Equipment fault prediction method and equipment based on power grid equipment semantic network

Abstract

The invention provides an equipment fault prediction method and equipment based on a power grid equipment semantic network. According to the implementation scheme, under the condition that the operation state of target power grid equipment is abnormal, attribute information of a corresponding entity node in a first power grid equipment semantic net is updated based on the operation state of the target power grid equipment; under the condition that attribute information of a first entity node in the first power grid equipment semantic network is updated, based on a rule edge connected with the first entity node, in the first power grid equipment semantic network, changing a connection relationship between the rule edge and a second entity node associated with the first entity node to obtain a second power grid equipment semantic network; determining an influence subgraph of the target power grid equipment from the second power grid equipment semantic network; and performing fault analysis on the influence subgraph of the target power grid equipment to obtain a fault influence range of the target power grid equipment. According to the invention, the accuracy of the fault influence range of the power grid equipment can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power and information management, and in particular to a device fault prediction method and device based on a power grid device semantic network. BACKGROUND

[0002] Existing power grid device knowledge management technologies have fragmented knowledge expression, and device attributes, relationships and rules are scattered in heterogeneous data sources (such as SCADA systems, device manuals), lack of unified semantic models, leading to difficulties in knowledge sharing and reuse. Moreover, the reasoning ability is insufficient, traditional databases only support static queries, cannot automatically deduce implicit relationships (such as potential associations of device faults), and are difficult to meet the intelligent analysis needs of complex scenarios. SUMMARY

[0003] The present application provides a device fault prediction method and device based on a power grid device semantic network, which can solve at least one of the above technical problems.

[0004] According to an aspect of the present application, a device fault prediction method based on a power grid device semantic network is provided, comprising: in the case that the operating state of a target power grid device is abnormal, updating the attribute information of the corresponding entity node in the first power grid device semantic network based on the operating state of the target power grid device; In the case that the attribute information of the first entity node in the first power grid device semantic network is updated, based on the rule edge connected by the first entity node, changing the connection relationship between the rule edge and the second entity node associated with the first entity node in the first power grid device semantic network to obtain a second power grid device semantic network; Determining the influence subgraph of the target power grid device from the second power grid device semantic network; Performing fault analysis on the influence subgraph of the target power grid device to obtain the fault influence range of the target power grid device.

[0005] According to another aspect of the present application, a device fault prediction device based on a power grid device semantic network is provided, comprising: an attribute information updating module, configured to update the attribute information of the corresponding entity node in the first power grid device semantic network based on the operating state of the target power grid device in the case that the operating state of the target power grid device is abnormal; The connection relationship updating module is configured to, in a case where attribute information of a first entity node in the first power grid equipment semantic network is updated, change, based on a rule edge connected to the first entity node, a connection relationship between the rule edge and a second entity node associated with the first entity node in the first power grid equipment semantic network, to obtain a second power grid equipment semantic network; the influence subgraph extraction module is configured to determine an influence subgraph of the target power grid equipment from the second power grid equipment semantic network; and the device fault prediction module is configured to perform fault analysis on the influence subgraph of the target power grid equipment, to obtain a fault influence range of the target power grid equipment.

[0006] According to an aspect of the present application, an electronic device is provided, comprising at least one processor, and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the processor, and the processor is configured to acquire the instructions from the memory and execute the instructions, so that the processor can execute the device fault prediction method based on the power grid equipment semantic network according to any of the embodiments of the present application.

[0007] According to an aspect of the present application, a non-transitory computer readable storage medium storing computer instructions is provided, the computer instructions are used to provide to a computer to instruct the computer to execute the device fault prediction method based on the power grid equipment semantic network according to any of the embodiments of the present application.

[0008] By using the technical scheme of the present application, in a case where the running state of the target power grid equipment is abnormal, the attribute information of the corresponding entity node in the first power grid equipment semantic network is updated based on the abnormal running state of the target power grid equipment; in a case where the attribute information of the first entity node in the first power grid equipment semantic network is updated, the connection relationship between the rule edge connected to the first entity node and the second entity node associated with the first entity node in the first power grid equipment semantic network is changed, to obtain a second power grid equipment semantic network; the influence subgraph of the target power grid equipment is determined from the second power grid equipment semantic network; and the fault influence range of the target power grid equipment is obtained by performing fault analysis on the influence subgraph of the target power grid equipment. In this way, when the state of the power grid equipment corresponding to an entity node changes, the attribute information of the node in the power grid equipment semantic network is updated, and the connection relationship of the corresponding node is changed according to the rule edge of the node, and then the influence subgraph is extracted. In this way, according to the influence subgraph, the fault influence range of the power grid equipment can be accurately predicted.

