the parameter weighting, it is assigned in ascending order according to the arrangement relationship of each feature in the parameter compression feature set, that is, the parameter weighting corresponding to the front feature is larger, and the parameter weighting is in an arithmetic decreasing relationship. Similarly, the braking weighting is also the same, and the sum of all parameter weightings and the sum of all braking weightings are 1.

[0051] S544: Based on the first fusion data set Fusion with the second dataset Determine the fusion feature set : ; In the formula, represents the fusion weight; Specifically, in this application, is 0.6.

[0052] S6, acquiring historical training data and corresponding friction fault labels, training a preset evaluation model based on the historical training data and the friction fault labels to obtain a training evaluation model, inputting the fused feature set into the training evaluation model for evaluation to output a corresponding friction fault label; Specifically, when conducting model training, the model can be subjected to a corresponding training optimization process through historical training data and its corresponding friction fault labels, and then the fused feature set is input into the trained training evaluation model for corresponding evaluation, and the friction fault label corresponding to the fused feature set can be output. In the present application, the preset evaluation model is a GA-BP neural network model.

[0053] The engineering vehicle brake friction fault assessment method provided in the first embodiment of the present invention first collects the friction parameter data of the engineering vehicle brake and the friction braking data of the brake during braking; then performs feature extraction on the friction parameter data to obtain a parameter feature set, and performs feature extraction on the friction braking data to obtain a braking feature set; then performs feature screening on the parameter feature set and the braking feature set respectively to obtain a parameter screening feature set and a braking screening feature set; then performs merging and compression on the parameter screening feature set and the braking screening feature set respectively to obtain a parameter compression feature set and a braking compression feature set; then performs feature fusion on the parameter compression feature set and the braking compression feature set to obtain a fusion feature set. The present invention first performs feature extraction on the data set, which can effectively extract feature information valuable for the brake fault assessment of engineering vehicles, and screens, compresses and fuses the extracted features, which can effectively eliminate irrelevant feature information, reduce the interference of repeated information on the fault assessment process, and effectively improve the accuracy of model prediction, so as to improve the effectiveness and accuracy of brake friction fault assessment.

[0054] Embodiment 2 like Figure 2 As shown, in the second embodiment of the present invention, a brake friction fault assessment system for an engineering vehicle is provided, and the system comprises: The acquisition module 1 is used to acquire the friction parameter data of the brake of the engineering vehicle and the friction braking data of the brake during braking; Extraction module 2, used for performing feature extraction on the friction parameter data to obtain a parameter feature set, and performing feature extraction on the friction braking data to obtain a braking feature set; A screening module 3 is used to perform feature screening on the parameter feature set and the braking feature set respectively to obtain a parameter screening feature set and a braking screening feature set; A compression module 4, used for merging and compressing the parameter screening feature set and the brake screening feature set respectively, so as to obtain a parameter compression feature set and a brake compression feature set; A fusion module 5, used for fusing the parameter compression feature set with the brake compression feature set to obtain a fused feature set; Evaluation module 6, used for obtaining historical training data and corresponding friction fault labels, training a preset evaluation model based on the historical training data and the friction fault labels to obtain a training evaluation model, inputting the fusion feature set into the training evaluation model for evaluation, and outputting corresponding friction fault labels; The extraction module 2 comprises: The first extraction submodule is used to perform the first feature extraction on the friction parameter data to obtain a data feature set : ; ; ; ; ; ; ; ; In the formula, Respectively represent the first, second, third, fourth, fifth, sixth, and seventh data features, Indicates Group friction parameter data, Indicates The average value of the friction parameter data of the group, represents the number of groups of friction parameter data, Indicates Standard deviation of group friction parameter data; The second extraction submodule is used to perform frequency domain conversion on the friction parameter data to obtain frequency domain data, and perform a second feature extraction on the frequency domain data to obtain a frequency feature set. : ; ; ; ; ; ; ; ; In the formula, represents the first, second, third, fourth, fifth, sixth, and seventh frequency characteristics, , Respectively represent The frequency value of the frequency domain data of the group Group frequency domain data, The number of groups representing frequency domain data; The third extraction submodule is used to calculate the intimacy between the friction parameter data , the intimacy The friction parameter data greater than the preset value is extracted to obtain the intimate feature set: ; In the formula, , Respectively represent Group, The first data, Indicates The average value of the friction parameter data of the group, Indicates Group, The number of data in the group friction parameter data; The first synthesis submodule is used to synthesize the data feature set, the frequency feature set and the intimacy feature set to obtain a parameter feature set.

