Fault detection method and device for power grid equipment, equipment, medium and product
By combining feature extraction from images and power data with counterfactual reasoning, the problem of low accuracy caused by environmental interference in power grid equipment fault detection is solved, achieving higher detection accuracy.
Patent Information
- Application Number
- CN202511993619.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-26
- Publication Date
- 2026-03-13
AI Technical Summary
In existing technologies, fault detection of power grid equipment is easily affected by environmental interference, resulting in low accuracy.
By acquiring image and power data of power grid equipment, feature vectors are extracted using a deep learning model, and a knowledge gating mask is generated by combining the equipment fault causal knowledge graph. Power and image feature information are then fused together to perform counterfactual reasoning to improve detection accuracy.
It improves the accuracy of fault detection in power grid equipment and reduces misjudgments caused by environmental factors.
Smart Images
Figure CN121656744A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of fault detection technology, and in particular to a fault detection method, apparatus, equipment, medium, and program product for power grid equipment. Background Technology
[0002] Power grid equipment and materials are a crucial component of the power system, and their operational status directly impacts the system's safety, stability, and economical operation. Timely and accurate detection and analysis of the operational status of power grid equipment and materials, and the identification of potential faults and hazards, are of great significance for preventing power accidents and reducing power grid losses.
[0003] Existing technologies typically rely on single image processing techniques for fault detection, which are prone to producing incorrect fault detection results under environmental interference, resulting in low accuracy. Summary of the Invention
[0004] This invention provides a method, apparatus, equipment, medium, and program product for fault detection of power grid equipment, so as to improve the accuracy of fault detection of power grid equipment.
[0005] In a first aspect, embodiments of the present invention provide a fault detection method for power grid equipment, comprising:
[0006] Acquire image data and power data of the target power grid equipment; the power data is voltage data or current data.
[0007] Based on the image data and the power data, determine the sampling feature vector of the target power grid equipment;
[0008] Based on the sampled feature vector, the auxiliary fault detection result of the power grid equipment is determined;
[0009] Perform counterfactual reasoning on the auxiliary fault detection results to obtain the baseline feature vector corresponding to the auxiliary fault detection results;
[0010] The target fault detection result of the power grid equipment is determined based on the auxiliary fault detection result, the sampled feature vector, and the benchmark feature vector.
[0011] Secondly, embodiments of the present invention also provide a fault detection device for power grid equipment, comprising:
[0012] The acquisition module is used to acquire image data and power data of the target power grid equipment; the power data is voltage data or current data.
[0013] The first vector determination module is used to determine the sampling feature vector of the target power grid equipment based on the image data and the power data;
[0014] The first result determination module is used to determine the auxiliary fault detection result of the power grid equipment based on the sampled feature vector.
[0015] The second vector determination module is used to perform counterfactual reasoning on the auxiliary fault detection result to obtain the benchmark feature vector corresponding to the auxiliary fault detection result.
[0016] The second result determination module is used to determine the target fault detection result of the power grid equipment based on the auxiliary fault detection result, the sampled feature vector, and the reference feature vector.
[0017] Thirdly, embodiments of the present invention also provide an electronic device, comprising:
[0018] At least one processor; and
[0019] A memory that is communicatively connected to at least one processor; wherein
[0020] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the fault detection method for power grid equipment provided in any embodiment of the present invention.
[0021] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute the fault detection method for power grid equipment according to any embodiment of the present invention.
[0022] Fifthly, embodiments of the present invention also provide a computer program product, characterized in that the computer program product includes a computer program, which, when executed by a processor, implements the fault detection method for power grid equipment according to any embodiment of the present invention.
[0023] This invention improves the accuracy of the determined auxiliary fault detection results and the accuracy of the subsequent counterfactual inference determined based on the auxiliary fault detection results by acquiring multimodal data, including image data and power data, and determining sampling feature vectors based on the image data and power data. By using the benchmark feature vector and the sampling feature vector, the accuracy of the auxiliary fault detection results is judged, thereby obtaining the target fault detection result and improving the accuracy of the target fault detection result.
