A method, device and medium for diagnosing defects in electric secondary equipment

Abstract

The present invention discloses a method, device and medium for diagnosing defects in secondary power equipment. The method includes: determining the alarm device that issues the alarm and the traceability state quantity according to the alarm information of the secondary power equipment; using the alarm device as the starting point of the traceability search, and searching on the secondary power equipment network according to the traceability state quantity to determine the defect diagnosis device; matching the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis device, and determining the troubleshooting state quantity according to the matching result; troubleshooting in the defect diagnosis device according to the troubleshooting state quantity to determine the defect diagnosis result of the secondary power equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of power secondary equipment operation analysis, and more specifically, to a power secondary equipment defect diagnosis method, device and medium. Background Art

[0002] The safe and reliable operation of the new power system is highly dependent on power secondary equipment. It is necessary to timely and accurately grasp the operating status of power secondary equipment. When the equipment has reported abnormal information, the defective parts must be located and dealt with as soon as possible to eliminate the hidden dangers of power secondary equipment failure or incorrect operation that threaten the safe and stable operation of the new power system.

[0003] Due to the complex structure of power secondary equipment and secondary circuits, the numerous defect types, and the multiple coupling associations between self-test alarms and defective parts, it is difficult to locate defects in power secondary equipment. At the same time, due to the lack of automatic diagnosis methods for power secondary equipment defects, defect diagnosis is time-consuming and the timely disposal rate is low, which poses severe challenges to the safe and reliable operation of new power systems. Existing methods have formed basic rules for defect diagnosis and constructed knowledge graphs for power secondary equipment defect diagnosis by building a test system and diagnosing typical defects in a laboratory environment. However, no specific defect diagnosis method based on the actual configuration of on-site power secondary equipment has been proposed.

[0004] There has long been a lack of effective technical means for instantiating the existing general rules for diagnosing defects in secondary power equipment to form an analysis method for specific protection equipment defects, combined with the state quantity information obtained online, to achieve automatic diagnosis of defects in secondary power equipment. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a method, device and medium for diagnosing defects in secondary power equipment.

[0006] According to one aspect of the present invention, there is provided a method for diagnosing defects in a power secondary device, comprising:

[0007] According to the alarm information of the power secondary equipment, determine the alarm device that issued the alarm and the traceability status quantity;

[0008] The alarm device is used as the starting point of the traceability search, and the fault diagnosis device is determined by searching on the power secondary equipment network based on the traceability state quantity;

[0009] Match the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis equipment, and determine the troubleshooting state quantity based on the matching result;

[0010] According to the troubleshooting status quantity, the defect diagnosis equipment is checked to determine the defect diagnosis result of the power secondary equipment.

[0011] Optionally, the alarm device is used as the starting point of the traceability search, and a search is performed on the power secondary equipment network according to the traceability state quantity to determine the defect diagnosis device, including:

[0012] The alarm device is taken as the starting point of the traceability search, and a traceability search is performed on the power secondary equipment network based on the traceability status quantity to obtain candidate defective devices, homologous devices, and mutual backup devices, and determine the defect diagnosis equipment.

[0013] Optionally, through source tracing search, the alarm device is used as the starting point of the source tracing search, and a source tracing search is performed on the power secondary equipment network according to the source tracing state quantity to obtain candidate defective devices, homologous devices, and mutual backup devices of the alarm device, and determine the defect diagnosis device, including:

[0014] Step 1: Take the alarm device as the starting place, select any traceability state quantity as the mark, search for the transition with the current place as the end point and containing the traceability state quantity according to the smart substation configuration description file, take the newly retrieved device as a place, and move the traceability state quantity to the place, and repeat the search until no new place and transition can be found;

[0015] Step 2: Execute the retrieval process of step 1 for different traceability state quantities in turn until the search for different traceability state quantities is completed;

[0016] Step 3: After completing the search for all traceability state quantities, add the electrical circuit as a transition, and add a starting place at the starting point of the electrical circuit transition to obtain candidate defective devices;

[0017] Step 4: Determine the defect traceability path, select any traceability state quantity, take the device in the searched defect traceability path as the starting place, search for the existing place as the starting point, and the transition containing the mark. If the end point of the transition is not the candidate defective device, then include the end point in the place set, traverse the transitions and places, and the searched place is the homologous device corresponding to the mark;

[0018] Step 5: Search step 4 for different traceability status quantities in turn to obtain the same-source devices corresponding to the different traceability status quantities;

[0019] Step 6: Search the primary device of the alarm device, and then search another secondary power device based on the correspondence between the primary device and the secondary power device to obtain the backup device of the alarm device;

[0020] Step 7: Match the candidate defective devices, homologous devices, and mutually-backed devices with the devices in the defect diagnosis knowledge graph to determine the defect diagnosis devices.

[0021] Optionally, matching the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis device, and determining the troubleshooting state quantity according to the matching result, including:

[0022] Accurately match the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis equipment to obtain an accurate matching result;

[0023] When there is a matched information point in the exact matching result, the troubleshooting state quantity is determined according to the exact matching result;

[0024] When there is no matched information point in the exact matching result, the state quantity in the defect diagnosis knowledge graph is fuzzy matched with the state quantity of the defect diagnosis equipment to obtain the fuzzy matching result;

[0025] The troubleshooting status quantity is determined based on the fuzzy matching results.

