Method and apparatus for determining device failure type, electronic device, and storage medium

Abstract

The application discloses a kind of equipment failure type determination method, device, electronic equipment and storage medium.The method comprises: by determining at least one failure feature corresponding to the power distribution equipment to be measured;Based on the failure feature and the semantic network constructed in advance, determine the failure type associated with the failure feature, in the case where the number of failure type associated with the failure feature is two or more than two, determine the associated failure feature set corresponding to each failure type;Determine the target failure type of the power distribution equipment to be measured based on multiple associated failure feature sets.Solve the problem that the existing technology diagnoses equipment failure type based on equipment failure record by artificial, resulting in poor fault diagnosis cost, poor accuracy and low efficiency, realize to reduce the cost of fault diagnosis, improve the accuracy and efficiency of fault diagnosis, achieve the effect of improving the safety and stability of power grid operation.

Description

Technical Field

[0001] This invention relates to the field of computer processing technology, and in particular to a method, apparatus, electronic device, and storage medium for determining equipment fault types. Background Technology

[0002] With the continuous development of my country's power system, the scale of the distribution network is expanding, and various faults in the terminal equipment of the distribution network occur frequently. At this time, it is necessary to quickly and accurately identify distribution network faults in order to formulate accurate repair plans for the identified faults, restore the stable operation of the system in a timely manner, ensure the power quality of users, and reduce the losses caused by the faults.

[0003] Currently, existing technologies for terminal fault diagnosis typically rely on expert experience to analyze information such as terminal operating status and defect records to assess the fault type. This subjective, manual assessment method is not only costly but also suffers from poor fault diagnosis accuracy and low efficiency, leading to instability in the distribution network. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for determining equipment fault types, so as to improve the accuracy and efficiency of fault diagnosis while reducing the cost of determining fault types, thereby achieving the technical effect of improving the safety and stability of power grid operation.

[0005] According to one aspect of the present invention, a method for determining the type of equipment failure is provided, the method comprising:

[0006] Identify at least one fault characteristic corresponding to the power distribution equipment under test;

[0007] Based on the fault features and a pre-constructed semantic network, the fault type associated with the fault features is determined, wherein the semantic network includes nodes and edges, the edges represent the association between nodes, and the nodes represent the fault features and fault types to be matched.

[0008] When the number of fault types associated with the fault feature is two or more, determine the associated fault feature set corresponding to each fault type;

[0009] The target fault type of the power distribution equipment under test is determined based on multiple associated fault feature sets.

[0010] According to another aspect of the present invention, an apparatus for determining the type of equipment failure is provided, the apparatus comprising:

[0011] The fault feature determination module is used to determine at least one fault feature corresponding to the power distribution equipment under test.

[0012] A fault type determination module is used to determine the fault type associated with the fault feature based on the fault feature and a pre-constructed semantic network, wherein the semantic network includes nodes and edges, the edges represent the association relationship between nodes, and the nodes represent the fault feature to be matched and the fault type to be matched.

[0013] The associated fault feature set determination module is used to determine the associated fault feature set corresponding to each fault type when the number of fault types associated with the fault feature is two or more.

[0014] The target fault type determination module is used to determine the target fault type of the power distribution equipment under test based on multiple associated fault feature sets.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the device fault type determination method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for determining the type of device fault as described in any embodiment of the present invention.

[0020] The technical solution of this invention determines at least one fault feature corresponding to the power distribution equipment under test; based on the fault feature and a pre-constructed semantic network, it determines the fault type associated with the fault feature; when there are two or more fault types associated with the fault feature, it determines the associated fault feature set corresponding to each fault type; and based on multiple associated fault feature sets, it determines the target fault type of the power distribution equipment under test. This solves the problems of high cost, poor accuracy, and low efficiency in the prior art, which relies on manual diagnosis of equipment fault types based on equipment fault records. It achieves fault diagnosis of the power distribution equipment under test through a semantic network that quantifies the probability of various fault occurrences, and determines the target fault type of the power distribution equipment under test by measuring the uncertainty of the fault type through the associated fault feature set corresponding to each fault type. This improves the speed of fault diagnosis while reducing the cost of determining the fault type, and simultaneously improves the accuracy and efficiency of fault diagnosis, thereby enhancing the safety and stability of power grid operation.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a method for determining equipment fault types according to Embodiment 1 of the present invention;

[0024] Figure 2 This is a schematic diagram of a method for determining equipment fault types according to Embodiment 1 of the present invention;

[0025] Figure 3 This is a semantic network diagram according to Embodiment 1 of the present invention;

[0026] Figure 4 This is a flowchart of a method for determining equipment fault types according to Embodiment 2 of the present invention;

[0027] Figure 5 This is a schematic diagram of a device for determining equipment fault types according to Embodiment 4 of the present invention;

[0028] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the method for determining the type of device fault in an embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] Figure 1 This is a flowchart of a method for determining equipment fault types according to Embodiment 1 of the present invention. This embodiment is applicable to situations involving equipment fault diagnosis. The method can be executed by a device for determining equipment fault types, which can be implemented in hardware and / or software and can be configured in a computing device. Figure 1 As shown, the method includes:

[0033] S110. Determine at least one fault characteristic corresponding to the power distribution equipment under test.

[0034] The equipment under test can be a power distribution monitoring terminal, such as a power distribution IoT convergence terminal, or other types of equipment. Fault characteristics can be characterized by the fault phenomena that occur when a fault occurs, such as equipment shutdown, error messages, data upload failure, error codes, no data return, lost instructions, abnormal indicator lights, abnormal cables, high latency, and other fault characteristics.

[0035] In this embodiment, when a fault is detected in the power distribution equipment under test, multiple fault phenomena existing in the power distribution equipment under test can be obtained in real time as fault features. Alternatively, multiple fault features recorded in the text record instance can be obtained by loading the text record instance generated during the fault defect inspection of the power distribution equipment under test, so as to diagnose the fault of the power distribution equipment under test based on each fault feature.

