Transformer fault diagnosis and early warning method based on Internet of Things

Abstract

The invention provides a transformer fault diagnosis and early warning method based on the Internet of Things, and the method comprises the following steps: S1, building a model: building a transformer three-dimensional simulation model and a diagnosis model; s2, adding constraints; s3, acquiring data; s4, performing simulation operation: performing simulation operation of the transformer through the transformer three-dimensional simulation model; s5, performing abnormal early warning; s6, performing fault diagnosis; s7, carrying out emergency treatment; s8, maintaining the transformer; s9, recording data; according to the invention, the transformer three-dimensional simulation model is set to simulate the actual operation state of the transformer, and the three-dimensional simulation model and the transformer are operated together, so that the transformer fault reason and solution can be deduced through the three-dimensional simulation model, and the diagnosis data and the processing scheme of the fault are obtained before the transformer fault occurs. Therefore, troubleshooting and transformer maintenance can be completed quickly, and the situation that the service life and the subsequent operation state of the transformer are affected due to the fact that fault processing cannot be completed in time after fault early warning is prevented.

Description

Technical Field

[0001] The present invention relates to a diagnosis and early warning method, and in particular to a transformer fault diagnosis and early warning method based on the Internet of Things, and belongs to the technical field of transformer fault diagnosis and early warning. Background Art

[0002] Transformer is a device that uses the principle of electromagnetic induction to change AC voltage. Its main components are primary coil, secondary coil and iron core (magnetic core). Its main functions include voltage conversion, current conversion, impedance conversion, isolation, voltage stabilization (magnetic saturation transformer), etc. Transformers can be divided into distribution transformers, power transformers, fully sealed transformers, combined transformers, dry-type transformers, oil-immersed transformers, single-phase transformers, electric furnace transformers, rectifier transformers, reactors, anti-interference transformers, lightning protection transformers, box-type transformer test transformers, corner transformers, high-current transformers, excitation transformers, etc. Transformers are basic equipment for power transmission and distribution, and are widely used in industry, agriculture, transportation, urban communities and other fields.

[0003] Transformers are high-voltage capacity devices that facilitate the transmission and distribution of electricity. Their main purpose is to reduce the voltage level in a given power system. However, although they are closed devices without rotating parts, they are not completely immune to failures. If these failures occur suddenly and are not controlled, they may damage the transformer and hinder daily operations, leading to catastrophic consequences. Existing transformer fault warning and diagnosis methods only rely on the detection system to provide transformer fault warnings, and cannot obtain the corresponding abnormality handling plan based on the real-time status of the transformer. It is impossible to quickly derive the cause of the transformer abnormality and handle it, resulting in some transformers still unable to be repaired in time after early warning, thereby affecting the service life and subsequent operation status of the transformer;

[0004] In order to solve the above technical problems, a transformer fault diagnosis and early warning method based on the Internet of Things is proposed. Summary of the invention

[0005] In view of this, the present invention provides a transformer fault diagnosis and early warning method based on the Internet of Things to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0006] The technical solution of the present invention is implemented as follows: A transformer fault diagnosis and early warning method based on the Internet of Things comprises the following steps:

[0007] S1. Establish a model, establish a three-dimensional simulation model and a diagnostic model of the transformer;

[0008] S2, adding constraints, adding characteristic constraints to the transformer three-dimensional simulation model to simulate the operating state of the actual transformer;

[0009] S3, obtain data, install monitoring components on the transformer to obtain real-time data;

[0010] S4, simulation operation, performing simulation operation of the transformer through the three-dimensional simulation model of the transformer, and the simulation operation is performed synchronously with the operation of the actual transformer;

[0011] S5, abnormal warning, warning when transformer data is abnormal;

[0012] S6, fault diagnosis, analyzing the causes of transformer abnormalities through the diagnostic model;

[0013] S7, emergency treatment, emergency treatment of the transformer according to the fault diagnosis results;

[0014] S8, transformer maintenance, updating transformer maintenance mode according to abnormal reasons;

[0015] S9. Record the data, the cause of the exception and the method of handling it so that the exception can be handled later.

