Fault rapid troubleshooting method, device, equipment, storage medium and product

Abstract

The application belongs to the technical field of data processing, and specifically discloses a fault rapid troubleshooting method, device, equipment, storage medium and product. According to the application, a fault feature matrix is established according to fault causes and check items required for troubleshooting fault causes; when it is determined that elements in a candidate check item number array meet preset conditions, an intermediate feature matrix is generated according to row numbers and the fault feature matrix, and an intermediate check matrix is generated according to row numbers and a check result matrix; an initial troubleshooting order is optimized according to the intermediate feature matrix and the intermediate check matrix, and troubleshooting is performed according to the optimized troubleshooting order. In the above manner, without knowing the rule of each check result during troubleshooting in advance, a complete check result is described by using an array, and troubleshooting is performed according to the optimized troubleshooting order by using multiple intermediate matrices, so that the troubleshooting efficiency can be effectively improved, and the fault can be quickly located.

Description

Technical Field

[0001] This application belongs to the field of data processing technology, and more specifically, relates to methods, apparatus, equipment, storage media and products for rapid fault diagnosis. Background Technology

[0002] When equipment malfunctions, troubleshooting is used to find the cause of the failure and then carry out targeted repairs. Therefore, rapid troubleshooting is extremely important. Equipment maintenance manuals typically include troubleshooting content for each maintenance item. This content is generally based on the equipment's working principles and structure, employing a method similar to a multi-branch tree search. A certain check is performed first, and the results determine the next check to be performed. This process is repeated multiple times until a sufficient number of check results are obtained, narrowing the possible causes of the failure down to a very small range. Finally, all possible causes within this range are sorted by probability and checked and confirmed sequentially.

[0003] However, the above methods often become difficult to implement when dealing with complex equipment. The quantitative results of each inspection tend to vary within a range, making it difficult to pinpoint the exact cause of the fault. More often, they narrow down the possible causes, leading to even more inspections after each inspection. Furthermore, the total number of searches in a multi-branch tree increases exponentially, resulting in significant time consumption even with pruning strategies. Therefore, the above methods are inefficient for troubleshooting. Summary of the Invention

[0004] In view of the shortcomings of the prior art, the purpose of this application is to provide a method, apparatus, equipment, storage medium and product for rapid fault diagnosis, which aims to solve the problem that the prior art is inefficient in fault diagnosis because it is difficult to pinpoint the cause of the fault and the total number of searches in a multi-branch tree increases exponentially.

[0005] To achieve the above objectives, firstly, this application provides a method for rapid fault diagnosis, comprising: Establish a fault feature matrix based on the causes of failures in complex equipment and the inspection items required to troubleshoot those causes. An inspection result matrix was established based on data from multiple actual fault investigation records. When it is determined that the elements in the array of candidate inspection item numbers meet the preset conditions, a row number is generated based on the elements in the array of candidate inspection item numbers and the elements in the array of optimized inspection item numbers. An intermediate feature matrix is ​​generated based on the row number and the fault feature matrix. An intermediate inspection matrix is ​​generated based on the row number and the inspection result matrix. The initial troubleshooting order is optimized based on the intermediate feature matrix and the intermediate check matrix, and the fault is troubleshooting is performed based on the optimized troubleshooting order.

[0006] In one embodiment, the step of establishing a fault feature matrix based on the causes of failure when complex equipment malfunctions and the inspection items required to troubleshoot the causes of failure includes: Obtain the cause of failure when complex equipment malfunctions, and check the results of the inspection items required to investigate the cause of failure; Determine the correlation between the cause of the equipment failure and the inspection results, and assign values ​​to elements based on the correlation to establish a fault feature matrix; Calculate the modulus of each column vector of the fault feature matrix; The fault feature matrix is ​​updated element by element based on the modulus.

[0007] In one embodiment, the steps of generating row numbers based on the elements in the array of candidate inspection item numbers and the array of optimized inspection item numbers when it is determined that the elements in the array of candidate inspection item numbers meet the preset conditions, generating intermediate feature matrices based on the row numbers and the fault feature matrix, and generating intermediate inspection matrices based on the row numbers and the inspection result matrix, include: Retrieve the flag values ​​of the flag array that indicates whether each inspection item needs optimization, where the flag value is 1 after initialization. When the flag value is greater than 0, it is determined that the elements in the array of candidate inspection item numbers meet the preset conditions, and the elements in the array of optimized inspection item numbers are extracted. The elements in the array of saved candidate inspection item numbers are merged with the elements in the array of saved optimized inspection item numbers to obtain an inspection item number group, and the inspection item number group is used as the row number; Based on the row number, extract the corresponding target row data from the fault feature matrix and the inspection result matrix respectively; An intermediate feature matrix is ​​generated based on the target row data in the fault feature matrix, and an intermediate inspection matrix is ​​generated based on the target row data in the inspection result matrix.

