Equipment fault analysis method and device, computer equipment and readable storage medium

Abstract

The invention relates to an equipment fault analysis method and device, computer equipment and a readable storage medium. The method comprises the following steps: constructing a structural modal map and a semantic modal map according to equipment identifiers, equipment icons and a physical connection relationship among equipment, obtaining equipment identifiers and fault phenomena of fault equipment, generating a fault propagation chain containing fault equipment nodes based on the equipment identifiers, the structural modal map and the semantic modal map of the fault equipment, and transmitting the fault propagation chain to the fault equipment. Determining a device priority processing sequence of each device node in the fault propagation chain, determining a fault reason from a historical case library based on the device identifier of the fault device and the fault phenomenon, and generating a fault processing suggestion of each device node in the fault propagation chain according to the device priority processing sequence and the fault reason; the fault positioning efficiency can be obviously improved, the maintenance resource scheduling is optimized, and the power system recovery time is shortened.

Description

Technical Field

[0001] The present application relates to the technical field of equipment failure analysis, and in particular to an equipment failure analysis method, apparatus, computer equipment, and readable storage medium. Background Art

[0002] As the core infrastructure of modern society, the stable operation of the power system is directly related to the sustainable development of the national economy and the normal order of people's lives. However, with the increasing scale and complexity of power grids, the frequency and scope of power system equipment failures have also increased significantly, posing severe challenges to the safe and stable operation of the power grid. In particular, when faced with sudden failures, how to quickly and accurately locate the cause of the failure and develop an effective response plan has become crucial to ensuring power grid security and reducing power outage losses. Summary of the Invention

[0003] Based on this, it is necessary to provide a device failure analysis method, device, computer device, computer-readable storage medium and computer program product that can quickly and accurately locate the cause of the failure of the faulty device in order to address the above technical problems.

[0004] In a first aspect, the present application provides a device failure analysis method, comprising:

[0005] Constructing a structural modal map and a semantic modal map based on device identifiers, device icons, and physical connection relationships between devices; the structural modal map represents the physical connection relationships between devices, and the semantic modal map represents the functional dependencies and logical relationships between devices;

[0006] Obtain the device identification and fault symptoms of the faulty device;

[0007] Generate a fault propagation chain based on the device identification of the faulty device, the structural modal graph, and the semantic modal graph; the fault propagation chain at least includes a faulty device node;

[0008] Determining a device priority handling sequence for each device node in the fault propagation chain;

[0009] Determine the cause of the fault from a historical case library based on the device identification and fault phenomenon of the faulty device;

[0010] Generate a fault handling suggestion for each device node in the fault propagation chain based on the device priority handling sequence and the fault cause.

[0011] In one embodiment, constructing a structural modal graph and a semantic modal graph based on device identifiers, device icons, and physical connection relationships between devices includes:

[0012] Generate a picture description text based on the device identifier, the device icon, and the physical connection relationship between the devices; the picture description text includes the device entity, device attributes, the physical connection relationship between the devices, and the functional dependency relationship;

[0013] The structural modal graph and the semantic modal graph are constructed based on the device entities, device attributes, physical connection relationships between devices, and functional dependencies in the image description text.

[0014] In one embodiment, generating image description text based on the device identifier, device icon, and physical connection relationship between devices includes:

[0015] Obtaining a device document including the device identifier, the device icon, and the physical connection relationship between the devices;

[0016] Based on a predefined industrial symbol library, detecting the device icon in the image in the device document to obtain a device icon recognition result; the icon recognition result includes the device entity and device attributes of each device;

[0017] Extracting the physical connection relationship between the devices in the device document, and obtaining a spatial connection relationship matrix between the device icons based on the physical connection relationship between the devices;

[0018] Based on the device icon recognition results and the spatial connection relationship matrix between the device icons, the functional dependency relationship between the device icons is determined to generate a device topology relationship set; the device topology relationship set includes the physical connection relationship and functional dependency relationship between the devices;

[0019] The device icon recognition result and the device topology relationship set are injected into a preset picture description text template to obtain the picture description text.

[0020] In one embodiment, constructing the structural modal graph and the semantic modal graph based on the device entities, device attributes, physical connection relationships between devices, and functional dependencies in the image description text includes:

[0021] Extracting the device entity, the device attributes, the physical connection relationship and the functional dependency relationship between the devices from the image description text;

[0022] The structural modal graph is constructed based on the device entity and the physical connection relationship; the structural modal graph uses the device entity as a node and the physical connection relationship as an edge, and associates the device attributes with the corresponding device entity nodes;

[0023] Constructing the semantic modal graph based on the device entity and the functional dependency relationship; the semantic modal graph uses the device entity as a node and the functional dependency relationship as an edge, and associates the device attributes with the corresponding device entity nodes;

[0024] A mapping relationship between the same device entity node in the structural modal graph and the semantic modal graph is established.

[0025] In one embodiment, generating a fault propagation chain based on the device identification of the faulty device, the structural modal graph, and the semantic modal graph includes:

[0026] Determining the faulty devices in the structural modal graph and the semantic modal graph based on the device identification;

[0027] In the structural modal graph, taking the device node of the faulty device as the source node, performing directed graph traversal along the direction of the physical connection edge, obtaining all reachable device nodes, and forming a first node set;

[0028] In the semantic modal graph, taking the device node of the faulty device as the source node, performing directed graph traversal along the direction of the functional dependency edge, obtaining all reachable device nodes, and forming a second node set;

[0029] Merging the first node set and the second node set to generate an initial propagation node set;

[0030] The device nodes in the initial propagation node set are sorted based on the depth of the nodes in the propagation path to generate the fault propagation chain.

[0031] In one embodiment, determining a device priority handling sequence for each device node in the fault propagation chain includes:

[0032] Obtaining the depth of each device node in the propagation path, the criticality of the fault type, and the device priority in the fault propagation chain;

[0033] A device priority handling sequence for each device node in the fault propagation chain is determined according to the depth of each device node in the propagation path, the criticality of the fault type, and the device priority.