[0026] Optionally, the state quantity in the defect diagnosis knowledge graph is accurately matched with the state quantity of the defect diagnosis device to obtain an accurate matching result, including:

[0027] Search the state quantity list of the defect diagnosis equipment to determine whether there is an information point that completely matches the state quantity in the defect diagnosis knowledge graph to obtain an exact match result.

[0028] Optionally, fuzzy matching is performed between the state quantity in the defect diagnosis knowledge graph and the state quantity of the defect diagnosis device to obtain a fuzzy matching result, including:

[0029] The Skip-gram model is trained according to the collected historical protection equipment status quantities to generate a Skip-gram pre-training model;

[0030] The Skip-gram pre-training model is used to extract word vectors from the state quantities in the defect diagnosis knowledge graph and the state quantities of the defect diagnosis equipment, and the first state quantity word vector of the defect diagnosis knowledge graph and the second state quantity word vector of the defect diagnosis equipment are obtained;

[0031] The cosine similarity between the first state quantifier word vector and the second state quantifier word vector is calculated, and the cosine similarity is compared with a preset cosine similarity threshold to determine a fuzzy matching result.

[0032] Optionally, the objective function of the Skip-gram pre-training model is:

[0033]

[0034] In the formula, c is the window size; T Indicates the size of the training text; t is the corpus number of the text; p is a preset constant; W is the word vector of the word; jIt is a sliding variable, and its value ranges from -c to c;

[0035] The calculated conditional probability of the Skip-gram pre-training model is:

[0036]

[0037] In the formula, v w , v' w Respectively represent words w Input vector and output vector of ; | v | indicates the total length of the word; w For words v A certain corpus, w 1 For words v The initial corpus, W 0 For the target corpus, W t For Text t The word vector of W 0 For the target corpus, T is the transpose symbol.

[0038] Optionally, performing troubleshooting in a defect diagnosis device according to the troubleshooting state quantity to determine a defect diagnosis result of the power secondary equipment includes:

[0039] Check the defect diagnosis equipment in turn according to the check status quantity, and determine the defect diagnosis result of the power secondary equipment when all the check points can be executed;

[0040] If there are situations where the troubleshooting points cannot be executed, determine the defect probability of each defective part of the defect diagnosis equipment, and determine the defect diagnosis result of the power secondary equipment based on the probability of each defective part.

[0041] Optionally, the probability calculation formula for each part is:

[0042]

[0043] In the formula, Pr( l ) refers to the part l The proportion of the statistical number of defects in the statistical number of all defects, symbol L Represents all defective parts l 1 , l 2 ,… l n}The set composed of; L 1is the remaining defective part set, .

[0044] According to another aspect of the present invention, there is provided a device for diagnosing defects in a secondary power device, comprising:

[0045] A determination module is used to determine the alarm device that issued the alarm and the traceability state quantity according to the alarm information of the power secondary equipment;

[0046] A search module is used to use the alarm device as the starting point of the traceability search, and search on the power secondary equipment network according to the traceability state quantity to determine the defect diagnosis device;

[0047] A matching module is used to match the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis equipment, and determine the troubleshooting state quantity according to the matching result;

[0048] The troubleshooting module is used to perform troubleshooting in the defect diagnosis equipment according to the troubleshooting state quantity to determine the defect diagnosis result of the power secondary equipment.

[0049] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the method described in any one of the above aspects of the present invention.

[0050] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of the above aspects of the present invention.

[0051] Therefore, the present invention proposes a method that relies on online data collection and SCD files of smart substations, and on the basis of SCD file path tracing, to realize the instantiation of diagnostic logic in the defect diagnosis knowledge graph, so as to apply the power secondary equipment defect diagnosis knowledge graph in actual on-site scenarios, and realize automatic diagnosis of defective parts of power secondary equipment (including loops). The present invention can support instantiation diagnosis of power secondary equipment defects, and lay a good foundation for quickly and timely handling of power secondary equipment defects and ensuring safe and stable operation of power grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0053] Figure 1 It is a flow chart of a method for diagnosing defects in secondary power equipment provided by an exemplary embodiment of the present invention;

[0054] Figure 2is a schematic diagram of a candidate defective device search process provided by an exemplary embodiment of the present invention;

[0055] Figure 3 is a schematic diagram of a homologous device search process provided by an exemplary embodiment of the present invention;

[0056] Figure 4 is a schematic diagram of the Skip-gram model structure provided by an exemplary embodiment of the present invention;

[0057] Figure 5 is a PT disconnection search result diagram provided by an exemplary embodiment of the present invention;

[0058] Figure 6 This is a Petri network diagram of a PT disconnection traceability path provided by an exemplary embodiment of the present invention;

[0059] Figure 7 is a schematic diagram of a Petri net composed of homologous devices provided by an exemplary embodiment of the present invention;

[0060] Figure 8 is a PT line break defect diagnosis flow chart provided by an exemplary embodiment of the present invention;

[0061] Fig. 9 is a schematic diagram of a specific process of defect location provided by an exemplary embodiment of the present invention;

[0062] Fig.10 It is a structural schematic diagram of a power secondary equipment defect diagnosis device provided by an exemplary embodiment of the present invention;

