Method and system for constructing operation and maintenance knowledge base of power distribution equipment

Abstract

The invention discloses a power distribution equipment operation and maintenance knowledge base construction method and system, and relates to the field of knowledge base construction, and the method comprises the steps: constructing a triple based on the operation and maintenance knowledge of each power distribution equipment; for any power distribution equipment, determining the fault rate of the power distribution equipment based on the fault text of the power distribution equipment and the solution corresponding to each fault; respectively calculating the similarity degree between every two power distribution devices; dividing all the power distribution equipment into a plurality of equipment groups based on the similarity degree between every two power distribution equipment and the fault rate of each power distribution equipment; and constructing a power distribution equipment operation and maintenance knowledge base based on the triple and the equipment groups corresponding to the power distribution equipment. The invention aims to solve the problem that an independent knowledge base cannot meet the multi-equipment fault comprehensive diagnosis requirement when cross-equipment or composite faults are processed based on a traditional power distribution equipment knowledge management mode.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of knowledge base construction, in particular to a power distribution equipment operation and maintenance knowledge base construction method and system. BACKGROUND

[0002] At present, the operation and maintenance knowledge of power distribution equipment is mainly stored and managed independently in units of equipment models. For example, for different types of equipment such as transformers, circuit breakers, and power distribution cabinets, the operation and maintenance knowledge base usually records their typical fault phenomena, fault causes, and corresponding maintenance measures, and forms structured documents or database entries through manual arrangement.

[0003] However, with the diversification of power distribution equipment types and the complexity of operating environment, although the traditional knowledge management mode can meet the operation and maintenance needs of single equipment, when dealing with cross-equipment or composite faults, it needs to rely on manual comparison of multiple independent knowledge bases by operation and maintenance personnel, and lacks systematic knowledge association mechanism. On the one hand, a lot of knowledge and principles are related, but due to the independent construction of knowledge by equipment in the traditional mode, there is a lot of repetition and redundancy. On the other hand, a fault phenomenon in a power distribution system often involves multiple equipment, and the independent knowledge base divided by equipment cannot meet the comprehensive diagnosis needs. SUMMARY

[0004] The main purpose of the present application is to provide a power distribution equipment operation and maintenance knowledge base construction method and system, which aims to solve the technical problems that the traditional power distribution equipment knowledge management mode relies on manual comparison of multiple independent knowledge bases by operation and maintenance personnel when dealing with cross-equipment or composite faults, lacks systematic knowledge association mechanism, and there is repetition and redundancy due to independent construction by equipment, and independent knowledge base cannot meet the needs of comprehensive diagnosis of multi-equipment faults.

[0005] To achieve the above purpose, the present application provides a power distribution equipment operation and maintenance knowledge base construction method, comprising: constructing triples based on the operation and maintenance knowledge of each power distribution equipment, the triples comprising power distribution equipment name, fault text, and corresponding solutions for each fault; for any power distribution equipment, determining the fault rate of the power distribution equipment based on the fault text of the power distribution equipment and the corresponding solutions for each fault; calculating the similarity between each pair of power distribution equipment based on the fault text of each power distribution equipment and the corresponding solutions for each fault, the similarity representing the similarity of fault text and the similarity of solutions between each pair of power distribution equipment; dividing all power distribution equipment into several equipment groups based on the similarity between each pair of power distribution equipment and the fault rate of each power distribution equipment, each equipment group comprising at least one power distribution equipment; constructing a power distribution equipment operation and maintenance knowledge base based on the triples and the corresponding equipment groups of each power distribution equipment.

[0006] Optionally, the determining, for any power distribution device, the failure rate of the power distribution device based on the failure text of the power distribution device and the solutions corresponding to each failure, comprises: determining, for any power distribution device, a plurality of failure types of the power distribution device based on the failure text of the power distribution device, and obtaining the occurrence frequency of each failure type within a preset period; determining the matching weight of each failure type based on the solutions corresponding to each failure of the power distribution device; and determining the failure rate of the power distribution device based on the occurrence frequency of each failure type within a preset period and the matching weight of each failure type.

[0007] Optionally, the calculating, based on the failure text of each power distribution device and the solutions corresponding to each failure, the similarity degree between each pair of power distribution devices, comprises: for a target power distribution device and a concerned power distribution device in the power distribution devices, vectorizing the failure text of the target power distribution device and the solutions corresponding to each failure to obtain a plurality of target failure vectors and a plurality of target solution vectors, and vectorizing the failure text of the concerned power distribution device and the solutions corresponding to each failure to obtain a plurality of concerned failure vectors and a plurality of concerned solution vectors; and determining the similarity degree between the target power distribution device and the concerned power distribution device based on the plurality of target failure vectors, the plurality of target solution vectors, the plurality of concerned failure vectors and the plurality of concerned solution vectors.

[0008] Optionally, the determining, based on the plurality of target failure vectors, the plurality of target solution vectors, the plurality of concerned failure vectors and the plurality of concerned solution vectors, the similarity degree between the target power distribution device and the concerned power distribution device, comprises: calculating the first similarity between each target failure vector and each concerned failure vector, adding all the first similarities to obtain the failure similarity between the target power distribution device and the concerned power distribution device; for any target failure vector and any concerned failure vector with a first similarity greater than a preset threshold, calculating the second similarity between the target solution vector corresponding to the target failure vector and the concerned solution vector corresponding to the concerned failure vector, adding all the second similarities to obtain the solution similarity between the target power distribution device and the concerned power distribution device; and determining the similarity degree between the target power distribution device and the concerned power distribution device based on the failure similarity and the solution similarity.