[0008] In one embodiment, the step of optimizing the initial troubleshooting order based on the intermediate feature matrix and the intermediate check matrix, and then performing fault troubleshooting based on the optimized troubleshooting order, includes: The intermediate check matrix is ​​traversed. Calculate the similarity array based on the traversed columns of data, the intermediate feature matrix, and the transpose of the intermediate feature matrix; The elements in the similarity array are sorted in a preset order, and the number of checks corresponding to each column of data is determined based on the sorting result. The initial troubleshooting order is optimized based on the number of troubleshooting attempts, and the fault is then investigated based on the optimized troubleshooting order.

[0009] In one embodiment, the step of optimizing the initial troubleshooting order based on each of the number of troubleshooting attempts, and then performing fault troubleshooting based on the optimized troubleshooting order, includes: Probability statistics are performed on each of the aforementioned number of investigations to obtain the probability that the number of investigations does not exceed the prescribed number; The inspection item number is updated, and when the updated inspection item number is greater than the number of inspection item types, the highest probability is selected from the probabilities that the number of inspections does not exceed the specified number, and the number of the element corresponding to the highest probability is stored in the optimized inspection item number array. Obtain the current number of optimizations after initialization, and update the current number of optimizations; When the number of optimizations after the update is greater than the number of inspection item types, the initial inspection order is optimized based on the target order optimization strategy, and the fault is investigated according to the optimized inspection order.

[0010] Secondly, this application provides a rapid fault diagnosis device, comprising: A module is established to optimize the initial troubleshooting order based on the intermediate feature matrix and the intermediate check matrix, and to troubleshoot faults based on the optimized troubleshooting order. The establishment module is also used to establish an inspection result matrix based on data from multiple actual fault troubleshooting work records; The generation module is used to generate row numbers based on the elements in the array of saved candidate inspection item numbers and the elements in the array of saved optimized inspection item numbers when it is determined that the elements in the array of saved candidate inspection item numbers meet the preset conditions, generate an intermediate feature matrix based on the row numbers and the fault feature matrix, and generate an intermediate inspection matrix based on the row numbers and the inspection result matrix. The troubleshooting module is used to optimize the initial troubleshooting order based on the intermediate feature matrix and the intermediate inspection matrix, and to perform fault troubleshooting based on the optimized troubleshooting order.

[0011] Thirdly, this application provides an electronic device, comprising: at least one memory for storing a program; and at least one processor for executing the program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the method described in the first aspect or any possible implementation thereof.

[0012] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to perform the method described in the first aspect or any possible implementation thereof.

[0013] Fifthly, this application provides a computer program product that, when run on a processor, causes the processor to perform the method described in the first aspect or any possible implementation thereof.

[0014] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0015] Overall, the technical solutions conceived in this application have the following beneficial effects compared with the prior art: (1) In this application, when a complex device malfunctions, each fault cause is represented by a fault number and each inspection item is represented by an inspection item number. The number value is independent of the order of inspection. At this time, an intermediate feature matrix is ​​generated based on the row number and the fault feature matrix, and an intermediate inspection matrix is ​​generated based on the row number and the inspection result matrix. The initial inspection order is optimized based on the intermediate feature matrix and the intermediate inspection matrix. For complex devices, since there is a strong coupling between certain units and some other units, the different sub-health states of these units will cause changes in the inspection results to a certain extent. At this time, it is not necessary to know the pattern of each inspection result in advance during fault troubleshooting. An array is used to describe the inspection result of a complete actual fault troubleshooting, and multiple intermediate matrices are used to optimize the inspection order for fault troubleshooting, thereby effectively improving the efficiency of fault troubleshooting.

[0016] (2) In the initial stage of equipment use, this application will count the number of actual fault investigation records and determine whether the number is greater than a preset threshold. If not, it indicates that there are no actual fault investigation records or the number is relatively small. In this case, after completing all inspections, the product of the current inspection result and the fault feature matrix can be directly calculated to determine the order of troubleshooting each fault cause, thereby effectively improving the accuracy of determining the troubleshooting order. If yes, it indicates that the number of actual fault investigation records is large. In this case, the probability array can be used to determine which inspections are completed before troubleshooting the fault causes according to the optimized troubleshooting order, and the fault causes can be found quickly with a higher probability, thereby effectively improving the efficiency of finding fault causes.

