Transformer fault detection method based on gas in oil and related equipment

Abstract

The invention discloses a transformer fault detection method based on gas in oil and related equipment, relates to the technical field of power equipment monitoring, and effectively solves the problem that the content difference of characteristic gas of the same fault type is large under different transformer oil temperatures due to the fluctuation of the transformer oil temperature in the traditional method by adopting the technical scheme. The detection system eliminates the influence of the oil temperature change on the gas content through oil temperature correction and standardization processing, so that the fault judgment of the transformer is more accurate and reliable. And meanwhile, the detection system adopts the characteristic gas ratio matrix to judge the fault type, so that misjudgment possibly caused by pure dependence on a content absolute value is avoided, and the accuracy and reliability of transformer fault diagnosis are improved.

Description

Technical Field

[0001] The present application relates to the technical field of power equipment monitoring, and in particular to a transformer fault detection method based on gas in oil and related equipment. Background Art

[0002] Transformers are important equipment in power systems, and their safe and stable operation is directly related to the reliability of the entire power system. During the operation of transformers, various faults may occur due to insulation aging, overload operation, etc. These faults are often accompanied by the generation of characteristic gases. Therefore, by analyzing the content and change pattern of characteristic gases in transformer oil, potential transformer faults can be discovered in a timely manner, which is of great significance to ensuring the safe operation of the power system.

[0003] At present, gas fault detection in transformer oil mainly adopts the method of regular sampling detection, that is, sampling and analyzing the transformer oil at fixed time intervals to obtain the content data of characteristic gas, and then judging whether the transformer has potential faults based on the absolute value of the content data.

[0004] This detection method has certain limitations in practical applications. Since the transformer oil temperature fluctuates with the change of transformer load, and the change of transformer oil temperature will affect the solubility of characteristic gas in oil, the content data of characteristic gas may vary greatly under different oil temperature conditions for the same fault type, making it difficult to accurately determine the fault type, which can easily lead to misjudgment or missed judgment. Summary of the invention

[0005] The present application provides a transformer fault detection method based on gas in oil and related equipment, which are used to improve the accuracy of transformer oil gas fault detection.

[0006] In a first aspect, the present application provides a transformer fault detection method based on gas in oil, which is applied to a detection system, and the method includes: collecting transformer oil temperature data, transformer load data, and content data of each characteristic gas in the transformer oil; judging whether the transformer oil temperature data and the transformer load data both meet the preset transformer oil temperature load operating characteristics, the preset transformer oil temperature load operating characteristics include the transformer oil temperature change rate standard and the transformer load change rate standard; if they meet, according to the preset oil temperature-gas type-solubility correspondence, determine the theoretical solubility of each characteristic gas at the current transformer oil temperature, and the current transformer oil temperature is determined by the transformer oil temperature data at the current moment; divide the content data of each characteristic gas by the theoretical solubility to obtain the standardized content of each characteristic gas at the current transformer oil temperature; based on the standardized content of each characteristic gas, calculate the concentration ratio between all the characteristic gases to construct a characteristic gas ratio matrix; according to the preset characteristic gas ratio fault judgment rule and the characteristic gas ratio matrix, determine the fault type of the transformer, and the preset characteristic gas ratio fault judgment rule includes multiple characteristic gas ratio fault intervals and corresponding fault types.

[0007] By adopting the above technical solution, the problem of large differences in the content of characteristic gases under different transformer oil temperatures caused by transformer oil temperature fluctuations in the traditional method is effectively solved. The detection system eliminates the influence of oil temperature changes on gas content through oil temperature correction and standardization, making the transformer fault judgment more accurate and reliable. At the same time, the detection system uses the characteristic gas ratio matrix to determine the fault type, avoiding the possible misjudgment caused by relying solely on the absolute value of the content, and improving the accuracy and reliability of transformer fault diagnosis.

[0008] In combination with some embodiments of the first aspect, in some embodiments, determining whether both the transformer oil temperature data and the transformer load data meet the preset transformer oil temperature and load operating characteristics specifically includes: calculating the oil temperature change rate of the transformer oil temperature data and the load change rate of the transformer load data within a preset time window; when the oil temperature change rate is less than a preset first change rate threshold and the load change rate is less than a preset second change rate threshold, determining that the transformer oil temperature data and the transformer load data meet the preset transformer oil temperature and load operating characteristics; when the oil temperature change rate is greater than or equal to the preset first change rate threshold or the load change rate is greater than or equal to the preset second change rate threshold, determining that the transformer oil temperature data and the transformer load data do not meet the preset transformer oil temperature and load operating characteristics.

[0009] By adopting the above technical solution, the detection system calculates the oil temperature change rate and load change rate within the preset time window, and compares them with the transformer oil temperature change rate standard and the transformer load change rate standard to determine the operating status of the transformer. This judgment mechanism can effectively identify whether the transformer is in a drastic change or a relatively stable operating state. When the oil temperature change rate is greater than or equal to the preset first change rate threshold or the load change rate is greater than or equal to the preset second change rate threshold, it means that the transformer is in a dynamic change process. At this time, the gas data obtained may have large fluctuations and is not suitable for fault diagnosis, avoiding data interference in the dynamic process and further improving the accuracy of fault diagnosis.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the fault type of the transformer is determined according to preset characteristic gas ratio fault judgment rules and a characteristic gas ratio matrix, specifically including: determining the target characteristic gas ratio fault interval with the highest matching degree in the preset characteristic gas ratio fault judgment rules according to each concentration ratio in the characteristic gas ratio matrix, the preset characteristic gas ratio fault judgment rules including multiple characteristic gas ratio fault intervals and corresponding fault types; determining the target fault type of the transformer based on the target characteristic gas ratio fault interval and the preset characteristic gas ratio fault judgment rules.