[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0026] Figure 1 This is a flowchart of a fault detection method for power grid equipment according to Embodiment 1 of the present invention;
[0027] Figure 2 This is a flowchart of a fault detection method for power grid equipment according to Embodiment 2 of the present invention;
[0028] Figure 3 This is a schematic diagram of the structure of a fault detection device for power grid equipment according to Embodiment 3 of the present invention;
[0029] Figure 4 This is a structural diagram of an electronic device that implements a fault detection method for power grid equipment according to an embodiment of the present invention. Detailed Implementation
[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0031] It should be noted that the terms "first" and "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0032] The acquisition, storage, and application of image data and power data involved in the technical solutions of this invention comply with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0033] Example 1
[0034] Figure 1 This is a flowchart of a fault detection method for power grid equipment provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of fault detection of power grid equipment. The method can be executed by a fault detection device for power grid equipment. The fault detection device for power grid equipment can be implemented in hardware and / or software and specifically configured in electronic equipment.
[0035] See Figure 1 The fault detection method for the power grid equipment shown includes:
[0036] S101. Acquire image data and power data of the target power grid equipment; the power data is voltage data or current data.
[0037] S102. Determine the sampling feature vector of the target power grid equipment based on the image data and the power data.
[0038] S103. Determine the auxiliary fault detection result of the power grid equipment based on the sampled feature vector.
[0039] S104. Perform counterfactual reasoning on the auxiliary fault detection results to obtain the baseline feature vector corresponding to the auxiliary fault detection results.
[0040] S105. Based on the auxiliary fault detection result, the sampled feature vector, and the reference feature vector, determine the target fault detection result of the power grid equipment.
[0041] In this embodiment, the target power grid equipment can be the power grid equipment to be fault detected, such as charging piles, transformers, and transmission lines. The sampling feature vector can be a vector representing the feature information of image data and power data; the auxiliary fault detection result can be the fault detection result of the target power grid equipment determined based on the sampling feature vector; the baseline feature vector can be a vector representing the feature information of the image data and power data of the target power grid equipment under the condition that the auxiliary fault detection result is the true fault detection result. The target fault detection result is the final determined fault detection result of the target power grid equipment.
[0042] Specifically, the process involves acquiring image data and power data of the target power grid equipment; extracting features from the image data and power data using a trained first deep learning model; fusing the feature extraction results of the image data and power data to obtain a sampled feature vector; and determining the auxiliary fault detection result of the power grid equipment based on the sampled feature vector; searching for benchmark image data and benchmark power data that match the auxiliary fault detection result; determining a benchmark feature vector based on the benchmark image data and benchmark power data using a process similar to that used to determine the sampled feature vector; determining the accuracy of the auxiliary fault detection result based on the auxiliary fault detection result, the sampled feature vector, and the benchmark feature vector; if the auxiliary fault detection result is accurate, determining it as the target fault detection result; if the auxiliary fault detection result is inaccurate, determining the target fault detection result as having no abnormality and generating a prompt message to alert technicians of an unknown disturbance.
[0043] Optionally, determining the sampling feature vector of the target power grid equipment based on the image data and the power data includes: extracting features from the image data to obtain an image feature vector, and extracting features from the power data to obtain a power feature vector; determining the correlation between the image feature vector and the node vectors of each fault entity node in the equipment fault causal knowledge graph; generating a knowledge gating mask based on the node vector of the fault entity node with the highest correlation and the image feature vector; and fusing the power feature vector and the image feature vector based on the knowledge gating mask to obtain the sampling feature vector.
[0044] The equipment fault causal knowledge graph can be a pre-constructed knowledge graph; the knowledge graph includes at least one fault entity node; fault entity nodes with causal relationships are connected in the knowledge graph; the fault entity can be a fault type. The node vector can be the embedding vector of the fault entity node; the knowledge gating mask can be used to increase or decrease the influence of the power feature vector in the fusion process according to the degree of correlation between the image feature vector and the fault entity node.