[0009] Optionally, the grouping all the power distribution devices into a plurality of device groups based on the similarity degree between each pair of power distribution devices and the failure rate of each power distribution device, comprises: grouping any two power distribution devices into a device pair, constructing a similarity degree matrix based on all the device pairs and the similarity degrees corresponding to each device pair in descending order of the similarity degrees; and grouping all the power distribution devices into a plurality of device groups based on the similarity degree matrix.

[0010] Optionally, the constructing the power distribution equipment operation and maintenance knowledge base based on the triplets and the device groups corresponding to the power distribution equipment comprises: establishing a node tree based on the device groups corresponding to the power distribution equipment, the node tree comprising a plurality of nodes, a connection relationship between the nodes, and a plurality of branches of each node, wherein a node corresponds to a power distribution equipment, the connection relationship is used to represent the similarity degree, and the plurality of branches comprise fault texts of each power distribution equipment in the triplets and solutions corresponding to each fault; and constructing a power distribution equipment operation and maintenance database based on the node tree.

[0011] Optionally, the determining the matching weight of each fault type based on the solutions corresponding to each fault in the power distribution equipment comprises: dividing all fault types into three types based on the solutions corresponding to each fault in the power distribution equipment, the three types comprising a first type, a second type, and a third type; and determining the matching weight of each fault type based on the matching weight corresponding to each type.

[0012] In addition, to achieve the above object, the present application further provides a power distribution equipment operation and maintenance knowledge base construction system, comprising: a triplet construction module, configured to construct triplets based on operation and maintenance knowledge of each power distribution equipment, the triplets comprising a power distribution equipment name, a fault text, and a solution corresponding to each fault; a single power distribution equipment fault rate determination module, configured to determine a fault rate of any power distribution equipment based on the fault text and the solution corresponding to each fault of the power distribution equipment; a similarity degree determination module, configured to calculate a similarity degree between each two power distribution equipment based on the fault text and the solution corresponding to each fault of each power distribution equipment, the similarity degree being used to represent similarity of the fault text and similarity of the solution between each two power distribution equipment; a power distribution equipment grouping module, configured to divide all power distribution equipment into a plurality of device groups based on the similarity degree between each two power distribution equipment and the fault rate of each power distribution equipment, each device group comprising at least one power distribution equipment; and a knowledge base construction module, configured to construct a power distribution equipment operation and maintenance knowledge base based on the triplets and the device groups corresponding to the power distribution equipment.

[0013] The present application further provides a power distribution equipment operation and maintenance knowledge base construction device, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method in any possible implementation manner described above.

[0014] The present application further provides a computer readable storage medium storing a computer program, and the computer program is executed by a processor to implement the method in any possible implementation manner described above.

[0015] The application provides a power distribution equipment operation and maintenance knowledge base construction method and system. First, a triple consisting of a power distribution equipment name, a fault text and a solution is constructed, so that structured processing of operation and maintenance knowledge is realized. Then, the similarity between power distribution equipment is calculated by using the triple information, and the equipment is grouped according to the similarity, so that each group of equipment has high consistency in fault characteristics and solutions. On this basis, a node tree is further constructed to intuitively display the similarity between equipment and fault solutions, so that the operation personnel can quickly locate and diagnose when facing cross-equipment or composite faults, the problems of knowledge redundancy and insufficient comprehensive diagnosis capability in the traditional knowledge management mode are solved, and the operation efficiency is significantly improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 FIG. 1 is a flowchart of a power distribution equipment operation and maintenance knowledge base construction method according to an embodiment of the application; Figure 2 FIG. 2 is a flowchart of a power distribution equipment operation and maintenance knowledge base construction method according to another embodiment of the application; Figure 3 FIG. 3 is a flowchart of a power distribution equipment operation and maintenance knowledge base construction method according to another embodiment of the application; Figure 4 FIG. 4 is a flowchart of a power distribution equipment operation and maintenance knowledge base construction method according to another embodiment of the application; Figure 5 FIG. 5 is a structural block diagram of a power distribution equipment operation and maintenance knowledge base construction system according to an embodiment of the application; Figure 6 FIG. 6 is a structural schematic diagram of a power distribution equipment operation and maintenance knowledge base construction device according to an embodiment of the application.

[0017] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the application and not to limit the application.

[0019] At present, the operation and maintenance knowledge of power distribution equipment is mainly stored and managed independently in units of equipment models. For example, for different types of equipment such as transformers, circuit breakers and power distribution cabinets, the operation knowledge base usually records the typical fault phenomena, fault causes and corresponding maintenance measures, and forms structured documents or database entries through manual arrangement.

[0020] However, with the diversification of power distribution equipment types and the complexity of operating environments, the traditional knowledge management mode can meet the operation and maintenance needs of single equipment, but when dealing with cross-equipment or composite faults, it needs to rely on manual comparison of multiple independent knowledge bases by operation and maintenance personnel, and lacks a systematic knowledge association mechanism. On the one hand, a lot of knowledge and principles are interconnected, but due to the independent construction of knowledge by equipment in the traditional mode, there is a lot of repetition and redundancy. For example, the phenomenon of "poor contact causing heating" and the basic treatment process (inspection, tightening, and applying conductive paste) can be applied to many scenarios such as circuit breaker joints, isolator contacts, and bus connection points. However, the traditional way records the operation and maintenance content for each device separately, which not only increases the workload of knowledge base construction, but also leads to knowledge storage redundancy, and requires repeated operations during subsequent maintenance and updates. On the other hand, a fault phenomenon in a power distribution system often involves multiple devices, and the traditional independent knowledge base divided by equipment cannot meet the comprehensive diagnosis needs. For example, the operation and maintenance personnel input "a line trip" to the knowledge base, but the fault reason may be in the circuit breaker itself, or the transformer protected by it, or the cable on the line, and the operation and maintenance personnel need to consult multiple independent knowledge bases of different devices under the traditional knowledge management mode, which makes it difficult to quickly integrate information for comprehensive judgment, not only prolongs the fault diagnosis time, but also may miss the key reason due to information fragmentation, resulting in low fault handling efficiency.