[0016] Further preferably, in the S1, the diagnostic model has a fault warning mode and a fault diagnosis mode. The fault warning mode focuses on abnormal data generated during the operation of the transformer and issues an alarm when the data continues to be abnormal. The fault diagnosis mode analyzes the cause of the transformer abnormality to obtain an abnormality handling solution. The diagnostic model is associated with the three-dimensional simulation model of the transformer. During the diagnosis process, the abnormality handling solution is analyzed using the actual operation data of the transformer and the simulated operation data of the three-dimensional simulation model of the transformer.

[0017] Further preferably, in S1, common abnormal data of transformers are fed to the diagnostic model, and corresponding processing solutions are matched for it, so that the diagnostic model can perform deep learning so as to quickly obtain solutions when the transformer is abnormal. The data fed to the diagnostic model should be differentiated according to the models and operating conditions of different transformers to obtain more accurate and effective solutions.

[0018] Further preferably, in S2, corresponding material feature constraints are added to the three-dimensional simulation model of the transformer, including physical properties, chemical properties, mechanical properties and other properties such as flexibility, hardness, processing performance, electrical insulation, heat resistance and fatigue resistance, and environmental variables are added to the three-dimensional simulation model of the transformer to simulate the impact of the transformer operating environment on the operating state.

[0019] Further preferably, in said S3, when acquiring transformer data, it is necessary to acquire transformer operating temperature, gas concentration in transformer, transformer oil level and oil temperature, transformer operating abnormal sound and transformer operating screen monitoring data.

[0020] Further preferably, in S4, during the simulated operation, the three-dimensional simulation model of the transformer is affected by the same environmental variables as the actual transformer, and before the actual operation of the transformer, the three-dimensional simulation model of the transformer can be used to perform simulated operation of the transformer in advance to eliminate possible abnormalities.

[0021] Further preferably, in S5, when abnormal data appears in the transformer in a short period of time, the data is paid special attention to and an initial warning is issued, and a fault prediction analysis is performed based on the abnormal data. A fault warning is issued after the abnormal data persists for a certain period of time, and the transformer is powered off for protection after the warning is generated.

[0022] Further preferably, in S6, fault diagnosis is performed based on the monitoring data of the transformer, and fault analysis is first performed through common abnormalities such as sound abnormalities, temperature abnormalities and discharge phenomena, and then matched with existing abnormal data of transformers of this type to obtain existing solutions. If this type of abnormality occurs for the first time, the fault repair plan is deduced in combination with an effective solution to this type of abnormality and a three-dimensional simulation model of the transformer.

[0023] Further preferably, in S7, emergency treatment is performed on the transformer according to the solution obtained from the diagnosis model, and other abnormalities are checked according to the operating data of the three-dimensional simulation model of the transformer.

[0024] Further preferably, in S8, the sound, temperature and discharge phenomenon of the transformer are regularly checked to keep the equipment clean, ensure that the tap changer is in good contact, and perform corresponding inspections according to any abnormalities that have occurred in the transformer.

[0025] The embodiment of the present invention has the following advantages due to the adoption of the above technical solution:

[0026] 1. The present invention simulates the actual operating state of the transformer by setting a three-dimensional simulation model of the transformer, so that the three-dimensional simulation model runs together with the transformer, so that the cause and solution of the transformer failure can be deduced through the three-dimensional simulation model, and the diagnostic data and processing plan of the fault can be obtained before the transformer failure occurs, so as to quickly complete the fault investigation and transformer maintenance, and prevent the failure to complete the fault processing in time after the fault warning, which will affect the service life and subsequent operating state of the transformer;

[0027] 2. The present invention feeds the diagnostic model with abnormal data of various transformers for deep learning, which facilitates the rapid retrieval of abnormal causes and matching with existing solutions when the transformer data is abnormal, and enables the diagnostic model to cooperate with the three-dimensional simulation model to infer and simulate solutions for unknown abnormalities, so as to assist the staff to quickly complete the transformer fault detection.