[0055] The extraction module 2 also includes: The decomposition submodule is used to perform wavelet decomposition on the friction brake data to obtain a number of wavelet coefficients. ; The updating submodule is used to update the wavelet coefficients to obtain updated wavelet coefficients. : ; In the formula, Indicates the preset threshold; The inverse transform submodule is used to update the wavelet coefficients based on the Performing inverse wavelet transform to obtain reconstructed friction brake data; a fourth extraction submodule, configured to extract the maximum value, the minimum value, the average value, the median value, the peak value, the variance, and the standard deviation of the reconstructed friction braking data to obtain a first feature set; a fifth extraction submodule, configured to perform frequency domain conversion on the reconstructed friction braking data to obtain braking frequency domain data, and extract the center frequency, frequency variance, frequency standard deviation, root mean square frequency, and mean square frequency of the braking frequency domain data to obtain a second feature set; The second integration submodule is used to integrate the first feature set and the second feature set to obtain a braking feature set.

[0056] The screening module 3 comprises: An index calculation submodule is used to calculate the classification index of the parameter feature set and the braking feature set. : ; In the formula, Indicates the number of categories of parameter feature set or brake feature set, represents the number of samples of parameter feature set or brake feature set, Indicates the first The number of samples in each category; A traversal submodule, used for traversing all feature dimensions in the parameter feature set and the brake feature set, and arranging them in ascending order according to the size of the feature dimensions, so as to obtain a parameter permutation set and a brake permutation set; a partitioning submodule, for respectively calculating the average values ​​of two adjacent items in the parameter arrangement set and the braking arrangement set to obtain a parameter average value set and a braking average value set, dividing the parameter average value set into large and small values ​​according to each item in the parameter average value to obtain a plurality of parameter partitioning sets, and dividing the braking average value set into large and small values ​​according to each item in the braking average value set to obtain a plurality of braking partitioning sets; The difference calculation submodule is used to calculate the classification index of each parameter partition set and each brake partition set respectively, and determine the classification index of the parameter partition set and the classification index of the brake partition set. and the classification index of the braking partition set and the classification index The second difference of A node submodule, used to determine a parameter partition set corresponding to when the first difference is maximum and a braking partition set corresponding to when the second difference is maximum, taking the parameter feature set as a parameter main node and taking the parameter partition set corresponding to when the first difference is maximum and its corresponding feature dimension as a first parameter subnode, taking the braking feature set as a braking main node and taking the braking partition set corresponding to when the second difference is maximum and its corresponding feature dimension as a first braking subnode; The screening submodule is used to iteratively repeat the node partitioning process to obtain a parameter partitioning tree and a braking partitioning tree, extract the parameter partitioning sets corresponding to the first several nodes in the parameter partitioning tree as the parameter screening feature set according to the parameter screening threshold, and extract the braking partitioning sets corresponding to the first several nodes in the braking partitioning tree as the braking screening feature set according to the braking screening threshold.

