Transformer oil tank fault diagnosis method, equipment, medium and product

Abstract

The invention discloses a transformer oil tank fault diagnosis method and device, a medium and a product, and relates to the field of transformer fault diagnos.The method comprises the steps that a sensor, a camera, a digital twin system and an artificial intelligence system are connected to a target transformer, and the sensor is adopted to obtain oil chromatography data of the target transformer; judging whether metal suspension discharge exists in an oil tank of the target transformer or not according to the oil chromatogram data, acquiring an oil tank hot-spot temperature of the target transformer by adopting a digital twin system, judging whether the oil tank temperature of the target transformer is abnormal or not according to the oil tank hot-spot temperature, and acquiring an oil tank image of the target transformer by adopting a camera; and an artificial intelligence system is adopted to judge whether the target transformer has the oil leakage condition of the oil tank according to the oil tank image, so that online diagnosis of the oil tank fault of the target transformer is realized.

Description

Technical Field

[0001] The present application relates to the field of transformer fault diagnosis, and in particular to a transformer oil tank fault diagnosis method, equipment, medium and product. Background Art

[0002] In today's era of rapid technological development, artificial intelligence and digital twin technology, as important driving forces for the development of power grids, are gradually leading the power industry into a new era of intelligence and digitalization. With the profound changes in the global energy structure and the rapid rise of clean energy, the power grid, as the "artery" of power transmission, faces unprecedented opportunities and challenges.

[0003] Existing transformer fault diagnosis technologies are basically based on oil chromatography and partial discharge monitoring, especially the former, which has been tested in many years of power grid operation and has high reliability and judgment accuracy. However, it has the defect of lag and usually cannot respond immediately when a fault occurs. Instead, it can provide a basis for diagnosis after the fault occurs. Summary of the invention

[0004] The purpose of this application is to provide a transformer oil tank fault diagnosis method, equipment, medium and product, which can realize online diagnosis of transformer oil tank faults.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a transformer oil tank fault diagnosis method, which is applied to a target transformer connected to a sensor, a camera, a digital twin system, and an artificial intelligence system; the transformer oil tank fault diagnosis method comprises:

[0007] A sensor is used to obtain oil chromatogram data of a target transformer, and based on the oil chromatogram data, it is determined whether there is metal suspended discharge in the oil tank of the target transformer;

[0008] The digital twin system is used to obtain the hot spot temperature of the oil tank of the target transformer, and whether the oil tank temperature of the target transformer is abnormal is determined according to the hot spot temperature of the oil tank;

[0009] A camera is used to obtain an image of the oil tank of the target transformer, and an artificial intelligence system is used to determine whether there is oil leakage in the oil tank of the target transformer based on the image of the oil tank.

[0010] Optionally, a sensor is used to obtain oil chromatogram data of a target transformer, and judging whether there is metal suspension discharge in an oil tank of the target transformer according to the oil chromatogram data, including:

[0011] A sensor is used to obtain oil chromatogram data of a target transformer; the oil chromatogram data includes hydrogen content, methane content, acetylene content, ethylene content and ethane content;

[0012] Determining whether the acetylene content is greater than a set caution value, and detecting low-energy discharge using a three-ratio method according to the oil chromatogram data;

[0013] If the acetylene content is greater than the set attention value and low-energy discharge is detected by the three-ratio method, then there is a metal suspension discharge in the oil tank of the target transformer;

[0014] If the acetylene content is less than or equal to the set attention value, or low-energy discharge is not detected by the three-ratio method, there is no metal suspension discharge in the oil tank of the target transformer.

[0015] Optionally, the set attention value is determined according to the inherent situation of the target transformer; the three-ratio method detects low-energy discharge by calculating the ratio of acetylene content to ethylene content, the ratio of methane content to hydrogen content, and the ratio of ethylene content to ethane content.