[0034] In a second aspect, the present application further provides a device for analyzing equipment failures, comprising:

[0035] A graph construction module is used to construct a structural modal graph and a semantic modal graph based on device identifiers, device icons, and physical connection relationships between devices; the structural modal graph represents the physical connection relationships between devices, and the semantic modal graph represents the functional dependencies and logical relationships between devices;

[0036] Fault acquisition module, used to obtain the device identification and fault phenomenon of the faulty device;

[0037] A fault chain generation module is configured to generate a fault propagation chain based on the device identification of the faulty device, the structural modal graph, and the semantic modal graph; the fault propagation chain at least includes a faulty device node;

[0038] a sequence determination module, configured to determine a device priority handling sequence for each device node in the fault propagation chain;

[0039] A fault cause determination module is used to determine the fault cause from a historical case library based on the device identification and fault phenomenon of the faulty device;

[0040] The suggestion generation module is used to generate fault handling suggestions for each device node in the fault propagation chain according to the device priority handling sequence and the fault cause.

[0041] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0042] Constructing a structural modal map and a semantic modal map based on device identifiers, device icons, and physical connection relationships between devices; the structural modal map represents the physical connection relationships between devices, and the semantic modal map represents the functional dependencies and logical relationships between devices;

[0043] Obtain the device identification and fault symptoms of the faulty device;

[0044] Generate a fault propagation chain based on the device identification of the faulty device, the structural modal graph, and the semantic modal graph; the fault propagation chain at least includes a faulty device node;

[0045] Determining a device priority handling sequence for each device node in the fault propagation chain;

[0046] Determine the cause of the fault from a historical case library based on the device identification and fault phenomenon of the faulty device;

[0047] Generate a fault handling suggestion for each device node in the fault propagation chain based on the device priority handling sequence and the fault cause.

[0048] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0049] Constructing a structural modal map and a semantic modal map based on device identifiers, device icons, and physical connection relationships between devices; the structural modal map represents the physical connection relationships between devices, and the semantic modal map represents the functional dependencies and logical relationships between devices;

[0050] Obtain the device identification and fault symptoms of the faulty device;

[0051] Generate a fault propagation chain based on the device identification of the faulty device, the structural modal graph, and the semantic modal graph; the fault propagation chain at least includes a faulty device node;

[0052] Determining a device priority handling sequence for each device node in the fault propagation chain;

[0053] Determine the cause of the fault from a historical case library based on the device identification and fault phenomenon of the faulty device;

[0054] Generate a fault handling suggestion for each device node in the fault propagation chain based on the device priority handling sequence and the fault cause.

[0055] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0056] Constructing a structural modal map and a semantic modal map based on device identifiers, device icons, and physical connection relationships between devices; the structural modal map represents the physical connection relationships between devices, and the semantic modal map represents the functional dependencies and logical relationships between devices;

[0057] Obtain the device identification and fault symptoms of the faulty device;

[0058] Generate a fault propagation chain based on the device identification of the faulty device, the structural modal graph, and the semantic modal graph; the fault propagation chain at least includes a faulty device node;

[0059] Determining a device priority handling sequence for each device node in the fault propagation chain;

[0060] Determine the cause of the fault from a historical case library based on the device identification and fault phenomenon of the faulty device;

[0061] Generate a fault handling suggestion for each device node in the fault propagation chain based on the device priority handling sequence and the fault cause.

[0062] The above-mentioned equipment failure analysis method, device, computer equipment, computer-readable storage medium and computer program product construct structural modal maps and semantic modal maps by combining equipment identification, icons and physical connection relationships. The system integrates equipment identification, icons and physical connection relationships, and can automatically generate a propagation chain containing fault nodes based on the identification and phenomenon of the faulty equipment, and derive the priority handling sequence of each node based on this. At the same time, it combines the historical case library to accurately match the cause of the fault, and finally generates targeted processing suggestions for all equipment nodes in the propagation chain, thereby significantly improving fault location efficiency, optimizing maintenance resource scheduling, shortening system recovery time, and enhancing the integrity, accuracy and intelligence level of fault diagnosis and handling of complex equipment systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0064] Figure 1 This is an application environment diagram of a device failure analysis method in one embodiment;

[0065] Figure 2 1 is a flow chart of a method for analyzing equipment failure in one embodiment;

[0066] Figure 3 is a schematic diagram of a structural modal spectrum in one embodiment;

[0067] Figure 4 is a schematic diagram of a semantic modal graph in one embodiment;

[0068] Figure 5 Schematic diagram of a flow chart of a method for constructing a map in one embodiment;

[0069] Figure 6 Schematic diagram of a flow chart of a method for generating picture description text in one embodiment;

[0070] Figure 7 A schematic diagram of a flow chart of a method for constructing a map in another embodiment;

[0071] Figure 8 1 is a flow chart of a method for generating a fault propagation chain in one embodiment;

[0072] Figure 9 is a schematic diagram of a structural modal graph and a semantic modal graph in one embodiment;

[0073] Figure 10is a structural block diagram of a device failure analysis apparatus in one embodiment;

[0074] Figure 11 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0076] It should be noted that the terms "first", "second", etc. used in this application may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "including" and "having" used in this application and any variations thereof are intended to cover non-exclusive inclusions. The term "plurality" used in this application refers to two or more. The term "and / or" used in this application refers to one of the solutions or any combination of multiple solutions.

[0077] The device failure analysis method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. The terminal 102 communicates with the server 104 through the network. The data storage system can store data that the server 104 needs to process, such as a historical case library, a structural modal map, a semantic modal map, etc. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, drones, low-altitude aircraft and Internet of Things devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection equipment, etc. The server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0078] Terminal 102 can obtain device identifiers, device icons, and physical connections between devices to construct a structural modal graph representing the physical connections between the devices and a semantic modal graph representing the functional dependencies and logical relationships between the devices. Terminal 102 can also obtain the device identifier and fault symptoms of the faulty device. Based on the obtained faulty device identifier, the constructed structural modal graph, and the semantic modal graph, Terminal 102 generates a fault propagation chain that includes at least the faulty device node. Terminal 102 determines a device priority handling sequence for each device node in the fault propagation chain. Based on the device identifier and fault symptoms of the faulty device, Terminal 102 determines the cause of the fault from a historical case library in a data storage system. Finally, based on the determined device priority handling sequence and the matched fault cause, Terminal 102 generates fault handling suggestions for each device node in the fault propagation chain and outputs the fault handling suggestions for the user's reference and implementation.

