Transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition

Abstract

The invention discloses a transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition, and relates to the technical field of power equipment fault diagnosis. The system comprises a data acquisition module used for acquiring concentration data of various characteristic dissolved gases in transformer oil; the gas production rate calculation module is used for receiving the concentration data of the various characteristic dissolved gases and calculating the absolute gas production rate of each gas; the big data analysis module is used for receiving the concentration data of the gas and establishing a mapping relation between fault features and fault types based on a machine learning algorithm; the fault diagnosis module is used for receiving the gas production rate calculation result and the big data analysis result and comprehensively judging the fault type of the transformer; and the result output module is used for receiving the fault diagnosis result and outputting the fault diagnosis result in a visual mode. The method is mainly suitable for sealed and oil-immersed transformers with the voltage class of 110kV and above, and can improve the accuracy and timeliness of transformer fault diagnosis in combination with big data analysis and gas production rate calculation.

Description

Technical Field

[0001] This invention relates to the field of power equipment fault diagnosis technology, specifically a transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition. Background Technology

[0002] As a core piece of equipment in the power system, the operational reliability of power transformers directly determines the safety and stability of the power system. When an electrical or thermal fault occurs in a transformer, the insulating oil and solid insulating materials decompose under electrical and thermal stress, producing characteristic gases such as hydrogen, methane, ethane, ethylene, acetylene, carbon monoxide, and carbon dioxide, which dissolve in the oil. Dissolved gas analysis (DGA) technology in transformer oil detects the types and amounts of these gases to identify fault types and assess their condition, and has become an important means of online monitoring and fault diagnosis of transformers.

[0003] However, traditional DGA methods mainly rely on the absolute value or ratio of gas concentration, such as the Duval triangular diagram method and the IEC three-ratio method. These methods have limitations, such as failing to accurately reflect the development trend of faults, insufficient sensitivity to early-stage faults, and susceptibility to external interference. With the development of big data technology, how to combine big data analysis and gas production rate calculation to improve the accuracy and timeliness of transformer fault diagnosis has become an urgent problem to be solved.

[0004] Therefore, this invention proposes a transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition. Summary of the Invention

[0005] The purpose of this invention is to provide a transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition, comprising: The data acquisition module is used to collect concentration data of various characteristic dissolved gases in transformer oil; A gas production rate calculation module, connected to the data acquisition module, is used to receive concentration data of various characteristic dissolved gases and calculate the absolute gas production rate of each gas. A big data analysis module, connected to the data acquisition module, is used to receive gas concentration data and establish a mapping relationship between fault characteristics and fault types based on machine learning algorithms; The fault diagnosis module is connected to the gas production rate calculation module and the big data analysis module respectively. It is used to receive the gas production rate calculation results and the mapping relationship between fault characteristics and fault types, and to comprehensively judge the transformer fault type. The result output module is connected to the fault diagnosis module and is used to receive fault diagnosis results and output them in a visual manner.

[0007] Furthermore, the concentration data of various characteristic dissolved gases in the transformer oil are collected by sensors arranged inside the transformer oil tank, specifically including the concentrations of hydrogen, methane, ethane, ethylene, acetylene, carbon monoxide, and carbon dioxide.

[0008] Furthermore, the gas production rate calculation module calculates the absolute gas production rate, using the following specific formula: R i =(C i2 -C i1 )·G / (Δt*d)(1) Among them, R i Indicates the absolute gas production rate; C i1 —The concentration of a certain gas in the oil was measured during the first sampling; C i2 Δt represents the concentration of a certain gas in the oil measured in the second sampling; Δt represents the actual running time during the time interval between the two samplings; G represents the total amount of oil in the equipment; and d represents the density of the oil.

[0009] Furthermore, the gas production rate calculation module compares the calculated absolute gas production rates of acetylene, methane, ethylene, ethane, hydrogen, carbon monoxide, and carbon dioxide with preset warning values. When it is preliminarily determined that the gas production rate exceeds the preset warning value, a fault warning trigger signal is output to the fault diagnosis module.

[0010] Furthermore, the machine learning algorithms used in the big data analysis module include support vector machine algorithm, random forest algorithm, or neural network algorithm; The gas concentration data output by the data acquisition module and the gas production rate data output by the gas production rate calculation module are input into the big data analysis module. The module is trained using historical fault data and normal operation data to output the mapping relationship between fault characteristics and fault types.

