Automobile part fault monitoring method based on vibration and CAN data analysis

Abstract

The invention relates to the technical field of part fault monitoring, and particularly discloses an automobile part fault monitoring method based on vibration and CAN data analysis, and the method comprises the following steps: generating monitoring points based on monitoring data, carrying out the clustering of the monitoring points, obtaining a cluster, and obtaining a target point based on the cluster; obtaining the residual life of the automobile part, and generating a training sample in combination with the target index; generating a data set based on the training sample; training and verifying the life prediction model based on the training set and the verification set, obtaining a confidence coefficient, and obtaining a target model based on the confidence coefficient; and obtaining the residual life of the automobile part based on the target model, and sending early warning information based on the residual life. The safety of the vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of component fault monitoring, and particularly relates to a method for monitoring faults of automotive components based on vibration and CAN data analysis. Background Art

[0002] As the service life of automobiles increases continuously, numerous components will be subjected to the combined effects of mechanical loads, thermal loads, and various environmental factors during long-term operation, gradually resulting in problems such as wear, fatigue, and aging. When these components deteriorate to a certain extent, various vehicle faults may be triggered, ranging from minor noises and vibrations to severe power system failures and brake function losses.

[0003] Most of the existing technologies for monitoring faults of automotive components through vibration and CAN data compare parameters under standard working conditions to determine whether there are abnormalities. Such monitoring means will issue a fault prompt when a signal deviating from the reference range is collected. Since the fault signs are often not obvious enough in the early stage, when the system finally detects an abnormality, a certain degree of wear or fatigue may have accumulated inside the component, thereby having a potential impact on the normal operation of the vehicle. Due to the time difference between monitoring and the occurrence of faults, vehicle safety also faces certain risks. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for monitoring faults of automotive components based on vibration and CAN data analysis, and solve the following technical problems: Most of the existing technologies for monitoring faults of automotive components through vibration and CAN data compare parameters under standard working conditions to determine whether there are abnormalities. Such monitoring means will issue a fault prompt when a signal deviating from the reference range is collected. Since the fault signs are often not obvious enough in the early stage, when the system finally detects an abnormality, a certain degree of wear or fatigue may have accumulated inside the component, thereby having a potential impact on the normal operation of the vehicle. Due to the time difference between monitoring and the occurrence of faults, vehicle safety also faces certain risks.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A method for monitoring faults of automotive components based on vibration and CAN data analysis includes the following steps: Collect monitoring data of automotive components at preset time nodes, where the monitoring data includes vibration data and CAN data. Generate monitoring points based on the monitoring data, cluster the monitoring points to obtain clustering clusters, and randomly select m monitoring points in a single clustering cluster as target points, where m is a preset quantity; Obtain the remaining life of the automotive component, obtain the monitoring index corresponding to the target point, mark it as the target index, and generate a training sample. Each training sample includes the target index and the corresponding remaining life; Generate a data set. Each data set includes m training samples corresponding to all the time nodes. Among different data sets, at least one of the m training samples corresponding to the time nodes comes from different clustering clusters; Divide a single data set into a training set and a validation set according to a preset ratio. Establish a life prediction model based on machine learning, train the life prediction model based on the training set, verify the trained life prediction model based on the validation set, and determine the confidence level of the remaining life output by the life prediction model during the verification process. Mark the life prediction model corresponding to the maximum confidence level as the target model; Obtain the remaining life of the automotive component based on the target model. When the remaining life is less than a preset remaining life threshold, send a warning message for prompt.

[0006] As a further solution of the present invention: The process of obtaining the clustering clusters includes: Set a number of time nodes at preset time intervals within a preset monitoring period. Collect the monitoring data of a single automotive component at the time nodes, standardize the monitoring data to remove the dimension to obtain the monitoring index, and generate monitoring points (C 1 , C 2 , …, C n ), where C n represents the nth type of the monitoring index; Number the time nodes, and cluster the monitoring points corresponding to the time nodes with the same number to obtain the clustering clusters.