[0057] The compression module 4 comprises: A segmentation submodule, used for segmenting the parameter screening feature set and the brake screening feature set according to the positions of the peaks and the troughs, so as to obtain a plurality of parameter segmentation feature sets and a plurality of brake segmentation feature sets; A matrix submodule, for constructing a first distance matrix based on the parameter segmentation feature set and the brake segmentation feature set With the second distance matrix : ; ; In the formula, , , , Respectively represent the first distance matrix Line Column, No. Line Column, No. Line Column, No. Line The elements of the column, , , , Respectively represent the first Line Column, No. Line Column, No. Line Column, No. Line The elements of the column, represents the Euclidean distance calculation, Respectively represent The parameter segmentation feature set elements, Indicates The parameter segmentation feature set elements, Respectively represent The brake segmentation feature set elements, Indicates The brake segmentation feature set elements; A similarity submodule is used to calculate the first similarity between each two parameter segmentation feature sets based on the distance matrix. And the second similarity between every two brake segmentation feature sets : ; ; A first retention submodule is used to determine the time series of the two parameter segmentation feature sets if the first similarity between the two parameter segmentation feature sets is not less than a preset similarity, retain the parameter segmentation feature set with an earlier time series and remove the parameter segmentation feature set with a later time series, and retain the corresponding two parameter segmentation feature sets if the first similarity between the two parameter segmentation feature sets is less than a preset similarity to obtain a retained parameter set; A second retention submodule is used for determining the time series of the two braking segmentation feature sets if the second similarity between the two braking segmentation feature sets is not less than a preset similarity, retaining the braking segmentation feature set with an earlier time series and eliminating the braking segmentation feature set with a later time series, and retaining the corresponding two braking segmentation feature sets if the second similarity between the two braking segmentation feature sets is less than the preset similarity, so as to obtain a retained braking set; The splicing submodule is used to splice a plurality of reserved parameter sets and a plurality of reserved brake sets in a time series to obtain a parameter compression feature set and a brake compression feature set.

[0058] The fusion module 5 comprises: a state submodule, configured to determine a first brake state corresponding to each set of data in the parameter compression feature set and a second brake state corresponding to each set of data in the brake compression feature set; A distance calculation submodule, used to determine a first characteristic distance of the parameter compression feature set based on the brake state and a second characteristic distance in the brake compression characteristic set : ; ; In the formula, Indicates that the first brake state is The total number of samples under Indicates that the first brake state is The parameter compression feature set under Group data, The first Features, Indicates the second brake status is The total number of samples under Indicates the second brake status is The brake compression characteristics under Group data, The first Features A coefficient submodule is used to calculate the coefficient of the first characteristic distance. Calculate the first compensation coefficient And based on the second characteristic distance Calculate the second compensation coefficient : ; ; In the formula, , Respectively indicate the first brake state is , The following parameters compress all samples in the feature set The mean of the features, Respectively indicate the state of the second brake , The first of all samples in the lower brake compression feature set The mean of the features; A fusion submodule is used to With the second compensation coefficient Determine the fusion feature set.

[0059] The fusion submodule includes: A factor calculation unit for calculating the compensation coefficient based on the first compensation coefficient. Calculate the first important factor Based on the second compensation coefficient Calculate the second most important factor : ; ; ; ; In the formula, , Represent the first impact factor and the second impact factor respectively. , The state numbers respectively represent the first brake state and the second brake state; a first weighted calculation unit, configured to arrange the first important factor of each feature in the parameter compression feature set in ascending order, and assign ascending weights to each feature in the parameter compression feature set according to the arrangement relationship of the features in the parameter compression feature set to obtain a plurality of parameter assignment weights, and perform weighted fusion on the parameter compression feature set based on the parameter assignment weights to obtain a first fused data set; a second weighted calculation unit, configured to arrange the second important factor of each feature in the brake compression feature set in ascending order, and assign weights in ascending order according to the arrangement relationship of each feature in the brake compression feature set to obtain a plurality of brake assignment weights, and perform weighted fusion on the brake compression feature set based on the brake assignment weights to obtain a second fused data set; A fusion unit, configured to: Fusion with the second dataset Determine the fusion feature set : ; In the formula, represents the fusion weight.

[0060] In some other embodiments of the present invention, the embodiments of the present invention provide the following technical solution: a computer, comprising a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101; the processor 101 implements the above-mentioned engineering vehicle brake friction fault assessment method when executing the computer program.

[0061] Specifically, the processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0062] Among them, the memory 102 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 102 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 102 may be inside or outside the data processing device. In a specific embodiment, the memory 102 is a non-volatile memory. In a specific embodiment, the memory 102 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0063] The memory 102 may be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 101 .