[0036] S120. Based on fault characteristics and a pre-built semantic network, determine the fault type associated with the fault characteristics.

[0037] The semantic network includes nodes and edges. Edges represent the relationships between nodes, which can be physical (e.g., A contains B, A is a component of B), spatial (e.g., A surrounds B, A is close to B), functional (e.g., A causes B, A is a result of B), temporal (e.g., A and B occur simultaneously, A precedes B), conceptual (e.g., A's evaluation of B, A's evaluation of the effect of B), and so on. Nodes represent the characteristics and types of faults to be matched. Fault types to be matched can include one or more, such as software faults, communication faults, and hardware system faults.

[0038] In this embodiment, after determining the fault characteristics of the power distribution equipment under test, matching can be performed based on each fault characteristic and a semantic network. The semantic network is used to find and mark the fault types that match each fault characteristic. The fault types that are associated with the marked fault types in the semantic network are the fault types associated with that fault characteristic. Accordingly, the fault types associated with each fault characteristic can be determined. There may be one or more fault types. If only one fault type exists, it can be used as the target fault type for the power distribution equipment under test. If multiple fault types exist, step S130 can be executed to determine the final target fault type from among these multiple fault types.

[0039] It should be noted that, when a fault is detected in the power distribution equipment under test, a fault feature set corresponding to each fault type to be matched in the semantic network is determined based on the pre-constructed semantic network and at least one fault feature corresponding to the power distribution equipment under test. If there are two or more non-empty fault feature sets, the non-empty fault feature sets are used as the associated fault feature sets of the fault types, so as to determine the target fault type of the power distribution equipment under test based on the associated fault feature sets.

[0040] Specifically, it can be checked whether the power distribution equipment under test exhibits fault characteristics associated with each fault type to be matched in the semantic network. The observed fault characteristics are then labeled to obtain the labeled fault feature set corresponding to each fault type to be matched. For example, the fault characteristics of software fault types (such as equipment shutdown, error messages, data upload failure, error codes, etc.) are listed as set A1; the fault characteristics of communication fault types (such as cable abnormalities, high latency) are listed as set A2; and the fault characteristics of hardware fault types (such as platform unresponsiveness, command loss, power failure, port unresponsiveness, etc.) are listed as set A3. The sets may be empty or non-empty. If there is only one non-empty fault feature set, then the fault type corresponding to the non-empty fault feature set is the target fault type. If there are two or more non-empty fault feature sets, it indicates that the fault features of the power distribution equipment under test are associated with two or more fault types. In this case, the non-empty fault feature sets can be used as the associated fault feature sets of the fault types of the power distribution equipment under test, so as to determine the target fault type of the power distribution equipment under test based on the associated fault feature sets corresponding to each fault type.

[0041] In this embodiment, the method further includes: constructing a semantic network; the construction of the semantic network can be achieved by: obtaining historical fault text information; the historical fault text information includes multiple fault attributes and reference fault types corresponding to the fault attributes; and constructing a semantic network based on the association relationship between the fault attributes and their associated objects and the relevance corresponding to the association relationship.

[0042] The associated objects include fault attributes and reference fault types. Fault attributes correspond to the fault characteristics to be matched, and reference fault types correspond to the fault types to be matched. The association relationships include at least one of the following: deterministic relationships, physical relationships, spatial relationships, functional relationships, temporal relationships, and conceptual relationships. Relevance can be used to characterize the strength of the association relationship.

[0043] Specifically, historical fault inspection records consistent with the equipment type of the power distribution equipment under test can be obtained as historical fault text information. This text information includes multiple fault attributes and corresponding reference fault types. Fault attributes and reference fault types can be used as nodes in a semantic network. The relevance of associated fault attributes and / or associated reference fault types to each fault attribute can be configured; these associated fault attributes and associated reference fault types are the associated objects. Relevance can be used to characterize the strength of the association. Relevance is added to the edges between nodes, thus obtaining the semantic network.

[0044] In this embodiment, a semantic network for fault cases of power distribution IoT converged terminals can be constructed using the UMLS (Unified Medical Language System) semantic type table. For example, see [link to example]. Figure 2The typical fault and defect inspection text records of the power distribution IoT converged terminal are divided according to semantic information such as the inspection records of the line, station, type, terminal ID, terminal user, and maintenance personnel, as well as time, fault characteristics, fault level, fault cause and elimination plan, and a semantic network including each semantic information is constructed. Furthermore, the relationships between semantic information in the semantic network are manually judged, and the relationships between different semantic information are divided into six categories: "definite relationship", "physical relationship", "spatial relationship", "functional relationship", "temporal relationship" and "conceptual relationship". Among them, physical relationship includes: A is part of B, A is a component of B, A contains B, A is connected to B, A is a branch of B, A is a contribution of B, and A is an ingradient of B; spatial relationship includes: A is located in B, A is adjacent to B, A surrounds B, and A is embedded in B; functional relationship includes: A affects B, A causes B, A exhibits B, A occurs in B, A uses B, and A manifests B. The semantic relationships are as follows: A indicates B, and A is the result of B. Temporally related relationships include: A and B co-occurs with, and A precedes B. Conceptually related relationships include: A's evaluation of B, A's degree of B, A performs B, and A assesses the effect of B. Furthermore, the correlation probability (i.e., relevance) of each functional fault characteristic, fault cause, and troubleshooting solution in the typical fault defect inspection text records of the distribution IoT converged terminal can be added to the arc representing semantic information relevance. This quantifies the strength of the semantic relationship between the fault information of the distribution IoT converged terminal fault cases. The semantic strength represents various uncertainties in terminal inspection and operation maintenance, constructing a tree-like semantic network of distribution IoT converged terminal fault cases. For example, a schematic diagram of the semantic network can be found in [reference needed]. Figure 3The method uses semantic networks to determine the fault types associated with each fault feature of the power distribution equipment under test, as well as the associated fault feature sets corresponding to each fault type.