[0063] Fig.11 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0064] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0065] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0066] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0067] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0068] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0069] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0070] It should also be understood that the description of the various embodiments of the present invention focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0071] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0072] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0073] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0074] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0075] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0076] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0077] Exemplary Methods

[0078] Figure 1 FIG. 1 is a flow chart of a method for diagnosing a defect in a secondary power device provided by an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as Figure 1 As shown, the power secondary equipment fault diagnosis method 100 includes the following steps:

[0079] Step 101, according to the alarm information of the power secondary equipment, determine the alarm device that issued the alarm and the traceability state quantity;

[0080] Step 102, taking the alarm device as the starting point of the tracing search, and searching on the power secondary equipment network according to the tracing state quantity to determine the defect diagnosis device;

[0081] Step 103, matching the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis device, and determining the troubleshooting state quantity according to the matching result;

[0082] Step 104, performing a check in the defect diagnosis device according to the check state quantity to determine the defect diagnosis result of the power secondary equipment.

[0083] Specifically, the present invention application aims to propose a method that relies on online data collection and SCD files of smart substations, and on the basis of SCD file path tracing, realizes the instantiation of diagnostic logic (including equipment and state quantity 2 levels) in the defect diagnosis knowledge graph, so as to apply the power secondary equipment defect diagnosis knowledge graph in actual on-site scenarios and realize automatic diagnosis of defective parts of power secondary equipment (including loops).

[0084] The present invention provides a method for diagnosing defects in electric secondary equipment, which specifically includes:

[0085] Step 1: Determine the alarm device and the corresponding logical node. Based on the alarm information, locate the device that issued the alarm; based on the alarm type, determine the corresponding logical node description of the traceability search path (a complete path consisting of the collection, transmission, and calculation of protection information such as voltage, current, circuit breakers, and disconnectors).

[0086] Step 2: Instantiate defect diagnosis related equipment. There are three types of equipment that need to be instantiated: ① Candidate defect equipment, which refers to equipment that can cause alarms (equipment on the traceability path); ② Same-source equipment, which refers to equipment that collects related status quantities from the same source as the alarm equipment; ③ Mutual backup equipment, which refers to equipment that serves as a backup for the alarm equipment.

[0087] Step 3: Instantiate the state quantities involved in defect diagnosis. Combined with the knowledge graph, determine the state quantities related to the troubleshooting point (including analog quantity, switch quantity, alarm, etc.), and search for the corresponding state quantities from the information point table of the device. For situations where accurate matching is not possible, use Skip-gram and cosine similarity algorithms to determine the relevant state quantities.

[0088] Step 4: Execute each inspection point in turn to achieve automatic defect diagnosis. For inspection points that cannot be executed, the probability of different defect locations is calculated through probability calculation.

[0089] In one embodiment of the present invention, step 1: determine the alarm device and the corresponding logical node

[0090] According to the device name attribute of the alarm information, the device that issued the alarm is determined as the starting point of the tracing path search.

[0091] According to the type of alarm information, the state quantity that may have abnormalities is determined, and then the logical node description corresponding to the state quantity in the SCD file is determined, laying the foundation for the search of the Petri net traceability path.

[0092] In one embodiment of the present invention, step 2: instantiate a device for defect diagnosis

[0093] Step 2-1: Obtain candidate defective devices through source tracing search

[0094] Construct a Petri network of the alarm traceability path and define the scope of the defective parts corresponding to the alarm. Figure 2 As shown, the specific implementation process is as follows:

[0095] 2-1.1: Describe the logical nodes determined in step 1 as labels of the Petri net;

[0096] 2-1.2: Take the device that issues the alarm as a place, select any tag determined in step 2-1.1, search for transitions based on the SCD file, and ensure that the path description of the sending or receiving end of the virtual circuit corresponding to the transition contains the tag as a keyword. The newly retrieved device is taken as a place, and the tag is moved to the place; based on the new place, use the same conditions to search for transitions and corresponding places; repeat the search until no new places and transitions are found. Perform this search process for different tags in turn until the search for different tags is completed;

[0097] 2-1.3: Based on the starting places of different marks in step 2-1.2, add transitions corresponding to the marks, whose properties are electrical circuits, such as voltage circuits, current circuits, circuit breaker opening and closing switch quantity circuits, disconnector position switch quantity circuits, etc. Add new places at the beginning of the transitions, corresponding to PT windings, CT windings, operating box circuit breaker contacts, disconnector position contacts, etc., and move the marks to the places. The places searched in step 2-1.2, transitions (with properties of optical circuits), and transitions determined in step 2-1.3 (with properties of electrical circuits) constitute the traceability path Petri network corresponding to the alarm, which is a collection of defect ranges that may cause the alarm to occur.

[0098] Step 2-2: Search for the same source device, refer to Figure 3 As shown, the specific implementation process is as follows:

[0099] Select any tag determined in step 2-1.1, and after enabling the transition in the Petri net determined in steps 2-1.2 and 2-1.3, you can get the library place of the tag. Use the library place as the sending end, retrieve the virtual circuit containing the tag in the sending end or the receiving end, and get the transition and library place; repeat the search until no new transition is found.

[0100] Select the next place and repeat the above process until no new transitions and places can be found.

[0101] The newly searched Petri subnetwork is the range covered by the homologous devices corresponding to the label.

[0102] The homologous device is a newly added place in the Petri subnet, and the label corresponding to the place is the label that can be obtained after enabling the transition in the Petri net.