[0011] By adopting the above technical solution, the detection system finds the target fault interval with the highest matching degree in the preset characteristic gas ratio fault judgment rule to determine the fault type. This comprehensive matching method based on multiple characteristic gas ratios overcomes the judgment ambiguity problem that may be caused by the traditional single ratio judgment, so that it can fully reflect the relative relationship between various characteristic gases, more accurately identify the fault type, improve the credibility of the fault diagnosis results, and provide a reliable basis for subsequent maintenance decisions.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after the step of calculating the concentration ratios between all characteristic gases based on the standardized content of each characteristic gas to construct a characteristic gas ratio matrix, the method also includes: calculating the standardized content change rate of each characteristic gas within a preset time window; determining whether the standardized content change rate exceeds a preset third change rate threshold; if the standardized content change rate exceeds the preset third change rate threshold, determining the mutation characteristic gas; and identifying equipment components whose correlation with the mutation characteristic gas exceeds the preset correlation threshold.

[0013] By adopting the above technical solution, after constructing the characteristic gas ratio matrix, the detection system calculates the standardized content change rate of each characteristic gas within the preset time window, and compares it with the preset third change rate threshold to identify the sudden change characteristic gas, and then identify the equipment components with high correlation with the sudden change characteristic gas. This method can not only detect abnormal changes in gas content in a timely manner, but also quickly locate specific components that may fail.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the mutation characteristic gas if the standardized content change rate exceeds a preset third change rate threshold, the method also includes: determining the concentration ratio related to the mutation characteristic gas in the characteristic gas ratio matrix as the mutation concentration ratio, the mutation concentration ratio is used to represent the concentration ratio of the mutation characteristic gas to the non-mutation characteristic gas; based on the mutation concentration ratio, determining the correlation between the content changes of the mutation characteristic gas and the non-mutation characteristic gas; based on the correlation, screening the associated characteristic gases affected by the mutation characteristic gas.

[0015] By adopting the above technical solution, after determining the mutation characteristic gas, the detection system analyzes the concentration ratio relationship between the mutation gas and the non-mutation gas, and establishes a correlation network of gas content changes to screen out the associated characteristic gases affected by the mutation characteristic gas, thereby identifying the chain reaction caused by the same fault cause, accurately grasping the expansion scope and development trend of the fault, and providing a scientific basis for evaluating the severity of the fault and formulating maintenance strategies.

[0016] In combination with some embodiments of the first aspect, in some embodiments, before the step of determining the fault type of the transformer according to the preset characteristic gas ratio fault judgment rule and the characteristic gas ratio matrix, the method also includes: obtaining historical transformer oil temperature data, historical transformer load data, historical characteristic gas ratio matrix and corresponding historical fault types; determining the historical characteristic gas ratio fault interval according to the historical characteristic gas ratio matrix; and determining the preset characteristic gas ratio fault judgment rule based on the historical characteristic gas ratio fault interval and the historical fault type.

[0017] By adopting the above technical solution, the detection system obtains historical transformer oil temperature data, historical transformer load data, historical characteristic gas ratio matrix and corresponding historical fault types to establish the corresponding relationship between characteristic gas ratio fault interval and fault type, and form a preset characteristic gas ratio fault judgment rule. This learning method based on historical data makes the preset characteristic gas ratio fault judgment rule have a strong practical guiding significance, so that different characteristic gas ratio fault intervals corresponding to different fault types can be accurately divided, which improves the accuracy and applicability of the fault judgment.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the fault type of the transformer according to preset characteristic gas ratio fault judgment rules and characteristic gas ratio matrix, the method also includes: inputting the transformer oil temperature data, the transformer load data and the characteristic gas ratio matrix into a preset fault evolution prediction model to predict the characteristic gas ratio evolution trajectory; determining the suspected fault type according to the characteristic gas ratio evolution trajectory and the characteristic gas ratio matrix; and generating corresponding fault reminder items based on the suspected fault type, the fault reminder items including the characteristic gas ratio evolution trajectory, the suspected fault type and the fault solution corresponding to the suspected fault type.

[0019] By adopting the above technical solution, the detection system predicts the changing trend of the characteristic gas ratio through the preset fault evolution prediction model, and identifies the suspected fault type in advance based on the prediction results, and generates early warning information including the evolution trajectory of the characteristic gas ratio, the suspected fault type and the fault solution corresponding to the suspected fault type. This predictive diagnosis method transforms fault diagnosis from passive response to active prevention, so that potential fault hazards can be discovered early, the development direction of the fault can be predicted, and the risk of serious faults in the transformer can be effectively reduced.

[0020] In a second aspect, an embodiment of the present application provides a detection system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the detection system to perform the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when the computer program product is run on a detection system, enables the detection system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a detection system, enables the detection system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0023] It is understandable that the detection system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By adopting the above technical solution, the problem of large differences in the content of characteristic gases under different transformer oil temperatures caused by transformer oil temperature fluctuations in the traditional method is effectively solved. The detection system eliminates the influence of oil temperature changes on gas content through oil temperature correction and standardization, making transformer fault judgment more accurate and reliable. At the same time, the detection system uses the characteristic gas ratio matrix to determine the fault type, avoiding the misjudgment that may be caused by relying solely on the absolute value of the content, and improving the accuracy and reliability of transformer fault diagnosis.

[0025] By adopting the above technical solution, the detection system finds the target fault interval with the highest matching degree in the preset characteristic gas ratio fault judgment rule to determine the fault type. This comprehensive matching method based on multiple characteristic gas ratios overcomes the judgment ambiguity problem that may be caused by the traditional single ratio judgment, so that it can fully reflect the relative relationship between various characteristic gases, more accurately identify the fault type, improve the credibility of the fault diagnosis results, and provide a reliable basis for subsequent maintenance decisions.