[0045] Specifically, feature extraction is performed on the image data to obtain image feature vectors, and feature extraction is performed on the power data to obtain power feature vectors. For each fault entity node, the cosine similarity between the node vector of the fault entity node and the image feature vector is calculated, and the calculated cosine similarity is determined as the correlation between the node vector of the fault entity node and the image feature vector. Optionally, before acquiring the image data and power data of the target power grid equipment, a causal knowledge graph of equipment faults can be pre-constructed, and each fault entity node in the causal knowledge graph of equipment faults can be mapped to a node vector.
[0046] The fault entity node with the highest correlation between the node vector and the image feature vector is selected from all fault entity nodes and is taken as the fault entity node with the highest correlation.
[0047] The knowledge gating mask is determined using the following formula:
[0048] ;
[0049] in, Knowledge gating mask; Represents the image feature vector; This represents the trainable projection matrix in the first deep learning model; This represents the transpose of the node vector of the faulty entity node with the highest correlation. This represents the activation function.
[0050] It is understandable that by adopting the above technical solution, the fault entity node with the highest correlation to the image feature vector is determined from the equipment fault causal knowledge graph, and a knowledge gating mask is generated by the node vector of the fault entity node with the highest correlation and the image feature vector. This increases the influence of the sampling feature vector on the process of fusing power feature vector and image feature vector, making the sampled feature vector more representative of the data feature information associated with the fault, thereby improving the accuracy of the subsequent auxiliary fault detection results.
[0051] Optionally, fusing the power feature vector and the image feature vector according to the knowledge gating mask to obtain a sampled feature vector includes: adjusting the power feature vector according to the knowledge gating mask to obtain an adjusted power feature vector; and concatenating the adjusted power feature vector with the image feature vector to obtain a sampled feature vector.
[0052] The fusion feature vector is determined using the following formula:
[0053] ;
[0054] in, Represents the fused feature vector; Indicates the concatenation function; Represents the power characteristic vector; It represents the Hadamardi (or Hadama) stack; This represents the knowledge guidance strength coefficient, used to adjust the degree of influence of the knowledge gating mask on the power characteristic signal.
[0055] It is understandable that by adopting the above technical solution, the knowledge gating mask generated based on the equipment fault causal knowledge graph and image feature vectors can enhance the information in the power feature information that is highly associated with the fault entity node, while suppressing irrelevant features, thereby further improving the accuracy of the sampled feature vectors.
[0056] Optionally, before acquiring image data and power data of the target power grid equipment, the process includes: continuously monitoring the spectral energy density of sound signals in the target monitoring location; at least one candidate power grid equipment is deployed in the target monitoring location; if the spectral energy density is greater than a second threshold, the target power grid equipment is located from among the candidate power grid equipment using a sound source localization algorithm.
[0057] The target monitoring location can be a location where at least one candidate power grid device is deployed; the candidate power grid device is the power grid device operating in the target monitoring location. It should be noted that the second threshold can be set independently by technical personnel based on actual needs or practical experience; this invention does not impose any limitations on it.
[0058] In one specific implementation, a sound sensor deployed at the target monitoring site can detect when the spectral energy density of a specific frequency band (such as 20kHz-100kHz corresponding to a partial discharge fault) exceeds a second threshold. Then, a sound source localization algorithm is used to target the power grid equipment. Furthermore, based on the determined location of the target power grid equipment, a control command is generated to drive a high-precision pan-tilt camera in a dormant state to physically rotate and zoom, so that its optical axis center is precisely aligned with the target power grid equipment. Simultaneously, a high-frequency waveform recorder is triggered to lock the transient power data within 500ms before and after the trigger moment, thereby ensuring strict spatiotemporal alignment between image data and power data.
[0059] This invention improves the accuracy of the determined auxiliary fault detection results and the accuracy of the subsequent counterfactual inference determined based on the auxiliary fault detection results by acquiring multimodal data, including image data and power data, and determining sampling feature vectors based on the image data and power data. By using the benchmark feature vector and the sampling feature vector, the accuracy of the auxiliary fault detection results is judged, thereby obtaining the target fault detection result and improving the accuracy of the target fault detection result.