[0007] As a further solution of the present invention: The process of sending a warning message for prompt includes: When the total duration of the automotive component in use reaches the preset duration, collect the monitoring data and obtain the corresponding monitoring index, denoted as the evaluation index. Input the evaluation index into the target model, and output the remaining life of the automotive component at this time, denoted as the expected life T1; When the expected life T1 is greater than the remaining life threshold, at the time point t + T1 / 2, obtain a new expected life, and repeat the above steps until a certain new expected life is less than the remaining life threshold, and send a warning message for prompt.

[0008] As a further solution of the present invention: During the process of determining the target model, when two or more of the confidence levels are the same and the maximum, perform the following steps: Mark the life prediction model with the same and maximum corresponding confidence as the pending model, obtain the mean of the confidence of all remaining lives output by the pending model during the verification process, and use the pending model with the maximum corresponding mean as the target model.

[0009] As a further solution of the present invention: The process of obtaining the clustering clusters further includes: Mark the monitoring points corresponding to the time nodes with the same number as the pending points, set the clustering radius R, take the pending point a as the clustering center, calculate the density of the pending points within the preset clustering radius R. If the density of the pending points is greater than the preset pending point density threshold, then take the pending point a as the clustering center and generate a pending cluster with a radius of the clustering radius R. If there is a pending point in the pending cluster whose corresponding pending point density is greater than the pending point density threshold, then take this pending point as the clustering center to generate a new pending cluster, and merge it with the original pending cluster into a new pending cluster.

[0010] As a further solution of the present invention: The process of obtaining the clustering clusters further includes: Step 1: Obtain the silhouette coefficient of the pending cluster. When the silhouette coefficient is less than the preset silhouette coefficient threshold, regard the pending cluster as a reducing cluster, sort the reducing clusters in ascending order according to the corresponding silhouette coefficient sizes to obtain the first sorting. Step 2: Obtain the first reducing cluster D1 in the first sorting, obtain the increasing cluster Z1 with the smallest target distance. The target distance represents the distance between the clustering center of the reducing cluster D1 and the clustering center of the increasing cluster. Obtain the silhouette coefficient of a single pending point in the reducing cluster D1, denoted as the sample coefficient, and divide the pending point Y1 corresponding to the smallest sample coefficient into the increasing cluster Z1. Step 3: Determine whether the new reducing cluster D1 is a reducing cluster. If it is, execute Step 2; if not, remove the reducing cluster D1 from the first sorting, obtain a new first sorting, and execute the subsequent steps.

[0011] As a further solution of the present invention: Before obtaining the silhouette coefficient of the pending cluster in Step 1, the following steps are further included: If there is a pending point whose silhouette coefficient is greater than 0 and less than 0.25, then mark the corresponding pending point as noise and remove it. If there is a pending point whose silhouette coefficient is less than -0.8, then mark the corresponding pending point as noise and remove it.

[0012] As a further solution of the present invention: In Step 2, if after the pending point Y1 is divided into the increasing cluster Z1, the increasing cluster is no longer an increasing cluster, then send an error prompt.

[0013] Advantages of the present invention: Compared with the prior art: 1) By performing multi-dimensional clustering on vibration and CAN data and analyzing them in combination with a life prediction model, potential fault signs can be identified at the early wear or fatigue stage of components, avoiding warnings being issued only when the abnormal amplitude significantly deviates from the reference value. As a result, the vehicle can be noticed and repaired at the initial stage of the fault, significantly reducing potential safety risks. 2) By using vibration data and CAN data in combination and standardizing and clustering the collected monitoring indicators, the mechanical state of components and the vehicle operating conditions can be comprehensively reflected. Compared with the practice of relying only on data from a single source, this fusion monitoring method can more accurately capture the fault signs and attenuation trends of the vehicle under variable operating conditions, improving the reliability of overall diagnosis.