[0009] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings are used to better understand the present scheme and do not constitute a limitation on the present application. Among them: Figure 1 is a flow chart of a device fault prediction method based on a power grid device semantic network according to an embodiment of the present application; Figure 2 is a structural block diagram of a device fault prediction apparatus based on a power grid device semantic network according to an embodiment of the present application; Figure 3 is a block diagram of an electronic device for implementing the method according to an embodiment of the present application. DETAILED DESCRIPTION

[0011] Exemplary embodiments of the present application are described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to assist in understanding them. These should be considered as merely exemplary. Therefore, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present application. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0012] Figure 1 is a flow chart of a device fault prediction method based on a power grid device semantic network according to an embodiment of the present application.

[0013] As shown in Figure 1 , the device fault prediction method based on the power grid device semantic network comprises: S110, in the case that there is an abnormality in the operating state of a target power grid device, updating attribute information of a corresponding entity node in a first power grid device semantic network based on the operating state of the target power grid device; S120, in the case that the attribute information of the first entity node in the first power grid device semantic network is updated, changing a connection relationship between the first entity node and a second entity node associated with the first entity node based on a rule edge connected to the first entity node in the first power grid device semantic network to obtain a second power grid device semantic network; S130, determining an influence subgraph of the target power grid device from the second power grid device semantic network; S140, performing fault analysis on the influence subgraph of the target power grid device to obtain a fault influence range of the target power grid device.

[0014] It can be understood that the power grid equipment can be a substation, a transformer, a circuit breaker, etc. The entity node can include a physical entity node, a functional entity node, and a physical entity node. For example, the physical entity node can be used to describe the attribute information of the power grid equipment such as the hardware type, the size, the manufacturer, the functional entity node is used to describe the power consumption function of the power grid equipment, for example, the protection voltage or current function, the function of adjusting the voltage or current, and the logical entity node is used to describe the data interface of the power grid equipment.

[0015] It can be understood that the operating state of the target power grid equipment is abnormal, for example, the temperature of the transformer changes and exceeds a certain threshold range. For example: assuming a specific transformer, the initial value of the winding temperature is 85°C (normal range). Subsequently, due to the increase of the load or the decrease of the cooling system efficiency, the winding temperature begins to gradually rise, for example: 85°C→95°C→105°C (at this time, a pre-warning is triggered)→115°C (further triggering an alarm)→125°C (exceeding the constraint, triggering an emergency processing suggestion), there are three abnormal stages and corresponding alarm stages.

[0016] Exemplarily, the entity node corresponding to the target power grid equipment in the first power grid equipment semantic network can include one or more. For example, when the winding temperature of a transformer changes, the corresponding physical entity node of the transformer can be found through the first electric equipment semantic network, and then the functional entity node and the logical entity node are found through the connection relationship between the physical entity node and other nodes, and the multiple entity nodes corresponding to the target power grid equipment are obtained. In this way, through the rule edge connected by these entity nodes, the change of the rule edge connection relationship and the update of the attribute information of the other nodes connected by the rule edge are performed, so as to obtain the second power grid equipment semantic network.

[0017] Exemplarily, the path related to the entity node corresponding to the target power grid equipment is extracted from the second power grid equipment semantic network to obtain an influence subgraph.

[0018] Exemplarily, a reasoning algorithm such as a Rete network can be used to perform fault analysis on the influence subgraph of the target power grid equipment, and the fault influence range of the target power grid equipment is obtained. Subsequently, these fault influence ranges can be provided to the operation and maintenance personnel for maintenance, thereby improving the maintenance efficiency.