[0026] 3. By adopting the above technical solution, after determining the mutation characteristic gas, the detection system analyzes the concentration ratio relationship between the mutation gas and the non-mutation gas, and establishes a correlation network of gas content changes to screen out the associated characteristic gases affected by the mutation characteristic gas, thereby identifying the chain reaction caused by the same fault cause, accurately grasping the expansion scope and development trend of the fault, and providing a scientific basis for assessing the severity of the fault and formulating maintenance strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of a transformer fault detection method based on gas in oil in an embodiment of the present application; Figure 2 is another flow chart of a transformer fault detection method based on gas in oil according to an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of the detection system in the embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] The following is a description of the process of the method provided by this implementation. Figure 1 , which is a flow chart of a transformer fault detection method based on gas in oil in an embodiment of the present application.

[0031] S101, collecting transformer oil temperature data, transformer load data, and content data of each characteristic gas in transformer oil; Among them, the transformer oil temperature data is used to indicate the real-time temperature value of the transformer oil medium; the transformer load data is used to indicate the real-time power load value carried by the transformer during operation, usually expressed as a percentage of the rated capacity; characteristic gas refers to the characteristic gas that may be produced when a transformer fails, such as hydrogen (H2), methane (CH4), ethane (C2H6), ethylene (C2H4), acetylene (C2H2), etc.; the content data refers to the concentration value of the characteristic gas in the transformer oil, usually in μL / L (ppm).

[0032] Specifically, the detection system collects transformer oil temperature data in real time through the oil temperature sensor installed on the transformer. The detection system obtains transformer load data through the power monitoring system. The detection system obtains the content data of dissolved gas (characteristic gas) in transformer oil through an online chromatograph or regular sampling and analysis. The collection frequency of these data can be set according to actual needs. Usually, the collection interval of transformer oil temperature data and transformer load data is at the minute level, and the collection interval of gas content data is at the hour level or day level.

[0033] S102, determining whether the transformer oil temperature data and the transformer load data both meet the preset transformer oil temperature load operating characteristics, where the preset transformer oil temperature load operating characteristics include a transformer oil temperature change rate standard and a transformer load change rate standard; Among them, the transformer oil temperature and load operating characteristics indicate the changing rules of oil temperature and load under normal operating conditions; the oil temperature change rate standard refers to the allowable range of oil temperature change per unit time; the load change rate standard indicates the allowable range of load change per unit time; the change rate refers to the ratio of the numerical change between two adjacent sampling moments to the time interval.

[0034] Specifically, first, the detection system calculates the oil temperature change rate and load change rate within a preset time window (such as 15 minutes or 30 minutes) based on the transformer oil temperature data and transformer load data. Then, the detection system compares the calculated oil temperature change rate and load change rate with the pre-set transformer oil temperature change rate standard and transformer load change rate standard. For example, the oil temperature change rate threshold in the transformer oil temperature change rate standard can be set to 2°C / min, and the load change rate threshold in the transformer load change rate standard can be set to 5% / min. Only when both change rates are less than their respective thresholds, the transformer is considered to be in a relatively stable operating state and is suitable for subsequent fault diagnosis and analysis.

[0035] The following is an example of a detection system calculating the oil temperature change rate and load change rate within a preset time window (such as 15 minutes or 30 minutes) based on the transformer oil temperature data and the transformer load data: Assume that the detection system collects the following transformer data within 15 minutes: Time point 1 (0 minutes): Transformer oil temperature data: 45.0℃; Transformer load data: 70.0%; Time point 2 (15 minutes): Transformer oil temperature data: 46.5℃; Transformer load data: 72.5%; Calculate the rate of change: Oil temperature change rate = (46.5℃-45.0℃) ÷ 15 minutes = 0.1℃ / min; Load change rate = (72.5%-70.0%) ÷ 15 minutes = 0.167% / min; Judgment result: Oil temperature change rate (0.1℃ / min) < oil temperature change rate threshold (2℃ / min); Load change rate (0.167% / min) < load change rate threshold (5% / min); Because both change rates are less than their corresponding thresholds, it can be determined that the transformer operation status is stable during this period and is suitable for fault diagnosis and analysis.

[0036] Optionally, under normal circumstances, determining whether both the transformer oil temperature data and the transformer load data conform to the preset transformer oil temperature and load operating characteristics can be achieved in the following manner, which is not limited here: calculating the oil temperature change rate of the transformer oil temperature data and the load change rate of the transformer load data within a preset time window; when the oil temperature change rate is less than a preset first change rate threshold and the load change rate is less than a preset second change rate threshold, determining that the transformer oil temperature data and the transformer load data conform to the preset transformer oil temperature and load operating characteristics; when the oil temperature change rate is greater than or equal to the preset first change rate threshold or the load change rate is greater than or equal to the preset second change rate threshold, determining that the transformer oil temperature data and the transformer load data do not conform to the preset transformer oil temperature and load operating characteristics.

[0037] S103, if it is in compliance, determine the theoretical solubility of each characteristic gas at the current transformer oil temperature according to the preset oil temperature-gas type-solubility correspondence relationship, and the current transformer oil temperature is determined by the transformer oil temperature data at the current moment; Among them, the preset oil temperature-gas type-solubility correspondence is used to represent the theoretical solubility of various characteristic gases in transformer oil at different transformer oil temperatures; the theoretical solubility refers to the maximum solubility of the characteristic gas in the transformer oil at a specific transformer oil temperature; the current transformer oil temperature refers to the real-time temperature value of the transformer oil medium at the time of fault diagnosis and analysis.

[0038] Specifically, first, the detection system obtains the current transformer oil temperature at the current moment. Then, the detection system searches or interpolates the theoretical solubility of each characteristic gas at the transformer temperature based on the pre-established preset oil temperature-gas type-solubility correspondence. By determining the theoretical solubility, it can prepare for the subsequent standardization of the characteristic gas content data.