[0016] Optionally, a digital twin system is used to obtain a hotspot temperature of an oil tank of a target transformer, and judging whether the oil tank temperature of the target transformer is abnormal according to the hotspot temperature of the oil tank, including:

[0017] Use the digital twin system to obtain the hot spot temperature of the oil tank of the target transformer;

[0018] Determining whether the hot spot temperature of the fuel tank is greater than a set temperature value;

[0019] If the hot spot temperature of the oil tank is greater than the set temperature value, the oil tank temperature of the target transformer is abnormal;

[0020] If the oil tank hot spot temperature is less than or equal to the set temperature value, the oil tank temperature of the target transformer is normal.

[0021] Optionally, the digital twin system is an agent model generated by simulation of the target transformer; the digital twin system runs on a server in the substation, and calculates the internal temperature distribution of the oil tank of the target transformer in real time by accessing the current load information, inlet oil temperature and ambient temperature of the target transformer, and obtains the hot spot temperature of the oil tank of the target transformer; the set temperature value is 85°C.

[0022] Optionally, a camera is used to obtain an image of an oil tank of a target transformer, and an artificial intelligence system is used to determine whether there is oil leakage in the oil tank of the target transformer according to the image of the oil tank, including:

[0023] A camera is used to obtain an image of the oil tank of the target transformer;

[0024] Using a first image recognition model deployed by the artificial intelligence system to perform target detection on the fuel tank image to determine whether there are signs of oil leakage from the fuel tank;

[0025] If there are signs of oil leakage from the oil tank, then the target transformer has oil leakage from the oil tank;

[0026] If there is no sign of oil leakage from the oil tank, then the target transformer does not have oil leakage from the oil tank.

[0027] Optionally, a camera is used to obtain an oil tank image of a target transformer, and an artificial intelligence system is used to determine whether there is oil leakage in the oil tank of the target transformer according to the oil tank image, further comprising:

[0028] If the target transformer has oil leakage in the oil tank, the second image recognition model deployed by the artificial intelligence system is used to locate the oil leakage area in the oil tank image and determine whether the oil leakage is serious;

[0029] If it is a minor oil leakage, an alarm will be issued;

[0030] If it is a serious oil leakage, an alarm will be issued and operation and maintenance suggestions for power outage will be given.

[0031] In a second aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the transformer oil tank fault diagnosis method.

[0032] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the transformer oil tank fault diagnosis method when executed by a processor.

[0033] In a fourth aspect, the present application provides a computer program product, including a computer program, which implements the transformer oil tank fault diagnosis method when executed by a processor.

[0034] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0035] The present application provides a transformer oil tank fault diagnosis method, equipment, medium and product. By connecting a target transformer to a sensor, a camera, a digital twin system and an artificial intelligence system, a sensor is used to obtain oil chromatography data of the target transformer, and it is judged whether there is metal suspension discharge in the oil tank of the target transformer based on the oil chromatography data. The digital twin system is used to obtain the hot spot temperature of the oil tank of the target transformer, and it is judged whether the oil tank temperature of the target transformer is abnormal based on the hot spot temperature of the oil tank. A camera is used to obtain an oil tank image of the target transformer, and an artificial intelligence system is used to judge whether there is oil leakage in the oil tank of the target transformer based on the oil tank image, thereby realizing online diagnosis of the target transformer oil tank fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A flow chart of a transformer tank fault diagnosis method provided for this application;

[0038] Figure 2 Logical reasoning flow chart of transformer oil tank failure provided for this application. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0040] The rise of artificial intelligence technology has brought unprecedented opportunities for intelligent upgrades to the power grid. Through advanced algorithms such as deep learning and big data analysis, artificial intelligence technology can achieve real-time monitoring of the power grid's operating status, fault identification, and intelligent dispatch, thereby greatly improving the operating efficiency and safety of the power grid.

[0041] Digital twin technology, as a product of the combination of physical power grid and digital model, provides a new solution for real-time monitoring, optimized operation and preventive maintenance of power grid. By building a digital twin model of the power grid, it is possible to achieve comprehensive digital modeling of power grid equipment, lines, sensors and other elements, and through real-time data collection and monitoring, the operation status of the power grid can be fully and accurately grasped.

[0042] Based on this, this application proposes a transformer oil tank fault diagnosis method, equipment, medium and product, which applies artificial intelligence technology and digital twin technology to the fault diagnosis logic reasoning of the transformer oil tank. It can make online autonomous judgments on the fault status of the transformer oil tank and give corresponding operation and maintenance suggestions, greatly improving work efficiency.