[0014] 3) In the clustering stage, by removing noise points and optimizing the sample division between clusters and adding clusters, the interference of abnormal data on the cluster center is effectively reduced. Subsequently, data with multi-cluster and multi-operating condition distributions are used to train and verify the life prediction model, avoiding overfitting to a single operating condition. This can greatly improve the generalization ability and prediction accuracy of the model, making it more adaptable to component fault diagnosis in complex real environments. 4) When the model outputs the remaining life of components, dynamic monitoring is achieved through the confidence evaluation of the validation set and the time / distance check mechanism: if the remaining life is still long, the detection period is extended; if it is below the threshold, an early warning is immediately triggered and maintenance is arranged. In this way, the service life of components can be extended as much as possible, and timely intervention can be carried out before the fault actually approaches, taking into account both economic benefits and vehicle operation safety. Brief Description of the Drawings

[0015] The present invention will be further described below with reference to the accompanying drawings.

[0016] Figure 1 is a schematic flow chart of a method for monitoring faults of automotive components based on vibration and CAN data analysis according to the present invention. Detailed Embodiment

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0018] Please refer to Figure 1 As shown, the present invention is a method for monitoring faults of automotive components based on vibration and CAN data analysis, including the following steps: During the operation of the vehicle, several time nodes are preset in advance, and data collection is carried out in sequence according to these preset time nodes. Whenever a certain time node is reached, the monitoring data of the vehicle's components at this time is collected, including but not limited to the vibration data output by the vibration sensor and the relevant operating parameters recorded in real time in the vehicle's internal control network (CAN). Subsequently, based on the obtained vibration data and CAN data, and in combination with the pre-agreed processing and expression methods, these data are mapped or combined into one or more monitoring points, so as to solidify the multi-dimensional or multi-type original information into a quantitative representation convenient for analysis. An appropriate clustering algorithm (such as K-Means, hierarchical clustering, or other common clustering methods) is used to perform clustering operations on all monitoring points. Through iterative or recursive methods, the clustering algorithm divides all monitoring points into several clustering clusters with relatively high distinctiveness based on the similarity or distance relationship between the monitoring points. After clustering, each clustering cluster will contain several monitoring points, and m target points are selected in each clustering cluster to meet the data requirements for subsequent analysis, modeling, or evaluation; In a preferred embodiment of the present invention, the process of obtaining the clustering clusters includes: Set several time nodes at preset time intervals within a preset monitoring period, collect the monitoring data of a single vehicle component at these time nodes, perform standardization on the monitoring data to remove the dimension to obtain monitoring indicators, and generate monitoring points (C 1 , C 2 , …, C n ), where C n represents the nth monitoring indicator; Number the time nodes, and cluster the monitoring points corresponding to the time nodes with the same number to obtain clustering clusters; It can be understood that within a pre-planned monitoring period, multiple time nodes are set at established time intervals or durations. Whenever a certain time node is reached, the operating state of the vehicle component at the moment of this time node is data-collected, including obtaining various original values or signals related to this component. Immediately afterwards, the obtained original data is standardized, and appropriate algorithms and proportional coefficients are used to remove the influence of different dimensions, so that various indicators can be compared or calculated under the same benchmark; In a preferred case of this embodiment, the process of obtaining the clustering clusters further includes: Mark the monitoring points corresponding to the time nodes with the same number as pending points, set a clustering radius R, take the pending point a as the clustering center, calculate the density of the pending