[0017] In summary, this application optimizes the initial troubleshooting order based on the intermediate feature matrix and the intermediate inspection matrix, and performs fault troubleshooting based on the optimized order. It establishes an inspection result matrix based on data from multiple actual fault troubleshooting work records. When an element in the array of candidate inspection item numbers satisfies a preset condition, a row number is generated based on the elements in the array of candidate inspection item numbers and the optimized array of inspection item numbers. An intermediate feature matrix is ​​generated based on the row number and the fault feature matrix, and an intermediate inspection matrix is ​​generated based on the row number and the inspection result matrix. The initial troubleshooting order is optimized based on the intermediate feature matrix and the intermediate inspection matrix, and fault troubleshooting is performed based on the optimized order. Through this method, it is not necessary to know the pattern of each inspection result in advance. An array is used to describe a complete inspection result, and multiple intermediate matrices are used to optimize the troubleshooting order, thereby effectively improving fault troubleshooting efficiency and enabling rapid fault location. Attached Figure Description

[0018] Figure 1 This is one of the flowcharts illustrating the rapid fault diagnosis method provided in the embodiments of this application; Figure 2 This is a schematic diagram of the investigation simulation results provided in the embodiments of this application; Figure 3 This is a second flowchart illustrating the rapid fault diagnosis method provided in the embodiments of this application; Figure 4 This is a schematic diagram of the module structure of the rapid fault diagnosis device provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0020] In this article, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0021] The terms "first" and "second," etc., used in the specification and claims herein are used to distinguish different objects, not to describe a specific order of objects. For example, "first response message" and "second response message," etc., are used to distinguish different response messages, not to describe a specific order of response messages.

[0022] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0023] Based on this, the embodiments of this application provide a method for rapid fault diagnosis, referring to... Figure 1 , Figure 1 This is one of the flowcharts illustrating the rapid fault diagnosis method provided in this application embodiment. In this embodiment, the rapid fault diagnosis method includes steps S10 to S40: Step S10: Optimize the initial troubleshooting order based on the intermediate feature matrix and the intermediate check matrix, and troubleshoot the fault based on the optimized troubleshooting order.

[0024] It should be noted that in this embodiment, after a device malfunctions, the number of possible causes of the malfunction is denoted as g, and each cause is represented by a malfunction number. The number of inspection items required to determine the cause of the malfunction is denoted as s, and each inspection is represented by an inspection item number. However, the inspection item number is irrelevant to the order of the inspection items; it is either performed or not. Each inspection result during troubleshooting is a ratio value, representing the ratio between the device's malfunction and normal operation. Even for the same malfunction cause, this ratio value is not fixed. For complex devices, due to the strong coupling between certain units, the different sub-optimal states of these units can cause variations in the inspection results. In this embodiment, it is not necessary to know the patterns of each inspection result during troubleshooting in advance (e.g., the mean, variance, etc. of the ratio value). An array is used to describe a complete inspection result. For example, array S describes a complete inspection result, and its elements S... i This indicates the first step after a device malfunction. i The results of the inspection items.

[0025] It should be understood that the fault feature matrix can be established based on the causes of failure when complex equipment fails and the inspection items required to troubleshoot the causes of failure. That is, the fault feature matrix has s rows and g columns.

[0026] Step S20: Establish an inspection result matrix based on data from multiple actual fault troubleshooting work records.

[0027] It is understandable that when the number of actual fault investigation records is n, the inspection result matrix has s rows and n columns. Each column of data corresponds to the inspection result during one actual fault investigation. The actual fault investigation record data includes, but is not limited to, various inspection results and actual fault causes. In addition to establishing the inspection result matrix, a fault cause array can also be established based on multiple actual fault investigation record data. The elements in this fault cause array R... To check the first element in the result matrix N j The columns correspond to the actual fault cause numbers. Taking 26 actual fault troubleshooting records as an example, the transpose of the inspection result matrix N after normalization can be found in Table 1: Table 1:

[0028] Step S30: When it is determined that the elements in the array of candidate inspection item numbers meet the preset conditions, a row number is generated based on the elements in the array of candidate inspection item numbers and the elements in the array of optimized inspection item numbers. An intermediate feature matrix is ​​generated based on the row number and the fault feature matrix. An intermediate inspection matrix is ​​generated based on the row number and the inspection result matrix.

