A failure analysis fault point prediction method and system

Abstract

This invention relates to a failure analysis fault point prediction method and system, belonging to the field of failure analysis technology, and solves the problem of low efficiency in existing failure analysis methods. The method includes constructing diagnostic sample sets for each testing process and training their respective basic classification models; obtaining the yield rate of fault points based on historical maintenance records, and using cluster analysis to identify normal points within the fault points, and statistically calculating the failure probability of normal points; adjusting the order of each testing step in each testing process based on the failure probability of normal points; obtaining the basic classification model for the corresponding testing process based on the latest diagnostic data of the assembly to be tested; if the accuracy of the current basic classification model is higher than a threshold, inputting the latest diagnostic data into the current basic classification model to predict the fault point; otherwise, obtaining the fault point based on the adjusted order of each testing step in the corresponding testing process and the obtained actual test values. This significantly improves the efficiency of failure analysis.

Description

Technical Field

[0001] This invention relates to the field of failure analysis technology, and in particular to a method and system for predicting failure points in failure analysis. Background Technology

[0002] Failure analysis, generally based on failure modes and phenomena, involves analyzing and verifying these modes, simulating and reproducing the failure phenomena, identifying the causes of failure, and uncovering the failure mechanisms. Failure analysis has significant practical value in improving product quality, technology development and improvement, product repair, and arbitrating failure incidents. With the increasing volume of equipment, the storage capacity of industrial failure analysis data will grow exponentially.

[0003] In existing technologies, for defective components, multiple fault phenomena are obtained through testing equipment. Then, maintenance engineers enter the failure analysis process based on the first fault phenomenon, and test the defective component step by step to find the final fault point.

[0004] The existing failure analysis process is not standardized, and historical diagnostic and maintenance records cannot be fully utilized. The detection steps and sequence of failure analysis are related to the engineer's industry knowledge and experience, resulting in low analysis efficiency. Summary of the Invention

[0005] Based on the above analysis, the embodiments of the present invention aim to provide a failure analysis fault point prediction method and system to solve the problem of low efficiency in existing failure analysis.

[0006] On one hand, embodiments of the present invention provide a failure analysis and fault point prediction method, comprising the following steps:

[0007] Based on historical diagnostic data, historical failure analysis records, and historical maintenance records, a diagnostic sample set for each testing process is constructed; based on the diagnostic sample set for each testing process, a basic classification model for each process is trained.

[0008] Based on historical maintenance records, the yield rate of fault points is obtained. By cluster analysis of the yield rate of fault points, normal points are obtained from the fault points. Based on historical failure analysis records, the failure probability of normal points is calculated. According to the failure probability of normal points, the order of each test step under each test process is adjusted.

[0009] Based on the latest diagnostic data of the assembly to be tested, obtain the basic classification model of the corresponding testing process. If the accuracy of the current basic classification model is higher than the threshold, input the latest diagnostic data into the current basic classification model to predict the fault point; otherwise, based on the adjusted order of each testing step under the corresponding testing process and the actual test value obtained, the fault point is obtained.

[0010] Based on further improvements to the above method, and using the adjusted sequence of each detection step within the corresponding detection process and the obtained actual detection values, the fault points are obtained, including:

[0011] Based on the adjusted order of each detection step under the corresponding detection process, the first detection step is obtained according to the preset operation step code. The actual detection value of the first detection step is used as the judgment result. According to the detection result entity associated with the first detection step entity, it is identified whether the fault point corresponding to the judgment result is empty. If it is not empty, the fault point is obtained. Otherwise, according to the actual detection value, the detection step associated with the next operation relationship of the first detection step entity is obtained, and the actual detection value of the detection step is obtained again until the fault point of the detection step entity corresponding to the actual detection value is not empty.

[0012] Based on further improvements to the above method, and using historical diagnostic data, historical failure analysis records, and historical maintenance records, a diagnostic sample set for each testing process is constructed, including:

[0013] For each historical diagnostic data point, retrieve the names and values ​​of multiple test items in sequence; then, obtain the corresponding testing procedure based on the first test item name.

[0014] According to the preset rules, the same test item name in the historical diagnostic data is mapped to the same string as the test code. The test code and its test value are combined into a pair of diagnostic information. Multiple pairs of diagnostic information are concatenated in sequence to obtain a diagnostic data.

[0015] Based on the historical failure analysis records and historical maintenance records corresponding to each historical diagnostic data, the repaired fault points are obtained. The diagnostic data and the corresponding repaired fault points are used as a diagnostic sample and placed into the diagnostic sample set of the corresponding testing process.