[0011] Furthermore, after receiving the fault warning trigger signal, the fault diagnosis module uses the pentagon method to make the final fault type judgment based on the mapping relationship output by the big data analysis module. The fault types include corona partial discharge, low-energy discharge, high-energy discharge, thermal fault temperature greater than 700℃, thermal fault temperature 300-700℃, thermal fault temperature less than 300℃, and low-temperature overheating corresponding to mineral oil stray gas. The pentagon method is used to determine the final fault type. The specific implementation steps are as follows: (61) Receive gas concentration data of hydrogen, methane, acetylene, ethylene and ethane provided by the data acquisition module; (62) Calculate the percentage of each gas in the total combustible gas as %H2, %CH4, %C2H2, %C2H4, and %C2H6 respectively. The specific calculation method is as follows: (2) (3) (4) (5) (6) (63) Construct a regular pentagon. The interior of the regular pentagon is divided into seven regions: PD, D1, D2, S, T1, T2, and T3, which correspond to seven types of faults: corona partial discharge, low-energy discharge, high-energy discharge, stray gas generated by mineral oil, thermal fault temperature less than 300℃, thermal fault temperature greater than 700℃, and thermal fault temperature 300-700℃. (64) The five vertices of the pentagon correspond to five gases: hydrogen, acetylene, ethylene, methane, and ethane. Lines are drawn from the centroid of the regular pentagon to the five vertices to form the coordinate axes of the five gases. The scale of the coordinate axes from the centroid to the vertices is set to 0 to 100%. (65) Based on the percentage of each gas calculated in step (62), map it onto the coordinate axis in step (64) to obtain five data points P1 to P5 for the five gases. Connect P1 to P5 sequentially to obtain a new pentagon. Calculate the centroid position of the new pentagon and obtain the specific fault type based on the location of the centroid of the new pentagon.

[0012] Furthermore, by training with historical fault data and normal operation data, the mapping relationship between fault features and fault types is output, as follows: Obtain gas concentration data and gas production rate data from transformers of different substations, models, and service lives; Each gas concentration data and gas production rate data is labeled with a corresponding fault type label. The fault type labels include corona partial discharge, low energy discharge, high energy discharge, thermal fault temperature greater than 700℃, thermal fault temperature 300-700℃, thermal fault temperature less than 300℃, and low temperature overheating corresponding to mineral oil stray gas. The data labeled with fault type is preprocessed, and then the preprocessed data is used to form a dataset. The preprocessed dataset is divided into a training set and a test set. Based on the gas concentration data in the dataset, the percentage characteristics of each gas concentration in the total combustible gas are calculated, and the percentage characteristics are combined with the gas production rate data and gas concentration data to form fault characteristics. A neural network algorithm is used to construct a mapping model. The training set and fault features are input into the mapping model for training until the mapping model converges, resulting in a trained mapping model. The trained mapping model is then used to output the mapping relationship between fault features and fault types.

[0013] Furthermore, the Adam optimizer is used during the training of the mapping model, with mean squared error as the loss function.

[0014] This invention has at least the following beneficial effects: 1. This invention upgrades the static threshold judgment of gas concentration to dynamic trend analysis and multi-dimensional feature fusion diagnosis through the collaborative work of the gas production rate calculation module and the big data analysis module. The big data analysis model, trained based on historical fault samples and normal operation data, can effectively identify the nonlinear correlation characteristics between gas components, overcoming the misjudgment and missed judgment problems caused by the rigid boundaries of the coding interval in the traditional IEC three-ratio method. At the same time, the gas production rate, as a direct quantitative indicator of fault activity, complements the gas composition characteristics, making the diagnostic results both timely and comprehensive, and significantly reducing the false alarm rate caused by external factors such as load fluctuations and oil temperature changes.

[0015] 2. Traditional DGA methods are slow to react to trace gas growth in the early stages of a fault, while this invention can sensitively capture trace gas increments by calculating the absolute gas production rate and setting graded attention values. When the gas production rate exceeds the threshold, an early warning is triggered immediately. Combined with the pentagonal method for regional centroid localization, early defects such as partial discharge and low-temperature overheating can be accurately identified in the reversible stage of fault development. Furthermore, the pentagonal method transforms abstract percentage data into intuitive geometric figures, and the visualization of fault type is achieved through centroid region mapping, making the diagnostic process transparent.