[0039] The following is an example of a preset oil temperature-gas type-solubility correspondence: ① Hydrogen (H2) solubility: 20℃: 7%; 40℃: 5%; 60℃: 3.5%; 80℃: 2.5% ② Solubility of methane (CH4): 20℃: 30%; 40℃: 25%; 60℃: 21%; 80℃: 18%; ③ Solubility of ethane (C2H6): 20℃: 280%; 40℃: 230%; 60℃: 190%; 80℃: 160%; ④ Ethylene (C2H4) solubility: 20℃: 280%; 40℃: 230%; 60℃: 190%; 80℃: 160%; ⑤ Solubility of acetylene (C2H2): 20℃: 400%; 40℃: 330%; 60℃: 270%; 80℃: 220%…… S104, dividing the content data of each characteristic gas by the theoretical solubility to obtain the standardized content of each characteristic gas at the current transformer oil temperature; Among them, the standardized content refers to the relative value of the gas content after correction for the transformer oil temperature, which is the ratio of the actual content to the theoretical solubility; the actual content refers to the original gas concentration data obtained by chromatographic analysis; the theoretical solubility refers to the maximum solubility of the characteristic gas under the current transformer oil temperature.

[0040] Specifically, the detection system divides the actual content of each characteristic gas by its corresponding theoretical solubility to obtain a dimensionless relative content value. For example, if the actual content of acetylene at a certain moment is 5ppm and the theoretical solubility is 100ppm, its standardized content is 0.05. This standardization process eliminates the influence of transformer oil temperature on gas solubility.

[0041] S105, based on the standardized content of each characteristic gas, calculating the concentration ratios of all characteristic gases in pairs to construct a characteristic gas ratio matrix; Among them, the concentration ratio refers to the ratio of the standardized contents of two characteristic gases; the characteristic gas ratio matrix is ​​used to represent the square matrix composed of the concentration ratios of all characteristic gases; the matrix elements represent the concentration ratios of the characteristic gas corresponding to the row and the characteristic gas corresponding to the column; the diagonal elements are always 1; the upper and lower triangular matrix elements are reciprocals of each other.

[0042] Specifically, the detection system calculates the concentration ratio between any two characteristic gases and arranges these concentration ratios in a fixed order into a matrix form. For example, for the five characteristic gases H2, CH4, C2H6, C2H4, and C2H2, a 5×5 ratio matrix will be formed. Each element aij in the matrix represents the concentration ratio of the i-th characteristic gas to the j-th characteristic gas, satisfying the characteristics of aii=1 and aij=1 / aji. This characteristic gas ratio matrix fully reflects the relative content relationship between various characteristic gases.

[0043] Next, we use a specific example to illustrate the construction process of the characteristic gas ratio matrix: Assuming that the five characteristic gases are H2, CH4, C2H6, C2H4, and C2H2, their standardized contents are: H2: 100 μL / L; CH4: 200 μL / L; C2H6: 50μL / L; C2H4: 150μL / L; C2H2: 25μL / L; The constructed 5×5 ratio matrix is ​​as follows (arranged in the order of H2, CH4, C2H6, C2H4, C2H2): illustrate: 1. All diagonal elements are 1 (the concentration ratio of the characteristic gas to itself); 2. For example, a12=100 / 200=0.5, which means the concentration ratio of H2 / CH4; 3. The corresponding a21=200 / 100=2, which is the reciprocal of a12; 4. The upper and lower triangular elements of the matrix are reciprocals of each other; 5. Each element aij represents the gas content in the i-th row divided by the gas content in the j-th column S106. Determine the fault type of the transformer according to a preset characteristic gas ratio fault criterion rule and a characteristic gas ratio matrix, wherein the preset characteristic gas ratio fault criterion rule includes a plurality of characteristic gas ratio fault intervals and corresponding fault types.

[0044] Among them, the characteristic gas ratio fault judgment rule refers to the fault diagnosis criteria established based on historical data and expert experience; the characteristic gas ratio fault interval refers to the characteristic gas ratio range corresponding to different fault types; the fault type refers to the different types of faults that may occur in the transformer, such as overheating, discharge, etc.

[0045] Specifically, first, the detection system compares each element in the characteristic gas ratio matrix with the preset characteristic gas ratio fault judgment rules. These preset characteristic gas ratio fault judgment rules usually contain multiple groups of concentration ratio ranges, such as C2H2 / C2H4>1 for discharge fault, CH4 / H2>1 for overheating fault, etc. The detection system calculates the criterion matching degree of each fault type, and can use methods such as fuzzy membership degree or weighted scoring. Finally, the detection system selects the fault type with the highest matching degree as the diagnosis result. If the matching degrees of multiple fault types are close, there may be a complex fault, which requires further analysis or confirmation in combination with other diagnostic methods.

[0046] Optionally, under normal circumstances, according to the preset characteristic gas ratio fault judgment rules and the characteristic gas ratio matrix, determining the fault type of the transformer can be achieved in the following manner, which is not limited here: according to the various concentration ratios in the characteristic gas ratio matrix, determining the target characteristic gas ratio fault interval with the highest matching degree in the preset characteristic gas ratio fault judgment rules, the preset characteristic gas ratio fault judgment rules including multiple characteristic gas ratio fault intervals and corresponding fault types; based on the target characteristic gas ratio fault interval and the preset characteristic gas ratio fault judgment rules, determining the target fault type of the transformer.