[0079] In an exemplary embodiment, Figure 2 As shown, a device failure analysis method is provided, which is applied to Figure 1 The terminal in FIG is taken as an example to illustrate the method, including the following steps 201 to 206. Among them:

[0080] Step 201: construct a structural modal graph and a semantic modal graph based on device identification, device icons, and physical connection relationships between devices.

[0081] Among them, the device identifier is the unique identifier of the device, which is the basis for constructing the structural modal map and the semantic modal map, and is used to accurately distinguish and locate each device entity in the map; for example, the device identifier can be but is not limited to the device identifier (Device Identifier, ID), or the unique code assigned within the system (DEV-Controller-001).

[0082] Device icons are graphical symbols that represent device types or functions. They are used to intuitively express the role and category of devices in the system, helping to quickly understand and visualize the map; for example, Represents a substation, stands for Small Hub, Represents the transformer, Represents a circuit breaker.

[0083] The physical connection relationship between devices is used to describe the direct connection relationship between devices through physical media (such as wires, cables, pipes, and buses). It is the core input for constructing structural modal diagrams. For example, the output port 1 of the Programmable Logic Controller (PLC) is connected to the control terminal of the valve through a cable, or the temperature sensor is connected to the data acquisition module through the RS485 (serial communication standard) bus.

[0084] A structural modal diagram is a diagram constructed based on device identifiers, device icons, and the physical connections between devices. Essentially a physical topology diagram, it clearly illustrates the physical connections between devices, reflecting their physical structure and connection methods. For example, a device node in a structural modal diagram represents a device with a device ID and icon. Edges between nodes represent physical connections, such as network cables and electrical cables. Edge labels can include information about the connection port.

[0085] Semantic modal graphs are used to describe the functional dependencies and logical relationships between devices, such as protection actions, power transmission paths, and cascading effects. They reflect the functional logical architecture between devices. For example, a transmission line provides power to substation B (functional dependency), while a relay protection device controls the opening of a circuit breaker (logical control). A transmission line fault triggers a protection action. If the circuit breaker fails to operate, it will cause a voltage loss in substation A (cascading effect).

[0086] Figure 3 FIG. 1 is a schematic diagram of a structural modal map in an embodiment. In one embodiment, the structural modal map constructed based on the device identification, device icon and the physical connection relationship between devices can be as follows: Figure 3 As shown, the 220 kilovolt (kV) busbar of substation A is connected to the transmission line through a circuit breaker and to the main transformer. Figure 4 FIG is a schematic diagram of a semantic modal graph in one embodiment. The semantic modal graph constructed based on device identification, device icons and physical connection relationships between devices can be as follows: Figure 4 As shown, the transmission line provides power to substation A (functional dependence), the relay protection device controls the opening action of the circuit breaker (logic control), and the transmission line fault triggers the protection action. If the circuit breaker fails to operate, it will cause substation B to lose voltage (cascading effect).

[0087] In the above embodiment, a structural modal map based on physical connection and a semantic modal map based on functional dependency are constructed respectively through device identification, device icon and physical connection relationship between devices, thereby realizing deep coupling of physical topology and functional logic, thereby significantly improving fault location accuracy, risk prediction capability and targeted handling suggestions.

[0088] Step 202: Obtain the device identification and fault symptoms of the faulty device;

[0089] A faulty device is a specific device experiencing an anomaly, which can be precisely located using a unique identifier (ID). Fault symptoms are observable characteristics of the device's anomaly, including alarm signals, performance deviations, or physical conditions. For example, an abnormal electrical quantity in the device might include: a short-circuit current continuously exceeding the rated value of 45 kiloamperes (kA), or a mechanical circuit breaker refusing to operate (the opening command is not executed).

[0090] In one embodiment, a short circuit fault on a 220kV transmission line causes an alarm at substation A. The device identifier and fault phenomenon of the faulty device are extracted from the system alarm information, and the fault phenomenon is collected in real time to monitor fault data, such as current value, circuit breaker status, and protection device action records.

[0091] In the above embodiment, by accurately obtaining the unique identification of the faulty equipment and multi-dimensional fault phenomena, such as electrical parameter out-of-limit, mechanical state abnormality, and protection action logic conflict, a high-confidence input source is provided for subsequent graph analysis, significantly improving the targetedness and response speed of fault diagnosis, and at the same time supporting the system to automatically associate historical case libraries to match similar fault phenomena.

[0092] Step 203: Generate a fault propagation chain based on the device identification, structural modal graph, and semantic modal graph of the faulty device.

[0093] Among them, the fault propagation chain represents the path sequence that may affect other related devices or system components through the physical connections or functional dependencies between devices, starting from the faulty device as the source node. It is a directed graph or ordered list that clearly shows how the fault "propagates" or "cascades".

[0094] In one embodiment, the device identification of the faulty device can be used to determine other device nodes that may be affected by the fault through physical connection relationships in the structural modal graph. The device identification of the faulty device can also be used to determine other device nodes that may be affected by the fault through functional dependencies in the semantic modal graph. These other device nodes can be combined to obtain a fault propagation chain. For example, the fault propagation chain generated based on the device identification of the circuit breaker, the fault propagation chain in the structural modal graph, and the fault propagation chain in the semantic modal graph can be:

[0095] Circuit breaker CB-001 (circuit breaker refuses to operate)

[0096] [Physical Conduction] 220kV busbar (voltage fluctuation)

[0097] [Function dependency] Main transformer-01 (overload)

[0098] [Cascading impact] 10kV distribution line (voltage loss)

[0099] Among them, "CB-001" is the device identification of the circuit breaker.

[0100] In the above embodiment, by fusing the structural modal graph and the semantic modal graph, a multi-level propagation chain starting from the faulty device is automatically generated, accurately revealing the fault's conduction path and cascade impact range in the system.

[0101] Step 204, determining a device priority handling sequence for each device node in the fault propagation chain;

[0102] The device priority handling sequence is a list of device nodes in the fault propagation chain ranked by urgency, which determines the order in which the device nodes are handled. For example, the device priority handling sequence can be determined based on the propagation depth of the device nodes in the fault propagation chain or the criticality of the fault type.