[0016] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the system described in this invention; Figure 2 This is a schematic diagram of the pentagonal region division in this invention. Detailed Implementation

[0018] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0019] Please see Figures 1-2 This invention provides a technical solution: a transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition, applicable to sealed, oil-immersed transformers with voltage levels of 110kV and above, comprising: The data acquisition module is used to collect concentration data of various characteristic dissolved gases in transformer oil; The gas production rate calculation module is connected to the data acquisition module and is used to receive the concentration data of various characteristic dissolved gases and calculate the absolute gas production rate of each gas. The big data analysis module, connected to the data acquisition module, is used to receive gas concentration data and establish a mapping relationship between fault characteristics and fault types based on machine learning algorithms. The fault diagnosis module is connected to the gas production rate calculation module and the big data analysis module respectively. It is used to receive the gas production rate calculation results and the big data analysis results, and to comprehensively determine the transformer fault type. The results output module is connected to the fault diagnosis module and is used to receive fault diagnosis results and output them in a visual manner.

[0020] Regarding the technical solution of this embodiment, the concentration data of various characteristic dissolved gases in transformer oil are collected by sensors arranged in the transformer oil tank, specifically including the concentrations of hydrogen, methane, ethane, ethylene, acetylene, carbon monoxide, and carbon dioxide.

[0021] Regarding the technical solution of this embodiment, the gas production rate calculation module calculates the absolute gas production rate, and the specific calculation formula is as follows: R i =(C i2 -C i1 )·G / (Δt*d)(1) Among them, R i Indicates the absolute gas production rate; C i1 —The concentration of a certain gas in the oil was measured during the first sampling; C i2 Δt represents the concentration of a certain gas in the oil measured in the second sampling; Δt represents the actual running time during the time interval between the two samplings; G represents the total amount of oil in the equipment; and d represents the density of the oil.

[0022] It should be further explained that the gas production rate calculation module compares the calculated absolute gas production rates of acetylene, methane, ethylene, ethane, hydrogen, carbon monoxide, and carbon dioxide with preset warning values. When it is preliminarily determined that the gas production rate exceeds the preset warning value, a fault warning trigger signal is output to the fault diagnosis module. The preset warning values ​​for the absolute gas production rate are shown in Table 1. Table 1. Precautions for the absolute gas production rate of dissolved gases in oil of operating equipment. The unit is mL / d For transformers of 750kV and above, the typical weekly increment values ​​of the laboratory offline test data can be used for further judgment. (See Table 2)

[0023] Table 2. Notes on Absolute Gas Increment Values ​​for Offline Oil Chromatography of Transformers (Reactors) with Voltage Levels Above 750kV The unit is mL / d If the absolute gas production rate (absolute increment) does not exceed the above attention value, it can be determined that there is no fault. If it exceeds the attention value, the fault type should be further determined by the pentagon method.

[0024] Regarding the technical solution of this embodiment, the machine learning algorithms used in the big data analysis module include support vector machine algorithm, random forest algorithm, or neural network algorithm; The gas concentration data output from the data acquisition module and the gas production rate data output from the gas production rate calculation module are input into the big data analysis module. The module is trained using historical fault data and normal operation data to output the mapping relationship between fault characteristics and fault types, as detailed below: Obtain gas concentration data and gas production rate data from transformers of different substations, models, and service lives; Each gas concentration data and gas production rate data is labeled with a corresponding fault type label. The fault type labels include corona partial discharge, low energy discharge, high energy discharge, thermal fault temperature greater than 700℃, thermal fault temperature 300-700℃, thermal fault temperature less than 300℃, and low temperature overheating corresponding to mineral oil stray gas. The data labeled with fault type is preprocessed, and then the preprocessed data is used to form a dataset. The preprocessed dataset is divided into a training set and a test set. The preprocessing includes using the 3σ method to identify and correct or remove obviously erroneous data, and using interpolation or based on the trend of data before and after the same transformer to fill in missing data. Based on the gas concentration data in the dataset, the percentage characteristics of each gas concentration in the total combustible gas are calculated, and the percentage characteristics are combined with the gas production rate data and gas concentration data to form fault characteristics. A neural network algorithm is used to construct a mapping model. The training set and fault features are input into the mapping model for training until the mapping model converges, resulting in a trained mapping model. The trained mapping model is then used to output the mapping relationship between fault features and fault types.