[0060] Example 2
[0061] Figure 2 This is a flowchart of a fault detection method for power grid equipment provided in Embodiment 2 of the present invention. Based on the technical solution of the above embodiments, the present invention optimizes and improves the operation of determining the target fault detection result.
[0062] Furthermore, the step of "determining the target fault detection result of the power grid equipment based on the auxiliary fault detection result, the sampled feature vector, and the reference feature vector" is refined to "calculating the logical mutual exclusion degree between the sampled feature vector and the reference feature vector based on the auxiliary fault detection result; if the logical mutual exclusion degree is less than a first threshold, then the auxiliary fault detection result is determined as the target fault detection result of the target power grid equipment; if the logical mutual exclusion degree is greater than or equal to the first threshold, then the target fault detection result of the target power grid equipment is determined to be without abnormality," thereby improving the operation of determining the target fault detection result.
[0063] It should be noted that for any parts not described in detail in the embodiments of the present invention, please refer to the description in the foregoing embodiments.
[0064] See Figure 2 The fault detection method for the power grid equipment shown includes:
[0065] S201. Acquire image data and power data of the target power grid equipment; the power data is voltage data or current data.
[0066] S202. Determine the sampling feature vector of the target power grid equipment based on the image data and the power data.
[0067] S203. Determine the auxiliary fault detection result of the power grid equipment based on the sampled feature vector.
[0068] S204. Perform counterfactual reasoning on the auxiliary fault detection results to obtain the baseline feature vector corresponding to the auxiliary fault detection results.
[0069] S205. Based on the auxiliary fault detection results, calculate the logical mutual exclusion between the sampled feature vector and the reference feature vector.
[0070] S206. If the logical mutual exclusion degree is less than the first threshold, then the auxiliary fault detection result is determined as the target fault detection result of the target power grid equipment fault.
[0071] S207. If the logical mutual exclusion degree is greater than or equal to the first threshold, then the target fault detection result of the target power grid equipment is determined to be no abnormality.
[0072] In this embodiment, logical mutual exclusion can be used to characterize the difference between the sampled feature vector and the reference feature vector. Specifically, a certain algorithm is used to calculate the logical mutual exclusion between the sampled feature vector and the reference feature vector based on the auxiliary fault detection result; for example, the Gaussian distance between the sampled feature vector and the reference feature vector is calculated as the logical mutual exclusion; if the logical mutual exclusion is less than a first threshold, the auxiliary fault detection result is determined as the target fault detection result of the target power grid equipment; if the logical mutual exclusion is greater than or equal to the first threshold, the target fault detection result of the target power grid equipment is determined to be without abnormality.
[0073] It should be noted that the first threshold can be set independently by technicians based on actual needs or practical experience, and this invention does not limit it.
[0074] Optionally, calculating the logical mutual exclusion between the sampled feature vector and the reference feature vector based on the auxiliary fault detection result includes: finding physical logic conditions that match the auxiliary fault detection result, and logical judgment parameters in the physical logic conditions; obtaining the true value of the logical judgment parameters of the target power grid equipment based on the logical judgment parameters; determining whether the true value of the logical judgment parameters of the target power grid equipment satisfies the physical logic conditions to obtain a first result; and calculating the logical mutual exclusion between the sampled feature vector and the reference feature vector based on the first result, the sampled feature vector, and the reference feature vector.
[0075] The physical logic condition can be the logical condition of the physical laws that the target power grid equipment should meet when the auxiliary fault detection result is a true fault detection result. The logical judgment parameter can be the parameter involved in the physical logic condition. For example, if the auxiliary fault detection result is "circuit breaker tripped", the physical logic condition found can be "loop current less than or equal to 0.1A", and the logical judgment parameter is loop current; if the power data of the target power grid equipment includes loop current, then the value of loop current in the power data is determined as the true value of loop current; if the power data of the target power grid equipment does not include loop current, then the true value of loop current of the target power grid equipment is collected; verify whether the true value of loop current meets the physical logic condition to obtain the first result.