[0045] S130. When there are two or more fault types associated with a fault feature, determine the associated fault feature set corresponding to each fault type.

[0046] In this embodiment, if the number of fault types associated with a fault feature is two or more, then the fault features associated with each fault type can be aggregated and processed to obtain the associated fault feature set corresponding to each fault type.

[0047] S140. Determine the target fault type of the power distribution equipment under test based on multiple associated fault feature sets.

[0048] In this embodiment, the associated fault feature set includes multiple fault features. Based on the correlation between multiple fault features and their associated fault types, the fault confidence level corresponding to each fault type can be determined. The fault type corresponding to the maximum fault confidence level can be used as the target fault type.

[0049] The technical solution of this embodiment determines at least one fault feature corresponding to the power distribution equipment under test; based on the fault feature and a pre-built semantic network, it determines the fault type associated with the fault feature; when there are two or more fault types associated with the fault feature, it determines the associated fault feature set corresponding to each fault type; and based on multiple associated fault feature sets, it determines the target fault type of the power distribution equipment under test. This solves the problems of high cost, poor accuracy, and low efficiency in the prior art, which relies on manual diagnosis of equipment fault types based on equipment fault records. It realizes fault diagnosis of the power distribution equipment under test through a semantic network based on quantifying the probability of various fault occurrences, and determines the target fault type of the power distribution equipment under test by measuring the uncertainty of the fault type through the associated fault feature set corresponding to each fault type. This improves the speed of fault diagnosis, reduces the cost of determining the fault type, and improves the accuracy and efficiency of fault diagnosis, thereby achieving the technical effect of improving the safety and stability of power grid operation.

[0050] Example 2

[0051] Figure 4 This is a flowchart of a method for determining equipment fault types according to Embodiment 2 of the present invention. Based on the foregoing embodiments, S140 is further refined. Specific implementation details can be found in the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0052] like Figure 4As shown, the method specifically includes the following steps:

[0053] S210. Determine at least one fault characteristic corresponding to the power distribution equipment under test.

[0054] S220. Based on fault characteristics and a pre-built semantic network, determine the fault type associated with the fault characteristics.

[0055] S230. When there are two or more fault types associated with a fault feature, determine the associated fault feature set corresponding to each fault type.

[0056] S240. For each fault type, determine at least one fault feature set to be used corresponding to the fault type based on multiple associated fault feature sets.

[0057] It should be noted that the implementation of determining at least one set of fault features to be used for each fault type is the same, and we can introduce it by determining the set of fault features to be used for one of the fault types.

[0058] In this embodiment, for a given fault type, the associated fault feature set of that fault type can be used as the fault feature set to be used for that fault type. Alternatively, it can be determined whether the fault features in the associated fault feature sets of other fault types overlap with the fault features in the associated fault feature set of the current fault type. If there is overlap, then the associated fault feature set of the other fault type can also be used as the fault feature set to be used for the current fault type. Accordingly, at least one fault feature set to be used for each fault type can be determined.

[0059] In this embodiment, during the process of determining at least one fault feature set to be used corresponding to a fault type from multiple associated fault feature sets, the intersection of every two associated fault feature sets corresponding to a fault type can be determined; and at least one fault feature set to be used corresponding to a fault type can be determined based on the intersection.

[0060] In this embodiment, the associated fault feature sets can be grouped, with each pair of associated fault feature sets forming a group, and the intersection of each pair of associated fault feature sets can be determined. Based on the intersection, it can be determined whether there is overlap between the associated fault feature sets of the two fault types corresponding to the intersection. If there is overlap, it can be considered that one fault type may be associated with the associated fault feature set corresponding to the other fault type, and it is also considered that there is a possibility that the fault features in the associated fault feature set are caused by one of the fault types. The associated fault feature set corresponding to the other fault type can be used as the fault feature set to be used for one of the fault types. Specifically, the implementation of determining at least one fault feature set to be used for each fault type based on the intersection can be as follows: when the intersection of the associated fault feature sets corresponding to the two fault types is not empty, the associated fault feature set corresponding to one fault type is used as the distinguishing fault feature set corresponding to the other fault type; based on the associated fault feature set and the distinguishing fault feature set corresponding to the fault type, at least one fault feature set to be used for each fault type is determined.

[0061] Among them, the processing priority of the associated fault feature set is higher than that of the distinguishing fault feature set.

[0062] In this embodiment, the intersection of the associated fault feature sets corresponding to the two fault types is determined. If the intersection is empty, then each associated fault feature set is used as its own fault feature set to be used. If the intersection is not empty, then the associated fault feature set corresponding to one fault type can be used as the distinguishing fault feature set corresponding to the other fault type. It should be noted that one fault type and another fault type are relative. For example, a software fault type can be considered as one fault type, or it can be considered as another fault type. Both the associated fault feature set and the distinguishing fault feature set of the fault type can be used as fault feature sets to be used. The number of fault feature sets to be used can be one or more.

[0063] For example, see [link to example]. Figure 2 After determining the associated fault feature sets, if the intersection of the associated fault feature set A1 for software fault types and the associated fault feature set A2 for communication fault types is not empty, then it is possible that the occurrence of fault features in A1 may be caused by communication faults, and the occurrence of fault features in A2 may be caused by software faults. Both A1 and A2 can be used as potential fault feature sets for software fault types, and both can be used as potential fault feature sets for communication fault types, to assess the reliability of fault types based on these potential fault feature sets and improve the accuracy of the assessment. If the intersection is empty, the potential fault feature set for software fault types will only contain A1, and the potential fault feature set for communication fault types will only contain A2.

