Substation equipment fault case recommendation method and system based on progressive feature comparison

Abstract

The present invention discloses a method and system for recommending substation equipment fault cases based on progressive feature comparison, relating to the field of power system substation technology. The method comprises building a substation equipment fault case library and extracting basic equipment information, fault feature information, and fault monitoring information for each fault case; obtaining a target fault to be resolved, comparing the target fault with the basic equipment information of the fault case one by one to obtain first-level matching similar cases; comparing the fault feature information of the target fault with the fault case one by one to obtain second-level matching similar cases; and comparing the fault monitoring information of the target fault with the fault case one by one to obtain fault cases for recommendation. A progressive feature comparison method is employed, taking into account the correlation between equipment features and faults, gradually narrowing the scope of fault cases and improving the accuracy of recommendations.

Description

Technical Field

[0001] The present invention relates to the technical field of power system transformation, and in particular to a method and system for recommending failure cases of transformation equipment based on progressive feature comparison. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] When traditional transformers and other equipment fail, the cause of the fault is diagnosed based on the on-site fault conditions, basic ledger information, fault pictures, and operating system monitoring. After the cause of the fault is determined, the fault is eliminated based on historical experience. The fault handling method lacks reference, and there are problems such as improper handling leading to the expansion of the fault, which affects the safe and stable operation of the power grid.

[0004] After years of operation, power system transformers have accumulated a large amount of fault data and handling cases. How to mine and analyze these cases is of great significance for how to quickly handle and eliminate various transformer faults. However, there is a large amount of fault data for various types of transformers, and the methods for eliminating abnormal faults are different. When the same or similar faults occur in transformers, it is difficult to directly query historical fault cases to guide troubleshooting.

[0005] Selecting similar fault cases, or recommending cases with the most similar characteristics to the target fault, relies on calculating the degree of similarity between the two cases. Existing research, however, mostly relies on complex mathematical models without considering the physical relationship between transformer characteristic parameters and faults. This results in a lack of mechanistic connection between the best source case retrieved and the target case.

[0006] Currently, most of the various case matching methods only use matching equipment types and fault types, and directly perform case similarity matching calculations. They do not further progressively match the fault characteristics with the voltage level, equipment model, manufacturer, voltage regulation method, and winding connection method of the faulty equipment. The scope is too large, resulting in actual applications where the matched cases span voltage levels, equipment models, manufacturers, voltage regulation methods, and winding connection methods. The case accuracy is low and the guidance significance is not great. Even because equipment of different models and manufacturers has differences in design principles, the abnormal handling methods are different, which makes the matched cases misleading operators. Summary of the Invention

[0007] In order to solve the above problems, the present invention proposes a method and system for recommending substation equipment fault cases based on progressive feature comparison. It adopts a layer-by-layer progressive feature comparison method, considers the correlation between equipment features and faults, gradually narrows the scope of fault cases, and improves the recommendation accuracy.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions:

[0009] In a first aspect, the present invention provides a method for recommending substation equipment fault cases based on progressive feature comparison, comprising:

[0010] Construct a substation equipment fault case library and extract basic equipment information, fault characteristic information, and fault monitoring information for each fault case; the basic equipment information includes voltage level, equipment model, manufacturer, voltage regulation method, and winding connection method; the fault characteristic information includes fault type, fault component, fault description, fault cause, and fault attachments;

[0011] Obtain the target fault to be solved, and compare the basic equipment information of the target fault and the fault case one by one in the order of equipment model, manufacturer, voltage level, voltage regulation method, and winding connection method, so as to filter out the first-level matching similar cases in the substation equipment fault case library;

[0012] The fault feature information of the target fault and the fault case are compared one by one in the order of fault type, fault component, fault description, fault cause, and fault attachments, so as to filter out the second-level matching similar cases from the first-level matching similar cases;

[0013] The fault monitoring information of the target fault and the fault case are compared one by one to screen out the fault cases for recommendation from the secondary matching similar cases.

[0014] As an optional implementation method, the process of screening and obtaining first-level matching similar cases includes:

[0015] In the order of equipment model, manufacturer, voltage level, voltage regulation method and winding connection method, first, in the substation equipment fault case library, filter the fault cases with successful equipment model matching; then, among the fault cases with successful equipment model matching, filter the fault cases with successful manufacturer matching; secondly, among the fault cases with successful equipment model and manufacturer matching, filter the fault cases with successful voltage level matching, and so on, until a set number of fault cases are obtained as first-level matching similar cases.