[0029] It should be understood that, in this embodiment, array A can be used to store the candidate inspection item numbers. Before use, the elements in array A need to be initialized. , The flag array is used to indicate whether each inspection item needs optimization. The initialization result of array A can be... , Alternatively, array B can be used to store the optimized inspection item numbers, for example, This indicates that the third check is performed first, and array B is initialized as an empty array.

[0030] Further, step S30 includes: obtaining flag values ​​of a flag array indicating whether each inspection item needs optimization, wherein the flag value after initialization is 1; when the flag value is greater than 0, determining that the elements in the candidate inspection item number array meet preset conditions, and extracting the elements in the optimized inspection item number array; merging the elements in the candidate inspection item number array with the optimized inspection item number array to obtain an inspection item number group, and using the inspection item number group as a row number; extracting corresponding target row data from the fault feature matrix and the inspection result matrix according to the row number; generating an intermediate feature matrix based on the target row data in the fault feature matrix, and generating an intermediate inspection matrix based on the target row data in the inspection result matrix.

[0031] It should be noted that the flag array indicating whether each inspection item needs optimization is initialized only once, with an initial flag value of 1. During subsequent optimization, the flag value may change, for example, from "1" to "0". After obtaining the flag value of the flag array indicating whether each inspection item needs optimization, it is necessary to determine if the flag value is greater than 0. If not, it indicates that the element has been optimized and will not participate in subsequent optimization processes. In this case, let the probability... Then, further update the inspection item number. The steps are as follows: If so, then the element in the array of candidate inspection item numbers is determined to be a valid element, that is, it meets the preset condition and needs to participate in optimization. At this time, the elements in the array of candidate inspection item numbers and the elements in the array of optimized inspection item numbers are merged into a group of inspection item numbers, that is, the inspection item number group. And according to the row number, the corresponding target row data is extracted from the fault feature matrix and the inspection result matrix respectively. An intermediate feature matrix is ​​generated according to the target row data in the fault feature matrix, and an intermediate inspection matrix is ​​generated according to the target row data in the inspection result matrix. For example, if array B is [4, 3, 6], the elements are... If a data element is valid, then the data in rows 1, 3, 4, and 6 are extracted from the fault feature matrix as target row data to generate the intermediate feature matrix Mt. Similarly, the data in rows 1, 3, 4, and 6 are extracted from the inspection result matrix as target row data to generate the intermediate inspection matrix Nt.

[0032] Step S40: Optimize the initial troubleshooting order based on the intermediate feature matrix and the intermediate check matrix, and troubleshoot the fault based on the optimized troubleshooting order.

[0033] It should be noted that after generating the intermediate feature matrix and intermediate inspection matrix, the initial inspection order needs to be optimized. This optimized inspection order can then be used for fault diagnosis, and the cause of the fault can be found quickly with a higher probability. The core idea of ​​this embodiment is to first complete the desired multiple inspection items, then optimize the initial inspection order based on the inspection results, and then inspect possible faulty units (fault sources) according to the optimized inspection order.

[0034] Further, step S40 includes: traversing the intermediate inspection matrix; calculating a similarity array based on the traversed column data, the intermediate feature matrix, and the transpose of the intermediate feature matrix; sorting each element in the similarity array according to a preset order, and determining the number of checks corresponding to each traversed column data based on the sorting result; optimizing the initial check order based on each check number, and performing fault troubleshooting based on the optimized check order.

[0035] Understandably, for the intermediate inspection matrix Nt, there are n columns. We can iterate through the data X for each column, calculate the product of each data X with the intermediate feature matrix Mt, and save the result to the similarity array. Specifically: .

[0036] Where Y represents the similarity array storing the calculation results, T represents the matrix transpose operator, Mt represents the intermediate feature matrix, X represents the data in each column, and * represents the matrix-vector multiplication operator.

[0037] It should be understood that for the similarity array Y, which describes the similarity between each column of data X and each column of data in the intermediate feature matrix Mt, the elements in the similarity array can be sorted according to a preset order, which can be from largest to smallest. The element number corresponding to the sorting result is the fault cause number. For example, if Y=[0.3, 0.2, 0.7], then the element numbers corresponding to the sorting result are 3, 1, and 2. This means that the most likely fault cause number for X is 3, followed by 1, and lastly 2. When the actual fault cause number corresponding to column data X is 2, when troubleshooting or confirming the fault cause according to the troubleshooting order of 3, 1, and 2, 3 troubleshooting steps are required, that is, the number of troubleshooting steps for column data X is 3.