[0025] It should be noted that after training, the trained mapping model is tested using a test set that was not used in the training. The fault features (X_test) of the test set are input, and the mapping model outputs the prediction result (Y_pred). Then, the result is compared with the true fault type label (Y_test). The performance of the mapping model is evaluated by calculating the accuracy, precision, recall, F1 score, and other metrics. The trained mapping model is then integrated into the big data analysis module for use.

[0026] Furthermore, the Adam optimizer is used during the training of the mapping model, with mean squared error as the loss function.

[0027] Regarding the technical solution of this embodiment, after receiving the fault warning trigger signal, the fault diagnosis module uses the pentagon method to make the final fault type judgment based on the mapping relationship output by the big data analysis module. The fault types include corona partial discharge, low-energy discharge, high-energy discharge, thermal fault temperature greater than 700℃, thermal fault temperature 300-700℃, thermal fault temperature less than 300℃, and low-temperature overheating corresponding to mineral oil stray gas. The pentagon method is used to determine the final fault type. The specific implementation steps are as follows: (1) Receive gas concentration data of hydrogen, methane, acetylene, ethylene and ethane provided by the data acquisition module; (2) Calculate the percentage of each gas in the total combustible gas as %H2, %CH4, %C2H2, %C2H4, and %C2H6 respectively. The specific calculation method is as follows: (2) (3) (4) (5) (6) (3) such as Figure 2As shown, a regular pentagon is constructed, and the interior of the regular pentagon is divided into seven regions: PD, D1, D2, S, T1, T2, and T3, which correspond to seven fault types: corona partial discharge, low-energy discharge, high-energy discharge, stray gas generated by mineral oil, thermal fault temperature less than 300℃, thermal fault temperature greater than 700℃, and thermal fault temperature 300-700℃, respectively. (4) The five vertices of the pentagon correspond to five gases: hydrogen, acetylene, ethylene, methane, and ethane. Lines are drawn from the centroid of the regular pentagon to the five vertices to form the coordinate axes of the five gases. The scale of the coordinate axes from the centroid to the vertices is set to 0 to 100%. (5) Based on the percentage of each gas calculated in step (2), map it onto the coordinate axis in step (4) to obtain five data points P1 to P5 for the five gases. Connect P1 to P5 sequentially to obtain a new pentagon. Calculate the centroid position of the new pentagon. Based on the location of the centroid of the new pentagon, obtain the specific fault type. For example, if the centroid is in region D1, the transformer fault type is low-energy discharge.

[0028] In summary, this invention upgrades the static threshold judgment of gas concentration to dynamic trend analysis and multi-dimensional feature fusion diagnosis through the collaborative work of the gas production rate calculation module and the big data analysis module. The big data analysis model is trained based on historical fault samples and normal operation data, which can effectively identify the nonlinear correlation characteristics between gas components. Furthermore, by calculating the absolute gas production rate and setting graded attention values, this invention can sensitively capture trace gas increments and immediately trigger an early warning when the gas production rate exceeds the threshold. Combined with the pentagonal method for regional centroid localization, it can accurately identify early defects such as partial discharge and low-temperature overheating in the reversible stage of fault development.

[0029] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0030] For those skilled in the art, the specific meaning of the above terms in this invention can be understood according to the specific circumstances. When an element is referred to as being "assembled on," "mounted on," "fixed to," or "set on" another element, it may be directly on the other element or there may be an intermediate element present. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element present. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible embodiments.

[0031] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

[0032] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

Claims

1. A transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition, characterized in that, include: The data acquisition module is used to collect concentration data of various characteristic dissolved gases in transformer oil; A gas production rate calculation module, connected to the data acquisition module, is used to receive concentration data of various characteristic dissolved gases and calculate the absolute gas production rate of each gas. A big data analysis module, connected to the data acquisition module, is used to receive gas concentration data and establish a mapping relationship between fault characteristics and fault types based on machine learning algorithms; The fault diagnosis module is connected to the gas production rate calculation module and the big data analysis module respectively. It is used to receive the gas production rate calculation results and the mapping relationship between fault characteristics and fault types, and to comprehensively judge the transformer fault type. The result output module is connected to the fault diagnosis module and is used to receive fault diagnosis results and output them in a visual manner.

2. The transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition according to claim 1, characterized in that: Concentration data of various characteristic dissolved gases in transformer oil are collected by sensors placed inside the transformer oil tank. These include the concentrations of hydrogen, methane, ethane, ethylene, acetylene, carbon monoxide, and carbon dioxide.