[0047] Assume that the preset characteristic gas ratio fault judgment rule is as follows: ① Overheating fault (low temperature <300℃) judgment criteria: C2H2 / C2H4<0.1; CH4 / H2>1; C2H4 / C2H6<1; ② Overheating fault (high temperature 300-700℃) judgment criteria: C2H2 / C2H4<0.2 CH4 / H2>1; C2H4 / C2H6>1; ③ Arc discharge fault judgment criteria: C2H2 / C2H4>0.6; CH4 / H2<1; C2H4 / C2H6>2; Now assume that the key concentration ratio in the detected characteristic gas ratio matrix is: C2H2 / C2H4=0.167; CH4 / H2=2.0; C2H4 / C2H6=3.0; Analysis process: Check C2H2 / C2H4=0.167: Meet the high temperature overheating fault range (<0.2); Does not meet the low temperature overheating fault range (<0.1); Does not meet the arc discharge fault range (>0.6); Check CH4 / H2=2.0: Meets the high temperature overheating fault range (>1); Comply with the low temperature overheating fault range (>1); Does not meet the arc discharge fault range (<1); Check C2H4 / C2H6=3.0: Meets the high temperature overheating fault range (>1); Does not meet the low temperature overheating fault range (<1); Comply with the arc discharge fault range (>2); Comprehensive judgment: This set of concentration ratios matches the criterion rule of "overheating fault (high temperature 300-700℃)" the most, because the three key concentration ratios are in line with the criterion range of this type of fault. Therefore, it can be determined that the current fault type of the transformer is a high temperature overheating fault.

[0048] By adopting the above technical solution, the problem of large differences in the content of characteristic gases under different transformer oil temperatures caused by transformer oil temperature fluctuations in the traditional method is effectively solved. The detection system eliminates the influence of oil temperature changes on gas content through oil temperature correction and standardization, making the transformer fault judgment more accurate and reliable. At the same time, the detection system uses the characteristic gas ratio matrix to determine the fault type, avoiding the possible misjudgment caused by relying solely on the absolute value of the content, and improving the accuracy and reliability of transformer fault diagnosis.

[0049] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the transformer fault detection method based on gas in oil in an embodiment of the present application.

[0050] After step S105, the following steps may be performed or not performed, which is not limited here: S201, calculating the standardized content change rate of each characteristic gas within a preset time window; Among them, the preset time window refers to the time range for calculating the standardized content change rate, which can usually be set to several hours; the standardized content change rate refers to the change amplitude of the standardized content of the characteristic gas within the preset time window.

[0051] Specifically, the step of calculating the standardized content change rate of each characteristic gas within the preset time window can be referred to step S102. First, the detection system obtains the standardized variables of the characteristic gas at multiple time points within the preset time window. Then, the detection system calculates the standardized content change of the characteristic gas within the preset time window. Next, the detection system divides the standardized content change by the preset time window to obtain the standardized content change rate of the characteristic gas. Specific examples are not listed here.

[0052] S202, determining whether the change rate of the standardized content exceeds a preset third change rate threshold; Among them, the preset third change rate threshold refers to a standard value used to determine whether the content of the characteristic gas has undergone an abnormal change; the preset third change rate threshold refers to the upper limit of the allowable change range determined based on historical operating experience and expert knowledge.

[0053] Specifically, the detection system compares the standardized content change rate of each characteristic gas with the preset third change rate threshold. The preset third change rate threshold can be determined based on the following methods: (1) statistically analyzing the change rate distribution during normal operation in historical data, and taking the upper limit of the 95% or 99% confidence interval; (2) setting differentiated thresholds according to the physical and chemical properties of different characteristic gases; (3) dynamically adjusting the thresholds considering factors such as seasonal changes. The detection system not only pays attention to single-time over-threshold situations, but also examines the duration and degree of over-threshold state to improve the reliability of judgment.

[0054] S203, if the normalized content change rate exceeds a preset third change rate threshold, determining a mutation characteristic gas; Among them, mutation characteristic gas refers to characteristic gas whose content changes abnormally; mutation characteristic refers to the drastic or abnormal change characteristics of the content; mutation degree is used to indicate the degree to which the content change exceeds the normal range; mutation moment refers to the time point when the content begins to change abnormally; mutation duration refers to the duration of the abnormal change; mutation mode refers to the specific form of content change, such as step type, gradual change type, etc.

[0055] Specifically, first, the detection system marks all characteristic gases whose standardized content change rate exceeds the preset third change rate threshold; then, the detection system conducts in-depth analysis on each characteristic gas exceeding the threshold, including: (1) calculating the multiple of the threshold and evaluating the degree of mutation; (2) determining the start time and duration of the mutation; (3) analyzing the time characteristics of the mutation process and determining the mutation mode; (4) combining historical data to evaluate the abnormal degree of the mutation. Finally, the detection system determines the characteristic gas that meets the mutation characteristic criterion as the mutation characteristic gas.

[0056] S204, identifying equipment components whose correlation with the mutation characteristic gas exceeds a preset correlation threshold; Among them, correlation refers to the degree of association between characteristic gases and equipment components; the preset correlation threshold refers to the standard value for judging the significance of association; equipment components refer to specific components in the transformer that may fail; and the failure mode is used to indicate the type of failure that may occur in the equipment components; Specifically, the detection system performs analysis based on a pre-established gas-component association knowledge base, which includes: (1) the correspondence between various characteristic gases and different equipment components; (2) characteristic gas combinations generated by different failure modes; (3) typical gas characteristic spectra of component failures. The detection system calculates the correlation between the mutation characteristic gas and each equipment component, and can use expert rules, fuzzy reasoning or machine learning methods. When the correlation exceeds the preset correlation threshold, the corresponding equipment component is marked as a potential fault site. At the same time, the detection system will also consider the combined characteristics of multiple mutation gases to improve the accuracy of fault location.

[0057] S205, determining the concentration ratio related to the mutation characteristic gas in the characteristic gas ratio matrix as the mutation concentration ratio, where the mutation concentration ratio is used to represent the concentration ratio of the mutation characteristic gas to the non-mutation characteristic gas; Among them, the mutation concentration ratio refers to the concentration ratio between the mutation characteristic gas and other characteristic gases; the non-mutation characteristic gas refers to the characteristic gas whose content has not undergone abnormal changes.