[0038] Further, the step of optimizing the initial inspection order based on each inspection count and performing fault troubleshooting based on the optimized inspection order includes: performing probability statistics on each inspection count to obtain the probability that the inspection count does not exceed a predetermined number; updating the inspection item number, and when the updated inspection item number is greater than the number of inspection item types, selecting the highest probability from the probabilities that the inspection count does not exceed the predetermined number, and storing the number of the element corresponding to the highest probability in the array of optimized inspection item numbers; obtaining the current optimization count after initialization and updating the current optimization count; when the updated optimization count is greater than the number of inspection item types, optimizing the initial inspection order based on the target order optimization strategy, and performing fault troubleshooting based on the optimized inspection order.

[0039] It should be noted that after determining the n number of investigation attempts, it is necessary to perform probability statistics on the n investigation attempts to obtain the probability that the number of investigation attempts does not exceed the specified number m. At this point, the inspection item number will be updated, i.e. It is also necessary to further determine whether the updated check item number is greater than the number of check item types. If not, then the initial value F is checked. i If the number of checks is less than 1, then the step is to select the highest probability from the probabilities of each check not exceeding the specified number of checks, and store the number of the element corresponding to the highest probability in the optimized check item number array. That is, the k-th check needs to be executed in the order of the check. Check the items and set the flag array. probability .

[0040] It should be understood that after obtaining the current number of optimizations after initialization, this current update count needs to be updated, that is... Furthermore, it is determined whether the number of optimizations after the update exceeds the number of inspection item types. If not, the inspection item number after the update needs to be reset. Continue executing the judgment of the initial value F i If the number of steps is less than 1, it indicates that the termination condition is met. At this time, the optimized troubleshooting order is directly output. This optimized troubleshooting order can be used to troubleshoot the fault and find the cause of the fault quickly with a higher probability.

[0041] It should be noted that, in order to optimize item s, a total of 10 calculations were performed, and the optimization results for each calculation are shown in Table 2: Table 2:

[0042] It should be understood that when all 10 checks need to be performed, the termination condition is met, and the optimization of the check items is stopped. The probability array q for finding the cause of the fault within 2 checks can be found in Table 5. If only 1 check item can be performed at the maintenance site, then check item 4 is performed; if only 3 check items can be performed at the maintenance site, then check items 4, 9, and 5 are performed. There is no requirement for the order of check items 4, 9, and 5. The order can be 4, 5, 9 or 9, 5, 4. This embodiment does not impose any restrictions on this and will use the order of 4, 5, 9 as an example for explanation.

[0043] Understandably, in the initial stage of equipment use, when there are few or no actual fault investigation records, after completing all inspections, the product of the current inspection results and the fault feature matrix is ​​directly calculated to determine the order of troubleshooting each fault cause. When there are many actual fault investigation records, the probability array q can determine which inspections are completed before proceeding with the optimized troubleshooting order, thus finding the fault cause quickly with a higher probability. Here, fault location time = inspection time + troubleshooting time; fewer inspection items and fewer troubleshooting attempts can effectively reduce fault location time.

[0044] It is important to emphasize that this embodiment also simulates the effect of the aforementioned rapid fault diagnosis method by simulating fault phenomena. After simulating a large number of faults for the above examples, fault diagnosis is performed using both optimized and random inspection items. The simulation results of the probability of finding the cause of the fault when the number of troubleshooting checks does not exceed 2 are obtained. For details, please refer to [the relevant documentation / reference]. Figure 2 ,visible, Figure 2 The probability of finding the fault is basically consistent with the probability q in Table 2. When using the optimized inspection items, the probability of finding the cause of the fault within two inspections with only 3 inspections is approximately 0.96, which is much greater than 0.5 for random inspection items. Extensive simulation results show that this embodiment can achieve rapid fault location with a smaller number of inspection items and fewer inspections. Furthermore, compared with fault diagnosis methods based entirely on the working principle and structure of the equipment, the maximum number of inspections in this embodiment is fixed, and it does not require accurate understanding of the patterns of various inspection results. This reduces the requirement for maintenance personnel to be familiar with the equipment, resulting in better universality, feasibility, and efficient fault location capabilities.