[0021] To solve the above problems, the present application provides a power distribution equipment operation and maintenance knowledge base construction method and system. The present application scheme will be introduced in detail below.

[0022] Figure 1 The power distribution equipment operation and maintenance knowledge base construction method provided by the embodiments of the present application has a flowchart, which can be executed by a knowledge base construction device. The knowledge base construction device can be a power distribution equipment operation and maintenance knowledge base construction device. Referring to Figure 1 The power distribution equipment operation and maintenance knowledge base construction method can include the following steps: S11, based on the operation and maintenance knowledge of each power distribution equipment, a triple is constructed, which includes the name of the power distribution equipment, the fault text, and the corresponding solution of each fault.

[0023] The fault text refers to a text content accurately describing the fault related information of the power distribution equipment, including the equipment state at the time of the fault, the specific abnormal phenomenon, the key parameters (such as temperature, voltage, running time, etc.), the fault scene (such as after closing, during load peak, etc.), and the fault text can be used to clearly define "what problem the equipment has and under what circumstances the problem occurs"; the solution corresponding to each fault refers to the operable and standardized processing procedure formulated for the specific problem described in the fault text, including safety preparation before fault handling (such as power-off measures), fault troubleshooting during fault handling, problem repair during fault handling, selection of tools and materials, and effect verification after fault repair. It can be understood that the solution can be used to ensure that the maintenance personnel efficiently handle the fault according to the process.

[0024] For example, the name of the power distribution equipment can be "10kV vacuum circuit breaker", the fault text can be "10kV vacuum circuit breaker is closed with load running for about 25 minutes, the infrared temperature measurement at the joint shows that the temperature reaches 82℃ (ambient temperature 28℃), which exceeds the normal running threshold of 65℃ specified in GB50150-2016, and near the joint, a slight "sizzle" discharge sound can be heard, and the load current is stable at 400A (rated current 630A)", and the solution corresponding to the fault can be "safety preparation: first disconnect the upper power switch of the circuit breaker, hang a "prohibit closing, human work" warning sign, and after confirming that there is no voltage on both sides of the circuit breaker with a voltage detector, install a grounding wire; fault diagnosis: remove the insulation sheath at the joint, check the joint bolt fastening with a wrench, find that the A-phase joint bolt torque is insufficient (standard torque 35N m, actual measurement 20N m), and there is a small amount of oxidation layer on the joint contact surface; problem repair: polish the oxidation layer on the joint contact surface with fine sandpaper to expose the metal gloss, apply conductive paste (model: electric composite grease 89D), and re-tighten the bolt according to the standard torque 35N m; effect verification: restore the insulation sheath, remove the grounding wire and warning sign, close the upper power switch, and after the circuit breaker runs with load for 30 minutes, the infrared temperature measurement shows that the joint temperature drops to 42℃ (ambient temperature 28℃), there is no discharge sound, and the fault is confirmed to be eliminated".

[0025] In the specific implementation process, first, collect the operation and maintenance documents of all power distribution equipment in the power distribution system, which can include equipment fault handling reports, manufacturer technical manuals, operation and maintenance system logs, and maintenance archives, etc. Then, according to the type of power distribution equipment (such as transformer, circuit breaker, disconnector, etc.), the operation and maintenance documents are classified to ensure centralized management of the related documents of various types of power distribution equipment.

[0026] Further, for paper documents in the operation and maintenance document, the paper documents are first converted into electronic documents through scanning, and then the text content is recognized by using an OCR (Optical Character Recognition) technology, and errors are corrected by combining manual checking; for electronic documents in the operation and maintenance document, the NLP (Natural Language Processing) technology or the keyword search function is used to extract the “power distribution equipment name”, “fault text” and “corresponding solution to the fault” respectively. It should be noted that the “power distribution equipment name” needs to specify the equipment model, specification and system to which it belongs, the “fault text” needs to include the fault phenomenon, occurrence scene and key parameters (such as temperature, voltage, running time), and the “corresponding solution to the fault” needs to include safety preparation, fault troubleshooting, problem repair, tools and materials and effect verification.

[0027] Further, the three types of information (the “power distribution equipment name”, the “fault text” and the “corresponding solution to the fault”) extracted are standardized, specifically, repeated or invalid document information (for example, multiple repeated records of the same fault) can be deleted, and the terminology is uniformly expressed (for example, “joint overheating” and “terminal temperature too high” are unified as “joint overheating”), and the step logic of the solution is standardized (arranged in the order of “safety preparation, fault troubleshooting, problem repair, effect verification”), so as to ensure that the information format of the same type of power distribution equipment is consistent and the semantics is unified, and to avoid deviation of the triple association caused by different expressions.

[0028] Finally, the “power distribution equipment name”, the “fault text” and the “corresponding solution to the fault” after cleaning are matched one by one to form complete triples, and the constructed triples are entered into the database to establish the association relationship between the power distribution equipment and the fault and the solution.

[0029] S12, for any power distribution equipment, determining the fault rate of the power distribution equipment based on the fault text of the power distribution equipment and the corresponding solutions to the faults.

[0030] The fault rate is used to represent the fault scale of the power distribution equipment, and specifically can represent the frequency of the fault occurrence of the power distribution equipment and whether the corresponding solution to the fault is sufficient. For example, when a certain power distribution equipment has many types of faults and a high total frequency of fault occurrence in a certain period (for example, 1 year or 1 operation and maintenance period), and the proportion of faults without corresponding solutions or with imperfect solutions (for example, missing steps or unclear tools) is high, the fault rate of the power distribution equipment is high; on the contrary, if the power distribution equipment has few types of faults and a low frequency of fault occurrence, and all faults have complete and operable solutions, the fault rate of the power distribution equipment is low.