[0076] For example, logical mutual exclusion can be determined using the following formula:
[0077] ;
[0078] Among them, the Indicates logical mutual exclusion; First weighting coefficient; This represents the second weighting coefficient; Represents the baseline eigenvector; Indicates the first result; This represents a logic indicator function. When the first result is that the true value of the logic judgment parameter does not meet the physical logic condition, the value of the logic indicator function is 0. When the first result is that the true value of the logic judgment parameter meets the physical logic condition, the value of the logic indicator function is 1.
[0079] It is understood that by adopting the above technical solution, the accuracy of the logical mutual exclusion is improved by finding the physical logic conditions that match the auxiliary fault detection results and the logical judgment parameters in the physical logic conditions; obtaining the true value of the logical judgment parameters of the target power grid equipment according to the logical judgment parameters; determining whether the true value of the logical judgment parameters of the target power grid equipment satisfies the physical logic conditions; and calculating the logical mutual exclusion between the sampled feature vector and the reference feature vector according to the first result, the sampled feature vector, and the reference feature vector.
[0080] In an optional embodiment, a pre-built physical mechanism model can be used to generate reference image data and reference power data for the target power grid equipment based on the auxiliary fault detection results. Furthermore, the cumulative trend of logical mutual exclusion and the vector residual between the sampled feature vector and the reference feature vector over time can be continuously tracked.
[0081] If the vector residuals of the target power grid equipment show a monotonically increasing trend, it indicates that the physical characteristics (such as internal resistance and heat capacity) of the target power grid equipment have undergone distributional drift due to aging, and the original physical mechanism model parameters are no longer applicable. High-confidence samples (i.e., samples with logical mutual exclusion below a preset threshold) within the most recent time window are obtained. Gradient descent is used to fine-tune the constant terms in the physical mechanism model (such as correcting the resistance R or heat dissipation coefficient k), and the corrected physical parameters are then updated inversely to the deep learning network.
[0082] This invention calculates the logical mutual exclusion between the sampled feature vector and the reference feature vector based on the auxiliary fault detection result. If the logical mutual exclusion is less than a first threshold, the auxiliary fault detection result is determined as the target fault detection result of the target power grid equipment. If the logical mutual exclusion is greater than or equal to the first threshold, the target fault detection result of the target power grid equipment is determined to be without abnormality. By calculating the logical mutual exclusion, misjudgment of fault detection results caused by environmental factors and other factors can be avoided, thereby improving the accuracy of the target fault detection result.
[0083] Example 3
[0084] Figure 3This is a schematic diagram of a fault detection device for power grid equipment provided in Embodiment 3 of the present invention. This embodiment of the invention is applicable to fault detection of power grid equipment. The device can execute a fault detection method for power grid equipment and can be implemented in hardware and / or software. The device can be configured in an electronic device.
[0085] like Figure 3 The fault detection device for power grid equipment shown includes: an acquisition module 301, a first vector determination module 302, a first result determination module 303, a second vector determination module 304, and a second result determination module 305. Among them,
[0086] The acquisition module 301 is used to acquire image data and power data of the target power grid equipment; the power data is voltage data or current data.
[0087] The first vector determination module 302 is used to determine the sampling feature vector of the target power grid equipment based on the image data and the power data;
[0088] The first result determination module 303 is used to determine the auxiliary fault detection result of the power grid equipment based on the sampled feature vector;
[0089] The second vector determination module 304 is used to perform counterfactual reasoning on the auxiliary fault detection result to obtain the benchmark feature vector corresponding to the auxiliary fault detection result.
[0090] The second result determination module 305 is used to determine the target fault detection result of the power grid equipment based on the auxiliary fault detection result, the sampled feature vector, and the reference feature vector.