[0045] This embodiment optimizes the initial troubleshooting order based on the intermediate feature matrix and the intermediate inspection matrix, and performs fault troubleshooting according to the optimized order. It establishes an inspection result matrix based on data from multiple actual fault troubleshooting work records. When an element in the array of candidate inspection item numbers satisfies a preset condition, a row number is generated based on the elements in the array of candidate inspection item numbers and the optimized array of inspection item numbers. An intermediate feature matrix is ​​generated based on the row number and the fault feature matrix, and an intermediate inspection matrix is ​​generated based on the row number and the inspection result matrix. The initial troubleshooting order is optimized based on the intermediate feature matrix and the intermediate inspection matrix, and fault troubleshooting is performed according to the optimized order. Through this method, it is not necessary to know the pattern of each inspection result in advance. An array is used to describe a complete inspection result, and multiple intermediate matrices are used to optimize the troubleshooting order, thereby effectively improving fault troubleshooting efficiency and enabling rapid fault location.

[0046] In one specific implementation, this application provides steps for establishing a fault feature matrix. Please refer to... Figure 3 , Figure 3 This is the second flowchart illustrating the rapid fault diagnosis method provided in this application embodiment. Step S10 includes steps S101 to S104: Step S101: Obtain the cause of failure when complex equipment malfunctions, and check the results of the inspection items required to investigate the cause of failure.

[0047] It should be noted that for the fault feature matrix to be established, any element therein depends on the first... i Are the inspection results of the items related to the cause of the fault? j Therefore, after obtaining the cause of failure when complex equipment malfunctions, it is necessary to determine the inspection results of the inspection items required to investigate the cause of the failure.

[0048] Step S102: Determine the correlation between the cause of the equipment failure and the inspection results, and assign values ​​to elements based on the correlation to establish a fault feature matrix.

[0049] Understandably, after determining the inspection results of the necessary items for troubleshooting the cause of the malfunction, the correlation between the results and the cause of the malfunction at the time the equipment failed is determined; that is, when the cause of the malfunction is... j When, determine the first i Are the inspection results of the items related to the cause of the fault? j The elements are assigned values ​​based on their relevance; for example, if they are unrelated or only slightly related, then... Conversely, To establish a fault feature matrix M, we take a complex piece of equipment with 8 similar faults, requiring 10 inspection items to troubleshoot. The fault feature matrix established in this case can be referenced in Table 3, and the 26 fault troubleshooting records can be referenced in Table 4, as follows: Table 3:

[0050] Table 4:

[0051] Step S103: Calculate the modulus of each column vector of the fault feature matrix.

[0052] Step S104: Update the elements of the fault feature matrix according to the modulus.

[0053] Understandably, after establishing the fault feature matrix, it is necessary to normalize each column vector in the fault feature matrix sequentially. The first step is to calculate the modulus of each column vector of the fault feature matrix, specifically: .

[0054] Where d represents the first element in the fault feature matrix. j The modulus of a column vector This represents an element in the fault feature matrix.

[0055] It should be understood that after calculating the modulus of each column vector of the fault feature matrix, the elements of the fault feature matrix can be updated based on the modulus, specifically as follows: .

[0056] in, Let d represent the element in the fault feature matrix, where d represents the element of the fault feature matrix. j For the modulus of column vectors, please refer to Table 5: Table 5:

[0057] This embodiment obtains the cause of a complex equipment failure and the inspection results of the necessary inspection items to investigate the cause of the failure; determines the correlation between the cause of the equipment failure and the inspection results, and assigns values ​​to elements based on the correlation to establish a fault feature matrix; calculates the modulus of each column vector of the fault feature matrix; and updates the elements of the fault feature matrix based on the modulus. Through this method, after determining the inspection results of the necessary inspection items to investigate the cause of the failure, values ​​are assigned to elements based on the correlation between the cause of the equipment failure and the inspection results, and then the established fault feature matrix is ​​normalized using modulus calculation and element updating, thereby effectively improving the accuracy of establishing the fault feature matrix.

[0058] The following describes the rapid fault diagnosis device provided in this application. The rapid fault diagnosis device described below corresponds to the rapid fault diagnosis method described above. Please refer to... Figure 4 , Figure 4 This is a schematic diagram of the module structure of the rapid fault diagnosis device provided in this application embodiment, including: Module T10 is established to optimize the initial troubleshooting order based on the intermediate feature matrix and the intermediate inspection matrix, and to troubleshoot faults based on the optimized troubleshooting order.