[0031] In an embodiment, with reference toFigure 2 , Figure 2 The flowchart two of the power distribution equipment operation and maintenance knowledge base construction method provided by the embodiment of the application is as follows: in step S12, for any power distribution equipment, the fault rate of the power distribution equipment is determined based on the fault text of the power distribution equipment and the solutions corresponding to each fault, and specifically can include the following steps: S121, determining a plurality of fault types of the power distribution equipment based on the fault text of the power distribution equipment, and obtaining the occurrence frequency of each fault type in a preset period; S122, determining the matching weight of each fault type based on the solution corresponding to each fault in the power distribution equipment; S123, determining the fault rate of the power distribution equipment based on the occurrence frequency of each fault type in a preset period and the matching weight of each fault type.

[0032] In the embodiment, a preset period is set as an operation and maintenance period, and in other embodiments, the preset period can also be set as a specific time, for example, 1 year, and the setting of the preset period in the embodiment is not limited specifically.

[0033] In the specific implementation process, any power distribution equipment is selected from all power distribution equipment as a target power distribution equipment, and the embodiment is described by taking the target power distribution equipment as an example. All fault texts in the target power distribution equipment are classified according to fault types, for example, “low oil level”, “excessive iron core grounding current”, “high voltage side sleeve leakage” and the like of the transformer are different fault types, and the occurrence frequency of each fault type in an operation and maintenance period is obtained (for example, “low oil level” occurs 3 times in an operation and maintenance period, and “excessive iron core grounding current” occurs 2 times in an operation and maintenance period).

[0034] It should be noted that the occurrence frequency of each fault type in an operation and maintenance period can determine the total fault frequency (i.e., the sum of the frequencies of all fault types) of the target power distribution equipment and the total number of fault types of the target power distribution equipment; and the total fault frequency and the total number of fault types can reflect the frequency of the target power distribution equipment.

[0035] Further, the solutions corresponding to each fault type in the triple are checked in sequence, all fault types are divided into three types based on the solution, the three types include a first type, a second type and a third type, wherein the matching weight of the first type is set as a, the matching weight of the second type is set as b, and the matching weight of the third type is set as c, and in the embodiment, a is set as 1.8, b is set as 1.3, and c is set as 1.

[0036] Specifically, any fault type is selected from all fault types as a target fault type, if the target fault type has no solution in the triple (for example, the fault type is new casing insulation aging, and no processing step is recorded in the triple), the target fault type is marked as the first type; if the target fault type has a missing solution in the triple (for example, only the solution of "checking casing" is recorded in the triple, and the contents such as safety preparation, selection of tool materials and effect verification are not included), the target fault type is marked as the second type; if the target fault type has a complete solution in the triple, the target fault type is marked as the third type. It can be understood that the first type can represent a fault without a solution, the second type can represent a fault with an imperfect solution, and the third type can represent a fault with a perfect solution. The matching weight of each fault type can reflect whether the corresponding solution of each fault is sufficient.

[0037] Further, the occurrence frequency of the target fault type in a preset period is multiplied by the matching weight of the target fault type to obtain the fault degree of the target fault type. The fault degrees of all fault types in the target power distribution equipment are added to obtain the fault rate of the target power distribution equipment.

[0038] In step S13, the similarity degrees between each two power distribution equipments are calculated based on the fault texts of the power distribution equipments and the solutions corresponding to the faults, and the similarity degrees are used to represent the similarities of the fault texts and the similarities of the solutions between each two power distribution equipments.

[0039] In an embodiment, with reference to Figure 3 , Figure 3 FIG. 3 is a flowchart of a method for constructing a power distribution equipment operation and maintenance knowledge base according to an embodiment of the present application. In step S1, a fault text of each power distribution equipment is obtained. In step S2, a solution corresponding to each fault of each power distribution equipment is obtained. In step S3, a matching weight of each fault type is determined based on the fault texts of the power distribution equipments and the solutions corresponding to the faults. In step S4, a fault degree of each fault type is determined based on the matching weight of the fault type and the occurrence frequency of the fault type in a preset period. In step S5, a fault rate of each power distribution equipment is determined based on the fault degrees of all fault types in the power distribution equipment. In step S6, a similarity degree between each two power distribution equipments is calculated based on the fault texts of the power distribution equipments and the solutions corresponding to the faults. S131, for a target power distribution equipment and a concerned power distribution equipment in each power distribution equipment, the fault texts of the target power distribution equipment and the solutions corresponding to the faults are vectorized to obtain a plurality of target fault vectors and a plurality of target solution vectors, and the fault texts of the concerned power distribution equipment and the solutions corresponding to the faults are vectorized to obtain a plurality of concerned fault vectors and a plurality of concerned solution vectors. S132, the similarity degree between the target power distribution equipment and the concerned power distribution equipment is determined based on the plurality of target fault vectors, the plurality of target solution vectors, the plurality of concerned fault vectors and the plurality of concerned solution vectors.

[0040] In the method, any power distribution equipment is selected as the target power distribution equipment from all power distribution equipments, and any power distribution equipment other than the target power distribution equipment is selected as the concerned power distribution equipment from all power distribution equipments.

[0041] In the implementation process, for the target power distribution equipment and the concerned power distribution equipment in all power distribution equipments, the fault text of the target power distribution equipment and the corresponding solution are vectorized by using the word2vec model to obtain a plurality of target fault vectors and a plurality of target solution vectors. The fault text of the concerned power distribution equipment and the corresponding solution are vectorized by using the word2vec model to obtain a plurality of concerned fault vectors and a plurality of concerned solution vectors.