[0064] The processor 101 implements the above-mentioned engineering vehicle brake friction fault assessment method by reading and executing the computer program instructions stored in the memory 102 .

[0065] In some embodiments, the computer may further include a communication interface 103 and a bus 100. Figure 3 As shown, the processor 101, the memory 102, and the communication interface 103 are connected via a bus 100 and communicate with each other.

[0066] The communication interface 103 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present invention. The communication interface 103 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0067] The bus 100 includes hardware, software or both, and couples the components of the computer device to each other. The bus 100 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 100 may include one or more buses. Although embodiments of the present invention describe and illustrate a particular bus, the present invention contemplates any suitable bus or interconnect.

[0068] The computer can execute the engineering vehicle brake friction fault assessment method of the present invention based on the acquired engineering vehicle brake friction fault assessment system, thereby realizing the engineering vehicle brake friction fault assessment.

[0069] In some further embodiments of the present invention, in combination with the above-mentioned construction vehicle brake friction fault assessment method, the embodiments of the present invention provide the following technical solutions: a storage medium having a computer program stored thereon, and the computer program implements the above-mentioned construction vehicle brake friction fault assessment method when executed by a processor.

[0070] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0071] More specific examples of readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0072] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0073] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described 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.

[0074] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for evaluating brake friction faults of an engineering vehicle, characterized in that: include: Collecting friction parameter data of the brake of the engineering vehicle and friction braking data of the brake during braking; Performing feature extraction on the friction parameter data to obtain a parameter feature set, and performing feature extraction on the friction braking data to obtain a braking feature set; Performing feature screening on the parameter feature set and the braking feature set respectively to obtain a parameter screening feature set and a braking screening feature set; Combining and compressing the parameter screening feature set and the brake screening feature set respectively to obtain a parameter compression feature set and a brake compression feature set; Performing feature fusion on the parameter compression feature set and the brake compression feature set to obtain a fused feature set; Historical training data and corresponding friction fault labels are obtained, a preset evaluation model is trained based on the historical training data and the friction fault labels to obtain a training evaluation model, and the fusion feature set is input into the training evaluation model for evaluation to output the corresponding friction fault labels.

2. The engineering vehicle brake friction fault assessment method according to claim 1, characterized in that: The step of extracting features from the friction parameter data to obtain a parameter feature set comprises: The friction parameter data is subjected to a first feature extraction to obtain a data feature set. : ； ； ； ； ； ； ； ； In the formula, Respectively represent the first, second, third, fourth, fifth, sixth, and seventh data features, Indicates Group friction parameter data, Indicates The average value of the friction parameter data of the group, represents the number of groups of friction parameter data, Indicates Standard deviation of group friction parameter data; The friction parameter data is converted into frequency domain to obtain frequency domain data, and the frequency domain data is subjected to a second feature extraction to obtain a frequency feature set. : ； ； ； ； ； ； ； ； In the formula, represents the first, second, third, fourth, fifth, sixth, and seventh frequency characteristics, , Respectively represent The frequency value of the frequency domain data of the group Group frequency domain data, The number of groups representing frequency domain data; Calculate the intimacy between the friction parameter data , the intimacy The friction parameter data greater than the preset value is extracted to obtain the intimate feature set: ； In the formula, , Respectively represent Group, The first data, Indicates The average value of the friction parameter data of the group, Indicates Group, The number of data in the group friction parameter data; The data feature set, the frequency feature set and the intimacy feature set are integrated to obtain a parameter feature set.