[0091] This invention improves the accuracy of the determined auxiliary fault detection results and the accuracy of the subsequent counterfactual inference determined based on the auxiliary fault detection results by acquiring multimodal data, including image data and power data, and determining sampling feature vectors based on the image data and power data. By using the benchmark feature vector and the sampling feature vector, the accuracy of the auxiliary fault detection results is judged, thereby obtaining the target fault detection result and improving the accuracy of the target fault detection result.
[0092] Optionally, the first vector determination module 302 includes:
[0093] The feature extraction unit is used to extract features from the image data to obtain an image feature vector, and to extract features from the power data to obtain a power feature vector;
[0094] The correlation degree determination unit is used to determine the correlation degree between the image feature vector and the node vector of each fault entity node in the equipment fault causal knowledge graph;
[0095] The generation unit is used to generate a knowledge gating mask based on the node vector of the faulty entity node with the highest correlation and the image feature vector;
[0096] The vector determination unit is used to fuse the power feature vector and the image feature vector according to the knowledge gating mask to obtain the sampled feature vector.
[0097] Optional, vector determination unit, specifically used for:
[0098] The power feature vector is adjusted according to the knowledge gating mask to obtain the adjusted power feature vector;
[0099] The adjusted power feature vector is concatenated with the image feature vector to obtain the sampled feature vector.
[0100] Optionally, the second result determination module includes:
[0101] The calculation unit is used to calculate the logical mutual exclusion between the sampled feature vector and the reference feature vector based on the auxiliary fault detection result;
[0102] The first determining unit is configured to determine the auxiliary fault detection result as the target fault detection result of the target power grid equipment fault if the logical mutual exclusion degree is less than the first threshold.
[0103] The second determining unit is configured to determine that the target fault detection result of the target power grid equipment is no abnormality if the logical mutual exclusion degree is greater than or equal to the first threshold.
[0104] Optional, computational units, specifically used for:
[0105] Find the physical logic conditions that match the auxiliary fault detection results, and the logical judgment parameters in the physical logic conditions;
[0106] Based on the logical judgment parameters, obtain the true values of the logical judgment parameters of the target power grid equipment;
[0107] Determine whether the true values of the logical judgment parameters of the target power grid equipment satisfy the physical logic conditions to obtain a first result;
[0108] Based on the first result, the sampled feature vector, and the reference feature vector, calculate the logical mutual exclusion between the sampled feature vector and the reference feature vector.
[0109] Optionally, the device may also include:
[0110] A monitoring module is used to continuously monitor the spectral energy density of sound signals in a target monitoring location; at least one candidate power grid device is deployed in the target monitoring location.
[0111] The positioning module is used to locate the target power grid device from among the candidate power grid devices by means of a sound source positioning algorithm if the spectral energy density is greater than a second threshold.
[0112] The fault detection device for power grid equipment provided in this embodiment of the invention can execute the fault detection method for power grid equipment provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the fault detection method for power grid equipment.
[0113] Example 4
[0114] Figure 4 A schematic diagram of a fault detection device 410 for a power grid device that can be used to implement embodiments of the present invention is shown. The fault detection device for a power grid device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The fault detection device for a power grid device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0115] like Figure 4 As shown, the fault detection device 410 for power grid equipment includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 can also store various programs and data required for the operation of the fault detection device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.
[0116] Multiple components in the power grid equipment fault detection device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, optical disk, etc.; and a communication unit 419, such as a network card, modem, wireless transceiver, etc. The communication unit 419 allows the power grid equipment fault detection device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0117] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as fault detection methods for power grid equipment.
[0118] In some embodiments, the fault detection method for power grid equipment may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded into and / or installed onto the fault detection device 410 of the power grid equipment via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the fault detection method for power grid equipment described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the fault detection method for power grid equipment by any other suitable means (e.g., by means of firmware).
[0119] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0120] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a fault detection device for a general-purpose computer, a special-purpose computer, or other programmable power grid equipment, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.
[0121] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0122] To provide user interaction, the systems and techniques described herein can be implemented on a fault detection device for power grid equipment, which includes: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the fault detection device. Other types of devices can also be used to provide user interaction; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0123] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0124] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability.