3. The transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition according to claim 2, characterized in that: The gas production rate calculation module calculates the absolute gas production rate using the following formula: R i =(C i2 -C i1 )·G / (Δt*d)(1) Among them, R i Indicates the absolute gas production rate; C i1 —The concentration of a certain gas in the oil was measured during the first sampling; C i2 Δt represents the concentration of a certain gas in the oil measured in the second sampling; Δt represents the actual running time during the time interval between the two samplings; G represents the total amount of oil in the equipment; and d represents the density of the oil.

4. The transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition according to claim 3, characterized in that: The gas production rate calculation module compares the calculated absolute gas production rates of acetylene, methane, ethylene, ethane, hydrogen, carbon monoxide, and carbon dioxide with preset warning values. When it is preliminarily determined that the gas production rate exceeds the preset warning value, a fault warning trigger signal is output to the fault diagnosis module.

5. The transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition according to claim 4, characterized in that: The machine learning algorithms used in the big data analysis module include support vector machine, random forest, or neural network algorithms. The gas concentration data output by the data acquisition module and the gas production rate data output by the gas production rate calculation module are input into the big data analysis module. The module is trained using historical fault data and normal operation data to output the mapping relationship between fault characteristics and fault types.

6. The transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition according to claim 5, characterized in that: After receiving the fault warning trigger signal, the fault diagnosis module uses the pentagon method to make the final fault type judgment based on the mapping relationship output by the big data analysis module. The fault types include corona partial discharge, low-energy discharge, high-energy discharge, thermal fault temperature greater than 700℃, thermal fault temperature 300-700℃, thermal fault temperature less than 300℃, and low-temperature overheating corresponding to mineral oil stray gas. The pentagon method is used to determine the final fault type. The specific implementation steps are as follows: (61) Receive gas concentration data of hydrogen, methane, acetylene, ethylene and ethane provided by the data acquisition module; (62) Calculate the percentage of each gas in the total combustible gas as %H2, %CH4, %C2H2, %C2H4, and %C2H6 respectively. The specific calculation method is as follows: (2) (3) (4) (5) (6) (63) Construct a regular pentagon. The interior of the regular pentagon is divided into seven regions: PD, D1, D2, S, T1, T2, and T3, which correspond to seven types of faults: corona partial discharge, low-energy discharge, high-energy discharge, stray gas generated by mineral oil, thermal fault temperature less than 300℃, thermal fault temperature greater than 700℃, and thermal fault temperature 300-700℃. (64) The five vertices of the pentagon correspond to five gases: hydrogen, acetylene, ethylene, methane, and ethane. Lines are drawn from the centroid of the regular pentagon to the five vertices to form the coordinate axes of the five gases. The scale of the coordinate axes from the centroid to the vertices is set to 0 to 100%. (65) Based on the percentage of each gas calculated in step (62), map it onto the coordinate axis in step (64) to obtain five data points P1 to P5 for the five gases. Connect P1 to P5 sequentially to obtain a new pentagon. Calculate the centroid position of the new pentagon and obtain the specific fault type based on the location of the centroid of the new pentagon.

7. The transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition according to claim 6, characterized in that: The system is trained using historical fault data and normal operation data to output the mapping relationship between fault features and fault types, as detailed below: Obtain gas concentration data and gas production rate data from transformers of different substations, models, and service lives; Each gas concentration data and gas production rate data is labeled with a corresponding fault type label. The fault type labels include corona partial discharge, low energy discharge, high energy discharge, thermal fault temperature greater than 700℃, thermal fault temperature 300-700℃, thermal fault temperature less than 300℃, and low temperature overheating corresponding to mineral oil stray gas. The data labeled with fault type is preprocessed, and then the preprocessed data is used to form a dataset. The preprocessed dataset is divided into a training set and a test set. Based on the gas concentration data in the dataset, the percentage characteristics of each gas concentration in the total combustible gas are calculated, and the percentage characteristics are combined with the gas production rate data and gas concentration data to form fault characteristics. A neural network algorithm is used to construct a mapping model. The training set and fault features are input into the mapping model for training until the mapping model converges, resulting in a trained mapping model. The trained mapping model is then used to output the mapping relationship between fault features and fault types.

8. The transformer oil dissolved gas fault diagnosis system based on gas production rate and gas composition according to claim 7, characterized in that: The Adam optimizer is used during the training of the mapping model, and the mean squared error is used as the loss function.

Images