[0103] Select the next marker and repeat the above process until no new homologous device can be found.

[0104] Step 2-3: Search for the mutual backup device

[0105] Retrieve the primary device of the alarm device, and then retrieve another power secondary device based on the correspondence between the primary device and the secondary device, and the result obtained is the mutual backup device.

[0106] Step 2-4: Instantiation of equipment in the defect diagnosis knowledge graph

[0107] Determine the types of equipment to be instantiated in the defect diagnosis knowledge graph, such as candidate defective equipment, homologous equipment, and mutual backup equipment. Combined with the equipment type (such as line protection, busbar protection, merging unit, intelligent terminal, etc.), select the corresponding type of equipment from the candidate defective equipment, homologous equipment, and mutual backup equipment searched in steps 2-1 to 2-3 to realize the instantiation of the equipment in the defect diagnosis knowledge graph.

[0108] In one embodiment of the present invention, step 3 instantiation of the defect diagnosis rule state quantity:

[0109] Step 3-1 Accurately match the state quantity:

[0110] According to the device instantiation result in step 2, search the state quantity list of the device to determine whether there is an information point that completely matches the target state quantity (the state quantity in the defect diagnosis knowledge graph). If so, the information point is the state quantity to be instantiated in the diagnosis rule.

[0111] Step 3-2 Fuzzy matching state quantity:

[0112] Considering that the expression of the state quantity may not be standardized and the directly matching state quantity cannot be obtained, the Skip-gram model is combined with the cosine similarity method to determine the target state quantity.

[0113] (1) Use the Skip-gram model to convert the state quantity text into the corresponding word vector. The structure of the Skip-gram model is as follows: Figure 4 shown.

[0114] The Skip-gram model takes word vectors as input and is trained to maximize the following value:

[0115] (1)

[0116] In the formula, c is the window size; T Indicates the size of the training text; t is the corpus number of the text; p is a preset constant; W is the word vector of the word; j is a sliding variable, with a value between -c and c. The Skip-gram model calculates the conditional probability as shown in formula (2):

[0117] (2)

[0118] In the formula, vw , v' w Respectively represent words w Input vector and output vector of ; | v | indicates the total length of the word; w For words v A certain corpus, w 1 For words v The initial corpus, W 0 For the target corpus, W t For Text t The word vector of W 0 For the target corpus, T is the transposed symbol. Finally, the Skip-gram model achieves the goal of predicting the context of the current word through the above process.

[0119] Using the Skip-gram model, the word vectors of the state quantities in the defect diagnosis knowledge graph and the state quantities in the defect diagnosis equipment are obtained, which can be expressed as:

[0120] { V l1 , V l2 , V l3 ,…, V lm} (3)

[0121] In the formula ，V l1 to V lm It is a word m word vector elements

[0122] (2) The cosine similarity between the word vector of the state quantity in the defect diagnosis equipment and the word vector of the state quantity in the defect diagnosis knowledge graph is determined in turn. If the similarity exceeds a pre-defined threshold, the state quantity of the defect diagnosis equipment is the target state quantity. This threshold is determined based on manual experience (set to 0.6), taking into account the accuracy of similar entity recognition and avoiding the mis-merging of different entities.

[0123] The cosine similarity calculation between word vectors can be expressed as:

[0124] (4)

[0125] In the formula, E is the word vector dimension obtained by Word2Vec transformation, V k is the word vectork A quantity. V l yes{ V l1 , V l2 , V l3 ,…, V lm}, V s yes{ V s1 , V s2 , V s3 ,…, V sn}, ||·|| points to the inner product of the quantity.

[0126] The cosine similarity between word vectors is used to determine whether the state quantity to be determined is the target state quantity. If the similarity threshold is reached, the searched state quantity is used for instantiation.

[0127] In one embodiment of the present invention, step 4: defect location diagnosis and analysis:

[0128] Step 4-1: Defect diagnosis when there is only one defective part:

[0129] First, perform logical judgment of a single checkpoint. Without loss of generality, there are two main types of checkpoints:

[0130] (1) Check whether a certain type of alarm has occurred. Check whether the equipment mentioned in the check point has an alarm within 1 hour before and after the original alarm occurs;

[0131] (2) Check whether the analog quantity, switch quantity, online monitoring and other state quantities are within a reasonable range. Extract the corresponding state quantity values ​​and determine whether the state quantity is within a reasonable range according to standards such as DL / T 587-2016 "Regulations on Operation Management of Relay Protection and Safety Automatic Devices".

[0132] According to the inspection results and the inspection logic flow, it is determined to jump to the next inspection point or a certain defect location. The defect inspection process is performed in sequence until the defect location is determined by the inspection results, and the defect diagnosis is completed.

[0133] Step 4-2: Defect diagnosis when the defect location is not unique:

[0134] When some inspection points cannot be automatically judged, the above method cannot produce a unique defect location result. The probability of different defect locations can be determined based on the historical statistical information of the defects, so that the operator can have an intuitive impression of the probability of each possible defect location before manual inspection.

[0135] symbol L Represents all defective parts l 1 , l 2 ,… l n After executing a series of inspection points, the remaining possible defect parts set (that is, the defect parts set that cannot be further subdivided) is L 1 L . Then the defect probability Pr( l | L 1 )for:

[0136] (5)

[0137] In the formula, Pr( l ) refers to the defective part l The proportion of the statistical number of defects in the statistical number of all defects is calculated based on historical statistical data.