[0019] According to the above embodiment, in the case that the operating state of the target power grid device is abnormal, the attribute information of the corresponding entity node in the first power grid device semantic network is updated based on the abnormal operating state of the target power grid device; in the case that the attribute information of the first entity node in the first power grid device semantic network is updated, the connection relationship between the rule edge connected with the first entity node and the second entity node associated with the first entity node is changed in the first power grid device semantic network based on the rule edge, to obtain a second power grid device semantic network; the influence subgraph of the target power grid device is determined from the second power grid device semantic network; and the fault analysis of the influence subgraph of the target power grid device is performed to obtain the fault influence range of the target power grid device. In this way, when the state of the power grid device corresponding to an entity node changes, the attribute information of the node in the power grid device semantic network is updated, the connection relationship of the corresponding node is changed according to the rule edge of the node, and then the influence subgraph is extracted therefrom. In this way, according to the influence subgraph, the fault influence range of the power grid device can be accurately predicted.

[0020] In an embodiment, the connection relationship between the rule edge and the second entity node associated with the first entity node is changed in the first power grid device semantic network based on the rule edge connected with the first entity node, including: in the case that the updated attribute information of the first entity node meets the rule premise condition of the rule edge connected with the first entity node, the rule edge of the first entity node is activated; in response to the activation of the rule edge of the first entity node, the second entity node associated with the first entity node is determined from the rule consequent execution content of the rule edge, and the connection relationship between the rule edge and the second entity node is changed based on the rule consequent execution content of the rule edge, and the attribute information of the second entity node is updated.

[0021] It can be understood that the above steps can be performed for the update of the attribute information of any entity node, and the rule edge and the associated other entity node of the second entity node can also be updated according to the above steps when the second entity node is updated.

[0022] It can be understood that the rule edge is an IF-THEN logical condition edge, the content defined by IF is a rule premise condition, and the content defined by THEN is a rule consequent execution content. If the attribute information of the first entity node meets the content defined by IF, the content defined by THEN can be executed, that is, the connection relationship between the rule edge and the other associated second entity node is changed, for example, connected or disconnected.

[0023] It can be understood that the rule edge can be equivalent to a connection edge with a switch, and can be a rule edge connecting one node with one or more nodes.

[0024] It can be understood that the power grid is a complex network structure, when a certain entity node changes, it will propagate along the electrical connection relationship edge, hierarchical membership relationship or functional dependence relationship edge, so that the related entity nodes also change and affect, therefore, through the rule edge to activate and execute the related operation, and realize the propagation of such information change.

[0025] According to the above embodiment, when the attribute information of any entity node in the power grid equipment semantic network is updated, and the rule premise condition of the rule edge connected with the entity node is met, the rule edge is activated, in response to the activation, the attribute information of the other associated entity nodes is changed and updated based on the rule consequent execution content in the rule edge, so that the propagation of the power grid equipment semantic network can be realized, and the influence subgraph of the target power grid equipment can be extracted from the updated power grid equipment semantic network.

[0026] In an embodiment, determining the influence subgraph of the target power grid equipment from the second power grid equipment semantic network comprises: determining each connection path of the first entity node corresponding to the target power grid equipment in the second power grid equipment semantic network; determining the propagation depth of each connection path based on the association degree between the first entity node and other nodes in each connection path; respectively cutting each connection path based on the propagation depth of each connection path; and determining the influence subgraph of the target power grid equipment based on each cut connection path.

[0027] It can be understood that the connection path of the first entity node is the path where the node is located, and each node in the path can be connected through each relationship edge and / or rule edge.

[0028] For example, for a connection path, if the association degree between the first entity node and other nodes is not high, the propagation depth from the first entity node to the end node of the path is also not deep. The higher the association degree, the deeper or longer the propagation depth from the first entity node to the end node of the path.

[0029] For example, for a connection path, the connection path is cut to a path with a specified propagation depth.

[0030] For example, each cut connection path is combined together to form the influence subgraph of the target power grid equipment.

[0031] According to the above-mentioned embodiments, the propagation depth of each connection path is determined according to the association degree between the first entity node and other nodes in each connection path, and each connection path is respectively pruned according to the propagation depth of each connection path. In this way, the influence subgraph of the target power grid device is determined based on the pruned connection paths. In this way, the influence subgraph can include paths with strong node relationships, which facilitates subsequent accurate analysis of the fault influence range.