[0064] S250. Determine the fault confidence level of a fault type based on the correlation between the fault type and the fault features in the set of fault features to be used.

[0065] Among them, fault confidence can characterize the probability that the fault characteristics are of this type. For example, the higher the fault confidence, the higher the probability that the fault is of this type, and the lower the fault confidence, the lower the probability that the fault is of this type.

[0066] In practical applications, the correlation of fault features in the set of fault features to be used for a fault type can be weighted and summed to obtain the fault confidence level corresponding to that fault type. Alternatively, the fault confidence levels corresponding to two fault types can be weighted and summed to obtain the comprehensive fault confidence level for both types. The comprehensive fault confidence level characterizes the probability that the current fault belongs to either of these two types.

[0067] For example, the software fault characteristics of the power distribution equipment under test are listed as a software fault characteristic set A1. The correlation of each software fault characteristic is weighted and summed to obtain the fault confidence level B1 of the software fault. The communication module fault characteristics are listed as a communication fault characteristic set A2, and the hardware system fault characteristics are listed as a hardware fault characteristic set A3. The correlation of A2 and A3 is weighted and summed to obtain the fault confidence level B2 of the communication module and hardware system faults. The target fault type is determined by comparing B1 and B2.

[0068] It should be noted that in this embodiment, the troubleshooting priority may differ for each fault type. The troubleshooting priority can be understood as the order in which fault diagnoses are performed. Optionally, fault types may include software fault types, communication fault types, and hardware fault types. Software fault types have the highest troubleshooting priority, while communication and hardware fault types have the second highest priority. The troubleshooting priorities for communication and hardware fault types can be further subdivided; for example, communication fault types have a higher troubleshooting priority than hardware fault types. The reliability of software fault types can be determined first, followed by the reliability of communication and hardware fault types.

[0069] In this embodiment, the method for determining the fault confidence of a fault type with the highest priority based on the correlation between the fault type and the fault features in the set of fault features to be used can be as follows: First, obtain the joint confidence of the fault type and at least one set of fault features to be used. Second, determine the initial confidence corresponding to at least one set of fault features to be used based on the correlation between the fault type and the fault features in the set of fault features to be used, and the weight corresponding to the correlation. Third, determine the usable confidence of the fault feature set based on the joint confidence and the initial confidence corresponding to the same set of fault features to be used. Fourth, determine the fault confidence corresponding to the fault type based on the usable confidence corresponding to at least one set of fault features to be used.

[0070] The joint confidence level can be pre-configured based on historical experience data, and it represents the joint distribution probability. For example, the joint confidence level CTR(B1, A1) of the fault feature set A1 to be used for fault type B1 represents the degree of confidence that fault type B1 is true when the fault feature set A1 to be used is true (occurs).

[0071] In this embodiment, the joint confidence level corresponding to each fault type and each set of fault features to be used can be obtained by looking up a table. For example, CTR(B1, A1) is 0.4, and CTR(B1, A2) = 0.6. The correlation between the fault type and each fault feature in the set of fault features to be used, along with the corresponding weights, are weighted and summed to obtain the initial confidence level. It should be noted that, to ensure that the initial confidence level can characterize the probability of the fault type, the sum of the correlations corresponding to each fault feature is 1. Furthermore, the joint confidence level and the initial confidence level corresponding to the same set of fault features to be used can be multiplied, and the product value can be used as the confidence level of the fault type under this set of fault features to be used. For example, the initial confidence level corresponding to the set of fault features to be used under fault type B1 is CTR(A1) = 0.5 × 0.3 + 0.6 × 0.3 + 0.3 × 0.1 + 0.3 × 0.1 + 0.3 × 0.1 + 0.4 × 0.1 = 0.79. The reliability CTR (A1→B1) is 0.4 × 0.79 = 0.32. If the set of fault features to be used only includes associated fault features, then it can be said that there is only one set of fault features to be used. In this case, the reliability of the set of fault features to be used can be taken as the reliability of the fault. For example, the reliability CTR (B1|A1) = 0.32 represents the reliability of proving that B1 is a fault through A1.

[0072] In this embodiment, if the set of fault features to be used includes an associated fault feature set and a distinguishable fault feature set, then the method for determining the fault confidence corresponding to the fault type based on the confidence corresponding to at least one set of fault features to be used can be as follows: determine a first intermediate value based on the confidence corresponding to the associated fault feature set and a preset parameter; determine a second intermediate value based on the first intermediate value and the confidence corresponding to the distinguishable fault feature set; and determine the fault confidence corresponding to the fault type based on the confidence corresponding to the associated fault feature set and the second intermediate value.

[0073] The preset parameter can be 1.

[0074] In this embodiment, for the set of fault features to be used, which includes an associated fault feature set and a distinguishable fault feature set, the difference between the preset parameters and the confidence level of the associated fault feature set can be processed, and the difference can be used as a first intermediate value. The first intermediate value and the confidence level of the distinguishable fault feature set can be multiplied, and the product value can be used as a second intermediate value. The second intermediate value and the confidence level of the associated fault feature set can be summed, and the sum can be used as the fault confidence level corresponding to the fault type. This allows for assessment of the confidence level of the fault type based on the fault confidence level, improving the accuracy of fault diagnosis.

[0075] For example, see [link to example]. Figure 2 The reliability of a fault type can be determined using fault reasoning. Assume that the set of fault features to be used under fault type B1 includes the associated fault feature set A1 and the distinguishing fault feature set A2. The initial reliability calculated based on A1 under fault type B1 is CTR(A1) = 0.79. The reliability to be used for A1 is CTR(A1→B1) = 0.4 × 0.79 = 0.32. The initial reliability calculated based on A2 under fault type B1 is CTR(A2) = 0.5 × 0.5 + 0.6 × 0.5 = 0.55. The reliability to be used for A2 is CTR(A2→B1) = 0.6 × 0.55 = 0.33. The reliability of the fault under fault type B1 is CTR(B1|A1∪A2) = 0.32 + 0.33 × (1 - 0.32) = 0.54, which represents the reliability of proving B1 is a fault through A1 and A2.