[0138] In one embodiment of the present invention, a case analysis (220kV Line I line protection A "PT disconnection") is conducted according to the technical solution proposed in this application, specifically including:

[0139] Step 1: Determine the alarm device and the corresponding logical node:

[0140] According to the reporting device attribute field of the alarm information, the starting point of the traceability search is determined to be the line protection A of 220kV Line I. According to the alarm information "PT disconnection" and the state quantity type discrimination rules prepared in advance, it can be determined that the state quantities of the traceability search are AC voltage and disconnector, and the logical node descriptions are TVTR (voltage signal) and CSWI (disconnector signal).

[0141] Step 2: Instantiate the device for defect diagnosis:

[0142] Step 2-1: Obtain candidate defective devices through source tracing search:

[0143] Combined with the SCD file, the devices that may cause the alarm are obtained, such as Figure 5 and Figure 6 As shown. Among them, the corresponding to the logical node description TVTR is:

[0144] p 0 —220kV Line I line protection A (alarm equipment, equipment type: line protection);

[0145] p 1 —220kV Line I merging unit 1 (equipment type: line merging unit);

[0146] p 2 —220kV 1M / 2M voltage merging unit A (equipment type: busbar merging unit);

[0147] p 4 —PT secondary winding (equipment type: PT winding).

[0148] The corresponding logical node description CSWI is:

[0149] p 1 —220kV Line I merging unit 1 (equipment type: line merging unit);

[0150] p 3 —220kV Line I switch intelligent terminal A (equipment type: line intelligent terminal);

[0151] p 5 —Operation box isolating switch position contact (equipment type: isolating switch position contact).

[0152] Step 2-2: Search for devices of the same source. The search results for devices of the same source are as follows: Figure 7 Different from the Petri network of the alarm tracing path, the Petri network where the homologous device is located is marked with a dotted line.

[0153] By searching the logical node descriptions TVTR and CSWI, the homologous devices are obtained as follows:

[0154] p 6 —220kV Line I measurement and control (equipment type: line measurement and control device)

[0155] p 7 —220kV 1M / 2M busbar differential protection A (equipment type: busbar protection)

[0156] p 8 —220kV Line II Merging Unit A (Equipment Type: Line Merging Unit)

[0157] p 9 —220kV Line III Merging Unit A (Equipment Type: Line Merging Unit)

[0158] p 10 —220kV Line IV Merging Unit A (Equipment Type: Line Merging Unit)

[0159] p 11 —220kV Line V Merging Unit A (Equipment Type: Line Merging Unit)

[0160] p 12 —220kV Line VI Merging Unit A (Equipment Type: Line Merging Unit)

[0161] p 13 —Medium voltage side merging unit A of No. 3 main transformer (equipment type: transformer merging unit)

[0162] p 14 —220kV Line VII Merging Unit A (Equipment Type: Line Merging Unit)

[0163] p 15 —220kV Line VIII Merging Unit A (Equipment Type: Line Merging Unit)

[0164] p 16 —220kV Line II Line Protection A (Equipment Type: Line Protection)

[0165] p 17 —220kV Line III Line Protection A (Equipment Type: Line Protection)

[0166] p 18 —No. 3 main transformer protection A (equipment type: transformer protection)

[0167] p 19 —220kV Line IV Line Protection A (Equipment Type: Line Protection)

[0168] p 20 —220kV Line V Line Protection A (Equipment Type: Line Protection)

[0169] p 21 —220kV Line VI Line Protection A (Equipment Type: Line Protection)

[0170] p 22 —220kV Line VII Line Protection A (Equipment Type: Line Protection)

[0171] p 23 —220kV Line VIII Line Protection A (Equipment Type: Line Protection)

[0172] Step 2-3: Search for the mutual backup device

[0173] The primary device of the alarm device 220kV Line Ⅰ line protection A is retrieved to be 220kV Line Ⅰ. Among the two sets of relay protection devices associated with the primary device, in addition to the alarm device, the other one is 220kV Line Ⅰ line protection B, so the backup device is 220kV Line Ⅰ line protection B.

[0174] Step 2-4: Instantiation of equipment in the defect diagnosis knowledge graph

[0175] Extract the line protection PT disconnection defect diagnosis rules under the double mother wiring mode, such as Figure 8 shown.

[0176] Figure 8 The relevant inspection points and defect locations in the PT line break defect diagnosis are instantiated and the equipment obtained is shown in Table 1:

[0177] Table 1

[0178]

[0179] Step 3: Instantiation of defect diagnosis rule state

[0180] Figure 8 The corresponding state quantities of the troubleshooting points in the PT disconnection defect diagnosis knowledge graph, the corresponding instantiation state quantities and the identification methods are shown in Table 2:

[0181] Table 2

[0182]

[0183] Step 4: Diagnosis and analysis of defective parts

[0184] Step 4-1: Defect diagnosis when there is only one defective part

[0185] According to the troubleshooting results and the troubleshooting logic flow, it is determined to jump to the next troubleshooting point or a certain defect location. The defect troubleshooting process is executed in sequence until the defect location is determined by the troubleshooting results, and the defect diagnosis is completed. During a certain diagnosis process, the specific process of the instantiation diagnosis of the line protection A PT of the 220kV I line is as follows: Fig. 9 shown.