[0042] Further, the first similarity between each target fault vector and each concerned fault vector is calculated by using the cosine similarity, and the fault similarity between the target power distribution equipment and the concerned power distribution equipment is obtained by adding all the first similarities.

[0043] It should be noted that in actual application scenarios, the implementer can also divide the fault text and the corresponding solution into a plurality of description words according to the semantic meaning of the text. Taking any fault text as an example, the fault text can be first divided into a plurality of description words, and then each description word is vectorized, and finally a plurality of single vectors obtained by vectorization form the fault vector corresponding to the fault text. When calculating the first similarity, each single vector can be multiplied by a preset coefficient. The range of the preset coefficient is 0 to 1, and the preset coefficient of each single vector can be set by the implementer, for example, the description words included in a certain fault text are “joint overheating” and “of”, wherein the preset coefficient of the single vector corresponding to “joint overheating” is greater than the preset coefficient of the single vector corresponding to “of”. It can be understood that multiplying the single vector by the preset coefficient can effectively improve the accuracy of the fault similarity calculation.

[0044] Further, for any target fault vector and any concerned fault vector whose first similarity is greater than a preset threshold, the second similarity between the target solution vector corresponding to the target fault vector and the concerned solution vector corresponding to the concerned fault vector is calculated by using the cosine similarity, and the solution similarity between the target power distribution equipment and the concerned power distribution equipment is obtained by adding all the second similarities.

[0045] Further, the fault similarity and the solution similarity are weighted and summed to obtain the similarity degree between the target power distribution equipment and the concerned power distribution equipment.

[0046] It should be noted that in other embodiments, other similarity calculation methods can also be used to replace the cosine similarity in this embodiment. The calculation method of the similarity in this embodiment is not specifically limited.

[0047] S14, divide all power distribution devices into a plurality of device groups based on the similarity between each pair of power distribution devices and the failure rate of each power distribution device, and each device group includes at least one power distribution device.

[0048] If a device group includes a plurality of power distribution devices, the similarity between the plurality of power distribution devices is greater than a preset merging threshold.

[0049] In an embodiment, referring to Figure 4 , Figure 4 The fourth flowchart of the power distribution device operation and maintenance knowledge base construction method provided by the embodiment of the present application is shown in FIG. 4. In step S14, all power distribution devices are divided into a plurality of device groups based on the similarity between each pair of power distribution devices and the failure rate of each power distribution device. Specifically, the step can include: S141, form a device pair with any two power distribution devices, and based on the order of similarity from large to small, all device pairs and the corresponding similarity of each device pair are constructed to form a similarity matrix; S142, divide all power distribution devices into a plurality of device groups based on the similarity matrix.

[0050] In the specific implementation process, first, a device pair is formed with any two power distribution devices, and all power distribution devices are divided until all power distribution devices are divided. Then, based on the order of similarity from large to small, all device pairs and the corresponding similarity of each device pair are constructed to form a similarity matrix. It can be understood that the first row of the similarity matrix includes the maximum similarity value and the device pair with the maximum similarity. In the similarity matrix, the first column is the device pair, and the second column is the corresponding similarity of the device pair. The similarity in the similarity matrix decreases as the row number increases. The first row and the first column of the similarity matrix are the device pair with the maximum similarity, and the second column of the first row is the maximum similarity value.

[0051] Further, in the first row of the similarity matrix, the power distribution device with a larger failure rate in the device pair is selected as the starting center. According to the order of the similarity matrix from top to bottom, the power distribution devices with a similarity greater than the merging threshold are selected and merged with the starting center to form a group until the preset number is reached, and the first device group is obtained.

[0052] For example, the similarity can be sorted in the order from large to small. In the sequence, the top 30% of the similarity is selected as a sub-similarity sequence, and the first similarity after the sub-similarity sequence is set as the merging threshold. The preset number can be set to 10% of the total number of power distribution devices. Of course, in other embodiments, the merging threshold and the preset number can also be set by the implementer.

[0053] Further, referring to the construction process of the first device group, a new starting center is selected according to the similarity degree matrix from top to bottom, and then according to the failure rate from small to large, to obtain a second device group, and so on, until all power distribution devices are divided, that is, each power distribution device has a corresponding device group.

[0054] It should be noted that the similarity degree can be sorted in descending order, and the top 60% of the similarity degree in the sequence is taken as a second sub-similarity sequence, and the first similarity degree after the second sub-similarity sequence is set as the merging threshold corresponding to the second device group; the preset number can still be set as 10% of the total number of power distribution devices. It can be understood that as the number of device groups increases, the merging threshold gradually decreases, and the merging threshold corresponding to other device groups in this embodiment will not be described in detail. The number of power distribution devices in the last group of device groups can be less than the preset number, that is, the stop condition for the division of the device group in this embodiment is that all power distribution devices are divided.

[0055] S15, constructing a power distribution device operation and maintenance knowledge base based on the triplets and the device groups corresponding to each power distribution device.

[0056] In the specific implementation process, first, a node tree is established based on the device groups corresponding to each power distribution device, the node tree includes a plurality of nodes, connection relationships between the nodes, and a plurality of branches of each node, wherein a node corresponds to a power distribution device, the connection relationship can represent the similarity between the power distribution devices, and the plurality of branches of each node include the fault text of each power distribution device in the triplet and the solution corresponding to each fault.

[0057] Further, a power distribution device operation and maintenance database is constructed based on the node tree.

[0058] The power distribution device operation and maintenance database in this embodiment will be described below in conjunction with an example.