[0059] The establishment module T10 is also used to establish an inspection result matrix based on the data from multiple actual fault troubleshooting work records.

[0060] The generation module T20 is used to generate row numbers based on the elements in the array of saved candidate inspection item numbers and the elements in the array of saved optimized inspection item numbers when it is determined that the elements in the array of saved candidate inspection item numbers meet the preset conditions, generate an intermediate feature matrix based on the row numbers and the fault feature matrix, and generate an intermediate inspection matrix based on the row numbers and the inspection result matrix.

[0061] The troubleshooting module T30 is used to optimize the initial troubleshooting order based on the intermediate feature matrix and the intermediate inspection matrix, and to perform fault troubleshooting based on the optimized troubleshooting order.

[0062] This embodiment optimizes the initial troubleshooting order based on the intermediate feature matrix and the intermediate inspection matrix, and performs fault troubleshooting according to the optimized order. It establishes an inspection result matrix based on data from multiple actual fault troubleshooting work records. When an element in the array of candidate inspection item numbers satisfies a preset condition, a row number is generated based on the elements in the array of candidate inspection item numbers and the optimized array of inspection item numbers. An intermediate feature matrix is ​​generated based on the row number and the fault feature matrix, and an intermediate inspection matrix is ​​generated based on the row number and the inspection result matrix. The initial troubleshooting order is optimized based on the intermediate feature matrix and the intermediate inspection matrix, and fault troubleshooting is performed according to the optimized order. Through this method, it is not necessary to know the pattern of each inspection result in advance. An array is used to describe a complete inspection result, and multiple intermediate matrices are used to optimize the troubleshooting order, thereby effectively improving fault troubleshooting efficiency and enabling rapid fault location.

[0063] It is understood that the detailed functional implementation of each of the above modules can be found in the description of the aforementioned method embodiments, and will not be repeated here.

[0064] It should be understood that the above-described device is used to execute the methods in the above embodiments. The implementation principle and technical effect of the corresponding program modules in the device are similar to those described in the above methods. The working process of the device can be referred to the corresponding process in the above methods, and will not be repeated here.

[0065] Based on the methods in the above embodiments, this application provides an electronic device, please refer to... Figure 5 , Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application.

[0066] It should be noted that the system may include: a processor 10, a communications interface 20, a memory 30, and a communication bus 40. The processor 10, communications interface 20, and memory 30 communicate with each other via the communication bus 40. The processor 10 can invoke logical instructions stored in the memory 30 to execute the methods described in the above embodiments.

[0067] Furthermore, the logical instructions in the aforementioned memory 30 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0068] Based on the methods in the above embodiments, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the methods in the above embodiments.

[0069] Based on the methods in the above embodiments, this application provides a computer program product that, when run on a processor, causes the processor to execute the methods in the above embodiments.

[0070] It is understood that the processor in the embodiments of this application can be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, field-programmable gate arrays, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0071] The method steps in this application embodiment can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor.

[0072] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. Those skilled in the art will readily understand that the above descriptions are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for rapid fault diagnosis, characterized in that, include: Establish a fault feature matrix based on the causes of failures in complex equipment and the inspection items required to troubleshoot those causes. An inspection result matrix is ​​established based on data from multiple actual fault investigation records; each inspection result during fault investigation is a ratio value, representing the ratio between the two results after the equipment malfunctions and during normal operation. When it is determined that the elements in the array of candidate inspection item numbers meet the preset conditions, a row number is generated based on the elements in the array of candidate inspection item numbers and the elements in the array of optimized inspection item numbers. An intermediate feature matrix is ​​generated based on the row number and the fault feature matrix. An intermediate inspection matrix is ​​generated based on the row number and the inspection result matrix. The initial troubleshooting order is optimized based on the intermediate feature matrix and the intermediate check matrix, and the fault is troubleshooting is performed based on the optimized troubleshooting order. The step of establishing a fault feature matrix based on the causes of failure in complex equipment and the inspection items required to troubleshoot the causes of failure includes: The step of optimizing the initial troubleshooting order based on the intermediate feature matrix and the intermediate check matrix, and then performing fault troubleshooting based on the optimized troubleshooting order, includes: The intermediate check matrix is ​​traversed. Calculate the similarity array based on the traversed columns of data, the intermediate feature matrix, and the transpose of the intermediate feature matrix; The elements in the similarity array are sorted in a preset order, and the number of checks corresponding to each column of data is determined based on the sorting result. Probability statistics are performed on each of the aforementioned number of investigations to obtain the probability that the number of investigations does not exceed the prescribed number; The inspection item number is updated, and when the updated inspection item number is greater than the number of inspection item types, the highest probability is selected from the probabilities that the number of inspections does not exceed the specified number, and the number of the element corresponding to the highest probability is stored in the optimized inspection item number array. Obtain the current number of optimizations after initialization, and update the current number of optimizations; When the number of optimizations after the update is greater than the number of inspection item types, the initial inspection order is optimized based on the target order optimization strategy, and the fault is investigated according to the optimized inspection order.