[0032] In an embodiment, determining the propagation depth of each connection path based on the association degree between the first entity node and other nodes in each connection path includes: using a linear function to calculate the number of regular edges connected between the first entity node and other nodes in the connection path to obtain the association degree between the first entity node and other nodes in the connection path; and using a mapping function to map the association degree between the first entity node and other nodes in the connection path to obtain the propagation depth of the connection path.

[0033] For example, a linear function with a positive slope is used to calculate the number of regular edges connected between the first entity node and other nodes in the connection path to obtain the association degree between the first entity node and other nodes in the connection path. The more regular edges connected between the first entity node and other nodes in the same connection path, the higher the association degree between the first entity node and other nodes.

[0034] For example, a mapping function or a piecewise function can be used to determine the propagation depth of the connection path. For example, within a certain interval, the association degree corresponds to a specific numerical value.

[0035] According to the above-mentioned embodiments, the association degree between the first entity node and other nodes is determined by the number of regular edges in the same path, and then the propagation depth of the path can be determined.

[0036] In an embodiment, determining the fault influence range of the target power grid device based on the influence subgraph of the target power grid device includes: determining the activity degree of each connection path based on the number of activated regular edges in each connection path in the influence subgraph of the target power grid device; pruning the connection paths in the influence subgraph of the target power grid device based on the activity degree of each connection path; and using a reasoning algorithm to perform fault prediction on the pruned influence subgraph of the target power grid device to obtain the fault influence range of the target power grid device.

[0037] Exemplarily, the activity degree of each connection path can be determined by using context information such as power grid operation mode affecting each node on the connection path, importance of device type, priority of rule, and the like. Alternatively, the activity degree of each connection path can be determined by using the number of activated rule edges of each connection path. The more the number of activated rule edges, the higher the activity degree of the connection path.

[0038] Exemplarily, if the activity degree of the connection path is lower than a preset activity degree threshold, the connection path is deleted from the influence subgraph, thereby achieving the effect of pruning.

[0039] Exemplarily, the fault prediction of the pruned influence subgraph of the target power grid device can be performed by using a graph neural network or a model for fault propagation analysis of an electric system, to obtain the fault influence range of the target power grid device.

[0040] According to the above embodiment, the activity degree of each connection path can be determined based on the number of activated rule edges of the connection path, so that the paths with low activity degree can be pruned from the influence subgraph according to the activity degree of each connection path. In subsequent fault reasoning, the reasoning speed can be improved, and the influence of the paths with low activity degree on the paths with high activity degree can be avoided due to the pruning of the paths with low activity degree, thereby improving the reasoning accuracy.

[0041] In an embodiment, the method further includes: constructing a physical entity node, a functional entity node, and a logical entity node of each power grid device based on device hardware information, function information, and logical signal information of each power grid device; connecting the physical entity node, the functional entity node, and the logical entity node based on an electrical connection relationship, a hierarchical membership relationship, and a function dependency relationship between each power grid device, to obtain a third power grid device semantic network; adding a corresponding rule edge to a related physical entity node, functional entity node, and / or logical entity node in the third power grid device semantic network based on attribute constraints and fault diagnosis rules of each power grid device, to obtain a first power grid device semantic network.

[0042] Exemplarily, the power grid device is abstracted into a physical entity node such as a circuit breaker, a transformer, and the like, a functional entity node such as a protection function, a regulation function, and the like, and a logical entity node such as a control signal, a state quantity, and the like, to construct a three-layer ontology classification system.

[0043] Exemplarily, the physical entity node can define device physical attributes such as rated voltage, material, and the like. The functional entity node can define behavior logic of the device such as an overcurrent protection action threshold or an overvoltage protection action threshold, and the like. The logical entity node can define a data interface such as a SCADA signal mapping rule, and the like.

[0044] It is appreciated that the electrical connection relationship is, for example, defined by the property of electricalConnection, whose domain and range are both physical entities or their subclasses (e.g. circuit breaker, transformer), to represent the direct power flow or the composition of electrical loop between devices. Further asymmetric sub-properties such as isUpstreamOf can be defined to represent the power flow direction.