[0059] For example, the operation and maintenance personnel input "poor contact causes heating" to the power distribution device operation and maintenance database. The database first preprocesses the input query text "poor contact causes heating", that is, disassembles the text into "poor contact" and "heating" core keywords, and then calls the word2vec word vector model trained in the foregoing to convert each keyword into a semantic vector.

[0060] Then, the database traverses the branches of all nodes in the node tree, extracts the fault text vectors under each node branch one by one (for example, the fault text of node A is "close to load for 25 minutes, joint temperature is 82°C, accompanied by slight discharge sound", and the fault text of node B is "after opening, the contact temperature is 68°C, no discharge but the contact gap exceeds the standard"), and calculates the similarity of each semantic vector and each fault text vector by cosine similarity, and filters out the fault texts and corresponding nodes with similarity greater than the preset semantic matching threshold, and takes these fault texts as matching fault texts.

[0061] Secondly, the database locates the device nodes and device groups to which the matching fault texts belong, for example, the matching degrees of 2 fault texts of node A (vacuum circuit breaker), 1 fault text of node D (SF6 circuit breaker) and 1 fault text of node B (isolator) are all greater than the preset semantic matching threshold, and these nodes all belong to the "first device group (10kV switch type)", that is, the number of matching fault texts in the first device group is the largest.

[0062] Finally, the database extracts the solution branches corresponding to the matching fault texts, that is, based on the triple association relationship, the solutions corresponding to the matching fault texts in nodes A, D and B are retrieved respectively, and according to the structure of "device group, device node, fault text and solution", the retrieval results are fed back to the operation and maintenance personnel, for example, the node tree topology graph (annotating the similarity between nodes) of the first device group can be displayed on the left side of the display interface, and the matching fault texts (annotating related expressions such as "heating" and "poor contact") and corresponding solutions of each node can be displayed in the right column, in addition, the database in this embodiment can also provide a cross-device solution comparison function (for example, comparing the solutions of nodes A, D and B, highlighting common steps such as "polishing oxide layer, applying conductive paste and torque tightening"), so as to help the operation and maintenance personnel quickly obtain the fault handling experience across devices and solve the problem of manually comparing multiple device documents in the traditional knowledge base.

[0063] On the basis of the above embodiment, Figure 5 The structure block diagram of the power distribution equipment operation and maintenance knowledge base construction system according to an embodiment of the present application is shown as follows, Figure 5 The power distribution equipment operation and maintenance knowledge base construction system 200 can include a triple construction module 210, a single power distribution equipment fault rate determination module 220, a similarity determination module 230, a power distribution equipment grouping module 240 and a knowledge base construction module 250.

[0064] The triple construction module 210 is configured to construct triples based on the operation and maintenance knowledge of each power distribution equipment, and the triples include the name of the power distribution equipment, the fault text and the solution corresponding to each fault; The single power distribution equipment failure rate determination module 220 is configured to determine, for any power distribution equipment, a failure rate of the power distribution equipment based on failure texts of the power distribution equipment and solutions corresponding to each failure; The similarity degree determination module 230 is configured to calculate, based on the failure texts of each power distribution equipment and the solutions corresponding to each failure, a similarity degree between each pair of power distribution equipment, which is used to represent the similarity of the failure texts and the similarity of the solutions between each pair of power distribution equipment. The power distribution equipment grouping module 240 is configured to group all the power distribution equipment into a plurality of equipment groups based on the similarity degrees between each pair of power distribution equipment and the failure rates of each power distribution equipment, each equipment group including at least one power distribution equipment. The knowledge base construction module 250 is configured to construct a power distribution equipment operation and maintenance knowledge base based on the triplets and the equipment groups corresponding to each power distribution equipment.

[0065] In an example embodiment, the single power distribution equipment failure rate determination module 220 is further configured to, for any power distribution equipment, determine a plurality of failure types of the power distribution equipment based on the failure texts of the power distribution equipment, obtain occurrence frequencies of each failure type within a preset period, determine matching weights of each failure type based on the solutions corresponding to each failure in the power distribution equipment, and determine a failure rate of the power distribution equipment based on the occurrence frequencies of each failure type within the preset period and the matching weights of each failure type.

[0066] In an example embodiment, the similarity degree determination module 230 can be further configured to, for a target power distribution equipment and an attention power distribution equipment in each power distribution equipment, vectorize the failure texts of the target power distribution equipment and the solutions corresponding to each failure to obtain a plurality of target failure vectors and a plurality of target solution vectors, vectorize the failure texts of the attention power distribution equipment and the solutions corresponding to each failure to obtain a plurality of attention failure vectors and a plurality of attention solution vectors, and determine a similarity degree between the target power distribution equipment and the attention power distribution equipment based on the plurality of target failure vectors, the plurality of target solution vectors, the plurality of attention failure vectors, and the plurality of attention solution vectors.

[0067] In the example embodiment, the similarity degree determining module 230 can also be configured to calculate a first similarity between each target fault vector and each concerned fault vector, add all the first similarities to obtain a fault similarity between the target power distribution equipment and the concerned power distribution equipment, calculate a second similarity between a target solution vector corresponding to any target fault vector and a concerned solution vector corresponding to any concerned fault vector if the first similarity between the target fault vector and the concerned fault vector is greater than a preset threshold, and add all the second similarities to obtain a solution similarity between the target power distribution equipment and the concerned power distribution equipment. The similarity degree between the target power distribution equipment and the concerned power distribution equipment is determined based on the fault similarity and the solution similarity.

[0068] In the example embodiment, the power distribution equipment grouping module 240 can also be configured to group any two power distribution equipments into an equipment pair, construct a similarity degree matrix based on all the equipment pairs and the similarity degrees corresponding to the equipment pairs in a descending order of the similarity degrees, and divide all the power distribution equipments into a plurality of equipment groups based on the similarity degree matrix.