points within the preset clustering radius R. If the density of the pending points is greater than the preset pending point density threshold, then take the pending point a as the clustering center and generate a pending cluster with a radius of the clustering radius R; If the density of a certain pending point in the pending cluster is greater than the pending point density threshold, a new pending cluster is generated with this pending point as the clustering center and merged with the original pending clusters into a new pending cluster; It should be noted that after obtaining the above monitoring indicators, the sequence or label of the time nodes is numbered one by one. Since each time node will generate a corresponding set of monitoring points, the time nodes marked with the same number are regarded as the same category or group, and then all the monitoring points they contain are concentrated together. According to the similarity or distance relationship of each monitoring point in the index space, the clustering algorithm is used to group them. In this way, the monitoring points corresponding to the time nodes with the same number can be divided into several clustering clusters with obvious differences; In another preferred case of this embodiment, the process of obtaining the clustering cluster further includes: Step 1: Obtain the silhouette coefficient of the pending cluster. When the silhouette coefficient is less than the preset silhouette coefficient threshold, the pending cluster is regarded as a reducing cluster, and the reducing clusters are sorted in ascending order according to the corresponding silhouette coefficient to obtain the first sorting; Step 2: Obtain the first reducing cluster D1 in the first sorting, obtain the adding cluster Z1 with the smallest target distance, where the target distance represents the distance between the clustering center of the reducing cluster D1 and the clustering center of the adding cluster, obtain the silhouette coefficient of a single pending point in the reducing cluster D1, denoted as the sample coefficient, and divide the pending point Y1 corresponding to the smallest sample coefficient into the adding cluster Z1; Step 3: Determine whether the new reducing cluster D1 is a reducing cluster. If so, execute Step 2; if not, remove the reducing cluster D1 from the first sorting, obtain a new first sorting, and execute the subsequent steps; It should be noted that by calculating the silhouette coefficient of each pending cluster, the pending clusters with silhouette coefficients lower than the preset threshold, that is, the reducing clusters, are identified and sorted in ascending order according to their silhouette coefficients, so that the clusters with the worst clustering quality can be processed first. When optimizing, select the reducing cluster with the lowest silhouette coefficient and find the adding cluster with the closest distance to its clustering center. Reclassify the points with the lowest silhouette coefficients in the reducing cluster into the adding cluster one by one to improve the silhouette coefficients of these clusters and the rationality of the data point distribution. If the quality of the reducing cluster still does not meet the standard after the transfer, continue to transfer the pending points until the threshold requirement is met; if the reducing cluster has been improved to be qualified, remove it from the sorting and continue the subsequent optimization process. Such an iterative adjustment mechanism makes the boundaries between the clustering clusters clearer, the data points within the clusters more closely consistent, helps to reduce the impact of abnormal data or outliers on the accuracy of the subsequent life prediction model, and thus improves the overall accuracy and robustness of the subsequent automotive component fault monitoring and early warning based on the clustering results; It can be understood that in the second step, if the to-be-determined point Y1 is divided into the added cluster Z1 and the added cluster is no longer an added cluster, an error prompt is sent; In another preferred case of this embodiment, before obtaining the silhouette coefficient of the to-be-determined cluster in the first step, the following steps are further included: If there is a to-be-determined point with a silhouette coefficient greater than 0 and less than 0.25, the corresponding to-be-determined point is marked as noise and removed; If there is a to-be-determined point with a silhouette coefficient less than -0.8, the corresponding to-be-determined point is marked as noise and removed; After determining the automotive components to be evaluated, through corresponding measurement or estimation means, obtain their