[0103] In the above embodiment, by determining the device priority handling sequence of each device node in the fault propagation chain, the theoretical propagation chain is converted into an executable priority handling sequence, which completely solves the blindness problem of empirical sorting in traditional fault handling.

[0104] Step 205 : Based on the device identification and the fault phenomenon of the faulty device, determine the cause of the fault from the historical case library.

[0105] Among them, the historical case library is a structured storage fault database, including data such as equipment identification, historical fault phenomena, and verified fault causes.

[0106] For example, the terminal detects that the substation circuit breaker CB-001 fails to operate, accompanied by overcurrent protection. The historical fault records of the circuit breaker are queried from the historical case library using the device identifier "ID=CB-001". One of the historical fault records is:

[0107] Historical case phenomenon: refusal to operate + current 40kA + overcurrent stage I action;

[0108] Match degree: 92%;

[0109] Cause of failure: Control circuit disconnection.

[0110] Therefore, based on the historical fault record, the fault cause of the circuit breaker CB-001 can be determined as a control circuit disconnection.

[0111] In the above embodiment, by accurately matching the historical case library and intelligently associating the current fault phenomenon with the verified root cause, multi-dimensional matching of thousands of cases can be quickly completed, greatly shortening the fault analysis time, and providing an irreplaceable decision-making basis for the handling suggestions of subsequent steps.

[0112] Step 206: Generate fault handling suggestions for each device node in the fault propagation chain based on the device priority handling sequence and the fault cause.

[0113] Among them, the fault handling suggestion is an executable operation suggestion generated for each device node in the fault propagation chain. The circuit maintenance personnel determine whether the executable operation suggestion needs to be executed.

[0114] For example, the terminal can output fault handling suggestions for each device node in the fault propagation chain based on the device priority handling sequence. The fault handling suggestions are generated based on the cause of the fault. For example, if the fault cause is: the operating mechanism is stuck, the fault handling suggestions can be:

[0115] Immediate action: cut off power and isolate (execute within 5 minutes);

[0116] Fundamental treatment: dismantle and remove dust from the mechanism;

[0117] Preventive measures: Install dust cover (complete within 48 hours).

[0118] In the above embodiment, by combining the device priority handling sequence and the cause of the fault, quantifiable, traceable, time-sharing and graded multi-device node handling suggestions are generated, thereby shortening the fault repair time.

[0119] The above-mentioned equipment fault analysis method constructs a structural modal map and a semantic modal map based on the equipment identification, equipment icon, and physical connection relationships between devices, obtains the equipment identification and fault phenomenon of the faulty equipment, generates a fault propagation chain including the faulty equipment node based on the equipment identification, structural modal map, and semantic modal map of the faulty equipment, and determines the equipment priority treatment sequence for each equipment node in the fault propagation chain. Based on the equipment identification and fault phenomenon of the faulty equipment, the fault cause is determined from the historical case library. Based on the equipment priority treatment sequence and the fault cause, fault handling suggestions are generated for each equipment node in the fault propagation chain. By combining the equipment identification, icon, and physical connection relationships to construct a structural modal map and a semantic modal map, the system integrates the equipment identification, icon, and physical connection relationships, and can automatically generate a propagation chain including the fault node based on the identification and phenomenon of the faulty equipment, and derive the priority treatment sequence for each node based on this. At the same time, the historical case library is used to accurately match the fault cause, and ultimately generate targeted treatment suggestions for all equipment nodes in the propagation chain, thereby significantly improving fault location efficiency, optimizing maintenance resource scheduling, shortening system recovery time, and enhancing the integrity, accuracy, and intelligence of fault diagnosis and treatment for complex equipment systems.

[0120] In an exemplary embodiment, Figure 5 A schematic diagram of a method for constructing a map in one embodiment is shown. Figure 2 The sub-steps of step 201 in FIG. Figure 5 The graph construction method shown in the figure involves constructing a structural modal graph and a specific implementation of the semantic modal graph. Figure 2 Based on the embodiment shown, for details not described in this embodiment, please refer to Figure 2 The method is applied to Figure 1 The application environment in FIG is used as an example to illustrate the process, including the following steps 2011 to 2012. Among them:

[0121] Step 2011: Generate image description text based on device identification, device icon, and physical connection relationship between devices.

[0122] The image description text contains key information such as device entities, device attributes, physical connections between devices, and functional dependencies. The image description text converts this key information into a structured natural language description. For example, the image description text can include:

[0123] Device entity: device ID and device type;

[0124] Equipment attributes: technical parameters, status, etc.;

[0125] Physical connection relationship: the connection between devices through physical media such as wires and busbars;

[0126] Functional dependency: semantic associations such as control logic, energy transmission, and protection actions between devices.

[0127] In an exemplary embodiment, step 2011 may further include the following sub-steps: Figure 6 As shown, Figure 6 Schematic diagram of a flow chart of a method for generating picture description text in one embodiment;

[0128] Step 20111: Obtain device documents including device identification, device icons, and physical connection relationships between devices.

[0129] Equipment documents include equipment layout diagrams and wiring diagrams, such as computer-aided design (CAD) drawings, SCADA (Supervisory Control and Data Acquisition) system screenshots, and substation design drawings.

[0130] In one embodiment, a 220 kV substation design drawing in CAD format may be obtained through a terminal as equipment documentation.

[0131] Step 20112: Based on the predefined industrial symbol library, detect the device icon in the image in the device document to obtain the device icon recognition result.

[0132] Among them, the predefined industrial symbol library is a standardized icon database used to match the equipment symbols in equipment document drawings; for example, the graphic symbols for electrical technical drawings (IEC 60617) or the graphic symbols for electrical schematics (GB / T 4728). IEC 60617 is an international standard developed by the International Electrotechnical Commission, which specifies the graphic symbols used in electrical diagrams and provides a common electrical drawing language for the electrical engineering field; the GB / T 4728 standard specifies the symbols for electrical design in major fields such as machinery, electricity, and construction. It is divided into 13 parts and covers a comprehensive range of content from basic symbols to complex symbols.