[0186] Step 4-2: Defect diagnosis when the defect location is not unique

[0187] In the defect diagnosis flow chart, when a checkpoint is difficult to automatically execute, the checkpoint is skipped to obtain the corresponding defect part range, and then the conditional probability formula is applied to determine the probability of each defect part within the range. Fig. 9 During the automatic execution of the defect diagnosis process, the check point 220kV 1M / 2M voltage merging unit A cannot be automatically executed due to lack of information to determine whether the hardware alarm has occurred. Therefore, the 220kV1M / 2M voltage merging unit A, PT body and PT electrical circuit are all possible defective parts.

[0188] Based on historical statistical information, the defect probabilities corresponding to the three defective parts of 220kV1M / 2M voltage merging unit A, PT body and PT electrical circuit are calculated to be 76.7%, 7.7% and 15.6% respectively.

[0189] Therefore, the present invention proposes a method that relies on online data collection and SCD files of smart substations, and on the basis of SCD file path tracing, to realize the instantiation of diagnostic logic in the defect diagnosis knowledge graph, so as to apply the power secondary equipment defect diagnosis knowledge graph in actual on-site scenarios, and realize automatic diagnosis of defective parts of power secondary equipment (including loops). The present invention can support instantiation diagnosis of power secondary equipment defects, and lay a good foundation for quickly and timely handling of power secondary equipment defects and ensuring safe and stable operation of power grids.

[0190] Exemplary Devices

[0191] Fig.10 FIG. 1 is a schematic diagram of a structure of a power secondary equipment defect diagnosis device provided by an exemplary embodiment of the present invention. Fig.10 As shown, the device 1000 includes:

[0192] The determination module 1010 is used to determine the alarm device that issued the alarm and the traceability state quantity according to the alarm information of the power secondary equipment;

[0193] The search module 1020 is used to use the alarm device as the starting point of the traceability search, and search on the power secondary equipment network according to the traceability state quantity to determine the defect diagnosis device;

[0194] A matching module 1030 is used to match the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis device, and determine the troubleshooting state quantity according to the matching result;

[0195] The troubleshooting module 1040 is used to perform troubleshooting in the defect diagnosis equipment according to the troubleshooting state quantity to determine the defect diagnosis result of the power secondary equipment.

[0196] Optionally, the search module 1020 includes:

[0197] The search submodule is used to use the alarm device as the starting point of the traceability search, and to perform a traceability search on the power secondary equipment network based on the traceability state quantity to obtain candidate defective equipment, homologous equipment, and mutual backup equipment, and determine the defect diagnosis equipment.

[0198] Optionally, search for submodules, including:

[0199] Step 1: Take the alarm device as the starting place, select any traceability state quantity as the mark, search for the transition with the current place as the end point and containing the traceability state quantity according to the smart substation configuration description file, take the newly retrieved device as a place, and move the traceability state quantity to the place, and repeat the search until no new place and transition can be found;

[0200] Step 2: Execute the retrieval process of step 1 for different traceability state quantities in turn until the search for different traceability state quantities is completed;

[0201] Step 3: After completing the search for all traceability state quantities, add the electrical circuit as a transition, and add a starting place at the starting point of the electrical circuit transition to obtain candidate defective devices;

[0202] Step 4: Determine the defect traceability path, select any traceability state quantity, take the device in the searched defect traceability path as the starting place, search for the existing place as the starting point, and the transition containing the mark. If the end point of the transition is not the candidate defective device, then include the end point in the place set, traverse the transitions and places, and the searched place is the homologous device corresponding to the mark;

[0203] Step 5: Search step 4 for different traceability status quantities in turn to obtain the same-source devices corresponding to the different traceability status quantities;

[0204] Step 6: Search the primary device of the alarm device, and then search another secondary power device based on the correspondence between the primary device and the secondary power device to obtain the backup device of the alarm device;

[0205] Step 7: Match the candidate defective devices, homologous devices, and mutually-backed devices with the devices in the defect diagnosis knowledge graph to determine the defect diagnosis devices.

[0206] Optionally, the matching module 1030 includes:

[0207] The first matching submodule is used to accurately match the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis device to obtain an accurate matching result;

[0208] A first determination submodule is used to determine the screening state quantity according to the accurate matching result when there is a matched information point in the accurate matching result;

[0209] The second matching submodule is used to perform fuzzy matching between the state quantity in the defect diagnosis knowledge graph and the state quantity of the defect diagnosis device to obtain a fuzzy matching result when there is no matched information point in the exact matching result;

[0210] The second determination submodule is used to determine the investigation state quantity according to the fuzzy matching result.

[0211] Optionally, the first matching submodule includes:

[0212] The matching unit is used to search the state quantity list of the defect diagnosis equipment to determine whether there is an information point that completely matches the state quantity in the defect diagnosis knowledge graph, and obtain an accurate matching result.