[0016] Based on the above method, further improvements are made. The yield rate of fault points is obtained from historical maintenance records. Then, through cluster analysis of the yield rate of fault points, normal points within the fault points are obtained, including:

[0017] Based on historical maintenance records, the yield rate of fault points is calculated on a periodic basis.

[0018] Remove fault points whose yield does not conform to the sigma principle to obtain the fault points to be clustered;

[0019] A density clustering algorithm is used to cluster the fault points to be clustered based on the yield rate of the fault points in the same period and the preset neighborhood radius, so as to obtain the cluster categories; the fault points in the categories with a number of fault points greater than or equal to the number threshold are regarded as normal points.

[0020] Based on further improvements to the above method, the order of each detection step in each detection process is adjusted according to the probability of failure at normal points, including:

[0021] Based on the failure analysis knowledge graph, the normal point name is matched with the part entity name associated with each detection step entity under the current detection process. The failure probability of the normal point is used as the failure probability of the corresponding detection step entity. According to the line entity associated with the part entity, the detection step entity corresponding to the part entity belonging to the same line under each detection process is put into each line set in sequence.

[0022] For each detection process, based on the failure probability of the detection step entity, the total probability of each line set is summarized as the first probability, and the line sets are sorted from largest to smallest according to the first probability; the line sets are merged, the relationships between detection step entities within each line set and the relationships between adjacent line sets are updated, and the detection step entities after the order is adjusted are obtained.

[0023] Based on a further improvement to the above method, the detection step entities corresponding to the part entities belonging to the same line under each detection process are sequentially placed into each line set, including:

[0024] Identify whether there are detection step entities with strong correlation labels under each detection process. If not, place the detection step entities into the corresponding line set in descending order of their failure probability. Otherwise, treat the detection step entities with strong correlation labels as linked steps, obtain the failure probability of each linked step, compare the failure probability of each linked step in the current line set with the failure probability of the detection step entities without strong correlation labels, and place them into the corresponding line set in descending order, with the linked steps moving together.

[0025] Based on further improvements to the above method, detection step entities with strong correlation markers are obtained through the following steps:

[0026] Based on all detection step entities, multiple detection step entities belonging to the same line are considered as transactions, and each detection step entity is considered as a project. The Generalized Sequence Pattern Algorithm (GSP) is used to obtain multiple frequent sequence sets according to the preset support and confidence. The detection step entities corresponding to each frequent sequence set are marked with a strong correlation label; different frequent sequence sets correspond to a unique strong correlation label.

[0027] Based on further improvements to the above method, the relationships between entities in the detection steps within each line set are updated, including:

[0028] Adjust the operation step code of the first detection step entity in the first line set according to the preset operation step code;

[0029] Sequentially extract a group of adjacent detection step entities from each line set, determine whether there is a next step operation relationship between the detection step entities in the group that is normal and / or abnormal, if not, obtain the detection result entity associated with the previous detection step entity, and establish the next step operation relationship between the detection result entity and the next detection step entity that is normal or abnormal based on the abnormal or normal judgment result in the detection result entity, until the traversal is completed.

[0030] Based on further improvements to the above method, the relationships between adjacent line sets are updated, including:

[0031] In each of two adjacent line sets, it is sequentially identified whether the first detection step entity in the preceding line set simultaneously has a next-step operation relationship for both normal and abnormal detection. If such a relationship exists, the next-step operation relationship that is not associated with the detection step entity in the current line set is associated with the first detection step entity in the following line set. If not, based on the detection result entity associated with the last detection step entity in the preceding line set, and according to the abnormal or normal judgment result in the detection result entity, a corresponding next-step operation relationship for normal or abnormal detection is established between the first detection step entity in the following line set and the first detection step entity in the following line set. This process continues until the traversal is complete.

[0032] On the other hand, embodiments of the present invention provide a failure analysis and fault point prediction system, comprising:

[0033] The sample set construction module is used to construct diagnostic sample sets for each testing process based on historical diagnostic data, historical failure analysis records, and historical maintenance records; and to train their respective basic classification models based on the diagnostic sample sets for each testing process.

[0034] The inspection step acquisition module is used to obtain the yield rate of fault points based on historical maintenance records, and to obtain the normal points among the fault points through cluster analysis of the yield rate of fault points; based on historical failure analysis records, it calculates the failure probability of normal points; and adjusts the order of each inspection step under each inspection process according to the failure probability of normal points.