[0069] In the example embodiment, the knowledge base constructing module 250 can also be configured to establish a node tree based on the equipment groups corresponding to the power distribution equipments, wherein the node tree includes a plurality of nodes, connection relationships between the nodes, and a plurality of branches of each node, a node corresponds to a power distribution equipment, the connection relationships are used to represent the similarity degrees, and the plurality of branches include fault texts of each power distribution equipment in the triplets and solutions corresponding to each fault, and construct a power distribution equipment operation and maintenance database based on the node tree.

[0070] In the example embodiment, the single power distribution equipment fault rate determining module 220 can also be configured to divide all the fault types into three types based on the solutions corresponding to the faults in the power distribution equipment, the three types include a first type, a second type, and a third type, and determine the matching weights of the fault types based on the matching weights corresponding to the types.

[0071] Those skilled in the art should understand that the division of each module in the embodiment is only a logical division of functions, and all or part of the modules can be integrated onto one or more actual carriers in actual applications, and the modules can all be implemented in the form of software through a processing unit, or all be implemented in the form of hardware, or be implemented in the form of software and hardware combination. It should be noted that the modules in the power distribution equipment operation and maintenance knowledge base constructing system in the embodiment are one-to-one corresponding to the steps in the power distribution equipment operation and maintenance knowledge base constructing method in the foregoing embodiment, and therefore, the specific embodiments of the embodiment can refer to the embodiments of the power distribution equipment operation and maintenance knowledge base constructing method, which will not be described herein.

[0072] On the basis of the above-described embodiments, Figure 6This is a schematic diagram of the structure of a power distribution equipment operation and maintenance knowledge base according to one embodiment of this application, such as... Figure 6 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a method for constructing a power distribution equipment operation and maintenance knowledge base. This method includes: constructing triples based on the operation and maintenance knowledge of each power distribution equipment, where each triple includes the power distribution equipment name, fault text, and corresponding solutions for each fault; for any given power distribution equipment, determining its failure rate based on the fault text and corresponding solutions; calculating the similarity between each pair of power distribution equipment based on the fault text and corresponding solutions, where the similarity represents the similarity of fault texts and solutions between each pair of power distribution equipment; dividing all power distribution equipment into several equipment groups based on the similarity between each pair and the failure rate of each power distribution equipment, where each equipment group includes at least one power distribution equipment; and constructing a power distribution equipment operation and maintenance knowledge base based on the triples and the corresponding equipment groups.

[0073] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0074] On the basis of the above-mentioned embodiments, in another aspect, the present application also provides a computer program product, the computer program product comprising a computer program, the computer program being stored on a non-transitory computer-readable storage medium, and the computer program being executable by a processor to cause a computer to execute a power distribution equipment operation and maintenance knowledge base construction method provided by any of the above-mentioned methods, the method comprising: constructing a triple based on operation and maintenance knowledge of each power distribution equipment, the triple comprising a power distribution equipment name, a fault text, and a solution corresponding to each fault; determining a fault rate of any power distribution equipment based on the fault text of the power distribution equipment and the solution corresponding to each fault; calculating a similarity degree between each pair of power distribution equipments based on the fault text of each power distribution equipment and the solution corresponding to each fault, the similarity degree being used to represent the similarity of the fault text and the similarity of the solution between each pair of power distribution equipments; dividing all power distribution equipments into a plurality of equipment groups based on the similarity degree between each pair of power distribution equipments and the fault rate of each power distribution equipment, each equipment group comprising at least one power distribution equipment; and constructing a power distribution equipment operation and maintenance knowledge base based on the triple and the equipment groups corresponding to each power distribution equipment.

[0075] On the basis of the above-mentioned embodiments, in another aspect, the present application also provides a computer program product, the computer program product comprising a computer program, the computer program being stored on a non-transitory computer-readable storage medium, and the computer program being executable by a processor to cause a computer to execute a power distribution equipment operation and maintenance knowledge base construction method provided by any of the above-mentioned methods, the method comprising: constructing a triple based on operation and maintenance knowledge of each power distribution equipment, the triple comprising a power distribution equipment name, a fault text, and a solution corresponding to each fault; determining a fault rate of any power distribution equipment based on the fault text of the power distribution equipment and the solution corresponding to each fault; calculating a similarity degree between each pair of power distribution equipments based on the fault text of each power distribution equipment and the solution corresponding to each fault, the similarity degree being used to represent the similarity of the fault text and the similarity of the solution between each pair of power distribution equipments; dividing all power distribution equipments into a plurality of equipment groups based on the similarity degree between each pair of power distribution equipments and the fault rate of each power distribution equipment, each equipment group comprising at least one power distribution equipment; and constructing a power distribution equipment operation and maintenance knowledge base based on the triple and the equipment groups corresponding to each power distribution equipment.

[0076] The above is merely preferred embodiments of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent flow transformation made by using the content of the specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for constructing a power distribution equipment operation and maintenance knowledge base, characterized in that, The method comprises: constructing a triple based on the operation and maintenance knowledge of each power distribution equipment, the triple comprising a power distribution equipment name, a fault text, and a solution corresponding to each fault; determining a fault rate of any power distribution equipment based on the fault text of the power distribution equipment and the solution corresponding to each fault; calculating a similarity degree between each pair of power distribution equipment based on the fault text of each power distribution equipment and the solution corresponding to each fault, the similarity degree representing the similarity of the fault text and the similarity of the solution between each pair of power distribution equipment; dividing all power distribution equipment into a plurality of equipment groups based on the similarity degree between each pair of power distribution equipment and the fault rate of each power distribution equipment, each equipment group comprising at least one power distribution equipment; constructing a power distribution equipment operation and maintenance knowledge base based on the triple and the equipment group corresponding to each power distribution equipment.