[0058] Specifically, the detection system extracts all concentration ratios related to the mutation characteristic gas from the characteristic gas ratio matrix, including: (1) the ratio of the mutation characteristic gas to other characteristic gases; (2) the ratio between the mutation characteristic gases (if there are multiple mutation characteristic gases). These concentration ratios include both the ratio with the mutation characteristic gas as the numerator and the ratio with the mutation characteristic gas as the denominator. The detection system will record the change process of these concentration ratios before and after the mutation, establish the ratio evolution sequence during the mutation process, and provide a data basis for the subsequent analysis of the correlation between gases.

[0059] S206. Determine the correlation between the content change of the mutation characteristic gas and the non-mutation characteristic gas based on the mutation concentration ratio; Specifically, the detection system uses a variety of data analysis methods to evaluate the degree of correlation between changes in different characteristic gas contents: (1) Calculate the Pearson correlation coefficient to evaluate the degree of linear correlation; (2) Use time series analysis methods to identify the synchronization and lag of characteristic gas content changes; (3) Use dynamic time warping algorithms to compare the similarity of change patterns; (4) Apply Granger causality test to evaluate the causal relationship between characteristic gas content changes. The detection system comprehensively considers correlation indicators in multiple dimensions and constructs a correlation network of characteristic gas content changes.

[0060] Assume that the content change data of two characteristic gases, H2 and C2H2, are monitored within 3 days (one data point every 6 hours): H2 (μL / L): Day1: [100, 105, 110, 115]; Day2: [150, 200, 250, 300]; Day3: [320, 325, 330, 335]; C2H2 (μL / L): Day 1: [20, 22, 24, 25]; Day2: [30, 45, 60, 75]; Day3: [80, 82, 84, 85]; Analysis process: (1) Pearson correlation coefficient analysis: Calculation result: 0.98; Note: The changes in the contents of the two characteristic gases have a strong positive correlation; Explanation: The growth trends of H2 and C2H2 are highly consistent; (2) Time series analysis: Growth rate comparison: H2 first day growth rate: 15% / day; H2 second day growth rate: 160% / day; H2 third day growth rate: 12% / day; C2H2 first day growth rate: 25% / day; C2H2 second day growth rate: 150% / day; C2H2 growth rate on the third day: 13% / day; Explanation: The two characteristic gases increased dramatically at the same time on the second day, showing obvious time synchronization; (3) Dynamic Time Warping (DTW) analysis: Change pattern similarity score: 0.85 (out of 1.0); Explanation: The change patterns of the two characteristic gases are highly similar; Characteristics: They all present a three-stage change pattern of "steady-sharp increase-steady"; (4) Granger causality test: Test results: H2→C2H2: p value = 0.03 (<0.05, significant); C2H2→H2: p value = 0.45 (> 0.05, not significant); Explanation: The change of H2 may be the reason for the change of C2H2; Comprehensive analysis conclusion: 1. The two characteristic gases show a strong correlation (correlation coefficient 0.98); 2. Changes have good time synchronization, especially during the mutation period; 3. The change patterns are highly similar (DTW score 0.85) 4. Changes in H2 may lead to changes in C2H2 Troubleshooting suggestions: Based on this correlation feature, combined with the result that H2 is a potential cause of C2H2, it may point to a discharge-type fault, and it is recommended to further check the partial discharge of the transformer.

[0061] S207. Based on the correlation, screening the associated characteristic gases affected by the mutation characteristic gases; The correlated characteristic gas refers to the characteristic gas that changes due to the influence of the sudden change characteristic gas.

[0062] Specifically, the detection system screens the associated characteristic gases according to the following steps: (1) setting a correlation screening threshold, which can be determined based on the statistical significance level or expert experience; (2) sorting the characteristic gases according to the correlation strength, and identifying the characteristic gases whose correlation exceeds the correlation screening threshold; (3) analyzing the temporal characteristics of the impact and determining the propagation order of the impact; (4) evaluating the persistence of the impact and distinguishing between short-term and long-term impacts; (5) combining the physical and chemical properties of the gas to verify the rationality of the association. Finally, the detection system outputs a characteristic spectrum containing the mutation characteristic gas and its associated characteristic gas to guide subsequent fault diagnosis.

[0063] Assuming that C2H2 (acetylene) is initially found to have a mutation, it is necessary to screen its associated characteristic gases. The monitoring data is for 7 consecutive days: C2H2 (mutation characteristic gas) data: Day1-7: [20, 25, 80, 150, 180, 200, 210]; Other characteristic gas data: H2: [100, 120, 300, 500, 550, 580, 590]; CH4: [150, 155, 160, 165, 170, 175, 180]; C2H4: [30, 35, 90, 160, 185, 200, 205]; C2H6: [40, 42, 45, 48, 50, 52, 55]; Analysis process: ①Relevance screening threshold setting: Pearson correlation coefficient threshold: 0.8; p-value significance level: 0.05; ②Ranking by correlation strength: Calculate the correlation coefficient between each characteristic gas and C2H2: H2: 0.95 (p=0.001); CH4: 0.72 (p=0.068); C2H4: 0.98 (p=0.000); C2H6: 0.75 (p=0.052); ③ Timing feature analysis: Mutation sequence (daily growth rate exceeding 20% ​​is considered a mutation): Day 3: C2H2 mutated first (220% increase); Day 3: H2 follows the mutation (150% growth); Day3: C2H4 followed the mutation (157% increase); There is no obvious mutation in other gases; ④ Impact sustainability assessment Short-term effects (within 3 days): H2, C2H4; Long-term effects (lasting 7 days): None; No significant effect: CH4, C2H6; ⑤Physical and chemical properties verification: C2H2 is associated with H2: it meets the characteristics of discharge failure; C2H2 and C2H4 are associated: consistent with the decomposition characteristics of high-energy discharge; CH4 and C2H6 are weakly correlated: in line with the general rules; Final screening results: Strongly correlated characteristic gases (mainly correlated spectra): H2: Correlation coefficient: 0.95; Response characteristics: fast following; Physical basis: discharge decomposition products; C2H4: Correlation coefficient: 0.98; Response characteristics: synchronous changes; Physical basis: thermal decomposition chain reaction; Non-correlated characteristic gases: CH4: correlation coefficient is lower than the threshold; no obvious response characteristics; C2H6: correlation coefficient is below the threshold; the trend of change is not relevant; Diagnostic recommendations: Based on the correlation characteristic spectrum of C2H2-H2-C2H4 and its changing characteristics, it is preliminarily judged that there may be a high-energy discharge fault, and further electrical testing is recommended for confirmation.