[0035] The fault prediction module is used to obtain the basic classification model of the corresponding inspection process based on the latest diagnostic data of the assembly to be inspected. If the accuracy of the current basic classification model is higher than the threshold, the latest diagnostic data is input into the current basic classification model to predict the fault point; otherwise, the fault point is obtained based on the inspection steps after adjusting the order under the corresponding inspection process and the actual inspection value obtained.

[0036] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects: a basic classification model is constructed based on historical diagnostic data, historical failure analysis records and historical maintenance records, and the failure point is predicted according to the diagnostic data output by the test machine, thereby improving the efficiency of failure analysis; at the same time, by utilizing circuit principles and the physical structure of parts, the detection steps are divided and the strong correlation between the detection steps is obtained, and the order of the detection steps is adjusted periodically in combination with the probability of failure, thereby improving the convenience of use for maintenance engineers and the efficiency of failure analysis.

[0037] In this invention, the above-described technical solutions can be combined with each other to achieve more preferred combinations. Other features and advantages of this invention will be set forth in the following description, and some advantages may become apparent from the description or be learned by practicing the invention. The objects and other advantages of this invention can be realized and obtained from what is particularly pointed out in the description and drawings. Attached Figure Description

[0038] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0039] Figure 1 This is a flowchart of a failure analysis and fault point prediction method according to Embodiment 1 of the present invention;

[0040] Figure 2 This is a tree diagram illustrating the detection steps in the detection process of Embodiment 1 of the present invention;

[0041] Figure 3 This is a tree diagram of the detection steps after the order has been adjusted in Embodiment 1 of the present invention. Detailed Implementation

[0042] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0043] Example 1

[0044] A specific embodiment of the present invention discloses a failure analysis method for predicting fault points, such as... Figure 1 As shown, it includes the following steps:

[0045] S11: Based on historical diagnostic data, historical failure analysis records, and historical maintenance records, construct diagnostic sample sets for each testing process; based on the diagnostic sample sets for each testing process, train their respective basic classification models.

[0046] It should be noted that historical diagnostic data refers to diagnostic data obtained from testing defective assemblies using testing equipment, including the names of test items and their corresponding test values ​​for multiple fault phenomena. Historical failure analysis records are records of the failure analysis process performed by maintenance engineers on defective assemblies according to the standard failure analysis procedure based on the diagnostic data. These records include the standard failure analysis procedure code, the defective assembly code, the test values ​​at each step, and the final fault point (i.e., the part). Historical repair records are records of repairs performed by maintenance engineers based on the fault points in the historical failure analysis records, indicating whether the fault points were repaired and the repair time. Therefore, by using the historical failure analysis records and historical repair records, the repaired fault points corresponding to each piece of diagnostic data can be obtained.

[0047] Specifically, based on historical diagnostic data, historical failure analysis records, and historical maintenance records, a diagnostic sample set is constructed for each testing process, including:

[0048] For each historical diagnostic data point, retrieve the names and values ​​of multiple test items in sequence; then, obtain the corresponding testing procedure based on the first test item name.

[0049] According to the preset rules, the same test item name in the historical diagnostic data is mapped to the same string as the test code. The test code and its test value are combined into a pair of diagnostic information. Multiple pairs of diagnostic information are concatenated in sequence to obtain a diagnostic data.

[0050] Based on the historical failure analysis records and historical maintenance records corresponding to each historical diagnostic data, the repaired fault points are obtained. The diagnostic data and the corresponding repaired fault points are used as a diagnostic sample and placed into the diagnostic sample set of the corresponding testing process.

[0051] For example, a diagnostic sample is: a -1 c -5 e 10 g 100 w 5, and the corresponding fault point is C9403. Here, "acegw" is a sequential detection code, and "-1 -5 10 100 5" are the detection values ​​corresponding to "acegw" respectively.

[0052] It should be noted that the detection items, detection processes, and their correspondence already exist in the failure analysis knowledge graph. Based on the name of the first detection item in each diagnostic sample, the corresponding detection process can be retrieved from the knowledge graph. The diagnostic data in each diagnostic sample is used as feature values, and the fault point is used as the classification result for training and testing of the classification model.

[0053] The classification models used in this embodiment include Random Forest, XGBoost, and Graph Neural Network (GNN). The sample set is divided into a training set and a test set. The training set is used to train the classification model, and the test set is used to test the performance and calculate the accuracy of the analysis model, in order to prevent the network from overfitting to the training dataset or undertraining. These are standard practices and will not be elaborated further.