[0028] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art 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.

[0030] Figure 1 The figure is a flow chart of the transformer fault diagnosis and early warning method of the present invention. DETAILED DESCRIPTION

[0031] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0032] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0033] Embodiment 1

[0034] like Figure 1 A transformer fault diagnosis and early warning method based on the Internet of Things is shown, comprising the following steps:

[0035] S1. Establish a model. Establish a three-dimensional simulation model and a diagnosis model for the transformer. The diagnosis model has a fault warning mode and a fault diagnosis mode. The fault warning mode focuses on the abnormal data generated during the operation of the transformer and issues an alarm when the data continues to be abnormal. The fault diagnosis mode analyzes the abnormal causes of the transformer to obtain an abnormal treatment plan. The diagnosis model is associated with the three-dimensional simulation model of the transformer. During the diagnosis process, the abnormal treatment plan is analyzed with the actual operation data of the transformer and the simulated operation data of the three-dimensional simulation model of the transformer. The common abnormal data of the transformer is fed to the diagnosis model, and the corresponding treatment plan is matched for it, so that the diagnosis model can perform deep learning so as to quickly obtain a solution when the transformer is abnormal. The data fed to the diagnosis model should be differentiated according to the models and operating conditions of different transformers to obtain a more accurate and effective solution;

[0036] S2. Add constraints, add characteristic constraints to the transformer 3D simulation model to simulate the actual operating state of the transformer, add corresponding material characteristic constraints to the transformer 3D simulation model, including physical properties, chemical properties, mechanical properties and other properties such as flexibility, hardness, processing performance, electrical insulation, heat resistance and fatigue resistance, and add environmental variables to the transformer 3D simulation model to simulate the impact of the transformer operating environment on the operating state;

[0037] S3, obtain data, add monitoring components to the transformer to obtain real-time data. When obtaining transformer data, it is necessary to obtain transformer operating temperature, gas concentration in the transformer, transformer oil level and oil temperature, transformer operating abnormal sound and transformer operating screen monitoring data;

[0038] S4, simulation operation, the transformer is simulated by the three-dimensional simulation model, the simulation operation is carried out synchronously with the operation of the actual transformer, the three-dimensional simulation model of the transformer is affected by the same environmental variables as the actual transformer during the simulation operation, and the three-dimensional simulation model of the transformer can be used to simulate the operation of the transformer in advance before the actual operation of the transformer to eliminate possible abnormalities;

[0039] S5, abnormal warning, warning when the transformer data is abnormal. When the transformer has abnormal data in a short period of time, the data will be paid special attention to and the initial warning will be issued. Fault prediction analysis will be performed based on the abnormal data. Fault warning will be issued after the abnormal data continues for a certain period of time, and the transformer will be powered off for protection after the warning is generated.

[0040] S6. Fault diagnosis: Analyze the cause of transformer abnormality through the diagnostic model, and perform fault diagnosis based on the monitoring data of the transformer. First, perform fault analysis through common abnormalities such as abnormal sound, abnormal temperature and discharge phenomenon, and then match it with the existing abnormal data of this type of transformer to obtain the existing solution. If this type of abnormality occurs for the first time, combine the effective solution of this type of abnormality with the three-dimensional simulation model of the transformer to deduce the fault repair plan;

[0041] S7, emergency treatment, emergency treatment of the transformer according to the fault diagnosis results, emergency treatment of the transformer according to the solution obtained by the diagnosis model, and other abnormalities are checked according to the operation data of the transformer 3D simulation model;

[0042] S8. Transformer maintenance: update the transformer maintenance mode according to the abnormal cause, regularly check the transformer sound, temperature and discharge phenomenon, keep the equipment clean, ensure the tap changer is in good contact, and perform corresponding inspections according to the abnormalities that have occurred in the transformer;

[0043] S9. Record the data, the cause of the exception and the method of handling it so that the exception can be handled later.