[0043] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0044] In an exemplary embodiment, the present application provides a transformer tank fault diagnosis method, which is applied to a target transformer connected to a sensor, a camera, a digital twin system, and an artificial intelligence system, such as Figure 1 As shown, the method includes the following steps 1 to 3.

[0045] Step 1: Use a sensor to obtain oil chromatogram data of a target transformer, and determine whether there is metal suspension discharge in the oil tank of the target transformer according to the oil chromatogram data.

[0046] Step 1 specifically includes:

[0047] Step 1-1: Use a sensor to obtain oil chromatogram data of a target transformer, wherein the oil chromatogram data includes hydrogen content, methane content, acetylene content, ethylene content and ethane content.

[0048] Step 1-2: Determine whether the acetylene content is greater than a set warning value, and use a three-ratio method to detect low-energy discharge based on the oil chromatography data.

[0049] Step 1-3: If the acetylene content is greater than the set attention value and low-energy discharge is detected by the three-ratio method, metal suspension discharge exists in the oil tank of the target transformer.

[0050] Step 1-4: If the acetylene content is less than or equal to the set attention value, or the three-ratio method does not detect low-energy discharge, then there is no metal suspension discharge in the oil tank of the target transformer.

[0051] The set attention value is used to determine the content, growth amount, and growth rate of certain gases in the oil chromatogram. It needs to be formulated according to the situation of each transformer. The same transformer may also change this value due to a fault. The three-ratio method is one of the classic methods for transformer oil chromatogram diagnosis. By monitoring hydrogen (H 2 ), methane (CH 4 ), acetylene (C 2 H 2 ), ethylene (C 2 H 4 ) and ethane (C 2 H 6 ) gas content, and C 2 H 2 / C 2 H 4 , CH 4 / H 2 and C 2 H 4 / C 2 H 6The type of fault is determined based on the range of the three groups of ratio data to detect low-energy discharge.

[0052] Step 2: Use the digital twin system to obtain the oil tank hotspot temperature of the target transformer, and determine whether the oil tank temperature of the target transformer is abnormal based on the oil tank hotspot temperature.

[0053] Step 2 specifically includes:

[0054] Step 2-1: Use the digital twin system to obtain the hot spot temperature of the oil tank of the target transformer.

[0055] Step 2-2: Determine whether the hot spot temperature of the fuel tank is greater than a set temperature value.

[0056] Step 2-3: If the hot spot temperature of the oil tank is greater than the set temperature value, the oil tank temperature of the target transformer is abnormal.

[0057] Step 2-4: If the oil tank hot spot temperature is less than or equal to the set temperature value, the oil tank temperature of the target transformer is normal.

[0058] The digital twin system is a proxy model generated by the target transformer through simulation. The digital twin system runs on the server of the substation, and calculates the internal temperature distribution of the target transformer's oil tank in real time by accessing the current load information, inlet oil temperature and ambient temperature of the target transformer, and obtains the hot spot temperature of the target transformer's oil tank. The set temperature value is 85°C.

[0059] Step 3: Use a camera to obtain an image of the oil tank of the target transformer, and use an artificial intelligence system to determine whether there is oil leakage in the oil tank of the target transformer based on the image of the oil tank.

[0060] Step 3 specifically includes:

[0061] Step 3-1: Use a camera to obtain an image of the oil tank of the target transformer.

[0062] Step 3-2: Use the first image recognition model deployed by the artificial intelligence system to perform target detection on the fuel tank image to determine whether there are signs of oil leakage from the fuel tank.

[0063] Step 3-3: If there are signs of oil tank leakage, the target transformer has oil tank leakage.

[0064] Step 3-4: If there is no sign of oil tank leakage, the target transformer does not have oil tank leakage.

[0065] Step 3 further includes:

[0066] Step 3-5: If the target transformer has oil leakage in the oil tank, the second image recognition model deployed by the artificial intelligence system is used to locate the oil leakage area in the oil tank image and determine whether the oil leakage is serious.