[0016] As an optional implementation method, the process of screening and obtaining secondary matching similar cases includes:

[0017] In the order of fault type, fault component, fault description, fault cause and fault attachments, first, among the first-level matching similar cases, filter the fault cases with successful fault type matching; then, among the fault cases with successful fault type matching, filter the fault cases with successful fault component matching; secondly, among the fault cases with successful matching of both fault type and fault component, filter the fault cases with successful fault description matching, and so on, until a set number of fault cases are obtained as second-level matching similar cases.

[0018] As an optional implementation method, the fault type and faulty component are compared using a byte matching method; the fault description and fault cause are compared using a fault cosine matching method to calculate the similarity of the fault description of the target fault and the fault case, as well as the similarity of the fault cause of the target fault and the fault case; and the fault attachments are compared by image pixel points.

[0019] As an optional implementation, the fault monitoring information includes transformer monitoring alarm information, meteorological monitoring information, vibration monitoring information, insulating oil temperature information, partial discharge information, core grounding current information and load information; in the secondary matching similar cases, the number of features of the successfully matched fault monitoring information is used as the similarity, and they are sorted from large to small to screen out fault cases for recommendation in the secondary matching similar cases.

[0020] As an optional implementation method, the substation equipment fault case library includes: failure cases of the same equipment, failure cases of the same type of equipment, and failure cases of the same model of equipment; relevant information includes basic equipment information, fault characteristic information, fault monitoring information, and corresponding fault handling plans and fault prevention measures.

[0021] As an optional implementation method, a substation equipment fault case library is established based on the fault cases corresponding to key components; wherein the key components include the transformer body, iron core, transformer high-voltage side sleeve, transformer medium-voltage side sleeve, transformer low-voltage side sleeve, oil tank, oil pillow, internal excitation coil and multiple insulation layers, tap changer, cooling system, non-electrical protection type, external auxiliary meters and thermometers.

[0022] In a second aspect, the present invention provides a system for recommending substation equipment fault cases based on progressive feature comparison, comprising:

[0023] A case library construction module is configured to construct a substation equipment fault case library and extract basic equipment information, fault characteristic information, and fault monitoring information for each fault case; the basic equipment information includes voltage level, equipment model, manufacturer, voltage regulation method, and winding connection method; the fault characteristic information includes fault type, fault component, fault description, fault cause, and fault attachments;

[0024] The first-level matching module is configured to obtain the target fault to be solved and compare the basic equipment information of the target fault and the fault case one by one in the order of equipment model, manufacturer, voltage level, voltage regulation method and winding connection method, so as to filter out the first-level matching similar cases in the substation equipment fault case library;

[0025] The secondary matching module is configured to compare the fault feature information of the target fault and the fault case one by one in the order of fault type, fault component, fault description, fault cause and fault attachments, so as to filter out the secondary matching similar cases from the primary matching similar cases;

[0026] The third-level matching module is configured to compare the fault monitoring information of the target fault and the fault case one by one, so as to screen out the fault case for recommendation from the second-level matching similar cases.

[0027] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the first aspect.

[0028] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method described in the first aspect is performed.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] The present invention proposes a method and system for recommending substation equipment fault cases based on progressive feature comparison, which extracts and stores substation equipment fault cases in a feature-based manner, and continuously accumulates them to form a substation equipment fault case library. After a transformer fails, based on feature comparison analysis, the same or similar fault cases are accurately and efficiently recommended, effectively solving problems such as unclear causal relationships, weak mechanism connections, and strong reliance on professional experience in substation equipment fault diagnosis, and realizing auxiliary handling of abnormal substation equipment faults. This is of great significance for the rapid and accurate handling of substation equipment faults.

[0031] The present invention proposes a method and system for recommending fault cases of substation equipment based on progressive feature comparison. The method focuses on the correlation between fault features and faults, maps and associates the fault features with the voltage level, equipment model, manufacturer, voltage regulation method and winding connection method of the faulty equipment, adopts a layer-by-layer progressive feature comparison and matching method, and after progressively comparing to specific components, performs similarity calculation and analysis, so that the fault cases are accurate and effective, fundamentally changing the problem of relying on complex model calculations without considering the relationship between equipment features and faults. The scope of fault cases is gradually narrowed by the degree of relationship between features and faults, and the recommendation accuracy is improved. Case recommendation is more beneficial to guiding fault handling.