[0133] The icon recognition result is a list of devices identified from the device document drawings, which may include device entities (device ID, device type) and device attributes (device parameters).

[0134] In one embodiment, a 220kV substation design drawing in CAD format can be obtained through a terminal, and based on the GB / T4728 standard, a device icon recognition result of the drawing can be identified. The device icon recognition result includes a correspondence between the device icon and the device ID\device attributes, and the device icon recognition result is output in the form of a device list.

[0135] Step 20113: extract the physical connection relationships between devices in the device document, and obtain a spatial connection relationship matrix between device icons based on the physical connection relationships between the devices;

[0136] The spatial connection relationship matrix is ​​a matrix that represents the physical connection positions between devices. The matrix element value = 1 represents a connection, such as terminal A → terminal B. “→” represents the direction of current, which here means that the current flows from terminal A to terminal B.

[0137] In one embodiment, the physical connection relationship between devices in the device document extracted by the terminal is:

[0138] Substation A (port P1) → circuit breaker A (port IN);

[0139] Circuit breaker A (port OUT) → transmission line.

[0140] The spatial connection relationship matrix of the above physical connection relationship can be expressed as:

[0141] Substation A Circuit breaker A Substation A 0 1 (P1→IN) Circuit breaker A 1 (IN←P1) 0

[0142] Among them, the matrix element value = 1 indicates connection, and the matrix element value = 0 indicates disconnection.

[0143] Step 20114: Based on the device icon recognition results and the spatial connection relationship matrix between the device icons, the functional dependency relationship between the device icons is determined, and a device topology relationship set is generated.

[0144] Among them, the device topology relationship set is a structured data set that integrates the physical connection relationship and functional dependency relationship between devices.

[0145] In one embodiment, a device topology relationship set in the form of a triple can be generated; for example, a physical connection relationship: {source device {}, target device {}, physical connection relationship {}}; wherein the physical connection relationship {} represents the physical connection relationship between the source device and the target device; a functional dependency relationship: {source device {}, target device {}, functional dependency relationship {}}; wherein the functional dependency relationship {} represents the functional dependency relationship between the source device and the target device.

[0146] Step 20115: inject the device icon recognition result and the device topology relationship set into the preset image description text template to obtain the image description text.

[0147] The preset image description text template is a predefined structured text generation framework that includes placeholders, such as ${device list}.

[0148] In one embodiment, the image description text may be as follows:

[0149] Drawing recognition results: ${count} devices in total.

[0150] Equipment List:

[0151] ${Device ID}:${Device Attributes}

[0152] Topological relationship:

[0153] Physical connection relationship: ${source device} is connected to ${target device} through ${interface}

[0154] Functional dependency: ${source device} ${relationship} ${target device}

[0155] Among them, {count} represents the quantity and $ is a placeholder.

[0156] In the above embodiment, by automatically parsing the industrial standard symbols in the device documents, the device icons, physical connections and functional dependencies in the device document drawings are converted into structured picture description text, which significantly improves the efficiency of drawing information extraction and avoids manual reading errors; the generated picture description text deeply integrates the device entity attributes, spatial connection matrix and topological semantic relationships, providing a parsable semantic basis for subsequent fault diagnosis.

[0157] Step 2012: construct a structural modal graph and a semantic modal graph based on the device entities, device attributes, physical connection relationships between devices, and functional dependencies in the image description text.

[0158] A device entity is a physical unit with independent functionality within the power grid system. It serves as the core node of the graph and must include a unique identifier (ID) and type classification. For example, the device ID is CB_Line1_SubA, and the device type is circuit breaker. The entity serves as a node in the structural modal graph and carries functional logic in the semantic modal graph. Device attributes describe key characteristic values ​​of the device's technical parameters or operating status, determining its behavior during fault propagation. For example, rated voltage: 220kV characterizes the device's insulation withstand capability.

[0159] In an exemplary embodiment, step 2012 may further include the following sub-steps: Figure 7 As shown, Figure 7 A schematic diagram of a flow chart of a method for constructing a map in another embodiment:

[0160] Step 20121, extract device entities, device attributes, physical connection relationships between devices, and functional dependencies from the image description text.

[0161] In one embodiment, the picture description text obtained in the above step 20115 can be directly input through the terminal, and the device entity, device attributes, physical connection relationship between devices and functional dependency relationship can be extracted from the picture description text.

[0162] Step 20122: Construct a structural modal graph based on the device entity and physical connection relationship.

[0163] The structural modal graph uses the device entity as the node and the physical connection relationship as the edge, and associates the device attributes with the corresponding device entity nodes. Figure 3 As shown, the 220 kilovolt (kV) busbar of substation A is connected to the transmission line through a circuit breaker and to the main transformer.

[0164] Step 20123, construct a semantic modal graph based on device entities and functional dependencies.

[0165] The semantic modal graph uses device entities as nodes and functional dependencies as edges, and associates device attributes with corresponding device entity nodes. Figure 4 As shown, the transmission line provides power to substation A (functional dependence), the relay protection device controls the opening action of the circuit breaker (logic control), and the transmission line fault triggers the protection action. If the circuit breaker fails to operate, it will cause substation B to lose voltage (cascading effect).

[0166] Step 20124: Establish a mapping relationship between the same device entity nodes in the structural modal graph and the semantic modal graph.

[0167] Among them, the mapping relationship of the physical nodes of the same device is in the structural modal graph and the semantic modal graph. The nodes of the same physical device establish a bidirectional link through a unique ID to ensure the precise association between the physical topology and the functional logic.

[0168] In one embodiment, when performing fault analysis, the server can jump between the structural modal map and the semantic modal map through the device ID, locate its physical position through the structural modal map, such as connecting to the substation A bus; and obtain its functional role through the semantic modal map, such as being controlled by a protection device.