[0076] In this embodiment, the method for determining the fault credibility of a fault type with a second priority based on the correlation between the fault type and the fault features in the set of fault features to be used can be as follows: obtain the collaborative credibility of the fault type under the set of fault features to be used; determine the initial credibility corresponding to each set of fault features to be used based on the correlation between the fault type and the fault features in the set of fault features to be used and the weight corresponding to the correlation; if the set of fault features to be used includes the associated fault feature set of the first priority fault type, then determine the credibility to be processed based on the fault credibility of the first priority fault type and the initial credibility; determine the credibility to be applied based on the credibility to be processed and the collaborative credibility, and then determine the fault credibility of the fault type based on the credibility to be applied.

[0077] Among them, collaborative credibility corresponds to joint credibility and can also be pre-configured based on historical experience data, which also represents the joint distribution probability.

[0078] It should be noted that when determining the reliability of a fault type with a second priority for investigation, there may be multiple fault types in this category (such as communication fault types and hardware communication types). In this case, the reliability of the fault type with a second priority for investigation can be determined by comprehensively considering the correlation between the fault types of these two categories and the fault features in the fault feature set to be used. Alternatively, the reliability of the fault type under each category can be determined separately.

[0079] In this embodiment, the collaborative credibility of a fault type under each set of fault features to be used can be obtained by a lookup table method. For example, CTR(B2, B1∩A3) = 0.9, which represents the joint distribution probability of the occurrence of software fault B1, and having software fault feature set A1, and the cause being a comprehensive fault B2 of the communication and hardware systems. In this case, the intersection between the associated fault feature set of comprehensive fault B2 and A1 is not empty. If the intersection between the associated fault feature set of comprehensive fault B2 and A1 is empty, the collaborative credibility of the fault type under each set of fault features to be used can be CTR(B2, A2∪A3), which represents the credibility of comprehensive fault B2 when communication fault feature set A2 and hardware fault feature set A3 occur. Furthermore, the correlation between the fault type and each fault feature in the set of fault features to be used, and the corresponding weights of the correlation, can be weighted and summed. The resulting sum can be used as the initial credibility. If the set of fault features to be used includes the set of associated fault features of the first priority fault type, then the fault confidence of the first priority fault type can be compared with the initial confidence of the set of associated fault features of the lowest priority fault type (e.g., hardware type) (e.g., A3). The minimum value of the two can be taken as the confidence to be processed. For example, the confidence to be processed CTR(B1∩A3) = min{CTR(B1), CTR(A3)} = min{0.54, 0.81} = 0.54. Furthermore, the collaborative confidence and the confidence to be processed can be multiplied, and the product value can be used as the confidence to be applied. Initially, there is no evidence to prove the fault type (e.g., communication module and hardware system fault B2), i.e., CTR(B2) = 0, so the confidence to be applied can be used as the fault confidence of this fault type.

[0080] In this embodiment, if the set of fault features to be used does not include the associated fault feature set of the first priority fault type, then the fault confidence level corresponding to the fault type is determined based on the initial confidence level of each set of fault features to be used. For example, the initial confidence levels of each set of fault features to be used can be weighted and summed, and the result value can be used as the fault confidence level.

[0081] S260. Based on each fault type and the corresponding fault confidence level, determine the target fault type of the power distribution equipment under test.

[0082] In this embodiment, the fault confidence levels corresponding to each fault type can be compared to determine the highest fault confidence level. Furthermore, the fault type corresponding to the highest fault confidence level can be used as the target fault type for the power distribution equipment under test. For example, the fault confidence level for a software fault type is 0.54, and the fault confidence level for a combined communication and hardware system fault is 0.49. Since 0.54 is greater than 0.49, the target fault type is considered to be a software fault type.

[0083] The technical solution of this embodiment determines at least one set of fault features corresponding to each fault type based on multiple associated fault feature sets for each fault type; determines the fault confidence of the fault type based on the correlation between the fault type and the fault features in the set of fault features to be used, thereby improving the accuracy of measuring the confidence of the fault type; and then determines the target fault type of the power distribution equipment under test based on each fault type and the corresponding fault confidence, thereby improving the accuracy of fault diagnosis.

[0084] Example 3

[0085] As an optional embodiment of the above embodiments, specific application scenario examples are provided to enable those skilled in the art to further understand the technical solutions of the embodiments of the present invention. Specifically, please refer to the following detailed content.

[0086] It should be noted that, given the large number of uncertainties involved in the diagnosis of faults in the IoT-integrated distribution terminal, a single fault type may have multiple fault characteristics. Inexperienced inspection personnel may find it difficult to determine the true cause of the fault. To improve the accuracy of fault diagnosis, this technical solution can apply a semantic network based on IoT-integrated distribution terminal fault cases for uncertainty reasoning to achieve fault diagnosis. For example, uncertainty measurement is performed on rule A→B, where A is the premise representing the fault feature set and B is the conclusion representing the fault type. The uncertainty of rule A→B is measured by the confidence level CTR(B,A), as shown in the following formula (1):

[0087]

[0088] Where P(B) represents the probability that B is true, and P(B|A) represents the probability that conclusion B is true when the evidence set (i.e., the fault feature set) A is true under the rule A→B. CTR(B,A) represents the degree of confidence that A is true for B when evidence A is true.