[0032] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0034] Figure 1 Flowchart of a method for recommending fault cases of substation equipment based on progressive feature comparison provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0035] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0036] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0037] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0038] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0039] Example 1

[0040] This embodiment provides a method for recommending substation equipment fault cases based on progressive feature comparison. Figure 1 As shown, including:

[0041] Construct a substation equipment fault case library and extract basic equipment information, fault characteristic information, and fault monitoring information for each fault case; the basic equipment information includes voltage level, equipment model, manufacturer, voltage regulation method, and winding connection method; the fault characteristic information includes fault type, fault component, fault description, fault cause, and fault attachments;

[0042] Obtain the target fault to be solved, and compare the basic equipment information of the target fault and the fault case one by one in the order of equipment model, manufacturer, voltage level, voltage regulation method, and winding connection method, so as to filter out the first-level matching similar cases in the substation equipment fault case library;

[0043] The fault feature information of the target fault and the fault case are compared one by one in the order of fault type, fault component, fault description, fault cause, and fault attachments, so as to filter out the second-level matching similar cases from the first-level matching similar cases;

[0044] The fault monitoring information of the target fault and the fault case are compared one by one to screen out the fault cases for recommendation from the secondary matching similar cases.

[0045] For transformers and other substation equipment, based on the voltage level, equipment model, manufacturer, voltage regulation method, and winding connection method as the basic equipment information, corresponding fault cases are generated according to key components, thereby building a substation equipment fault case library;

[0046] Among them, the key components include the transformer body, iron core, transformer high-voltage side sleeve, transformer medium-voltage side sleeve, transformer low-voltage side sleeve, oil tank, oil pillow, internal excitation coil and multiple insulation layers, tap changer, cooling system, non-electrical protection type, external auxiliary meters and thermometers.

[0047] The substation equipment fault case database includes: fault cases of the same equipment, fault cases of the same type of equipment, and fault cases of the same model of equipment; related information includes basic equipment information, fault characteristic information, fault monitoring information, and corresponding fault handling solutions and fault prevention measures;

[0048] Among them, the basic equipment information includes voltage level, equipment model, manufacturer, voltage regulation method and winding connection method; fault characteristic information includes fault type, fault component, fault description, fault cause and fault attachments; fault monitoring information includes transformer monitoring quantity alarm information, meteorological monitoring information, vibration monitoring information, insulating oil temperature information, partial discharge information, core grounding current information and load information.

[0049] Extracting representative feature parameters and establishing a reasonable matching mechanism directly determines the quality of recommendations and whether, after reusing this information, it can effectively guide users in resolving current faults. In this embodiment, basic equipment information, fault feature information, and fault monitoring information are extracted for each fault case in the substation equipment fault case library and the target fault to be resolved. This information is then associated with the basic equipment information. After feature association is complete, feature extraction and clustering are performed on all case library information, ultimately achieving the fusion of multiple types of data, followed by a step-by-step comparison.

[0050] In this embodiment, the basic equipment information, fault feature information and fault monitoring information of the target fault and the fault case are compared and matched step by step, and similar cases are selected according to the matching degree to assist the user in referring to the fault handling plan and fault prevention measures of the fault case to quickly resolve the current abnormal fault.

[0051] Specifically include:

[0052] S1: Comparison of basic equipment information;

[0053] The basic equipment information of the target fault and the fault case is compared and matched one by one in the order of equipment model, manufacturer, voltage level, voltage regulation method and winding connection method;

[0054] If an identical fault case is matched, it will be treated as a first-level matching similar case;

[0055] If they are not exactly the same, the comparison order of device model, manufacturer, voltage level, voltage regulation method and winding connection method is followed. First, the fault cases with successful device model matching are screened. Then, among the fault cases with successful device model matching, the fault cases with successful manufacturer matching are screened. Secondly, among the fault cases with successful device model and manufacturer matching, the fault cases with successful voltage level matching are screened again. This process is repeated until the set number of fault cases are obtained as first-level matching similar cases.

[0056] S2: Comparison of fault characteristic information;

[0057] Compare and match the target fault and the fault case's fault type, fault component, fault description, fault cause, and fault attachments one by one;

[0058] S2-1: For the fault type and fault component, directly compare the fault type and fault component of the target fault case with the source fault case through byte matching to determine whether they are consistent.