[0169] In the above embodiment, by accurately extracting device entities, attributes, physical connection relationships and functional dependencies from the image description text, a structural modal graph with physical connections as the link and a semantic modal graph with functional dependencies as the core are constructed respectively, and a bidirectional mapping relationship between device nodes in the two graphs is established to achieve deep coupling of physical topology and functional logic. Therefore, during fault diagnosis, the spatial location of the device (such as the physical deployment of the circuit breaker in the substation) and the functional behavior (such as the action constraints of the protection device) can be dynamically associated, significantly improving the fault location accuracy, risk prediction capabilities and the pertinence of disposal suggestions, while supporting real-time synchronization and collaborative analysis of data between graphs.

[0170] In an exemplary embodiment, Figure 8 A flowchart of a method for generating a fault propagation chain in one embodiment is shown in FIG. Figure 2 The sub-steps of step 203. Figure 8 The method for generating a fault propagation chain shown in the figure relates to a specific implementation method of generating a fault propagation chain based on the device identification, structural modal map and semantic modal map of the faulty device. Figure 2 Based on the embodiment shown, for details not described in this embodiment, please refer to Figure 2 The method is applied to Figure 1 The application environment in FIG. 1 is taken as an example to illustrate the method, which includes the following steps 2031 to 2034. Among them:

[0171] Step 2031: Determine the faulty devices in the structural modal graph and the semantic modal graph based on the device identification.

[0172] For example, the faulty device in the structural modal map can be accurately located according to the device identification, and the faulty device in the semantic modal map can be accurately located according to the device identification.

[0173] In one embodiment, Figure 9 As shown, Figure 9 is a schematic diagram of a structural modal graph and a semantic modal graph in one embodiment; Figure 9 (a) is a schematic diagram of a structural modal spectrum in one embodiment, Figure 9 In (a), the transmission line is connected to the circuit breaker CB-001 via a cable. The circuit breaker CB-001 is connected to the 220 kV busbar via a busbar. The 220 kV busbar is connected to the main transformer-01 via a transformer. The main transformer-01 is connected to the 10 kV distribution line via a feeder. "CB-001" is the device identifier of the circuit breaker.

[0174] Figure 9 (b) is a schematic diagram of a semantic modality graph in one embodiment, Figure 9 In (b), the functional dependency between the transmission line and the 220KV busbar is: power supply dependency; the functional dependency between the relay protection device and the circuit breaker CB-001 is: tripping control; the functional dependency between the action "circuit breaker CB-001 refuses to operate" and the action "main transformer-01 overload" is: cascade effect; the functional dependency between the action "main transformer-01 overload" and the action "10KV distribution line loss of voltage" is: result.

[0175] exist Figure 9 In (a), assuming that the circuit breaker CB-001 is the faulty device, the faulty device is located in the structural modal spectrum by the device identifier "CB-001", and Figure 9 In (b), the faulty device is located in the semantic modal graph by the device identifier “CB-001”.

[0176] Step 2032: In the structural modal graph, with the device node of the faulty device as the source node, perform a directed graph traversal along the direction of the physical connection edge to obtain all reachable device nodes to form a first node set.

[0177] The reachable device nodes are all device nodes affected by the fault, with the faulty device as the source node in the structural modal graph; the first node set is the set of the faulty device node and all reachable device nodes of the faulty device node.

[0178] Continue reading Figure 9 (a) Assuming that circuit breaker CB-001 is the faulty device and serves as the source node, after circuit breaker CB-001 fails, a directed graph traversal along the physical connection edges in the structural modal graph reveals the following fault propagation chain: the fault current is transmitted through circuit breaker CB-001 to the 220kV busbar, and then to the main transformer-01. The reachable device nodes include: 220kV busbar, main transformer-01. Therefore, the first node set includes the "circuit breaker CB-001" node, the "220kV busbar" node, and the "main transformer-01" node.

[0179] Step 2033: In the semantic modal graph, with the device node of the faulty device as the source node, perform a directed graph traversal along the direction of the functional dependency edge to obtain all reachable device nodes to form a second node set.

[0180] The reachable device nodes are all device nodes affected by the fault, with the faulty device as the source node in the semantic modal graph; the second node set is the set of the faulty device node and all reachable device nodes of the faulty device node.

[0181] Continue reading Figure 9 (b) Take circuit breaker CB-001 as the faulty device and the source node. After circuit breaker CB-001 fails, a directed graph traversal along the functional dependency edge in the semantic modal graph reveals the fault propagation chain in the semantic modal graph: because circuit breaker CB-001 refuses to operate, the relay protection cannot isolate the fault, triggering a cascade action; and the main transformer-01 is subjected to abnormal current, resulting in overload, which ultimately causes the 10kV distribution line to lose voltage; the reachable device nodes include: main transformer-01, 10kV distribution line; therefore, the second node set includes the "circuit breaker CB-001" node, the "main transformer-01" node, and the "10kV distribution line" node.

[0182] Step 2034: merge the first node set and the second node set to generate an initial propagation node set.

[0183] The initial propagation node set is the union of the first node set and the second node set.

[0184] For example, the first node set includes the "Circuit Breaker CB-001" node, the "220kV Busbar" node, and the "Main Transformer-01" node; the second node set includes the "Circuit Breaker CB-001" node, the "Main Transformer-01" node, and the "10kV Distribution Line" node. The initial propagation node set generated by merging the first and second node sets includes the "Circuit Breaker CB-001" node, the "220kV Busbar" node, the "Main Transformer-01" node, and the "10kV Distribution Line" node.

[0185] Step 2035 : sort the device nodes in the initial propagation node set based on the depth of the nodes in the propagation path to generate a fault propagation chain.

[0186] The depth of a node in the propagation path refers to the number of steps in the shortest path from the fault source node (depth = 0) to the target node through the physical connection edge (structural modal graph) or functional dependency edge (semantic modal graph).

[0187] For example, Figure 9 In (a), the depth of circuit breaker CB-001 = 0, the depth of 220kV busbar = 1, and the depth of main transformer-01 = 2.

[0188] In an exemplary embodiment, the depth of 0-1 is directly related equipment, such as circuit breaker CB-001 and 220kV busbar, which requires immediate treatment to block the spread of the fault; the depth greater than or equal to 2 is secondary impact equipment, such as main transformer-01 and 10kV distribution line, which requires predictive monitoring to prevent cascading failure.

[0189] In an exemplary embodiment, the device nodes in the fault propagation chain may be sorted in ascending order of propagation depth to obtain the fault propagation chain.