[0213] Optionally, the second matching submodule includes:

[0214] A training unit, used for training the Skip-gram model according to the collected historical protection device state quantities to generate a Skip-gram pre-training model;

[0215] An extraction unit, used to extract word vectors from the state quantities in the defect diagnosis knowledge graph and the state quantities of the defect diagnosis equipment using a Skip-gram pre-training model, to obtain a first state quantity word vector of the defect diagnosis knowledge graph and a second state quantity word vector of the defect diagnosis equipment;

[0216] The calculation unit is used to calculate the cosine similarity between the first state quantifier word vector and the second state quantifier word vector, compare the cosine similarity with a preset cosine similarity threshold, and determine the fuzzy matching result.

[0217] Optionally, the objective function of the Skip-gram pre-training model is:

[0218]

[0219] In the formula, c is the window size; T Indicates the size of the training text; t is the corpus number of the text; p is a preset constant; W is the word vector of the word; j It is a sliding variable, and its value ranges from -c to c;

[0220] The calculated conditional probability of the Skip-gram pre-training model is:

[0221]

[0222] In the formula, v w , v' wRespectively represent words w Input vector and output vector of ; | v | indicates the total length of the word; w For words v A certain corpus, w 1 For words v The initial corpus, W 0 For the target corpus, W t For Text t The word vector of W 0 For the target corpus, T is the transpose symbol.

[0223] Optionally, the troubleshooting module 1040 includes:

[0224] The first troubleshooting submodule is used to troubleshoot the defect diagnosis equipment in sequence according to the troubleshooting state quantity, and determine the defect diagnosis result of the power secondary equipment when all the troubleshooting points can be executed;

[0225] The second troubleshooting submodule is used to determine the defect probability of each defective part of the defect diagnosis equipment if there is a situation where the troubleshooting point cannot be executed, and determine the defect diagnosis result of the power secondary equipment according to the probability of each defective part.

[0226] Optionally, the probability calculation formula for each part is:

[0227]

[0228] In the formula, Pr( l ) refers to the part l The proportion of the statistical number of defects in the statistical number of all defects, symbol L Represents all defective parts l 1 , l 2 ,… l n}The set composed of; L 1 is the remaining defective part set, .

[0229] Exemplary Electronic Devices

[0230] Fig.11 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. Fig.11 As shown, the electronic device 110 includes one or more processors 111 and a memory 112 .

[0231] The processor 111 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0232] The memory 112 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 111 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may also include: an input device 113 and an output device 114, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0233] In addition, the input device 113 may also include, for example, a keyboard, a mouse, and the like.

[0234] The output device 114 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0235] Of course, to simplify, Fig.11 Only some of the components related to the present invention in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device may further include any other appropriate components according to specific application conditions.

[0236] Exemplary computer program products and computer-readable storage media

[0237] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above-mentioned "Exemplary Method" section of this specification.

[0238] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0239] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0240] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, system or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0241] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0242] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0243] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0244] The method and system of the present invention may be implemented in many ways. For example, the method and system of the present invention may be implemented by software, hardware, firmware or any combination of software, hardware, firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0245] It should also be noted that in the system, device and method of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present invention. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown here, but in accordance with the widest range consistent with the principles and novel features disclosed here.

[0246] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for diagnosing defects in secondary power equipment, characterized in that: include: According to the alarm information of the power secondary equipment, determine the alarm device that issued the alarm and the traceability status quantity; Taking the alarm device as the starting point of the tracing search, searching on the power secondary equipment network according to the tracing state quantity, and determining the defect diagnosis device; Matching the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis device, and determining the troubleshooting state quantity according to the matching result; Performing troubleshooting in the defect diagnosis device according to the troubleshooting state quantity to determine a defect diagnosis result of the power secondary device; The alarm device is used as the starting point of the traceability search, and a search is performed on the power secondary equipment network according to the traceability state quantity to determine the defect diagnosis device, including: The alarm device is used as the starting point of the traceability search, and a traceability search is performed on the power secondary equipment network according to the traceability state quantity to obtain candidate defective equipment, homologous equipment and mutual backup equipment, and determine the defect diagnosis device; Through the source tracing search, the alarm device is used as the starting point of the source tracing search, and the source tracing search is performed on the power secondary equipment network according to the source tracing state quantity to obtain the candidate defective device, homologous device and mutual backup device of the alarm device, and determine the defect diagnosis device, including: Step 1: Take the alarm device as the starting place, select any traceability state quantity as a mark, search for the transition with the current place as the end point and containing the traceability state quantity according to the smart substation configuration description file, take the newly retrieved device as a place, and move the traceability state quantity to the place, and repeat the search until no new place and transition are found; Step 2: Execute the retrieval process of step 1 for different traceability state quantities in turn until the search for different traceability state quantities is completed; Step 3: After completing the search of all traceability state quantities, add the electrical circuit as a transition, and add a starting library at the starting point of the electrical circuit transition to obtain the candidate defective device; Step 4: Determine the defect traceability path, select any traceability state quantity, take the device in the searched defect traceability path as the starting place, search for the existing place as the starting point, and the transition containing the mark. If the end point of the transition is not the candidate defective device, then include the end point in the place set, traverse the transitions and places, and the searched place is the homologous device corresponding to the mark; Step 5: Search step 4 for different traceability status quantities in turn to obtain the same-source devices corresponding to the different traceability status quantities; Step 6: Retrieve the primary device of the alarm device, and then retrieve another secondary power device based on the correspondence between the primary device and the secondary power device to obtain the backup device of the alarm device; Step 7: Match the candidate defective devices, the homologous devices, and the mutually-backed devices with the devices in the defect diagnosis knowledge graph to determine the defect diagnosis device.