[0059] S2-2: Based on the fault description and fault cause, the fault cosine matching method is used to calculate the similarity between the fault description of the target fault and the fault case, as well as the similarity between the fault cause of the target fault and the fault case;

[0060] The fault cosine comparison matching method is:

[0061]

[0062] Where vector a is represented by coordinates (x1, y1) and vector b is represented by coordinates (x2, y2), then the lengths of vector a and vector b in rectangular coordinates are The distance between vector a and vector b is represented by vector c, and the length of vector c in the rectangular coordinate system is From this we get:

[0063]

[0064] This is the expression formula in two-dimensional space. The expression in multi-dimensional space is:

[0065]

[0066] The cosine value of the angle between two vectors in a vector space is used to determine the difference between the target fault and the fault case. When the cosine value is close to 1 and the angle approaches 0, it indicates that the fault descriptions and fault causes of the two vectors, i.e., the target fault and the fault case, are more similar and closer. When the cosine value is close to 0 and the angle approaches 90 degrees, it indicates that the fault descriptions and fault causes of the two vectors, i.e., the target fault and the fault case, are more dissimilar and less similar. This characteristic is used for comparison and matching of fault descriptions and fault causes.

[0067] Where a=(x1,x2,…,x n ),b=(y1,y2,…,y n ), a represents the fault description and fault cause of the target fault, b represents the fault description and fault cause of the fault case, and the final calculated cosine similarity value is between [-1, 1]. In order to ensure that the final similarity is between [0, 1], the following transformation is performed to obtain the final similarity; By setting a similarity threshold, a match greater than the similarity threshold is considered successful.

[0068] S2-3: For the fault attachment, extract the image features of the fault case through pattern recognition, extract and analyze each pixel point one by one, and compare it with the image of the target fault one by one.

[0069] S2-4: In the first-level matching similar cases, first screen the fault cases with successful fault type matching in the order of fault type, fault component, fault description, fault cause and fault attachments. Then, among the fault cases with successful fault type matching, continue to screen the fault cases with successful fault component matching. Next, among the fault cases with successful matching of both fault type and fault component, screen the fault cases with successful fault description matching again. This process continues in this order until a set number of fault cases are obtained as second-level matching similar cases.

[0070] S3: Compare the fault monitoring information of the target fault and the fault case one by one. In the second-level matching similar cases, the number of features of the successfully matched fault monitoring information is used as the similarity with the fault case, and the similarities are sorted from large to small. Finally, the top N fault cases are selected as the final fault cases for recommendation; thereby, the on-site fault is quickly handled and the normal operation of the equipment is restored.

[0071] Example 2

[0072] This embodiment provides a system for recommending substation equipment fault cases based on progressive feature comparison, including:

[0073] A case library construction module is configured to construct a substation equipment fault case library and extract basic equipment information, fault characteristic information, and fault monitoring information for each fault case; the basic equipment information includes voltage level, equipment model, manufacturer, voltage regulation method, and winding connection method; the fault characteristic information includes fault type, fault component, fault description, fault cause, and fault attachments;

[0074] The first-level matching module is configured to obtain the target fault to be solved and compare the basic equipment information of the target fault and the fault case one by one in the order of equipment model, manufacturer, voltage level, voltage regulation method and winding connection method, so as to filter out the first-level matching similar cases in the substation equipment fault case library;

[0075] The secondary matching module is configured to compare the fault feature information of the target fault and the fault case one by one in the order of fault type, fault component, fault description, fault cause and fault attachments, so as to filter out the secondary matching similar cases from the primary matching similar cases;

[0076] The third-level matching module is configured to compare the fault monitoring information of the target fault and the fault case one by one, so as to screen out the fault case for recommendation from the second-level matching similar cases.

[0077] It should be noted that the above modules correspond to the steps described in Example 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above Example 1. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.

[0078] In further embodiments, there is also provided:

[0079] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed by the processor, wherein when the computer instructions are executed by the processor, the method described in Example 1 is performed. For the sake of brevity, no further details are given here.

[0080] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0081] The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0082] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method described in Example 1 is performed.

[0083] The method in Example 1 can be directly implemented as a hardware processor, or can be implemented using a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, it will not be described in detail here.