[0054] S12: Based on historical maintenance records, obtain the yield rate of fault points, and obtain normal points among the fault points through cluster analysis of the yield rate of fault points; based on historical failure analysis records, calculate the failure probability of normal points; adjust the order of each detection step under each detection process according to the failure probability of normal points.

[0055] It should be noted that, based on whether the faults in historical maintenance records have been repaired, the yield rate of the faults is calculated periodically, i.e., the probability that a fault is repaired. The period can be monthly or weekly, and the statistical range is determined according to the actual maintenance situation, such as the number of historical maintenance records and the frequency of maintenance. For example, the yield rate of faults over six consecutive months is calculated.

[0056] After obtaining the yield of all fault points, fault points whose yield does not conform to the sigma principle are removed to obtain the fault points to be clustered. The density clustering algorithm is used to cluster the fault points to be clustered according to the yield of the fault points in the same period and the preset neighborhood radius to obtain the cluster categories. Fault points in the category with a number of fault points greater than or equal to the number threshold are regarded as normal points.

[0057] For example, using the three-sigma principle based on normal distribution, when the yield of a faulty point is less than the average value minus 3 sigma, it is considered an outlier and needs to be removed from the faulty point list. The DBSCAN algorithm is used to cluster the remaining faulty points based on their yield over the most recent month. Based on the clustering results, if the number of faulty points in a category is less than a threshold, the faulty points in that category are considered outliers; otherwise, they are considered normal points.

[0058] Based on historical failure analysis records, the probability of failure occurring at normal points is statistically calculated on a periodic basis. This means the probability that a normal point is identified as a failure point in all failure analysis records of its assembly. It should be noted that this period can be monthly or weekly, and the time range can be the same as or different from the time range used to calculate yield in cluster analysis.

[0059] It should be noted that each detection step in each detection process already exists in the failure analysis knowledge graph. In this embodiment, the failure analysis knowledge graph was constructed by extracting each detection step and result from manually written historical failure analysis files. The detection objects involved in each detection step are part entities already established in the knowledge graph. By segmenting the operation step descriptions, a relationship between the detection steps and part entities was established, and the part entities are associated with circuit entities, allowing the identification of the circuit to which the part belongs. When instantiating the detection step entity, the next operation relationship between detection step entities was initialized, including the next operation when the detection is normal and the next operation when the detection is abnormal. The detection results of each detection step provide the fault points corresponding to normal and / or abnormal detections. The operation step code for the first detection step in each detection process is set to a preset operation step code, such as uniformly set to A001. The operation step codes for other detection steps can be set according to preset rules.

[0060] For example, Table 1 is a standard failure analysis process generated based on the failure analysis knowledge graph. The step numbers and operation types in Table 1 are directly derived from the attribute values ​​of the detection step entities. The operation step descriptions are filled into the operation step description templates corresponding to visual inspection and measurement based on the associated part entities. The next step is the step number of the detection step entity corresponding to the next operation after detection is normal (0) and / or abnormal (1). The fault point is the faulty part corresponding to the detection result (0) when detection is normal and / or the detection result (1) when detection is abnormal, based on the associated detection results.

[0061] Table 1 Example of Standard Failure Analysis Process

[0062]

[0063]

[0064] In Table 1, step A001 is associated with part C9400. The associated detection result is that the fault point is C9400 when the detection is abnormal. It establishes a next step operation relationship with step A002 when the detection is normal. So when the maintenance engineer performs failure analysis, he first displays the operation type and operation step description of step A001. When the visual inspection of part C9400 shows a problem, he enters the actual detection value 1, and the fault point C9400 is obtained, completing one failure analysis. When the visual inspection of part C9400 shows no problem, he enters the actual detection value 0, and step A002 is executed. Then the operation type and operation step description of step A002 are displayed. When the visual inspection of part R3300 shows no problem, he enters the actual detection value 0, and continues to execute step A003 until the fault point is obtained, completing one failure analysis.

[0065] This embodiment utilizes subsequent failure analysis processes and recorded maintenance information of fault points to periodically adjust the order of each testing step in the original testing process in the knowledge graph based on the probability of failure at normal points, making it closer to actual usage and improving failure analysis efficiency.

[0066] Specifically, it includes:

[0067] ① Based on the failure analysis knowledge graph, the normal point name is matched with the part entity name associated with each detection step entity under the current detection process. The failure probability of the normal point is used as the failure probability of the corresponding detection step entity. According to the line entity associated with the part entity, the detection step entity corresponding to the part entity belonging to the same line under each detection process is put into each line set.

[0068] It should be noted that the operation steps described in the inspection step entity are specific operation steps, involving the inspection object and inspection method. The inspection object comes from the part entity.