[0067] Step 3-6: If it is a minor oil leakage, an alarm will be issued.

[0068] Step 3-7: If it is a serious oil leakage, an alarm is issued and operation and maintenance suggestions for power outage are given.

[0069] This application uses knowledge graph as the reasoning basis, artificial intelligence technology and digital twin technology as key data support, and realizes online diagnosis of transformer oil tank faults. Among them, the knowledge graph is completed by the expert team based on actual cases and expert experience. By sorting out common faults of components, deducing the causes of faults, and building connections with various manifestations of faults, it finally completes the fault diagnosis logic knowledge graph that discovers abnormalities from manifestations, triggers diagnosis, confirms defects after fault diagnosis logic, and gives operation and maintenance suggestions.

[0070] like Figure 2 As shown in the figure, the logical reasoning diagnosis process of the fuel tank fault specifically includes:

[0071] Step 1: By connecting sensors, artificial intelligence and digital twin systems to the normally operating transformer, acetylene content, oil chromatography data three-ratio method, oil tank hot spot temperature and oil leakage traces are used as trigger conditions for the diagnostic system. Among them, the oil chromatography data including acetylene is sensor data, which is a conventional online monitoring method installed in most of the transformers in operation. The oil tank hot spot temperature detection adopts digital twin technology, specifically the real-time simulation of the proxy model generated by the transformer through simulation reduction. It runs on the server of the substation, and calculates the temperature distribution inside the oil tank in real time by connecting to the current load information, inlet oil temperature and ambient temperature of the transformer. The temperature distribution simulation result is regarded as the feedback of the real transformer operation state, and plays the role of virtual sensor in the fault diagnosis reasoning process of the transformer oil tank components, so as to realize the comprehensive perception of the oil tank temperature. The oil leakage detection adopts artificial intelligence technology, and the pictures taken by the camera are used for target detection through artificial intelligence image recognition technology (such as YOLO, FasterR-CNN, SSD, etc.) to determine whether there is oil leakage. If there is, the oil leakage area in the image is located, and it is determined whether the oil leakage is slight or serious.

[0072] Step 2: When the trigger condition is met, the diagnostic system will start and start the logical reasoning of the corresponding route according to the corresponding trigger condition. When the three-ratio method detects low-energy discharge, the system will query the acetylene content and determine whether it is greater than the set attention value, or triggered by the acetylene content. The system checks the results of the three-ratio method. When both exist at the same time, the diagnostic system concludes that there is a metal suspension discharge in the fuel tank. When there is a node exceeding 85°C in the fuel tank part of the real-time simulation results of the reduced-order model of the digital twin system, the diagnostic system concludes that the fuel tank temperature is abnormal. When artificial intelligence image recognition detects oil leakage, the diagnostic system concludes that there is an oil leakage problem in the fuel tank. When the oil leakage is serious, the diagnostic system will alarm and give operation and maintenance suggestions for power outage processing.

[0073] In summary, this application combines artificial intelligence technology, digital twin technology and knowledge graph logical reasoning to achieve online logical reasoning diagnosis of transformer oil tank faults, and gives corresponding operation and maintenance suggestions to improve the efficiency of operation and maintenance work. The relevant technical solutions can be extended to the diagnosis of various faults such as overheating, partial discharge, oil leakage, insulation moisture, etc. of other main components of transformers such as cores, leads, windings, and bushings, and have good application prospects.

[0074] In an exemplary embodiment, the present application further provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0075] In an exemplary embodiment, the present application further provides a computer-readable storage medium storing a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0076] In an exemplary embodiment, the present application further provides a computer program product, including a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0077] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where the application is located, and with the authorization of the corresponding device owner. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant legal provisions.

[0078] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0079] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0080] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A transformer oil tank fault diagnosis method, characterized in that: Applied to a target transformer connected to a sensor, a camera, a digital twin system and an artificial intelligence system; the transformer oil tank fault diagnosis method includes: A sensor is used to obtain oil chromatogram data of a target transformer, and based on the oil chromatogram data, it is determined whether there is metal suspended discharge in the oil tank of the target transformer; The digital twin system is used to obtain the hot spot temperature of the oil tank of the target transformer, and whether the oil tank temperature of the target transformer is abnormal is determined according to the hot spot temperature of the oil tank; A camera is used to obtain an image of the oil tank of the target transformer, and an artificial intelligence system is used to determine whether there is oil leakage in the oil tank of the target transformer based on the image of the oil tank.