[0064] S208, obtaining historical transformer oil temperature data, historical transformer load data, historical characteristic gas ratio matrix and corresponding historical fault types; Among them, historical transformer oil temperature data refers to the historical oil temperature measurement values ​​recorded during the operation of the transformer; historical transformer load data refers to the historical load record values ​​recorded during the operation of the transformer; the historical characteristic gas ratio matrix is ​​used to represent the records of the concentration ratios of each characteristic gas during the historical operation; historical fault types refer to confirmed transformer fault cases and their type labels.

[0065] Specifically, the detection system extracts historical data from the database, including: (1) historical transformer oil temperature data, historical transformer load data, and historical characteristic gas ratio matrix arranged in chronological order; (2) fault case records confirmed by experts; (3) relevant operating environment parameters. The detection system preprocesses the data, including: removing outliers, supplementing missing values, unifying data formats, marking data quality, etc.

[0066] S209, determining a historical characteristic gas ratio fault interval according to a historical characteristic gas ratio matrix; Specifically, the detection system performs the following analysis on each historical fault type: (1) Calculate the statistical characteristics of the concentration ratios of each characteristic gas when the fault occurs, such as the mean, standard deviation, and quantile; (2) Use methods such as kernel density estimation to fit the probability distribution of the concentration ratios; (3) Determine the concentration ratio interval based on the set confidence level (such as 95%); (4) Analyze the overlap of intervals of different fault types and adjust the interval range if necessary; (5) Verify the time stability of the interval and evaluate whether it is necessary to set the interval in different time periods.

[0067] S210, determining a preset characteristic gas ratio fault criterion rule based on the historical characteristic gas ratio fault interval and the historical fault type; Among them, the preset characteristic gas ratio fault judgment rule refers to the decision criterion used for fault diagnosis.

[0068] Specifically, the detection system establishes the preset characteristic gas ratio fault judgment rules through the following steps: (1) For each fault type, select the gas ratio combination with the highest discrimination as the main judgment criterion; (2) Design a multi-level judgment structure, including necessary conditions, sufficient conditions, and auxiliary conditions; (3) Set weights for different judgments to reflect their diagnostic value; (4) Develop a strategy for handling rule conflicts, such as priority sorting or fuzzy synthesis; (5) Evaluate the diagnostic accuracy of the rules through cross-validation; (6) Clarify the use conditions and constraints of the rules. Finally, a complete judgment rule system is formed to guide real-time fault diagnosis.

[0069] S211, determining a fault type of the transformer according to a preset characteristic gas ratio fault criterion rule and a characteristic gas ratio matrix, wherein the preset characteristic gas ratio fault criterion rule includes a plurality of characteristic gas ratio fault intervals and corresponding fault types; For details, please refer to step S106, which will not be described in detail here.

[0070] S212, inputting transformer oil temperature data, transformer load data and characteristic gas ratio matrix into a preset fault evolution prediction model, and predicting the characteristic gas ratio evolution trajectory; Among them, the preset fault evolution prediction model represents a mathematical model used to predict the changing trend of the gas concentration ratio; the characteristic gas ratio evolution trajectory refers to the predicted path of the gas concentration ratio changing over time.

[0071] Specifically, first, the detection system preprocesses the input data, including data standardization and feature extraction; then, the detection system inputs the processed input data into the preset fault evolution prediction model, which may adopt the following methods: (1) time series prediction algorithm, such as ARIMA, LSTM, etc.; (2) multivariate regression model, considering the influence of factors such as transformer oil temperature and transformer load; (3) hybrid method of physical model and data-driven model. The detection system predicts the concentration ratio of each characteristic gas and outputs a time series containing the predicted value and confidence interval. The prediction time span can be set according to actual needs, usually from several hours to several days.

[0072] S213, determining the suspected fault type according to the characteristic gas ratio evolution trajectory and the characteristic gas ratio matrix; Specifically, the detection system performs analysis through the following steps to determine the suspected fault type, where the suspected fault type refers to the type of fault that may occur in the future: (1) dynamically matching the predicted characteristic gas ratio evolution trajectory with the preset characteristic gas ratio fault judgment rule to identify the ratio combination that may exceed the limit; (2) calculating the similarity between the ratio combination that may exceed the limit and the characteristics of each type of fault, and evaluating the possibility of the fault type; (3) combining the current characteristic gas ratio matrix to analyze the fault development trend and speed; (4) determining the fault warning level based on the matching results and development trend; (5) considering the results of multiple prediction time points, evaluating the stability of the fault judgment.

[0073] S214. Generate a corresponding fault reminder item based on the suspected fault type, where the fault reminder item includes a characteristic gas ratio evolution trajectory, a suspected fault type, and a fault solution corresponding to the suspected fault type.

[0074] Among them, the fault reminder item refers to the set of fault warning information generated by the detection system; the fault solution refers to the processing suggestions for suspected fault types.

[0075] Specifically, the detection system constructs reminder items in the following manner: (1) Visually display the predicted evolution trajectory in a graphical manner; (2) List all suspected fault types and sort them by likelihood; (3) Configure corresponding fault solutions for each suspected fault type, including: emergency handling measures, inspection points, required tools and materials, safety precautions, etc.