[0069] For example, a detection process may have 10 detection steps. To make it easier to explain, let's say... Figure 2 The tree structure shows the relationship between the detection steps. The numbers 1 to 10 correspond to the 10 detection step numbers. Y indicates normal detection and N indicates abnormal detection. The probability value in the figure is the probability of failure in the detection step. The parts in steps 1, 3 and 7 have never failed and cannot be matched with normal point names, so the probability of failure is 0.

[0070] It should be noted that when placing the detection step entities corresponding to the part entities belonging to the same line under each detection process into each line set, they can also be sorted according to the probability of failure. The detection steps with the higher failure rate in each line set are sorted first to improve the efficiency of locating the fault point. This includes the following steps:

[0071] Identify whether there are detection step entities with strong correlation labels under each detection process. If not, place the detection step entities into the corresponding line set in descending order of their failure probability. Otherwise, take the detection step entities with strong correlation labels as the failure probability of the linked steps and compare them with the failure probabilities of other linked steps and / or detection step entities without strong correlation labels in the same line set. Place them into the corresponding line set in descending order of their failure probability, where linked steps move together.

[0072] It should be noted that, considering that some detection steps need to be executed together continuously, the entities of the detection steps in the linked operation are marked with strong correlation, the probabilities are summarized, and they are moved at the same time. This improves detection efficiency while ensuring the accuracy of the detection step adjustment.

[0073] Specifically, entities with strong correlation markers in the detection steps are obtained through the following steps:

[0074] Based on all detection step entities, multiple detection step entities belonging to the same line are considered as transactions, and each detection step entity is considered as a project. The Generalized Sequence Pattern Algorithm (GSP) is used to obtain multiple frequent sequence sets according to the preset support and confidence. The detection step entities corresponding to each frequent sequence set are marked with a strong correlation label; different frequent sequence sets correspond to a unique strong correlation label.

[0075] For example, in Figure 2 In the given information, {1,2}, {3,4,5,6}, and {7,8,9,10} belong to three different route sets. Steps 1 and 2 have the same strong correlation label, with a probability of 30% when summed. Steps 3 and 4 have the same strong correlation label, with a probability of 4% when summed. Steps 7 and 8 have the same strong correlation label, with a probability of 20% when summed. Steps 9 and 10 have the same strong correlation label, with a probability of 30% when summed. Therefore, {1,2} does not need to be adjusted. {7,8,9,10} is adjusted to {9,10,7,8}, and {3,4,5,6} is adjusted to {6,5,3,4}.

[0076] ② For each detection process, based on the failure probability of the detection step entity, summarize the total probability of each line set as the first probability, and sort the line sets in descending order of the first probability; merge the line sets, update the relationship between the detection step entities within each line set, as well as the relationship between adjacent line sets, to obtain the detection step entities after the order is adjusted.

[0077] For example, in Figure 2 In the diagram, {1,2}, {3,4,5,6}, and {7,8,9,10} belong to three different line sets. Based on the probability of fault occurrence for each detection step, the total probability of {1,2} is 30%, the total probability of {3,4,5,6} is 20%, and the total probability of {7,8,9,10} is 50%. Given the strong correlation between steps 1 and 2, steps 3 and 4, steps 7 and 8, and steps 9 and 10, and considering adjustments to the detection steps within each line set, the final adjusted detection steps are as follows: Figure 3 As shown, the sets of lines will be merged in the order of {9,10,7,8}{1,2}{6,5,3,4}.

[0078] Specifically, updating the relationships between entities in the detection steps within each line set includes:

[0079] Based on the preset operation step codes, adjust the operation step code of the first detection step entity in the first line set; for example, in Figure 3 In the process, the operation step code of step 1 is regenerated, and the operation step code of step 7 is set to the preset A001.

[0080] Sequentially extract a group of adjacent detection step entities from each line set, determine whether there is a next step operation relationship between the detection step entities in the group that is normal and / or abnormal, if not, obtain the detection result entity associated with the previous detection step entity, and establish the next step operation relationship between the detection result entity and the next detection step entity that is normal or abnormal based on the abnormal or normal judgment result in the detection result entity, until the traversal is completed.