2. The method as described in claim 1, characterized in that, The step of determining the correlation between the cause of the equipment failure and the inspection results, and assigning values ​​to elements based on the correlation to establish a fault feature matrix, includes: Obtain the cause of failure when complex equipment malfunctions, and check the results of the inspection items required to investigate the cause of failure; Determine the correlation between the cause of failure when the complex equipment fails and the inspection results, and assign values ​​to elements based on the correlation to establish a fault feature matrix; Calculate the modulus of each column vector of the fault feature matrix; The fault feature matrix is ​​updated element by element based on the modulus.

3. The method as described in claim 1, characterized in that, The steps of generating row numbers based on the elements in the array of candidate inspection item numbers and the array of optimized inspection item numbers when the elements in the array of candidate inspection item numbers meet the preset conditions, generating an intermediate feature matrix based on the row numbers and the fault feature matrix, and generating an intermediate inspection matrix based on the row numbers and the inspection result matrix include: Retrieve the flag values ​​of the flag array that indicates whether each inspection item needs optimization, where the flag value is 1 after initialization. When the flag value is greater than 0, it is determined that the elements in the array of candidate inspection item numbers meet the preset conditions, and the elements in the array of optimized inspection item numbers are extracted. The elements in the array of saved candidate inspection item numbers are merged with the elements in the array of saved optimized inspection item numbers to obtain an inspection item number group, and the inspection item number group is used as the row number. Based on the row number, extract the corresponding target row data from the fault feature matrix and the inspection result matrix respectively; An intermediate feature matrix is ​​generated based on the target row data in the fault feature matrix, and an intermediate inspection matrix is ​​generated based on the target row data in the inspection result matrix.

4. A rapid fault diagnosis device, characterized in that, include: A module is established to create a fault feature matrix based on the causes of failures in complex equipment and the inspection items required to troubleshoot those causes. The establishment module is also used to establish an inspection result matrix based on the data from multiple actual fault troubleshooting work records; wherein, each inspection result during fault troubleshooting is a ratio value, which represents the ratio of the two results after the equipment has failed to the result during normal operation. The generation module is used to generate row numbers based on the elements in the array of saved candidate inspection item numbers and the elements in the array of saved optimized inspection item numbers when it is determined that the elements in the array of saved candidate inspection item numbers meet the preset conditions, generate an intermediate feature matrix based on the row numbers and the fault feature matrix, and generate an intermediate inspection matrix based on the row numbers and the inspection result matrix. The troubleshooting module is used to optimize the initial troubleshooting order based on the intermediate feature matrix and the intermediate inspection matrix, and to perform fault troubleshooting based on the optimized troubleshooting order. The investigation module is further configured to: traverse the intermediate inspection matrix; calculate a similarity array based on the traversed column data, the intermediate feature matrix, and the transpose of the intermediate feature matrix; sort each element in the similarity array according to a preset order, and determine the number of investigations corresponding to each traversed column data based on the sorting result; perform probability statistics on each number of investigations to obtain the probability that the number of investigations does not exceed a specified number; update the inspection item number, and when the updated inspection item number is greater than the number of inspection item types, select the highest probability from the probabilities that the number of investigations does not exceed the specified number, and store the number of the element corresponding to the highest probability in the array of optimized inspection item numbers; obtain the current optimization count after initialization, and update the current optimization count; when the updated optimization count is greater than the number of inspection item types, optimize the initial investigation order based on the target order optimization strategy, and perform fault investigation based on the optimized investigation order.

5. An electronic device, characterized in that, include: At least one memory for storing computer programs; At least one processor is configured to execute a program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to perform the method as described in any one of claims 1-3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is run on the processor, it causes the processor to perform the method as described in any one of claims 1-3.

7. A computer program product, characterized in that, When the computer program product is run on a processor, the processor causes the processor to perform the method as described in any one of claims 1-3.

Images