3. The engineering vehicle brake friction fault assessment method according to claim 1, characterized in that: The step of extracting features from the friction braking data to obtain a braking feature set comprises: The friction brake data is subjected to wavelet decomposition to obtain a number of wavelet coefficients. ; The wavelet coefficients are updated to obtain updated wavelet coefficients. : ； In the formula, Indicates the preset threshold; Based on the updated wavelet coefficients Performing inverse wavelet transform to obtain reconstructed friction brake data; Extracting the maximum value, minimum value, average value, median value, peak value, variance, and standard deviation of the reconstructed friction brake data to obtain a first feature set; Performing frequency domain conversion on the reconstructed friction braking data to obtain braking frequency domain data, and extracting the center frequency, frequency variance, frequency standard deviation, root mean square frequency, and mean square frequency of the braking frequency domain data to obtain a second feature set; The first feature set and the second feature set are combined to obtain a braking feature set.

4. The engineering vehicle brake friction fault assessment method according to claim 1, characterized in that: The step of performing feature screening on the parameter feature set and the braking feature set respectively to obtain the parameter screening feature set and the braking screening feature set comprises: Calculate the classification index of the parameter feature set and the braking feature set : ； In the formula, Indicates the number of categories of parameter feature set or brake feature set, represents the number of samples of parameter feature set or brake feature set, Indicates the first The number of samples in each category; Traversing all feature dimensions in the parameter feature set and the brake feature set, and arranging them in ascending order according to the size of the feature dimensions, so as to obtain a parameter permutation set and a brake permutation set; Calculate the average values ​​of two adjacent items in the parameter permutation set and the braking permutation set respectively to obtain a parameter average value set and a braking average value set, divide the parameter average value set into large and small values ​​according to each item in the parameter average value set to obtain a plurality of parameter partition sets, and divide the braking average value set into large and small values ​​according to each item in the braking average value set to obtain a plurality of braking partition sets; Calculate the classification index of each parameter partition set and each brake partition set respectively, and determine the classification index and classification index of the parameter partition set and the classification index of the braking partition set and the classification index The second difference of Determine a parameter partition set corresponding to when the first difference is maximum and a braking partition set corresponding to when the second difference is maximum, use the parameter feature set as a parameter main node and use the parameter partition set corresponding to when the first difference is maximum and its corresponding feature dimension as a first parameter sub-node, use the braking feature set as a braking main node and use the braking partition set corresponding to when the second difference is maximum and its corresponding feature dimension as a first braking sub-node; The node partitioning process is iteratively repeated to obtain a parameter partitioning tree and a braking partitioning tree. The parameter partitioning sets corresponding to the first several nodes in the parameter partitioning tree are extracted as parameter screening feature sets according to the parameter screening threshold. The braking partitioning sets corresponding to the first several nodes in the braking partitioning tree are extracted as braking screening feature sets according to the braking screening threshold.

5. The engineering vehicle brake friction fault assessment method according to claim 1, characterized in that: The step of merging and compressing the parameter screening feature set and the brake screening feature set to obtain a parameter compression feature set and a brake compression feature set comprises: Segmenting the parameter screening feature set and the brake screening feature set according to the positions of the peaks and troughs to obtain a plurality of parameter segmentation feature sets and a plurality of brake segmentation feature sets; A first distance matrix is ​​constructed based on the parameter segmentation feature set and the brake segmentation feature set. With the second distance matrix : ； ； In the formula, , , , Respectively represent the first distance matrix Line Column, No. Line Column, No. Line Column, No. Line The elements of the column, , , , Respectively represent the first Line Column, No. Line Column, No. Line Column, No. Line The elements of the column, represents the Euclidean distance calculation, Respectively represent The parameter segmentation feature set elements, Indicates The parameter segmentation feature set elements, Respectively represent The brake segmentation feature set elements, Indicates The brake segmentation feature set elements; Calculate the first similarity between each two parameter segmentation feature sets based on the distance matrix And the second similarity between every two brake segmentation feature sets : ； ； If the first similarity between the two parameter segmentation feature sets is not less than the preset similarity, the time series of the two parameter segmentation feature sets is determined, the parameter segmentation feature set with the earlier time series is retained and the parameter segmentation feature set with the later time series is eliminated; if the first similarity between the two parameter segmentation feature sets is less than the preset similarity, the corresponding two parameter segmentation feature sets are retained to obtain a retained parameter set; If the second similarity between the two braking segmentation feature sets is not less than the preset similarity, the time series of the two braking segmentation feature sets are determined, the braking segmentation feature set with the earlier time series is retained and the braking segmentation feature set with the later time series is eliminated; if the second similarity between the two braking segmentation feature sets is less than the preset similarity, the corresponding two braking segmentation feature sets are retained to obtain a retained braking set; Several reserved parameter sets are spliced ​​together according to a time series, and several reserved brake sets are spliced ​​together to obtain a parameter compression feature set and a brake compression feature set.