[0045] It is appreciated that the hierarchical membership relationship is, for example, defined by the properties of isPartOf or contains. The domain of contains can be a higher level physical entity, such as substation or bay. The range can be a lower level physical entity, such as bay or device. Alternatively, the domain can be a complex functional entity, and the range can be its sub-functional entities. This relationship is used to construct the assembly hierarchy and management area of devices.

[0046] It is appreciated that the functional dependency relationship is, for example, defined by the properties of functionallyDependsOn, triggers or monitors. The domain of functionallyDependsOn can be a functional entity, and the range can be another functional entity, a physical or logical entity providing data (e.g. sensor signal). This relationship is used to describe the interaction, control logic and data flow dependency between device functions, for example, a protection function (functional entity) monitors the current of a line (data obtained through associated physical or logical entities), and triggers another circuit breaker tripping function (functional entity) when the condition is met.

[0047] By the above relationships between entities, the entities are connected, i.e. the relationship edges between two entity nodes are provided.

[0048] It is exemplarily that the property constraint is a data type property describing the state parameters of devices (e.g. temperature, voltage, oil level, pressure, switch position, etc.), and the value range (rdfs:range) is defined by using XML Schema Datatype (XSD) and its facets to limit the value. For example, for the hasWindingTemperature property of a transformer, the value range can be defined as xsd:float[<= 120.0], to ensure that the temperature value does not exceed 120.0 degrees Celsius; for the hasSwitchPosition property of a switch, the value range can be defined as a boolean type xsd:boolean or an enumerated string (e.g. "Open", "Closed").

[0049] It can be understood that these state constraints, although not directly defining the topological connection relationship between devices (the topology is mainly defined by the object attributes in step 1.2), limit the effective operation state and parameter range of each device entity constituting the topology. For example, the rated current capacity constraint of the line will affect its operation capacity in a certain topology. Therefore, these constraints are crucial for ensuring data consistency, verifying the validity of device state, and serving as a prerequisite for subsequent rule reasoning (such as SWRL rules to determine whether a device is abnormal). In this way, the normal working state and boundary conditions of the entity can be accurately defined.

[0050] Exemplarily, the fault diagnosis rule can adopt a rule logic in the form of "if…then…". The rule logic includes an antecedent and a consequent, the antecedent is the implementation condition of the consequent, and the consequent is the specific execution content.

[0051] According to the above-mentioned embodiments, a semantic network of power grid equipment can be constructed, which includes physical entity nodes, functional entity nodes and logical entity nodes. And through the relationship edges and rule edges between these nodes, a reasoning semantic network is connected.

[0052] Figure 2 is a structural block diagram of a device fault prediction device based on a power grid equipment semantic network according to an embodiment of the present application.

[0053] As Figure 2 shown, the device fault prediction device based on the power grid equipment semantic network includes: An attribute information updating module 210 is configured to update attribute information of an entity node corresponding to a target power grid equipment in the first power grid equipment semantic network based on an abnormal operating state of the target power grid equipment in a case where the operating state of the target power grid equipment is abnormal. A connection relationship updating module 220 is configured to change a connection relationship between a rule edge and a second entity node associated with a first entity node in the first power grid equipment semantic network based on the rule edge connected to the first entity node in a case where attribute information of the first entity node in the first power grid equipment semantic network is updated, to obtain a second power grid equipment semantic network. An influence subgraph extracting module 230 is configured to determine an influence subgraph of the target power grid equipment from the second power grid equipment semantic network. A device fault prediction module 240 is configured to perform fault analysis on the influence subgraph of the target power grid equipment to obtain a fault influence range of the target power grid equipment.

[0054] In an embodiment, the base connection relationship updating module 220 includes: a rule edge activation unit, configured to activate a rule edge of the first entity node in a case where updated attribute information of the first entity node satisfies a rule precondition of the rule edge connected to the first entity node; a relationship and node updating unit, configured to determine a second entity node associated with the first entity node from a rule consequent execution content of the rule edge of the first entity node in response to activation of the rule edge of the first entity node, and change a connection relationship between the rule edge and the second entity node and update attribute information of the second entity node based on the rule consequent execution content of the rule edge.

[0055] In an embodiment, the connection relationship includes connection or disconnection.