[0044] In one embodiment, in S4, during the simulation operation, a real-time backup is added to the three-dimensional simulation model of the transformer, and when an abnormal warning occurs, the source model is used to assist the diagnosis model in fault diagnosis and solution deduction, and the backup model continues to run synchronously with the transformer.

[0045] Embodiment 2

[0046] like Figure 1 A transformer fault diagnosis and early warning method based on the Internet of Things is shown, comprising the following steps:

[0047] S1. Establish a model and add constraints. Establish a three-dimensional simulation model and a diagnostic model for the transformer. The diagnostic model has a fault warning mode and a fault diagnosis mode. The fault warning mode focuses on the abnormal data generated during the operation of the transformer and issues an alarm when the data continues to be abnormal. The fault diagnosis mode analyzes the abnormal causes of the transformer to obtain an abnormal treatment plan. The diagnostic model is associated with the three-dimensional simulation model of the transformer. During the diagnosis process, the abnormal treatment plan is analyzed with the actual operation data of the transformer and the simulated operation data of the three-dimensional simulation model of the transformer. The common abnormal data of the transformer is fed to the diagnostic model, and the corresponding treatment plan is matched for it, so that the diagnostic model can perform deep learning to quickly obtain a solution when the transformer is abnormal. The data fed to the diagnostic model should be differentiated according to the models and operating conditions of different transformers to obtain a more accurate and effective solution. Feature constraints are added to the three-dimensional simulation model of the transformer to simulate the actual operating state of the transformer. Corresponding material feature constraints are added to the three-dimensional simulation model of the transformer, including physical properties, chemical properties, mechanical properties and other properties such as flexibility, hardness, processing performance, electrical insulation, heat resistance and fatigue resistance. Environmental variables are added to the three-dimensional simulation model of the transformer to simulate the impact of the transformer operating environment on the operating state;

[0048] S2. Acquire data. Install monitoring components on the transformer to acquire real-time data. When acquiring transformer data, it is necessary to acquire transformer operating temperature, gas concentration in the transformer, transformer oil level and oil temperature, transformer abnormal sound, and transformer operation screen monitoring data;

[0049] S3, simulation operation, the transformer is simulated by the three-dimensional simulation model of the transformer, the simulation operation is carried out synchronously with the operation of the actual transformer, the three-dimensional simulation model of the transformer is affected by the same environmental variables as the actual transformer during the simulation operation, and the three-dimensional simulation model of the transformer can be used to simulate the operation of the transformer in advance before the actual operation of the transformer to eliminate possible abnormalities;

[0050] S4, abnormal warning, warning when the transformer data is abnormal. When the transformer has abnormal data in a short period of time, the data will be paid special attention to and the initial warning will be issued. Fault prediction analysis will be performed based on the abnormal data. Fault warning will be issued after the abnormal data continues for a certain period of time, and the transformer will be powered off for protection after the warning is generated.

[0051] S5. Fault diagnosis: Analyze the cause of transformer abnormality through the diagnostic model, and perform fault diagnosis based on the monitoring data of the transformer. First, perform fault analysis through common abnormalities such as abnormal sound, abnormal temperature and discharge phenomenon, and then match it with the existing abnormal data of this type of transformer to obtain the existing solution. If this type of abnormality occurs for the first time, combine the effective solution of this type of abnormality with the three-dimensional simulation model of the transformer to deduce the fault repair plan;

[0052] S6. Emergency treatment: perform emergency treatment on the transformer according to the fault diagnosis results, perform emergency treatment on the transformer according to the solution obtained by the diagnosis model, and conduct other abnormality investigations based on the operating data of the transformer 3D simulation model;

[0053] S7, transformer maintenance, update the transformer maintenance mode according to the abnormal cause, regularly check the transformer sound, temperature and discharge phenomenon, keep the equipment clean, ensure the tap changer is in good contact, and perform corresponding inspections according to the abnormalities that have occurred in the transformer;

[0054] S8. Record data, record the cause of the exception and the treatment method so as to handle the exception in the future, and feed the processing flow data to the diagnosis model for update learning to enrich the database of the diagnosis model.