remaining life values, and extract the monitoring indicators matching the target points from the previously determined target points. Record these monitoring indicators as target indicators, and at the same time, make the target indicators correspond to the obtained remaining life, and construct a number of training samples. Each training sample contains at least one set of target indicators characterizing the component state and the remaining life measured at the same time or in the same state as it; In order to effectively organize the obtained training samples, the training samples corresponding to m target points from all time nodes are aggregated into a data set according to a predetermined strategy, and it is ensured that between different data sets, at least one time node's m training samples come from clusters different from the previous clustering results, that is, without destroying the data integrity of each time node, each data set contains a sample combination from different clustering clusters, so as to have a richer and more diverse data distribution in subsequent modeling; After the data set is constructed, the single data set is further divided into a training set and a validation set according to a preset ratio, and on this basis, a suitable machine learning method is selected to establish a life prediction model. Subsequently, the training set is used to iteratively train the model so that the model can gradually learn the mapping relationship between the monitoring indicators and the remaining life. After the training is completed, the validation set is input into the model for prediction, and the prediction result is compared with the actual given remaining life in the validation set to obtain the validation accuracy or difference degree of the model at this stage. At the same time, the remaining life output by the model is quantified in terms of confidence during the validation process, and the life prediction model with the highest confidence is selected as the target model. Finally, this target model can be called by subsequent processes or systems to undertake the task of predicting and evaluating the remaining life of automotive components; In another preferred embodiment of the present invention, during the process of determining the target model, when two or more of the confidences are the same and the largest, the following steps are executed: Mark the life prediction model with the same and maximum corresponding confidence level as the to-be-determined model, obtain the mean value of the confidence levels of all remaining lives output by the to-be-determined model during the verification process, and use the to-be-determined model with the maximum corresponding mean value as the target model; After the target model is determined, by inputting real-time or periodic monitoring data related to the current operating state of the automotive component, the output result of the target model is used as the predicted value of the remaining life of the component. Subsequently, the predicted remaining life is compared with a pre-set safety threshold. If the remaining life value is lower than the threshold, it means that the component has approached its safe usage limit or performance critical point. After the system detects such a situation, it will automatically trigger the warning information sending process and send a prompt to the user or relevant maintenance personnel through an appropriate signal channel (such as the in-vehicle information system interface, maintenance management platform, or mobile terminal notification, etc.), informing of the impending or possible component failure risk, so that the maintenance party can arrange replacement or repair in time before the failure occurs, ensuring the normal operation and safety performance of the vehicle; In a preferred embodiment of the present invention, the process of sending a warning message for prompting includes: When the total duration of use of the automotive component reaches a preset duration, collect the monitoring data and obtain the corresponding monitoring indicators, denoted as evaluation indicators. Input the evaluation indicators into the target model to output the remaining life of the automotive component at this time, denoted as the expected life T1; When the expected life T1 is greater than the remaining life threshold, at the time point t + T1 / 2, obtain a new expected life, and repeat the above steps until a new expected life is less than the remaining life threshold, and send a warning message for prompting It should be noted that each of the different automotive components performs the steps in the present invention once, and one target model is only applicable to one type of automotive component.