[0056] In an embodiment, the influence subgraph extraction module 230 includes: a connection path determination unit, configured to determine each connection path of the first entity node corresponding to the target power grid device in the second power grid device semantic network; a propagation depth determination unit, configured to determine a propagation depth of each connection path based on a degree of association between the first entity node and other nodes in each connection path; a path pruning unit, configured to prune each connection path based on the propagation depth of each connection path; andan influence subgraph determination unit, configured to determine an influence subgraph of the target power grid device based on the pruned connection paths.

[0057] In an embodiment, the propagation depth determination unit is specifically configured to: calculate a number of rule edges connected between the first entity node and other nodes in the connection path by using a linear function, to obtain the degree of association between the first entity node and other nodes in the connection path; andmap the degree of association between the first entity node and other nodes in the connection path by using a mapping function, to obtain the propagation depth of the connection path.

[0058] In an embodiment, the device fault prediction module 240 includes: an activity determination unit, configured to determine an activity of each connection path in the influence subgraph of the target power grid device based on a number of activated rule edges of each connection path; and a path pruning unit, configured to prune the connection paths in the influence subgraph of the target power grid device based on the activity of each connection path. A fault range reasoning unit is configured to employ a reasoning algorithm to perform fault prediction on the pruned influence subgraph of the target power grid device, and obtain a fault influence range of the target power grid device.

[0059] In an embodiment, the apparatus further comprises: An entity node determination module is configured to construct a physical entity node, a functional entity node and a logical entity node of each power grid device based on device hardware information, functional information and logical signal information of each power grid device. An entity node connection module is configured to perform node connection on the physical entity node, the functional entity node and the logical entity node based on an electrical connection relationship, a hierarchical membership relationship and a functional dependency relationship between each power grid device, and obtain a third power grid device semantic network. A rule edge adding module is configured to add a corresponding rule edge to a relevant physical entity node, functional entity node and / or logical entity node in the third power grid device semantic network based on attribute constraints and fault diagnosis rules of each power grid device, and obtain the first power grid device semantic network.

[0060] The specific functions and examples of the modules and sub-modules of the system of the embodiments of the present application are described in the related description of the corresponding steps in the above method embodiments, and will not be described here.

[0061] In the technical solution of the present application, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0062] According to the embodiments of the present application, the present application further provides a system and a readable storage medium.

[0063] Figure 3 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0064] As Figure 3As shown, the electronic device 800 includes a computing unit 801 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 802 or a computer program loaded into a random access memory (RAM) 803 from a storage unit 808. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0065] A plurality of components in the electronic device 800 are connected to the I / O interface 805, including an input unit 806 such as a keyboard, a mouse, and the like, an output unit 807 such as various types of displays, a speaker, and the like, a storage unit 808 such as a magnetic disk, an optical disk, and the like, and a communication unit 809 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0066] The computing unit 801 can be various general-purpose and / or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, and the like. The computing unit 801 performs various methods and processes described above, such as the power grid equipment semantic web based device fault prediction method. For example, in some embodiments, the power grid equipment semantic web based device fault prediction method can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the power grid equipment semantic web based device fault prediction method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the power grid equipment semantic web based device fault prediction method by any other appropriate means, such as by means of firmware.

[0067] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0068] Program code to implement methods of the present application can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, or entirely on a remote machine or server.

[0069] In the context of the present application, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0070] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0071] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0072] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0073] It should be understood that various forms of flow shown above can be used, re-ordered, added to, or deleted from without departing from the spirit of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed herein are achieved, and the present disclosure is not limited herein.

[0074] The specific embodiments described above are not intended to limit the scope of the present application. Those skilled in the art will understand that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments described above without departing from the principles of the present application. Any such modifications, equivalents, and alternatives are intended to fall within the scope of the present application.

Claims

1. A power grid equipment semantic web-based equipment failure prediction method, characterized in that, Comprise: In the case of abnormality in the operating state of the target power grid device, update the attribute information of the corresponding entity node in the first power grid device semantic network based on the operating state of the target power grid device; In the case of updating the attribute information of the first entity node in the first power grid device semantic network, based on the rule edge connected by the first entity node, change the connection relationship between the rule edge and the second entity node associated with the first entity node in the first power grid device semantic network to obtain a second power grid device semantic network; Determine the influence subgraph of the target power grid device from the second power grid device semantic network; Perform fault analysis on the influence subgraph of the target power grid device to obtain the fault influence range of the target power grid device.