[0081] It should be noted that, based on the abnormal or normal determination result in the detection result entity, a corresponding next step operation relationship is established between the entity in the subsequent detection step and the entity in the next detection step, including:

[0082] When the judgment result in the detection result entity is normal and the corresponding fault point is not empty, the previous detection step entity and the next detection step entity establish a next step operation relationship of abnormal detection; when the judgment result in the detection result entity is abnormal and the corresponding fault point is not empty, the previous detection step entity and the next detection step entity establish a next step operation relationship of normal detection; when the judgment result in the detection result entity is empty, the previous detection step entity and the next detection step entity establish a next step operation relationship of both normal and abnormal detection; when the previous detection step entity has both normal and abnormal judgment results and the fault points are not empty, the fault point corresponding to the judgment result of normal is cleared, and the previous detection step and the next detection step establish a next step operation relationship of normal detection.

[0083] For example, in Figure 3 If the judgment result of step 10 only contains the fault point when it is judged to be normal, then a next step operation relationship is established with step 7 when the detection is abnormal.

[0084] It should be noted that updating the relationship between adjacent line sets includes:

[0085] In each of two adjacent line sets, it is sequentially identified whether the first detection step entity in the preceding line set has both normal and abnormal next step operation relationships. If they exist, the next step operation relationships that are not associated with the detection step entity in the current line set are associated with the first detection step entity in the following line set. If they do not exist, the next step operation relationship corresponding to the normal or abnormal detection is established with the first detection step entity in the following line set based on the abnormal or normal judgment result in the detection result entity associated with the last detection step entity in the preceding line set. This process continues until the traversal is complete.

[0086] For example, in Figure 3 In the diagram, the relationship between the line sets {9,10,7,8} and {1,2} is the relationship between step 8 and step 1, while the relationship between {1,2} and {6,5,3,4} is the relationship between step 1 and step 6.

[0087] Preferably, a timer is used to periodically acquire normal points among the fault points and count the fault occurrence rate of normal points. If a change in the fault occurrence probability of any normal point is detected, the order of each detection step under each detection process is updated.

[0088] Compared with existing technologies, this step adjusts the order of each detection step based on the failure probability of the part. This is done by considering the failure probability, combining circuit principles and the physical structure of the part, placing detection steps belonging to the same circuit together, and prioritizing the detection of steps with a high overall failure probability, thereby improving the efficiency of failure analysis.

[0089] S13: Based on the latest diagnostic data of the assembly to be tested, obtain the basic classification model of the corresponding testing process. If the accuracy of the current basic classification model is higher than the threshold, input the latest diagnostic data into the current basic classification model to predict the fault point; otherwise, based on the adjusted order of each testing step under the corresponding testing process and the actual test value obtained, obtain the fault point.

[0090] It should be noted that each detection process corresponds to a basic classification model, but the accuracy of each model obtained from the test set must be higher than the threshold before it can be used for actual prediction. Otherwise, the detection steps of the current process will be displayed, allowing the maintenance engineer to input the actual detection value in the corresponding step based on the detection results, and obtain the fault point from the current detection step based on the actual detection value.

[0091] Specifically, it includes:

[0092] Based on the adjusted order of each detection step under the corresponding detection process, the first detection step is obtained according to the preset operation step code. The actual detection value of the first detection step is used as the judgment result. According to the detection result entity associated with the first detection step entity, it is identified whether the fault point corresponding to the judgment result is empty. If it is not empty, the fault point is obtained. Otherwise, according to the actual detection value, the detection step associated with the next operation relationship of the first detection step entity is obtained, and the actual detection value of the detection step is obtained again until the fault point of the detection step entity corresponding to the actual detection value is not empty.

[0093] For example, the diagnostic data of the assembly to be tested is: a-1c-15d 20e 300f50. The accuracy threshold of the classification model is 0.8. If the accuracy of the basic classification model is higher than 0.8, then "a-1c-15d 20e 300f50" is directly input into the basic classification model to predict the fault point; otherwise, the maintenance engineer performs actual testing on the parts in the assembly and inputs the actual value according to the testing steps. For example, after executing step 1 (input 1) and step 3 (input 0), step 4 is reached. In step 4, 1 is input to obtain the fault point corresponding to this step.

[0094] Compared with existing technologies, the failure analysis fault point prediction method in this embodiment constructs a basic classification model based on historical diagnostic data, historical failure analysis records, and historical maintenance records. It predicts fault points based on the diagnostic data output by the test machine, thereby improving the efficiency of failure analysis. At the same time, it utilizes circuit principles and component physical structures to divide the testing steps and obtain strong correlations between the testing steps. It also periodically adjusts the order of testing steps based on the probability of fault occurrence, thereby improving the convenience for maintenance engineers and the efficiency of failure analysis.