[0190] In the above embodiment, the fault propagation chain sorted by propagation depth reveals the temporal sequence and diffusion path of the fault impact, providing a quantitative basis for the handling priority of subsequent steps. The smaller the depth value, the higher the priority, which can avoid blind maintenance.

[0191] In an exemplary embodiment, the device priority handling sequence for each device node in the fault propagation chain determined in step 204 may include the following:

[0192] In one embodiment, the device priority handling sequence may be determined based on the depth of each device node in the fault propagation chain in the propagation path; for example, the smaller the depth value, the higher the priority.

[0193] In one embodiment, the device priority handling sequence can be determined based on the fault type criticality of each device node in the fault propagation chain; for example, the priority of short circuit is higher than overload, and the priority of overload is higher than alarm, that is, short circuit > overload > alarm.

[0194] In one embodiment, the device priority handling sequence can be determined based on the device priority of each device node in the fault propagation chain; for example, the priority of the protection device is higher than that of the transmission device, and the priority of the transmission device is higher than that of the distribution device, that is, the protection device>transmission device>distribution equipment.

[0195] In another exemplary embodiment, the device priority handling sequence of each device node in the fault propagation chain is determined based on the depth of each device node in the propagation path, the fault type criticality and the device priority of each device node in the fault propagation chain, different weights are defined for the depth, fault type criticality and device priority, and the urgency ranking value of each device node in the fault propagation chain is calculated. Finally, the device priority handling sequence of each device node in the fault propagation chain is determined according to the size of the urgency ranking value.

[0196] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps. It is understandable that the various steps in different embodiments can be freely combined as needed, and the various non-contradictory schemes formed by the combination all fall within the scope of protection of this application.

[0197] Based on the same inventive concept, embodiments of the present application also provide a device failure analysis apparatus for implementing the aforementioned device failure analysis method. The solution provided by this apparatus is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more embodiments of the device failure analysis apparatus provided below can be found in the limitations of the device failure analysis method described above and will not be further elaborated here.

[0198] In an exemplary embodiment, Figure 10 As shown, a device failure analysis apparatus 1000 is provided, comprising: a graph construction module 1001, a failure acquisition module 1002, a failure chain generation module 1003, a sequence determination module 1004, a failure cause determination module 1005, and a suggestion generation module 1006, wherein:

[0199] A graph construction module 1001 is configured to construct a structural modal graph and a semantic modal graph based on device identifiers, device icons, and physical connection relationships between devices; the structural modal graph represents the physical connection relationships between devices, and the semantic modal graph represents the functional dependencies and logical relationships between devices;

[0200] The fault acquisition module 1002 is used to obtain the device identification and fault phenomenon of the faulty device;

[0201] A fault chain generation module 1003 is configured to generate a fault propagation chain based on the device identification of the faulty device, the structural modal graph, and the semantic modal graph; the fault propagation chain at least includes a faulty device node;

[0202] A sequence determination module 1004 is configured to determine a device priority handling sequence for each device node in the fault propagation chain;

[0203] A fault cause determination module 1005 is configured to determine the fault cause from a historical case library based on the device identification and fault phenomenon of the faulty device;

[0204] The suggestion generating module 1006 is configured to generate a fault handling suggestion for each device node in the fault propagation chain according to the device priority handling sequence and the fault cause.

[0205] In the above-mentioned standby fault analysis device, the graph construction module 1001 constructs a structural modal graph and a semantic modal graph by combining equipment identification, icons and physical connection relationships. The fault chain generation module 1003 systematically integrates equipment identification, icons and physical connection relationships. The sequence determination module 1004 can automatically generate a propagation chain containing fault nodes based on the identification and phenomenon of the faulty equipment. The fault cause determination module 1005 derives the priority handling sequence of each node based on this, and at the same time combines the historical case library to accurately match the fault cause. Finally, the suggestion generation module 1006 generates targeted processing suggestions for all equipment nodes in the propagation chain, thereby significantly improving the efficiency of fault location, optimizing maintenance resource scheduling, shortening system recovery time, and enhancing the integrity, accuracy and intelligence level of fault diagnosis and treatment of complex equipment systems.

[0206] In one embodiment, the graph construction module 1001 is further configured to generate a picture description text based on the device identifier, the device icon, and the physical connection relationship between the devices; the picture description text includes the device entity, device attributes, the physical connection relationship between the devices, and the functional dependency relationship;

[0207] The structural modal graph and the semantic modal graph are constructed based on the device entities, device attributes, physical connection relationships between devices, and functional dependencies in the image description text.

[0208] In one embodiment, the graph construction module 1001 is further configured to obtain a device document including the device identifier, the device icon, and the physical connection relationship between the devices;

[0209] Based on a predefined industrial symbol library, detecting the device icon in the image in the device document to obtain a device icon recognition result; the icon recognition result includes the device entity and device attributes of each device;

[0210] Extracting the physical connection relationship between the devices in the device document, and obtaining a spatial connection relationship matrix between the device icons based on the physical connection relationship between the devices;

[0211] Based on the device icon recognition results and the spatial connection relationship matrix between the device icons, the functional dependency relationship between the device icons is determined to generate a device topology relationship set; the device topology relationship set includes the physical connection relationship and functional dependency relationship between the devices;

[0212] The device icon recognition result and the device topology relationship set are injected into a preset picture description text template to obtain the picture description text.

[0213] In one embodiment, the graph construction module 1001 is further configured to extract the device entity, the device attributes, the physical connection relationship between the devices, and the functional dependency relationship from the image description text;

[0214] The structural modal graph is constructed based on the device entity and the physical connection relationship; the structural modal graph uses the device entity as a node and the physical connection relationship as an edge, and associates the device attributes with the corresponding device entity nodes;

[0215] Constructing the semantic modal graph based on the device entity and the functional dependency relationship; the semantic modal graph uses the device entity as a node and the functional dependency relationship as an edge, and associates the device attributes with the corresponding device entity nodes;

[0216] A mapping relationship between the same device entity node in the structural modal graph and the semantic modal graph is established.