2. The transformer oil tank fault diagnosis method according to claim 1, characterized in that: The oil chromatogram data of the target transformer is obtained by using a sensor, and whether there is a metal suspension discharge in the oil tank of the target transformer is determined according to the oil chromatogram data, including: A sensor is used to obtain oil chromatogram data of a target transformer; the oil chromatogram data includes hydrogen content, methane content, acetylene content, ethylene content and ethane content; Determining whether the acetylene content is greater than a set caution value, and detecting low-energy discharge using a three-ratio method according to the oil chromatogram data; If the acetylene content is greater than the set attention value and low-energy discharge is detected by the three-ratio method, then there is a metal suspension discharge in the oil tank of the target transformer; If the acetylene content is less than or equal to the set attention value, or the low-energy discharge is not detected by the three-ratio method, then there is no metal suspension discharge in the oil tank of the target transformer.

3. The transformer oil tank fault diagnosis method according to claim 2, characterized in that: The set attention value is determined according to the inherent condition of the target transformer; the three-ratio method detects low-energy discharge by calculating the ratio of acetylene content to ethylene content, the ratio of methane content to hydrogen content, and the ratio of ethylene content to ethane content.

4. The transformer oil tank fault diagnosis method according to claim 1, characterized in that: The digital twin system is used to obtain the hot spot temperature of the oil tank of the target transformer, and whether the oil tank temperature of the target transformer is abnormal is determined according to the hot spot temperature of the oil tank, including: Use the digital twin system to obtain the hot spot temperature of the oil tank of the target transformer; Determining whether the hot spot temperature of the fuel tank is greater than a set temperature value; If the hot spot temperature of the oil tank is greater than the set temperature value, the oil tank temperature of the target transformer is abnormal; If the oil tank hot spot temperature is less than or equal to the set temperature value, the oil tank temperature of the target transformer is normal.

5. The transformer oil tank fault diagnosis method according to claim 4, characterized in that: The digital twin system is an agent model generated by simulation of the target transformer; the digital twin system runs on the server of the substation, and by accessing the current load information, inlet oil temperature and ambient temperature of the target transformer, it simulates and calculates the internal temperature distribution of the oil tank of the target transformer in real time to obtain the hot spot temperature of the oil tank of the target transformer; the set temperature value is 85°C.

6. The transformer oil tank fault diagnosis method according to claim 1, characterized in that: A camera is used to obtain an image of the oil tank of the target transformer, and an artificial intelligence system is used to determine whether the target transformer has oil tank leakage according to the image of the oil tank, including: A camera is used to obtain an image of the oil tank of the target transformer; Using a first image recognition model deployed by the artificial intelligence system to perform target detection on the fuel tank image to determine whether there are signs of oil leakage from the fuel tank; If there are signs of oil leakage from the oil tank, then the target transformer has oil leakage from the oil tank; If there is no sign of oil leakage from the oil tank, then the target transformer does not have oil leakage from the oil tank.

7. The transformer oil tank fault diagnosis method according to claim 6, characterized in that: A camera is used to obtain an image of the oil tank of the target transformer, and an artificial intelligence system is used to determine whether the target transformer has oil leakage in the oil tank according to the image of the oil tank, and further includes: If the target transformer has oil leakage in the oil tank, the second image recognition model deployed by the artificial intelligence system is used to locate the oil leakage area in the oil tank image and determine whether the oil leakage is serious; If it is a minor oil leakage, an alarm will be issued; If it is a serious oil leakage, an alarm will be issued and operation and maintenance suggestions for power outage will be given.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the transformer oil tank fault diagnosis method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the transformer oil tank fault diagnosis method described in any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the transformer oil tank fault diagnosis method described in any one of claims 1 to 7 is implemented.

Images