[0095] Example 2

[0096] Another embodiment of the present invention discloses a failure analysis fault point prediction system, thereby implementing the failure analysis fault point prediction method in Embodiment 1. The specific implementation of each module is described in the corresponding description in Embodiment 1. The system includes:

[0097] The sample set construction module is used to construct diagnostic sample sets for each testing process based on historical diagnostic data, historical failure analysis records, and historical maintenance records; and to train their respective basic classification models based on the diagnostic sample sets for each testing process.

[0098] The inspection step acquisition module is used to obtain the yield rate of fault points based on historical maintenance records, and to obtain the normal points among the fault points through cluster analysis of the yield rate of fault points; based on historical failure analysis records, it calculates the failure probability of normal points; and adjusts the order of each inspection step under each inspection process according to the failure probability of normal points.

[0099] The fault prediction module is used to obtain the basic classification model of the corresponding inspection process based on the latest diagnostic data of the assembly to be inspected. If the accuracy of the current basic classification model is higher than the threshold, the latest diagnostic data is input into the current basic classification model to predict the fault point; otherwise, the fault point is obtained based on the inspection steps after adjusting the order under the corresponding inspection process and the actual inspection value obtained.

[0100] Since the failure analysis fault point prediction system in this embodiment and the aforementioned generation method can be mutually referenced, and this is a repetition, it will not be repeated here. Because this system embodiment shares the same principle as the above method embodiment, it also possesses the corresponding technical effects of the above method embodiment.

[0101] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0102] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A failure analysis fault point prediction method characterized by, Includes the following steps: Based on historical diagnostic data, historical failure analysis records, and historical maintenance records, a diagnostic sample set for each testing process is constructed; based on the diagnostic sample set for each testing process, a basic classification model for each process is trained. Based on historical maintenance records, the yield rate of fault points is obtained, and the normal points among the fault points are obtained by cluster analysis of the yield rate of fault points. Based on historical failure analysis records, the probability of failure occurring at normal points is statistically analyzed. Based on the failure probability of normal points, the order of each inspection step under each inspection process is adjusted, including: matching the normal point name with the part entity name associated with each inspection step entity under the current inspection process based on the failure analysis knowledge graph; using the failure probability of normal points as the failure probability of the corresponding inspection step entity; and according to the line entity associated with the part entity, placing the inspection step entities corresponding to the part entities belonging to the same line under each inspection process into each line set in order; for each inspection process, summarizing the total probability of each line set based on the failure probability of the inspection step entity as the first probability, and sorting each line set in descending order of the first probability; merging each line set, updating the relationship between inspection step entities within each line set, as well as the relationship between adjacent line sets, to obtain the inspection step entities after the order is adjusted. Based on the latest diagnostic data of the assembly to be tested, obtain the basic classification model of the corresponding testing process. If the accuracy of the current basic classification model is higher than the threshold, input the latest diagnostic data into the current basic classification model to predict the fault point; otherwise, based on the adjusted order of each testing step under the corresponding testing process and the actual test value obtained, the fault point is obtained.

2. The failure analysis fault point prediction method according to claim 1, characterized by, The fault point is obtained by adjusting the order of each detection step based on the corresponding detection process and the actual detection values, including: Based on the adjusted order of each detection step under the corresponding detection process, the first detection step is obtained according to the preset operation step code. The actual detection value of the first detection step is used as the judgment result. According to the detection result entity associated with the first detection step entity, it is identified whether the fault point corresponding to the judgment result is empty. If it is not empty, the fault point is obtained. Otherwise, according to the actual detection value, the detection step associated with the next operation relationship of the first detection step entity is obtained, and the actual detection value of the detection step is obtained again until the fault point of the detection step entity corresponding to the actual detection value is not empty.

3. The failure analysis fault point prediction method according to claim 1, characterized by, The diagnostic sample set for each testing process is constructed based on historical diagnostic data, historical failure analysis records, and historical maintenance records, including: For each historical diagnostic data point, retrieve the names and values ​​of multiple test items in sequence; then, obtain the corresponding testing procedure based on the first test item name. According to preset rules, the same test item names in historical diagnostic data are mapped to the same string as test codes. The test code and its test value are then combined to form a pair of diagnostic information. By sequentially piecing together multiple pairs of diagnostic information, a single diagnostic data point is obtained. Based on the historical failure analysis records and historical maintenance records corresponding to each historical diagnostic data, the repaired fault points are obtained. The diagnostic data and the corresponding repaired fault points are used as a diagnostic sample and placed into the diagnostic sample set of the corresponding testing process.