[0089] In practical applications, uncertainty measures of evidence are performed. When evidence A is true, CTR(A) = 1; when evidence A is false, CTR(A) = -1; and when evidence A is invalid, CTR(A) = 0. Therefore, when CTR(A) > 0, it indicates the degree to which evidence A is true; when CTR(A) < 0, it indicates the degree to which evidence A is false. The initial uncertainty measure CTR value of the evidence needs to be subjectively provided based on inspection records and expert experience. The reasoning calculation formula based on the uncertainty measure of rule A→B and the uncertainty measure of the evidence is as follows:

[0090] CTR(B)=CTR(B,A)×max{0,CTR(A)}

[0091] CTR(~A) = CTR(A)

[0092] CTR(A1∩A2)=min{CTR(A1), CTR(A2)}

[0093] CTR(A1∪A2)=max{CTR(A1),CTR(A2)}

[0094] In this embodiment, a semantic network for fault cases of power distribution IoT converged terminals can be constructed using the UMLS (Unified Medical Language System) semantic type table. In practical applications, typical fault defect inspection text record instances of power distribution IoT converged terminals are loaded into the semantic network to diagnose faults in the power distribution IoT converged terminals (i.e., the power distribution equipment under test). The diagnostic process can be divided into three stages: the first step checks whether the power distribution IoT converged terminal exhibits software fault characteristics; the second step checks whether the semantic network exhibits communication module fault characteristics of the power distribution IoT converged terminal; and the third step checks whether the semantic network exhibits hardware system fault characteristics of the power distribution IoT converged terminal. All uncertainties are marked on the arcs of the semantic network, as shown in [reference needed]. Figure 3 Assuming the software fault characteristics of the distribution IoT converged terminal are listed as evidence set A1, the software fault credibility CTR(B1) can be obtained by weighted summation of the correlation and weights between the software fault types and each software fault characteristic; the communication module fault characteristics of the distribution IoT converged terminal are listed as evidence set A2, and the hardware system fault characteristics of the distribution IoT converged terminal are listed as evidence set A3. The correlation and weights of the fault characteristics in A2 and A3 can be weighted summation to obtain the credibility CTR(B2) of the communication module and hardware system faults. By comparing the values ​​of CTR(B1) and CTR(B2), the target fault type of the distribution IoT converged terminal can be determined.

[0095] For example, the confidence levels CTR(A1), CTR(A2), and CTR(A3) of A1, A2, and A3 are known manually calculated statistics. The confidence level CTR(B1) for software fault types and the confidence level CTR(B2) for communication hardware fault types can be obtained using rules R1, R2, and R3. Specific rules and manually calculated confidence levels can be as follows:

[0096] R1: A1→B1, CTR(B1, A1)=0.4

[0097] R2: A2→B1, CTR(B1, A2)=0.6

[0098] R3: B1∩A3→B2, CTR(B2, B1∩A3)=0.9

[0099] Wherein, CTR(B1, A1) is the joint probability distribution of software failure B1 caused by software failure feature A1, CTR(B1, A2) is the joint probability distribution of software failure B1 caused by communication module failure feature A2, and CTR(B2, B1∩A3) represents the joint probability distribution of software failure B1 after it occurs, and having software failure feature A1, with the cause being a failure of the communication module and the hardware system.

[0100] Based on rule R1 and the semantic network, the initial credibility and the credibility to be used in the semantic network can be determined. For example, the initial credibility is CTR(A1) = 0.5×0.3 + 0.6×0.3 + 0.3×0.1 + 0.3×0.1 + 0.3×0.1 + 0.4×0.1 = 0.79; the credibility to be used is CTR(A1→B1) = 0.4×0.79 = 0.32.

[0101] Based on rule R2 and the semantic network, the initial credibility and the credibility to be used in the semantic network can be determined. For example: CTR(A2) = 0.5 × 0.5 + 0.6 × 0.5 = 0.55. The credibility to be used, CTR(A2→B1) = 0.6 × 0.55 = 0.33.

[0102] CTR(B1|A1)=CTR(B1)+CTR(B,A)×(1-CTR(B1))=0+0.32×(1-0)=0.32. Initially, there is no evidence to prove the software fault characteristic B1, i.e., CTR(B1)=0. Further, let CTR(B1|A1)=CTR(B1).

[0103] CTR(B1|A1∪A2)=CTR(B1)+CTR(A2→B1)×(1-CTR(B1))=0.32+0.33×

[0104] (1-0.32)=0.54. Let CTR(B1|A1∪A2)=CTR(B1)=0.54, that is, the fault confidence of the software fault type is 0.54.

[0105] Furthermore, based on rule R3 and the semantic network, the initial credibility and the credibility to be processed of A3 in the semantic network can be determined. For example: the initial credibility CTR(A3) = 0.9 × 0.7 + 0.6 × 0.3 = 0.81; the credibility to be processed CTR(B1∩A3) = min{CTR(B1), CTR(A3)} = min{0.54, 0.81} = 0.54.

[0106] Credibility to be applied CTR(B1∩A3→B2)=0.9×0.54=0.49.

[0107] Initial fault credibility CTR(B2)=0, CTR(B2|B1∩A3)=CTR(B2)+CTR(B1∩A3→B2)×(1-CTR(B2))=0+0.49*(1-0)=0.49. Let CTR(B2|B1∩A3)=CTR(B2), that is, the fault credibility of the communication module and hardware system fault is 0.49. In view of CTR(B2)<CTR(B1), it can be inferred based on the current fault inspection record of the power distribution Internet of Things fusion terminal that the credibility of terminal software fault is higher, and the software fault type can be taken as the target fault type.

[0108] The technical solution provided by the present invention performs fault diagnosis of power distribution Internet of Things fusion terminals based on a semantic network, divides and adds relevant probabilities according to semantic information, realizes quantification of the occurrence probability of various faults, at the same time constructs a semantic network of tree-shaped fault cases of power distribution Internet of Things fusion terminals, performs uncertainty measurement on evidence and rules, infers the credibility of various faults of the terminal, and improves the accuracy and efficiency of fault diagnosis.