2. The power distribution equipment operation and maintenance knowledge base construction method of claim 1, wherein, The method comprises: determining a plurality of fault types of any power distribution equipment based on the fault text of the power distribution equipment, and obtaining the occurrence frequency of each fault type within a preset period; determining a matching weight of each fault type based on the solution corresponding to each fault in the power distribution equipment; determining the fault rate of the power distribution equipment based on the occurrence frequency of each fault type within a preset period and the matching weight of each fault type.

3. The power distribution equipment operation and maintenance knowledge base construction method of claim 1, wherein The method comprises: vectorizing the fault text and the solution vector corresponding to each fault of the target power distribution equipment and the attention power distribution equipment to obtain a plurality of target fault vectors and a plurality of target solution vectors, and vectorizing the fault text and the solution vector corresponding to each fault of the attention power distribution equipment to obtain a plurality of attention fault vectors and a plurality of attention solution vectors; determining the similarity degree between the target power distribution equipment and the attention power distribution equipment based on the plurality of target fault vectors, the plurality of target solution vectors, the plurality of attention fault vectors, and the plurality of attention solution vectors.

4. The power distribution equipment operation and maintenance knowledge base construction method according to claim 3, characterized by, The method comprises: calculating a first similarity between each target fault vector and each attention fault vector, and adding all the first similarities to obtain a fault similarity between the target power distribution equipment and the attention power distribution equipment; for any target fault vector and any attention fault vector with a first similarity greater than a preset threshold, calculating a second similarity between the target solution vector corresponding to the target fault vector and the attention solution vector corresponding to the attention fault vector, and adding all the second similarities to obtain a solution similarity between the target power distribution equipment and the attention power distribution equipment; determine a similarity degree between the target power distribution equipment and the concerned power distribution equipment based on the fault similarity and the solution similarity.

5. The power distribution equipment operation and maintenance knowledge base construction method of claim 1, wherein, group all the power distribution equipment into a plurality of equipment groups based on the similarity degree between each pair of power distribution equipment and the fault rate of each power distribution equipment, including: group any two power distribution equipment into a pair of equipment, and construct a similarity degree matrix based on all the pairs of equipment and the corresponding similarity degree in descending order of the similarity degree; group all the power distribution equipment based on the similarity degree matrix.

6. The power distribution device operation and maintenance knowledge base construction method of claim 1, wherein, construct a power distribution equipment operation and maintenance knowledge base based on the triplets and the equipment groups corresponding to each power distribution equipment, including: establish a node tree based on the equipment groups corresponding to each power distribution equipment, the node tree including a plurality of nodes, connection relationships between the nodes, and a plurality of branches of each node, wherein a node corresponds to a power distribution equipment, the connection relationships are used to represent the similarity degree, and the plurality of branches include fault texts of each power distribution equipment in the triplets and solutions corresponding to each fault; construct a power distribution equipment operation and maintenance database based on the node tree.

7. The power distribution device operation and maintenance knowledge base construction method according to claim 2, characterized by, determine a matching weight of each fault type based on the solutions corresponding to each fault in the power distribution equipment, including: group all fault types into three types based on the solutions corresponding to each fault in the power distribution equipment, the three types including a first type, a second type, and a third type; determine the matching weight of each fault type based on the matching weight corresponding to each type.

8. A power distribution equipment operation and maintenance knowledge base construction system characterized by comprising: a power distribution equipment operation and maintenance knowledge base construction device; and a power distribution equipment operation and maintenance knowledge base construction method. including: a triplet construction module configured to construct triplets based on operation and maintenance knowledge of each power distribution equipment, the triplets including a power distribution equipment name, a fault text, and a solution corresponding to each fault; a single power distribution equipment fault rate determination module configured to determine a fault rate of any power distribution equipment based on fault texts of the power distribution equipment and solutions corresponding to each fault of the power distribution equipment; a similarity degree determination module configured to calculate a similarity degree between each pair of power distribution equipment based on fault texts of each power distribution equipment and solutions corresponding to each fault of each power distribution equipment, the similarity degree being used to represent similarity of fault texts and similarity of solutions between each pair of power distribution equipment; a power distribution equipment grouping module configured to group all the power distribution equipment into a plurality of equipment groups based on the similarity degree between each pair of power distribution equipment and the fault rate of each power distribution equipment, each equipment group including at least one power distribution equipment; a knowledge base construction module configured to construct a power distribution equipment operation and maintenance knowledge base based on the triplets and the equipment groups corresponding to each power distribution equipment.

9. The power distribution device operation and maintenance knowledge base construction system according to claim 8, characterized by, The single power distribution equipment fault rate determination module is further configured to, for any power distribution equipment, determine a plurality of fault types of the power distribution equipment based on fault texts of the power distribution equipment, and obtain occurrence frequencies of each fault type within a preset period; determine a matching weight of each fault type based on the solutions corresponding to each fault in the power distribution equipment; determine the fault rate of the power distribution equipment based on the occurrence frequencies of each fault type within a preset period and the matching weight of each fault type.

10. The power distribution equipment operation and maintenance knowledge base construction system according to claim 8, characterized by, The knowledge base construction module is further configured to establish a node tree based on the device groups to which the power distribution devices correspond, the node tree comprising a plurality of nodes, a connection relationship between the nodes, and a plurality of branches of each node, wherein a node corresponds to a power distribution device, the connection relationship is used to represent the similarity degree, and the plurality of branches comprise fault texts of each power distribution device in the triplets and solutions corresponding to each fault; A power distribution device operation and maintenance database is constructed based on the node tree.

Images