[0055] When the present invention is working, a three-dimensional simulation model and a diagnostic model of a transformer are established, and corresponding material feature constraints are added to the three-dimensional simulation model of the transformer, including physical properties, chemical properties, mechanical properties and other properties such as flexibility, hardness, processing performance, electrical insulation, heat resistance and fatigue resistance, and environmental variables are added to the three-dimensional simulation model of the transformer to simulate the influence of the transformer operating environment on the operating state, and the common abnormal data of the transformer are fed to the diagnostic model, and the corresponding processing scheme is matched for it, so that the diagnostic model can perform deep learning so as to quickly obtain a solution when the transformer is abnormal. The data fed to the diagnostic model should be differentiated according to the models and operating conditions of different transformers to obtain a more accurate and effective solution. A monitoring component is added to the transformer to obtain real-time data. When obtaining transformer data, it is necessary to obtain the transformer operating temperature, gas concentration in the transformer, transformer oil level and oil temperature, transformer operating abnormal sound and transformer operating screen monitoring data. The simulation operation is carried out synchronously with the operation of the actual transformer. When the three-dimensional simulation model of the transformer is simulated, the influence of environmental variables on the transformer is consistent with that of the actual transformer, and the three-dimensional simulation model of the transformer can be used in advance before the actual operation of the transformer. The three-dimensional simulation model of the transformer simulates the operation of the transformer to eliminate possible abnormalities. When abnormal data appears in the transformer in a short period of time, the data is focused on and the initial warning is issued. Fault prediction analysis is performed based on the abnormal data. After the abnormal data continues for a certain period of time, a fault warning is issued, and the transformer is powered off after the warning is generated. The cause of the transformer abnormality is analyzed through the diagnostic model, and fault diagnosis is performed based on the monitoring data of the transformer. First, the fault analysis is performed through common abnormalities such as sound abnormalities, temperature abnormalities, and discharge phenomena, and then matched with the existing abnormal data of this type of transformer to obtain the existing solution. If this type of abnormality occurs for the first time, the effective solution to this type of abnormality is combined with the three-dimensional simulation model of the transformer to deduce the fault repair plan. The transformer is treated in an emergency according to the solution obtained by the diagnostic model, and other abnormalities are checked according to the operation data of the three-dimensional simulation model of the transformer. The sound, temperature and discharge phenomenon of the transformer are regularly checked, the equipment is kept clean, and the tap switch is ensured to be in good contact. According to the abnormalities that have occurred in the transformer, corresponding inspections are performed, and the causes and treatment methods of the abnormalities are recorded for subsequent processing of such abnormalities.

[0056] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A transformer fault diagnosis and early warning method based on the Internet of Things, characterized in that: The following steps are involved: S1. Establish a model, establish a three-dimensional simulation model and a diagnostic model of the transformer; S2, adding constraints, adding characteristic constraints to the transformer three-dimensional simulation model to simulate the operating state of the actual transformer; S3, obtain data, install monitoring components on the transformer to obtain real-time data; S4, simulation operation, performing simulation operation of the transformer through the three-dimensional simulation model of the transformer, and the simulation operation is performed synchronously with the operation of the actual transformer; S5, abnormal warning, warning when transformer data is abnormal; S6, fault diagnosis, analyzing the causes of transformer abnormalities through the diagnostic model; S7, emergency treatment, emergency treatment of the transformer according to the fault diagnosis results; S8, transformer maintenance, updating transformer maintenance mode according to abnormal reasons; S9. Record the data, the cause of the exception and the method of handling it so that the exception can be handled later.