2. The method of claim 1, wherein, The connection relationship between the rule edge and the second entity node associated with the first entity node in the first power grid device semantic network based on the rule edge connected by the first entity node, comprising: In the case that the updated attribute information of the first entity node meets the rule premise condition of the rule edge connected by the first entity node, activate the rule edge of the first entity node; In response to the activation of the rule edge of the first entity node, determine the second entity node associated with the first entity node from the rule consequent execution content of the rule edge, and change the connection relationship between the rule edge and the second entity node based on the rule consequent execution content of the rule edge, and update the attribute information of the second entity node.

3. The method of claim 2, wherein, The connection relationship includes connection or disconnection.

4. The method of claim 1, wherein, The connection relationship includes connection or disconnection. Determine the influence subgraph of the target power grid device from the second power grid device semantic network, comprising: Determine each connection path of the first entity node corresponding to the target power grid device in the second power grid device semantic network; Determine the propagation depth of each connection path based on the degree of association between the first entity node and other nodes in each connection path; Based on the propagation depth of each connection path, respectively clip each connection path; 5. The method of claim 4, wherein, Determine the influence subgraph of the target power grid device based on the clipped each connection path. Determine the propagation depth of each connection path based on the degree of association between the first entity node and other nodes in each connection path, comprising:

6. The method of claim 2, wherein, Use a linear function to calculate the number of rule edges connected by the first entity node and other nodes in the connection path to obtain the degree of association between the first entity node and other nodes in the connection path; use a mapping function to map the degree of association between the first entity node and other nodes in the connection path to obtain the propagation depth of the connection path. Determine the fault influence range of the target power grid device based on the influence subgraph of the target power grid device, comprising: Determine the activity of each connection path based on the number of activated rule edges in each connection path in the influence subgraph of the target power grid device; Prune the connection paths in the influence subgraph of the target power grid device based on the activity of each connection path; and perform fault prediction on the pruned influence subgraph of the target power grid device by using a reasoning algorithm to obtain the fault influence range of the target power grid device.

7. The method according to any one of claims 1 to 6, characterized in that, Also includes Construct physical entity nodes, functional entity nodes and logical entity nodes of each power grid device based on device hardware information, functional information and logical signal information of each power grid device; Based on the electrical connection relationship, hierarchical membership relationship and functional dependency relationship between each power grid device, connect each physical entity node, each functional entity node and each logical entity node to obtain a third power grid device semantic network; Based on the attribute constraints and fault diagnosis rules of each power grid device, add corresponding rule edges to the relevant physical entity nodes, functional entity nodes and / or logical entity nodes in the third power grid device semantic network to obtain the first power grid device semantic network.

8. A device failure prediction apparatus based on a power grid device semantic web, characterized by, Includes An attribute information updating module configured to update attribute information of a corresponding entity node in the first power grid device semantic network based on the operating state of the target power grid device if the operating state of the target power grid device is abnormal; A connection relationship updating module configured to change the connection relationship between a rule edge and a second entity node associated with the first entity node in the first power grid device semantic network based on the rule edge connected to the first entity node if the attribute information of the first entity node in the first power grid device semantic network is updated, to obtain a second power grid device semantic network; An influence subgraph extraction module configured to determine an influence subgraph of the target power grid device from the second power grid device semantic network; A device fault prediction module configured to perform fault analysis on the influence subgraph of the target power grid device to obtain a fault influence range of the target power grid device.

9. An electronic device, comprising: Includes At least one processor and a memory connected in communication with the at least one processor; The memory stores instructions executable by the processor, and the processor is configured to obtain the instructions from the memory and execute the instructions to enable the processor to perform the power grid device semantic network-based device fault prediction method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to provide a computer to instruct the computer to perform the power grid device semantic network-based device fault prediction method according to any one of claims 1-7. The computer instructions are used to provide a computer to instruct the computer to perform the power grid device semantic network-based device fault prediction method according to any one of claims 1-7.

Images