6. The engineering vehicle brake friction fault assessment method according to claim 1, characterized in that: The step of fusing the parameter compression feature set with the brake compression feature set to obtain a fused feature set comprises: Determining a first brake state corresponding to each set of data in the parameter compression feature set and a second brake state corresponding to each set of data in the brake compression feature set; Determining a first characteristic distance of the parameter compression characteristic set based on the brake state and a second characteristic distance in the brake compression characteristic set : ； ； In the formula, Indicates that the first brake state is The total number of samples under Indicates that the first brake state is The parameter compression feature set under Group data, The first Features, Indicates the second brake status is The total number of samples under Indicates the second brake status is The brake compression characteristics under Group data, The first Features Based on the first characteristic distance Calculate the first compensation coefficient And based on the second characteristic distance Calculate the second compensation coefficient : ； ； In the formula, , Respectively indicate the first brake state is , The following parameters compress all samples in the feature set The mean of the features, Respectively indicate the state of the second brake , The first of all samples in the lower brake compression feature set The mean of the features; Based on the first compensation coefficient With the second compensation coefficient Determine the fusion feature set.

7. The engineering vehicle brake friction fault assessment method according to claim 6, characterized in that: based on the first compensation coefficient With the second compensation coefficient The steps of determining the fusion feature set include: Based on the first compensation coefficient Calculate the first important factor Based on the second compensation coefficient Calculate the second most important factor : ； ； ； ； In the formula, , Represent the first impact factor and the second impact factor respectively. , The state numbers respectively represent the first brake state and the second brake state; Arrange the first important factor of each feature in the parameter compression feature set in ascending order, and assign ascending weights to each feature in the parameter compression feature set according to the arrangement relationship of the features in the parameter compression feature set to obtain a plurality of parameter assignment weights, and perform weighted fusion on the parameter compression feature set based on the parameter assignment weights to obtain a first fused data set; Arrange the second most important factor of each feature in the brake compression feature set in ascending order, and assign ascending weights to each feature in the brake compression feature set according to the arrangement relationship of the features in the brake compression feature set to obtain a plurality of brake assignment weights, and perform weighted fusion on the brake compression feature set based on the brake assignment weights to obtain a second fused data set; Based on the first fusion dataset Fusion with the second dataset Determine the fusion feature set : ； In the formula, represents the fusion weight.

8. A brake friction fault assessment system for an engineering vehicle, characterized in that: The system comprises: A collection module, used for collecting friction parameter data of the brake of the engineering vehicle and friction braking data of the brake during braking; An extraction module, used for performing feature extraction on the friction parameter data to obtain a parameter feature set, and performing feature extraction on the friction braking data to obtain a braking feature set; A screening module, used for performing feature screening on the parameter feature set and the braking feature set respectively, so as to obtain a parameter screening feature set and a braking screening feature set; A compression module, used for merging and compressing the parameter screening feature set and the brake screening feature set respectively, so as to obtain a parameter compression feature set and a brake compression feature set; A fusion module, used for fusing the parameter compression feature set with the brake compression feature set to obtain a fused feature set; An evaluation module is used to obtain historical training data and corresponding friction fault labels, train a preset evaluation model based on the historical training data and the friction fault labels to obtain a training evaluation model, input the fusion feature set into the training evaluation model for evaluation, and output the corresponding friction fault labels.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for evaluating brake friction fault of an engineering vehicle as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the method for evaluating the friction fault of the brake of an engineering vehicle according to any one of claims 1 to 7 is implemented.

Images