2. The method for transformer fault diagnosis and early warning based on the Internet of Things according to claim 1, characterized in that: In S1, the diagnostic model has a fault warning mode and a fault diagnosis mode. The fault warning mode focuses on abnormal data generated during the operation of the transformer and issues an alarm when the data continues to be abnormal. The fault diagnosis mode analyzes the cause of the transformer abnormality to obtain an abnormality handling solution. The diagnostic model is associated with the three-dimensional simulation model of the transformer. During the diagnosis process, the abnormality handling solution is analyzed using the actual operation data of the transformer and the simulated operation data of the three-dimensional simulation model of the transformer.

3. The transformer fault diagnosis and early warning method based on the Internet of Things according to claim 1 is characterized in that: In S1, common abnormal data of transformers are fed to the diagnostic model, and corresponding processing solutions are matched for it, so that the diagnostic model can perform deep learning so as to quickly obtain solutions when the transformer is abnormal. The data fed to the diagnostic model should be differentiated according to the models and operating conditions of different transformers to obtain more accurate and effective solutions.

4. The transformer fault diagnosis and early warning method based on the Internet of Things according to claim 1 is characterized in that: In the S2, corresponding material feature constraints are added to the three-dimensional simulation model of the transformer, including physical properties, chemical properties, mechanical properties and other properties such as flexibility, hardness, processing performance, electrical insulation, heat resistance and fatigue resistance, and environmental variables are added to the three-dimensional simulation model of the transformer to simulate the impact of the transformer operating environment on the operating state.

5. The transformer fault diagnosis and early warning method based on the Internet of Things according to claim 1 is characterized in that: In S3, when obtaining transformer data, it is necessary to obtain transformer operating temperature, gas concentration in transformer, transformer oil level and oil temperature, transformer operating abnormal sound and transformer operating screen monitoring data.

6. The method for transformer fault diagnosis and early warning based on the Internet of Things according to claim 1 is characterized in that: In S4, during the simulated operation, the three-dimensional transformer simulation model is affected by the same environmental variables as the actual transformer, and before the actual operation of the transformer, the three-dimensional transformer simulation model can be used to simulate the operation of the transformer in advance to eliminate possible abnormalities.

7. The method for transformer fault diagnosis and early warning based on the Internet of Things according to claim 1 is characterized in that: In S5, when abnormal data appears in the transformer in a short period of time, the data is focused on and an initial warning is issued, and fault prediction analysis is performed based on the abnormal data. A fault warning is issued after the abnormal data continues for a certain period of time, and the transformer is powered off for protection after the warning is generated.

8. The method for transformer fault diagnosis and early warning based on the Internet of Things according to claim 1, characterized in that: In S6, fault diagnosis is performed based on the monitoring data of the transformer. First, fault analysis is performed through common abnormalities such as sound abnormalities, temperature abnormalities and discharge phenomena. Then, the fault is matched with existing abnormal data of transformers of this type to obtain existing solutions. If this type of abnormality occurs for the first time, the fault repair plan is deduced in combination with an effective solution for this type of abnormality and a three-dimensional simulation model of the transformer.

9. The method for transformer fault diagnosis and early warning based on the Internet of Things according to claim 1, characterized in that: In S7, emergency treatment is performed on the transformer according to the solution obtained from the diagnosis model, and other abnormalities are checked according to the operation data of the three-dimensional simulation model of the transformer.

10. The method for transformer fault diagnosis and early warning based on the Internet of Things according to claim 1, characterized in that: In the above S8, the sound, temperature and discharge phenomenon of the transformer are regularly checked, the equipment is kept clean, the tap changer is ensured to be in good contact, and corresponding inspections are performed according to any abnormalities that have occurred in the transformer.

Images