[0019] The above has described a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the present invention application should still fall within the scope covered by the patent of the present invention.

Claims

1. A method for monitoring automobile parts failure based on vibration and CAN data analysis, characterized in that: The following steps are involved: Collect monitoring data of automobile parts at preset time nodes, the monitoring data including vibration data and CAN data, generate monitoring points based on the monitoring data, cluster the monitoring points to obtain clusters, and randomly select m monitoring points in a single cluster as target points, where m is a preset number; Obtain the remaining life of the automobile parts, obtain the monitoring index corresponding to the target point, mark it as the target index, and generate a training sample, wherein a single training sample includes the target index and the corresponding remaining life; Generate a data set, wherein a single data set includes the m training samples corresponding to all the time nodes, and different data sets have at least one m training sample corresponding to the time node coming from different clusters; Dividing the single data set into a training set and a validation set in a preset ratio, establishing a life prediction model based on machine learning, training the life prediction model based on the training set, validating the trained life prediction model based on the validation set, and determining the confidence of the remaining life output by the life prediction model during the validation process, and marking the life prediction model corresponding to the maximum confidence as the target model; The remaining life of the automobile component is obtained based on the target model, and when the remaining life is less than a preset remaining life threshold, an early warning message is sent for prompting.

2. The method for monitoring automobile parts failure based on vibration and CAN data analysis according to claim 1, characterized in that: The process of obtaining the clustering clusters includes: A number of time nodes are set at preset time intervals within a preset monitoring cycle, monitoring data of a single automobile component is collected at the time nodes, the monitoring data is standardized and dimensioned to obtain monitoring indicators, and monitoring points (C1, C2, ..., C n ), C n Indicates the nth monitoring indicator; The time nodes are numbered, and the monitoring points corresponding to the time nodes with the same number are clustered to obtain clusters.

3. The automobile parts fault monitoring method based on vibration and CAN data analysis according to claim 1 is characterized in that: The process of sending warning information for prompting includes: When the total time the automobile parts have been in use reaches a preset time, the monitoring data is collected and the corresponding monitoring index is obtained, recorded as an evaluation index, the evaluation index is input into the target model, and the remaining life of the automobile parts at this time is output, recorded as the expected life T1; When the expected life T1 is greater than the remaining life threshold, a new expected life is obtained at time point t+T1 / 2, and the above steps are repeated until a new expected life is less than the remaining life threshold, and an early warning message is sent for prompting.

4. The method for monitoring automobile parts failure based on vibration and CAN data analysis according to claim 1, characterized in that: In the process of determining the target model, when two or more confidence levels are the same and the maximum, the following steps are performed: The corresponding life prediction model with the same and largest confidence level is marked as a pending model, the mean of the confidence levels of all remaining lives output by the pending model during the verification process is obtained, and the pending model with the largest corresponding mean level is used as the target model.

5. The method for monitoring automobile parts failure based on vibration and CAN data analysis according to claim 2, characterized in that: The process of obtaining the clustering clusters further includes: The monitoring points corresponding to the time nodes with the same number are marked as pending points, a cluster radius R is set, and the pending point a is taken as the cluster center. The density of the pending points within the preset cluster radius R is calculated. If the density of the pending points is greater than the preset threshold of the density of the pending points, the pending point a is taken as the cluster center to generate a pending cluster with a radius of the cluster radius R; If there is a pending point in the pending cluster whose corresponding pending point density is greater than the pending point density threshold, a new pending cluster is generated with the pending point as the cluster center, and is merged with the original pending cluster into a new pending cluster.

6. The method for monitoring automobile parts failure based on vibration and CAN data analysis according to claim 5, characterized in that: The process of obtaining the clustering clusters further includes: Step 1: obtaining the silhouette coefficient of the cluster to be determined, and when the silhouette coefficient is less than a preset silhouette coefficient threshold, taking the cluster to be determined as a reduced cluster, and sorting the reduced clusters in ascending order according to the corresponding silhouette coefficients to obtain a first sorting; Step 2: Obtain the first reduction cluster D1 in the first sorting, obtain the increase cluster Z1 with the smallest target distance, the target distance represents the distance between the cluster center of the reduction cluster D1 and the cluster center of the increase cluster, obtain the silhouette coefficient of a single undetermined point in the reduction cluster D1, record it as the sample coefficient, and divide the undetermined point Y1 corresponding to the minimum sample coefficient into the increase cluster Z1; Step 3: Determine whether the new reduced cluster D1 is a reduced cluster, if so, execute step 2; if not, remove the reduced cluster D1 from the first sorting, obtain a new first sorting, and execute subsequent steps.

7. The method for monitoring automobile parts failure based on vibration and CAN data analysis according to claim 6, characterized in that: In the step 1, before obtaining the silhouette coefficient of the cluster to be determined, the following steps are also included: If there is a point whose silhouette coefficient is greater than 0 and less than 0.25, the corresponding point is marked as noise and removed; If there is a point whose silhouette coefficient is less than -0.8, the corresponding point will be marked as noise and removed.

8. The method for monitoring automobile parts failure based on vibration and CAN data analysis according to claim 6, characterized in that: In the step 2, if the undetermined point Y1 is divided into the added cluster Z1 and the added cluster is no longer an added cluster, an error prompt is sent.

Images