[0076] The following describes the detection system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a detection system in an embodiment of the present application.

[0077] It should be noted that Figure 3 The structure of the detection system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0078] like Figure 3 As shown, the detection system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, the ROM 302 and the RAM 303 are connected to each other through the bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0079] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0080] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0081] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0082] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0083] Specifically, the detection system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the transformer fault detection method based on gas in oil provided in the above embodiment is implemented.

[0084] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the detection system described in the above embodiment; or may exist independently without being assembled into the detection system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the detection system, the detection system implements the transformer fault detection method based on gas in oil provided in the above embodiment.

[0085] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0086] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0087] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A transformer fault detection method based on gas in oil, characterized in that: Applied to a detection system, the method comprises: Collect transformer oil temperature data, transformer load data, and content data of each characteristic gas in transformer oil; Determine whether the transformer oil temperature data and the transformer load data both meet preset transformer oil temperature load operation characteristics, wherein the preset transformer oil temperature load operation characteristics include a transformer oil temperature change rate standard and a transformer load change rate standard; If it is in accordance with the preset oil temperature-gas type-solubility correspondence, the theoretical solubility of each characteristic gas at the current transformer oil temperature is determined, and the current transformer oil temperature is determined by the transformer oil temperature data at the current moment; Dividing the content data of each characteristic gas by the theoretical solubility to obtain the standardized content of each characteristic gas at the current transformer oil temperature; Based on the standardized content of each characteristic gas, the concentration ratios of all characteristic gases are calculated to construct a characteristic gas ratio matrix; The fault type of the transformer is determined according to a preset characteristic gas ratio fault criterion rule and the characteristic gas ratio matrix, wherein the preset characteristic gas ratio fault criterion rule includes a plurality of characteristic gas ratio fault intervals and corresponding fault types.

2. The method according to claim 1, characterized in that The determining whether the transformer oil temperature data and the transformer load data both meet the preset transformer oil temperature and load operating characteristics specifically includes: Calculate the oil temperature change rate of the transformer oil temperature data and the load change rate of the transformer load data within a preset time window; When the oil temperature change rate is less than a preset first change rate threshold and the load change rate is less than a preset second change rate threshold, determining that the transformer oil temperature data and the transformer load data meet the preset transformer oil temperature and load operating characteristics; When the oil temperature change rate is greater than or equal to the preset first change rate threshold or the load change rate is greater than or equal to the preset second change rate threshold, it is determined that the transformer oil temperature data and the transformer load data do not meet the preset transformer oil temperature and load operating characteristics.

3. The method according to claim 1, characterized in that The step of determining the fault type of the transformer according to the preset characteristic gas ratio fault judgment rule and the characteristic gas ratio matrix specifically includes: According to each concentration ratio in the characteristic gas ratio matrix, determining a target characteristic gas ratio fault interval with the highest matching degree in the preset characteristic gas ratio fault criterion rule, wherein the preset characteristic gas ratio fault criterion rule includes a plurality of characteristic gas ratio fault intervals and corresponding fault types; Based on the target characteristic gas ratio fault interval and the preset characteristic gas ratio fault criterion rule, a target fault type of the transformer is determined.

4. The method according to claim 2, characterized in that: After the step of calculating the concentration ratios of all characteristic gases in pairs based on the standardized contents of the respective characteristic gases to construct a characteristic gas ratio matrix, the method further includes: Calculating the standardized content change rate of each characteristic gas within the preset time window; Determining whether the change rate of the standardized content exceeds a preset third change rate threshold; If the standardized content change rate exceeds the preset third change rate threshold, determining a mutation characteristic gas; Identify equipment components whose correlation with the mutation characteristic gas exceeds a preset correlation threshold.

5. The method according to claim 4, characterized in that After the step of determining the mutation characteristic gas if the standardized content change rate exceeds the preset third change rate threshold, the method further includes: Determine the concentration ratio related to the mutation characteristic gas in the characteristic gas ratio matrix as the mutation concentration ratio, wherein the mutation concentration ratio is used to represent the concentration ratio of the mutation characteristic gas to the non-mutation characteristic gas; Based on the mutation concentration ratio, determining the correlation between the content change of the mutation characteristic gas and the non-mutation characteristic gas; Based on the correlation, the associated characteristic gases affected by the sudden change characteristic gas are screened.

6. The method according to claim 1, characterized in that Before the step of determining the fault type of the transformer according to the preset characteristic gas ratio fault criterion rule and the characteristic gas ratio matrix, the method further includes: Obtain historical transformer oil temperature data, historical transformer load data, historical characteristic gas ratio matrix and corresponding historical fault types; Determining a historical characteristic gas ratio fault interval according to the historical characteristic gas ratio matrix; The preset characteristic gas ratio fault criterion rule is determined based on the historical characteristic gas ratio fault interval and the historical fault type.

7. The method according to claim 1, characterized in that After the step of determining the fault type of the transformer according to the preset characteristic gas ratio fault criterion rule and the characteristic gas ratio matrix, the method further includes: Inputting the transformer oil temperature data, the transformer load data and the characteristic gas ratio matrix into a preset fault evolution prediction model to predict the characteristic gas ratio evolution trajectory; Determining a suspected fault type according to the characteristic gas ratio evolution trajectory and the characteristic gas ratio matrix; Based on the suspected fault type, a corresponding fault reminder item is generated, and the fault reminder item includes the characteristic gas ratio evolution trajectory, the suspected fault type and a fault solution corresponding to the suspected fault type.

8. A detection system, characterized in that: The detection system comprises: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and the one or more processors call the computer instructions so that the detection system executes the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a detection system, the detection system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a detection system, the detection system is caused to perform the method according to any one of claims 1 to 7.

Images