4. The failure analysis fault point prediction method according to claim 1, characterized by, The process of obtaining the yield rate of fault points based on historical maintenance records, and then using cluster analysis to analyze the yield rate of fault points to obtain normal points among the fault points, includes: Based on historical maintenance records, the yield rate of fault points is calculated on a periodic basis. Remove fault points whose yield does not conform to the sigma principle to obtain the fault points to be clustered; A density clustering algorithm is used to cluster the fault points to be clustered based on the yield rate of the fault points in the same period and the preset neighborhood radius, so as to obtain the cluster categories; the fault points in the categories with a number of fault points greater than or equal to the number threshold are regarded as normal points.

5. The failure analysis fault point prediction method according to claim 1, characterized by, The step of sequentially placing the detection step entities corresponding to the part entities belonging to the same line under each detection process into each line set includes: Identify whether there are detection step entities with strong correlation labels under each detection process. If not, place the detection step entities into the corresponding line set in descending order of their failure probability. Otherwise, treat the detection step entities with strong correlation labels as linked steps, obtain the failure probability of each linked step, compare the failure probability of each linked step in the current line set with the failure probability of the detection step entities without strong correlation labels, and place them into the corresponding line set in descending order, with the linked steps moving together.

6. The failure analysis fault point prediction method according to claim 5, characterized by, The detection step entity with strong correlation markers is obtained through the following steps: Based on all detection step entities, multiple detection step entities belonging to the same line are considered as transactions, and each detection step entity is considered as a project. The Generalized Sequence Pattern Algorithm (GSP) is used to obtain multiple frequent sequence sets according to the preset support and confidence. The detection step entities corresponding to each frequent sequence set are marked with a strong correlation label; different frequent sequence sets correspond to a unique strong correlation label.

7. The failure analysis fault point prediction method according to claim 5, characterized by, The update of the relationships between entities in the detection steps within each line set includes: Adjust the operation step code of the first detection step entity in the first line set according to the preset operation step code; Sequentially extract a group of adjacent detection step entities from each line set, determine whether there is a next step operation relationship between the detection step entities in the group that is normal and / or abnormal, if not, obtain the detection result entity associated with the previous detection step entity, and establish the next step operation relationship between the detection result entity and the next detection step entity that is normal or abnormal based on the abnormal or normal judgment result in the detection result entity, until the traversal is completed.

8. The failure analysis fault point prediction method according to claim 5, characterized by, The updating of the relationship between adjacent line sets includes: In each of two adjacent line sets, it is sequentially identified whether the first detection step entity in the preceding line set simultaneously has a next-step operation relationship for both normal and abnormal detection. If such a relationship exists, the next-step operation relationship that is not associated with the detection step entity in the current line set is associated with the first detection step entity in the following line set. If not, based on the detection result entity associated with the last detection step entity in the preceding line set, and according to the abnormal or normal judgment result in the detection result entity, a corresponding next-step operation relationship for normal or abnormal detection is established between the first detection step entity in the following line set and the first detection step entity in the following line set. This process continues until the traversal is complete.

9. A failure analysis and fault point prediction system, characterized in that, include: The sample set construction module is used to construct diagnostic sample sets for each testing process based on historical diagnostic data, historical failure analysis records, and historical maintenance records. Based on the diagnostic sample sets of each detection process, their respective basic classification models are trained. The detection step acquisition module is used to obtain the yield rate of fault points based on historical maintenance records, and to obtain the normal points among the fault points through cluster analysis of the yield rate of fault points; Based on historical failure analysis records, the probability of failure occurring at normal points is statistically analyzed. Based on the failure probability of normal points, the order of each inspection step under each inspection process is adjusted, including: matching the normal point name with the part entity name associated with each inspection step entity under the current inspection process based on the failure analysis knowledge graph; using the failure probability of normal points as the failure probability of the corresponding inspection step entity; and according to the line entity associated with the part entity, placing the inspection step entities corresponding to the part entities belonging to the same line under each inspection process into each line set in order; for each inspection process, summarizing the total probability of each line set based on the failure probability of the inspection step entity as the first probability, and sorting each line set in descending order of the first probability; merging each line set, updating the relationship between inspection step entities within each line set, as well as the relationship between adjacent line sets, to obtain the inspection step entities after the order is adjusted. The fault prediction module is used to obtain the basic classification model of the corresponding inspection process based on the latest diagnostic data of the assembly to be inspected. If the accuracy of the current basic classification model is higher than the threshold, the latest diagnostic data is input into the current basic classification model to predict the fault point; otherwise, the fault point is obtained based on the inspection steps after adjusting the order under the corresponding inspection process and the actual inspection value obtained.

Images