[0109] Embodiment 4

[0110] Figure 5 is a structural schematic diagram of an apparatus for determining device fault types provided according to the fourth embodiment of the present invention. As Figure 5 shown, the apparatus includes: a fault feature determining module 310, a fault type determining module 320, an associated fault feature set determining module 330 and a target fault type determining module 340.

[0111] Wherein, the fault feature determining module 310 is configured to determine at least one fault feature corresponding to the power distribution device to be tested; the fault type determining module 320 is configured to determine a fault type associated with the fault feature based on the fault feature and a pre-constructed semantic network, wherein the semantic network includes nodes and edges, the edges represent the association relationship between nodes, and the nodes represent to-be-matched fault features and to-be-matched fault types; the associated fault feature set determining module 330 is configured to determine an associated fault feature set corresponding to each of the fault types when the number of fault types associated with the fault feature is two or more; the target fault type determining module 340 is configured to determine a target fault type of the power distribution device to be tested based on a plurality of the associated fault feature sets.

[0112] The technical solution of this embodiment determines at least one fault feature corresponding to the power distribution equipment under test; based on the fault feature and a pre-constructed semantic network, it determines the fault type associated with the fault feature; when there are two or more fault types associated with the fault feature, it determines the associated fault feature set corresponding to each fault type; and based on multiple associated fault feature sets, it determines the target fault type of the power distribution equipment under test. This solves the problems of high cost, poor accuracy, and low efficiency in the prior art, which relies on manual diagnosis of equipment fault types based on equipment fault records. It achieves fault diagnosis of the power distribution equipment under test through a semantic network that quantifies the probability of various fault occurrences, and determines the target fault type of the power distribution equipment under test by measuring the uncertainty of the fault type through the associated fault feature set corresponding to each fault type. This improves the speed of fault diagnosis, reduces the cost of determining the fault type, and improves the accuracy and efficiency of fault diagnosis, thereby enhancing the safety and stability of power grid operation.

[0113] Optionally, based on the above-mentioned device, the target fault type determination module 340 includes a fault feature set determination unit, a fault confidence determination unit, and a target fault type determination unit.

[0114] The fault feature set determination unit is used to determine at least one fault feature set corresponding to each fault type based on multiple associated fault feature sets for each fault type.

[0115] The fault confidence determination unit is used to determine the fault confidence of the fault type based on the correlation between the fault type and the fault features in the set of fault features to be used;

[0116] The target fault type determination unit is used to determine the target fault type of the power distribution equipment under test based on each fault type and the fault confidence level corresponding to the fault type.

[0117] Based on the above-mentioned device, optionally, the fault feature set determination unit to be used includes an intersection determination subunit and a fault feature set determination subunit to be used.

[0118] An intersection determination subunit is used to determine the intersection of every two associated fault feature sets corresponding to the fault type;

[0119] The fault feature set determination subunit is used to determine at least one fault feature set corresponding to the fault type based on the intersection.

[0120] Based on the above-mentioned device, optionally, the fault feature set determination subunit includes a fault feature set determination subunit and a fault feature set determination small unit.

[0121] The fault feature set determination unit is used to determine the fault feature set corresponding to one fault type as the fault feature set corresponding to the other fault type when the intersection of the associated fault feature sets corresponding to the two fault types is not empty.

[0122] The fault feature set determination unit is used to determine at least one fault feature set corresponding to the fault type based on the associated fault feature set and the distinguishing fault feature set corresponding to the fault type, wherein the processing priority of the associated fault feature set is higher than that of the distinguishing fault feature set.

[0123] Based on the above device, optionally, the fault type investigation priority is the first priority, and the fault credibility determination unit includes a joint credibility determination subunit, an initial credibility determination subunit, a credibility determination subunit to be used, and a fault credibility determination first subunit.

[0124] A joint credibility determination subunit is used to obtain the joint credibility corresponding to the fault type and at least one fault feature set to be used, respectively.

[0125] An initial confidence determination subunit is used to determine the initial confidence corresponding to the at least one set of fault features to be used based on the correlation between the fault type and the fault features in the set of fault features to be used, and the weight corresponding to the correlation.

[0126] The reliability determination subunit is used to determine the reliability of the fault feature set to be used based on the joint reliability and initial reliability corresponding to the same fault feature set to be used;

[0127] The first subunit for determining fault credibility is used to determine the fault credibility corresponding to the fault type based on the credibility of the at least one set of fault features to be used.

[0128] Based on the above-mentioned device, optionally, the set of fault features to be used includes an associated fault feature set and a distinguishable fault feature set, and the first sub-unit for determining fault confidence includes a first intermediate value determination sub-unit, a second intermediate value determination sub-unit, and a fault confidence determination sub-unit.

[0129] The first intermediate value determination unit is used to determine the first intermediate value based on the reliability of the associated fault feature set and the preset parameters.

[0130] The second intermediate value determination unit is used to determine the second intermediate value based on the first intermediate value and the confidence level to be used corresponding to the distinguishing fault feature set;

[0131] The fault confidence determination subunit is used to determine the fault confidence corresponding to the fault type based on the confidence to be used corresponding to the associated fault feature set and the second intermediate value.

[0132] Based on the above device, optionally, the fault type investigation priority is the second priority, and the fault credibility determination unit includes a collaborative credibility determination subunit, an initial credibility determination subunit, a pending credibility determination subunit, and a fault credibility determination second subunit.

[0133] A collaborative credibility determination subunit is used to obtain the collaborative credibility of the fault type under the fault feature set to be used.

[0134] The initial confidence determination subunit is used to determine the initial confidence corresponding to each of the fault feature sets to be used based on the correlation between the fault type and the fault features in the fault feature set to be used and the weight corresponding to the correlation.

[0135] The pending confidence determination subunit is used to determine the pending confidence based on the failure confidence of the first priority failure type and the initial confidence if the set of failure features to be used includes the set of associated failure features of the first priority failure type.