2. The method according to claim 1, characterized in that Matching the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis device, and determining the troubleshooting state quantity according to the matching result, including: Accurately matching the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis device to obtain an accurate matching result; In the case that the exact matching result has a matched information point, determining the troubleshooting state quantity according to the exact matching result; In the case that there is no matched information point in the exact matching result, fuzzy matching is performed on the state quantity in the defect diagnosis knowledge graph and the state quantity of the defect diagnosis device to obtain a fuzzy matching result; The troubleshooting status quantity is determined according to the fuzzy matching result.

3. The method according to claim 2, characterized in that Accurately matching the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis device to obtain an accurate matching result includes: Search the state quantity list of the defect diagnosis device to determine whether there is an information point that completely matches the state quantity in the defect diagnosis knowledge graph, and obtain the exact matching result.

4. The method according to claim 2, characterized in that: Performing fuzzy matching on the state quantity in the defect diagnosis knowledge graph and the state quantity of the defect diagnosis device to obtain a fuzzy matching result includes: Training the Skip-gram model according to the collected historical protection device state quantities to generate the Skip-gram pre-trained model; The Skip-gram pre-trained model is used to extract word vectors from the state quantities in the defect diagnosis knowledge graph and the state quantities of the defect diagnosis equipment, so as to obtain a first state quantity word vector of the defect diagnosis knowledge graph and a second state quantity word vector of the defect diagnosis equipment; The cosine similarity between the first state quantifier word vector and the second state quantifier word vector is calculated, and the cosine similarity is compared with a preset cosine similarity threshold to determine the fuzzy matching result.

5. The method according to claim 4, characterized in that The objective function of the Skip-gram pre-training model is: In the formula, c is the window size; T Indicates the size of the training text; t is the corpus number of the text; p is a preset constant; W is the word vector of the word; j It is a sliding variable, and its value ranges from -c to c; The calculated conditional probability of the Skip-gram pre-training model is: In the formula, v w , v' w Respectively represent words w Input vector and output vector of ; | v | indicates the total length of the word; w For words v A certain corpus, w 1 for word v The initial corpus, W 0 is the target corpus, W t For text t The word vector of T is the transpose symbol.

6. The method according to claim 4, characterized in that Performing troubleshooting in the defect diagnosis device according to the troubleshooting state quantity to determine the defect diagnosis result of the power secondary device includes: Check the defect diagnosis equipment in sequence according to the check state quantity, and determine the defect diagnosis result of the power secondary equipment when all the check points can be executed; If there is a situation where the troubleshooting point cannot be executed, the defect probability of each defective part of the defect diagnosis equipment is determined, and the defect diagnosis result of the power secondary equipment is determined according to the probability of each defective part.

7. The method according to claim 6, characterized in that The probability calculation formula for each part is: In the formula, Pr( l ) refers to the part l The proportion of the statistical number of defects in the statistical number of all defects, symbol L Represents all defective parts l 1, l 2,… l n }The set composed of; L 1 is the remaining defective part set, .

8. A device for diagnosing defects in secondary power equipment, characterized in that: include: A determination module is used to determine the alarm device that issued the alarm and the traceability state quantity according to the alarm information of the power secondary equipment; A search module, used to use the alarm device as a starting point for tracing back the source, and to search on the power secondary equipment network according to the tracing back state quantity to determine the defect diagnosis device; A matching module, used to match the state quantity in the defect diagnosis knowledge graph with the state quantity of the defect diagnosis device, and determine the troubleshooting state quantity according to the matching result; A troubleshooting module, used to perform troubleshooting in the defect diagnosis device according to the troubleshooting state quantity to determine the defect diagnosis result of the power secondary equipment; Search modules, including: The alarm device is used as the starting point of the traceability search, and a traceability search is performed on the power secondary equipment network according to the traceability state quantity to obtain candidate defective equipment, homologous equipment and mutual backup equipment, and determine the defect diagnosis device; Search submodules, including: Step 1: Take the alarm device as the starting place, select any traceability state quantity as a mark, search for the transition with the current place as the end point and containing the traceability state quantity according to the smart substation configuration description file, take the newly retrieved device as a place, and move the traceability state quantity to the place, and repeat the search until no new place and transition are found; Step 2: Execute the retrieval process of step 1 for different traceability state quantities in turn until the search for different traceability state quantities is completed; Step 3: After completing the search of all traceability state quantities, add the electrical circuit as a transition, and add a starting library at the starting point of the electrical circuit transition to obtain the candidate defective device; Step 4: Determine the defect traceability path, select any traceability state quantity, take the device in the searched defect traceability path as the starting place, search for the existing place as the starting point, and the transition containing the mark. If the end point of the transition is not the candidate defective device, then include the end point in the place set, traverse the transitions and places, and the searched place is the homologous device corresponding to the mark; Step 5: Search step 4 for different traceability status quantities in turn to obtain the same-source devices corresponding to the different traceability status quantities; Step 6: Retrieve the primary device of the alarm device, and then retrieve another secondary power device based on the correspondence between the primary device and the secondary power device to obtain the backup device of the alarm device; Step 7: Match the candidate defective devices, the homologous devices, and the mutually-backed devices with the devices in the defect diagnosis knowledge graph to determine the defect diagnosis device.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 7.

Images