[0084] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in conjunction with this embodiment can be implemented using electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0085] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A method for recommending fault cases of substation equipment based on progressive feature comparison, characterized in that: include: Construct a substation equipment fault case library and extract basic equipment information, fault characteristic information, and fault monitoring information for each fault case; the basic equipment information includes voltage level, equipment model, manufacturer, voltage regulation method, and winding connection method; the fault characteristic information includes fault type, fault component, fault description, fault cause, and fault attachments; Build a substation equipment fault case database based on the fault cases corresponding to key components; The substation equipment failure case database includes: failure cases of the same equipment, failure cases of the same type of equipment, and failure cases of the same model of equipment; relevant information includes basic equipment information, fault characteristic information, fault monitoring information, and corresponding fault handling solutions and fault prevention measures; Obtain the target fault to be solved, and compare the basic equipment information of the target fault and the fault case one by one in the order of equipment model, manufacturer, voltage level, voltage regulation method, and winding connection method, so as to filter out the first-level matching similar cases in the substation equipment fault case library; The fault feature information of the target fault and the fault case are compared one by one in the order of fault type, fault component, fault description, fault cause, and fault attachments, so as to filter out the second-level matching similar cases from the first-level matching similar cases; The fault type and faulty component are compared using byte matching. The fault description and fault cause are compared using the fault cosine matching method to calculate the similarity between the fault description of the target fault and the fault case, as well as the similarity between the fault cause of the target fault and the fault case. The fault attachment is compared with image pixels. The fault monitoring information of the target fault and the fault case are compared one by one to screen out the fault cases for recommendation from the secondary matching similar cases. The number of features of the successfully matched fault monitoring information is used as the similarity with the fault case, and they are sorted from large to small. Finally, the top N fault cases are selected as the final fault cases for recommendation.

2. The method for recommending substation equipment fault cases based on progressive feature comparison according to claim 1, wherein: The process of screening and obtaining first-level matching similar cases includes: In the order of equipment model, manufacturer, voltage level, voltage regulation method and winding connection method, first, in the substation equipment fault case library, filter the fault cases with successful equipment model matching; then, among the fault cases with successful equipment model matching, filter the fault cases with successful manufacturer matching; secondly, among the fault cases with successful equipment model and manufacturer matching, filter the fault cases with successful voltage level matching, and so on, until a set number of fault cases are obtained as first-level matching similar cases.

3. The method for recommending failure cases of substation equipment based on progressive feature comparison according to claim 1, characterized in that: The process of screening and obtaining secondary matching similar cases includes: In the order of fault type, fault component, fault description, fault cause and fault attachments, first, among the first-level matching similar cases, filter the fault cases with successful fault type matching; then, among the fault cases with successful fault type matching, filter the fault cases with successful fault component matching; secondly, among the fault cases with successful matching of both fault type and fault component, filter the fault cases with successful fault description matching, and so on, until a set number of fault cases are obtained as second-level matching similar cases.

4. The method for recommending failure cases of substation equipment based on progressive feature comparison according to claim 1, wherein: The fault monitoring information includes transformer monitoring alarm information, meteorological monitoring information, vibration monitoring information, insulating oil temperature information, partial discharge information, core grounding current information and load information. In the secondary matching similar cases, the number of features of the successfully matched fault monitoring information is used as the similarity, and the features are sorted from large to small to screen out fault cases for recommendation in the secondary matching similar cases.

5. The method for recommending failure cases of substation equipment based on progressive feature comparison according to claim 1, characterized in that: Key components include transformer body, iron core, transformer high-voltage side sleeve, transformer medium-voltage side sleeve, transformer low-voltage side sleeve, oil tank, oil pillow, internal excitation coil and multiple insulation layers, tap changer, cooling system, non-electrical protection type, external auxiliary meters and thermometers.

6. The power substation equipment fault case recommendation system based on feature progressive comparison is characterized by: Implementing the method for recommending substation equipment fault cases based on progressive feature comparison as described in any one of claims 1 to 5, comprising: A case library construction module is configured to construct a substation equipment fault case library and extract basic equipment information, fault characteristic information, and fault monitoring information for each fault case; the basic equipment information includes voltage level, equipment model, manufacturer, voltage regulation method, and winding connection method; the fault characteristic information includes fault type, fault component, fault description, fault cause, and fault attachments; The first-level matching module is configured to obtain the target fault to be solved and compare the basic equipment information of the target fault and the fault case one by one in the order of equipment model, manufacturer, voltage level, voltage regulation method and winding connection method, so as to filter out the first-level matching similar cases in the substation equipment fault case library; The secondary matching module is configured to compare the fault feature information of the target fault and the fault case one by one in the order of fault type, fault component, fault description, fault cause and fault attachments, so as to filter out the secondary matching similar cases from the primary matching similar cases; The third-level matching module is configured to compare the fault monitoring information of the target fault and the fault case one by one, so as to screen out the fault case for recommendation from the second-level matching similar cases.

7. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method according to any one of claims 1 to 5 is completed.

8. A computer-readable storage medium, characterized in that Used to store computer instructions, which, when executed by a processor, complete the method according to any one of claims 1 to 5.

Images