[0136] The second subunit for determining fault credibility is used to determine the credibility to be applied based on the credibility to be processed and the collaborative credibility, so as to determine the fault credibility of the fault type based on the credibility to be applied.

[0137] Optionally, based on the above-mentioned device, the device may further include: a semantic network construction module, which includes a historical fault text information determination unit and a semantic network determination unit.

[0138] A historical fault text information determination unit is used to obtain historical fault text information; wherein, the historical fault text information includes multiple fault attributes and reference fault types corresponding to the fault attributes, the fault attributes correspond to the fault features to be matched, and the reference fault types correspond to the fault types to be matched;

[0139] A semantic network determination unit is used to construct the semantic network based on the association relationship between the fault attribute and its associated associated objects, as well as the relevance corresponding to the association relationship.

[0140] The associated objects include the fault attributes and the reference fault types, and the association relationships include at least one of the following: deterministic relationships, physical relationships, spatial relationships, functional relationships, temporal relationships, and conceptual relationships.

[0141] The device for determining the type of equipment failure provided in this embodiment of the invention can execute the method for determining the type of equipment failure provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0142] Example 5

[0143] Figure 6 This is a schematic diagram of the structure of an electronic device implementing the method for determining device fault types according to embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0144] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0145] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0146] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as methods for determining the type of device fault.

[0147] In some embodiments, the method for determining the type of device failure may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining the type of device failure described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining the type of device failure by any other suitable means (e.g., by means of firmware).

[0148] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0149] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0150] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0151] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0152] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0153] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0154] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0155] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining equipment failure type, characterized in that, include: Identify at least one fault characteristic corresponding to the power distribution equipment under test; Based on the fault features and a pre-constructed semantic network, the fault type associated with the fault features is determined, wherein the semantic network includes nodes and edges, the edges represent the association between nodes, and the nodes represent the fault features and fault types to be matched. When the number of fault types associated with the fault feature is two or more, determine the associated fault feature set corresponding to each fault type; For each of the fault types, at least one fault feature set to be used corresponding to the fault type is determined based on multiple associated fault feature sets; The reliability of the fault type is determined based on the correlation between the fault type and the fault features in the set of fault features to be used. Based on each of the fault types and the corresponding fault confidence level, the target fault type of the power distribution equipment under test is determined. The fault type is prioritized for investigation as the first priority. Determining the fault reliability of the fault type based on the correlation between the fault type and the fault features in the set of fault features to be used includes: Obtain the joint confidence level of the fault type and at least one fault feature set to be used; Based on the correlation between the fault type and the fault features in the set of fault features to be used, and the weight corresponding to the correlation, an initial confidence level corresponding to the at least one set of fault features to be used is determined. Based on the joint confidence and initial confidence corresponding to the same set of fault features to be used, the confidence of the set of fault features to be used is determined. Based on the available reliability corresponding to the at least one available fault feature set, the fault reliability corresponding to the fault type is determined.

2. The method according to claim 1, characterized in that, The step of determining at least one fault feature set to be used corresponding to the fault type based on multiple associated fault feature sets includes: Determine the intersection of every two associated fault feature sets corresponding to the fault type; Based on the intersection, at least one set of fault features to be used corresponding to the fault type is determined.

3. The method according to claim 2, characterized in that, The step of determining at least one set of fault features to be used corresponding to the fault type based on the intersection includes: If the intersection of the associated fault feature sets corresponding to the two fault types is not empty, the associated fault feature set corresponding to one fault type shall be used as the distinguishing fault feature set corresponding to the other fault type. Based on the associated fault feature set and the distinguishing fault feature set corresponding to the fault type, at least one fault feature set to be used corresponding to the fault type is determined, wherein the processing priority of the associated fault feature set is higher than that of the distinguishing fault feature set.

4. The method according to claim 1, characterized in that, The set of fault features to be used includes an associated fault feature set and a distinguishable fault feature set. Based on the usability confidence corresponding to the at least one set of fault features to be used, the fault confidence corresponding to the fault type is determined, including: Based on the reliability of the associated fault feature set and the preset parameters, a first intermediate value is determined. Based on the first intermediate value and the confidence level to be used corresponding to the distinguishing fault feature set, a second intermediate value is determined; Based on the confidence level to be used corresponding to the associated fault feature set and the second intermediate value, the confidence level of the fault corresponding to the fault type is determined.

5. The method according to claim 1, characterized in that, The fault type is prioritized for investigation as the second priority. Determining the fault reliability of the fault type based on the correlation between the fault type and the fault features in the set of fault features to be used includes: Obtain the collaborative reliability of the fault type under the fault feature set to be used; Based on the correlation between the fault type and the fault features in the set of fault features to be used, and the weight corresponding to the correlation, the initial confidence level corresponding to each set of fault features to be used is determined. If the set of fault features to be used includes the set of associated fault features of the first priority fault type, then the confidence level to be processed is determined based on the confidence level of the first priority fault type and the initial confidence level. Based on the trustworthiness to be processed and the collaborative trustworthiness, the trustworthiness to be applied is determined, and based on the trustworthiness to be applied, the fault trustworthiness of the fault type is determined.

6. The method according to claim 1, characterized in that, Also includes: Construct a semantic network; where, The construction of the semantic network includes: Obtain historical fault text information; wherein, the historical fault text information includes multiple fault attributes and reference fault types corresponding to the fault attributes, the fault attributes correspond to the fault features to be matched, and the reference fault types correspond to the fault types to be matched; The semantic network is constructed based on the relationship between the fault attributes and their associated objects, as well as the relevance of the relationship. The associated objects include the fault attributes and the reference fault types, and the association relationships include at least one of the following: deterministic relationships, physical relationships, spatial relationships, functional relationships, temporal relationships, and conceptual relationships.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining the type of equipment failure as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining the type of device fault as described in any one of claims 1-6.

Images