[0217] In one embodiment, the fault chain generation module 1003 is further configured to determine the faulty devices in the structural modal graph and the semantic modal graph based on the device identifier;

[0218] In the structural modal graph, taking the device node of the faulty device as the source node, performing directed graph traversal along the direction of the physical connection edge, obtaining all reachable device nodes, and forming a first node set;

[0219] In the semantic modal graph, taking the device node of the faulty device as the source node, performing directed graph traversal along the direction of the functional dependency edge, obtaining all reachable device nodes, and forming a second node set;

[0220] Merging the first node set and the second node set to generate an initial propagation node set;

[0221] The device nodes in the initial propagation node set are sorted based on the depth of the nodes in the propagation path to generate the fault propagation chain.

[0222] In one embodiment, the sequence determination module 1004 is further configured to obtain the depth of each device node in the fault propagation chain in the propagation path, the criticality of the fault type, and the device priority;

[0223] A device priority handling sequence for each device node in the fault propagation chain is determined according to the depth of each device node in the propagation path, the criticality of the fault type, and the device priority.

[0224] Each module in the above-mentioned device failure analysis device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0225] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 11 As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, and the wireless means can be implemented via Wi-Fi, mobile cellular networks, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for analyzing equipment failures. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0226] Those skilled in the art will understand that Figure 11The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0227] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0228] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0229] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0230] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0231] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0232] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for analyzing equipment failure, characterized in that: The method comprises: Constructing a structural modal map and a semantic modal map based on device identifiers, device icons, and physical connection relationships between devices; the structural modal map represents the physical connection relationships between devices, and the semantic modal map represents the functional dependencies and logical relationships between devices; Obtain the device identification and fault symptoms of the faulty device; Generate a fault propagation chain based on the device identification of the faulty device, the structural modal graph, and the semantic modal graph; the fault propagation chain at least includes a faulty device node; Determining a device priority handling sequence for each device node in the fault propagation chain; Determine the cause of the fault from a historical case library based on the device identification and fault phenomenon of the faulty device; Generate a fault handling suggestion for each device node in the fault propagation chain based on the device priority handling sequence and the fault cause.

2. The method according to claim 1, characterized in that The construction of the structural modal graph and the semantic modal graph based on the device identification, device icon and the physical connection relationship between the devices includes: Generate a picture description text based on the device identifier, the device icon, and the physical connection relationship between the devices; the picture description text includes the device entity, device attributes, the physical connection relationship between the devices, and the functional dependency relationship; The structural modal graph and the semantic modal graph are constructed based on the device entities, device attributes, physical connection relationships between devices, and functional dependencies in the image description text.

3. The method according to claim 2, characterized in that Generating picture description text according to the device identification, device icon and physical connection relationship between devices includes: Obtaining a device document including the device identifier, the device icon, and the physical connection relationship between the devices; Based on a predefined industrial symbol library, detecting the device icon in the image in the device document to obtain a device icon recognition result; the icon recognition result includes the device entity and device attributes of each device; Extracting the physical connection relationship between the devices in the device document, and obtaining a spatial connection relationship matrix between the device icons based on the physical connection relationship between the devices; Based on the device icon recognition results and the spatial connection relationship matrix between the device icons, the functional dependency relationship between the device icons is determined to generate a device topology relationship set; the device topology relationship set includes the physical connection relationship and functional dependency relationship between the devices; The device icon recognition result and the device topology relationship set are injected into a preset picture description text template to obtain the picture description text.

4. The method according to claim 2, characterized in that The constructing of the structural modal graph and the semantic modal graph based on the device entities, device attributes, physical connection relationships between devices, and functional dependencies in the image description text includes: Extracting the device entity, the device attributes, the physical connection relationship and the functional dependency relationship between the devices from the image description text; The structural modal graph is constructed based on the device entity and the physical connection relationship; the structural modal graph uses the device entity as a node and the physical connection relationship as an edge, and associates the device attributes with the corresponding device entity nodes; Constructing the semantic modal graph based on the device entity and the functional dependency relationship; the semantic modal graph uses the device entity as a node and the functional dependency relationship as an edge, and associates the device attributes with the corresponding device entity nodes; A mapping relationship between the same device entity node in the structural modal graph and the semantic modal graph is established.

5. The method according to claim 1, wherein The generating of a fault propagation chain based on the device identification of the faulty device, the structural modal graph, and the semantic modal graph includes: Determining the faulty devices in the structural modal graph and the semantic modal graph based on the device identification; In the structural modal graph, taking the device node of the faulty device as the source node, performing directed graph traversal along the direction of the physical connection edge, obtaining all reachable device nodes, and forming a first node set; In the semantic modal graph, taking the device node of the faulty device as the source node, performing directed graph traversal along the direction of the functional dependency edge, obtaining all reachable device nodes, and forming a second node set; Merging the first node set and the second node set to generate an initial propagation node set; The device nodes in the initial propagation node set are sorted based on the depth of the nodes in the propagation path to generate the fault propagation chain.

6. The method according to claim 1, characterized in that Determining a device priority handling sequence for each device node in the fault propagation chain includes: Obtaining the depth of each device node in the propagation path, the criticality of the fault type, and the device priority in the fault propagation chain; A device priority handling sequence for each device node in the fault propagation chain is determined according to the depth of each device node in the propagation path, the criticality of the fault type, and the device priority.

7. A device for analyzing equipment failure, characterized in that: The device comprises: A graph construction module is used to construct a structural modal graph and a semantic modal graph based on device identifiers, device icons, and physical connection relationships between devices; the structural modal graph represents the physical connection relationships between devices, and the semantic modal graph represents the functional dependencies and logical relationships between devices; Fault acquisition module, used to obtain the device identification and fault phenomenon of the faulty device; A fault chain generation module is configured to generate a fault propagation chain based on the device identification of the faulty device, the structural modal graph, and the semantic modal graph; the fault propagation chain at least includes a faulty device node; a sequence determination module, configured to determine a device priority handling sequence for each device node in the fault propagation chain; A fault cause determination module is used to determine the fault cause from a historical case library based on the device identification and fault phenomenon of the faulty device; The suggestion generation module is used to generate fault handling suggestions for each device node in the fault propagation chain according to the device priority handling sequence and the fault cause.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images