[0125] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0126] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A fault detection method for power grid equipment, characterized in that, The method includes: Acquire image data and power data of the target power grid equipment; the power data is voltage data or current data. Based on the image data and the power data, determine the sampling feature vector of the target power grid equipment; Based on the sampled feature vector, the auxiliary fault detection result of the power grid equipment is determined; Perform counterfactual reasoning on the auxiliary fault detection results to obtain the baseline feature vector corresponding to the auxiliary fault detection results; The target fault detection result of the power grid equipment is determined based on the auxiliary fault detection result, the sampled feature vector, and the benchmark feature vector.
2. The method according to claim 1, characterized in that, The step of determining the sampling feature vector of the target power grid equipment based on the image data and the power data includes: Feature extraction is performed on the image data to obtain an image feature vector, and feature extraction is performed on the power data to obtain a power feature vector; Determine the correlation between the image feature vector and the node vectors of each fault entity node in the device fault causal knowledge graph; A knowledge gating mask is generated based on the node vector of the faulty entity node with the highest correlation and the image feature vector. Based on the knowledge gating mask, the power feature vector and the image feature vector are fused to obtain the sampled feature vector.
3. The method according to claim 2, characterized in that, The step of fusing the power feature vector and the image feature vector according to the knowledge gating mask to obtain the sampled feature vector includes: The power feature vector is adjusted according to the knowledge gating mask to obtain the adjusted power feature vector; The adjusted power feature vector is concatenated with the image feature vector to obtain the sampled feature vector.
4. The method according to claim 1, characterized in that, Determining the target fault detection result of the power grid equipment based on the auxiliary fault detection result, the sampled feature vector, and the reference feature vector includes: Based on the auxiliary fault detection results, calculate the logical mutual exclusion between the sampled feature vector and the reference feature vector; If the logical mutual exclusion degree is less than the first threshold, then the auxiliary fault detection result is determined as the target fault detection result of the target power grid equipment fault; If the logical mutual exclusion degree is greater than or equal to the first threshold, then the target fault detection result of the target power grid equipment is determined to be no abnormality.
5. The method according to claim 4, characterized in that, The step of calculating the logical mutual exclusion between the sampled feature vector and the reference feature vector based on the auxiliary fault detection result includes: Find the physical logic conditions that match the auxiliary fault detection results, and the logical judgment parameters in the physical logic conditions; Based on the logical judgment parameters, obtain the true values of the logical judgment parameters of the target power grid equipment; Determine whether the true values of the logical judgment parameters of the target power grid equipment satisfy the physical logic conditions to obtain a first result; Based on the first result, the sampled feature vector, and the reference feature vector, calculate the logical mutual exclusion between the sampled feature vector and the reference feature vector.
6. The method according to claim 1, characterized in that, Before acquiring image and power data of the target power grid equipment, the following steps are included: Continuously monitor the spectral energy density of sound signals in the target monitoring location; at least one candidate power grid device is deployed in the target monitoring location; If the spectral energy density is greater than the second threshold, the target power grid device is located from among the candidate power grid devices using a sound source localization algorithm.
7. A fault detection device for power grid equipment, characterized in that, The device includes: The acquisition module is used to acquire image data and power data of the target power grid equipment; the power data is voltage data or current data. The first vector determination module is used to determine the sampling feature vector of the target power grid equipment based on the image data and the power data; The first result determination module is used to determine the auxiliary fault detection result of the power grid equipment based on the sampled feature vector. The second vector determination module is used to perform counterfactual reasoning on the auxiliary fault detection result to obtain the benchmark feature vector corresponding to the auxiliary fault detection result. The second result determination module is used to determine the target fault detection result of the power grid equipment based on the auxiliary fault detection result, the sampled feature vector, and the reference feature vector.
8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a fault detection method for power grid equipment according to any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the fault detection method for the power grid equipment as described in any one of claims 1-6.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the fault detection method for power grid equipment as described in any one of claims 1-6.