Transformer state comprehensive prediction evaluation method and system based on decision cascade fusion analysis and storage medium
Patent Information
- Application Number
- CN202510553943.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-29
- Publication Date
- 2026-11-03
- Estimated Expiration
- 2045-04-29
AI Technical Summary
In existing technologies, transformer fault diagnosis methods based on dissolved gases in oil suffer from misjudgments and omissions in classification and boundary determination, and cannot accurately and comprehensively predict the transformer condition.
A decision-based cascade fusion analysis method is adopted, which combines multiple decision-making tools to analyze dissolved gases in oil. Through the identification of characteristic gas concentrations, partial discharge signals, and insulation systems, the transformer condition can be accurately assessed.
It enables accurate, comprehensive, and rapid assessment of transformer condition, significantly improving diagnostic accuracy, reducing misjudgments and omissions, providing accurate early warning and fault location, and reducing maintenance costs and cycles.
Smart Images

Figure CN120405278B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of power transformer monitoring technology, specifically relating to a method, system, and storage medium for comprehensive prediction and evaluation of transformer status based on decision cascade fusion analysis. Background Technology
[0002] With the expansion of the power grid, more stringent requirements have been placed on the safe and reliable operation of the power system. As a crucial piece of power transmission and transformation equipment, the operational reliability of transformers is vital to the safe and stable operation of the entire power grid. Dissolved gas monitoring in oil is currently the primary method for transformer condition monitoring, widely used due to its high accuracy and strong anti-interference capabilities. When a transformer is under normal operating conditions or under certain fault conditions, the insulating oil and some possible insulating materials in an oil-immersed transformer may produce characteristic gases under the influence of factors such as electrothermal activity. Analyzing these characteristic gases dissolved in the transformer's insulating oil allows for the assessment of the transformer's operating status based on their main components and concentrations, thus enabling rapid and effective prediction of the oil-immersed power transformer's operating condition.
[0003] Currently, the research on DGA diagnostic methods for oil-immersed transformers in engineering practice is relatively mature, mainly including key characteristic gas concentration analysis, Duval triangle method, IEC method, Rogers ratio method, and Dornenburg gas ratio method. These methods have been widely used in the fault diagnosis of transformers in actual operation. However, these judgment methods are too absolute in terms of classification and boundary determination, resulting in boundary overlap, misjudgment, and missed data, failing to accurately and comprehensively predict the transformer condition. In order to comprehensively, accurately, and efficiently monitor the operating condition of transformers, a comprehensive prediction method for transformer condition based on decision cascade fusion analysis technology is proposed from the perspective of practical application. Summary of the Invention
[0004] In view of this, the present invention provides a method, system, and storage medium for comprehensive prediction and evaluation of transformer status based on decision cascade fusion analysis. Addressing the problems of inaccurate fault judgment at boundary points and contradictory decision-making in current standards based on dissolved gases in oil during practical applications, this invention studies the characteristics of different decision-making methods and integrates multiple methods to comprehensively analyze and predict transformer operating status. This solves the problems of fuzzy boundary point monitoring, incomplete monitoring status, and inaccurate evaluation caused by current single-method monitoring.
[0005] The technical solution adopted in this invention is: a comprehensive prediction and evaluation method for transformer condition based on decision cascade fusion analysis, including...
[0006] Oil samples were collected from the oil-immersed transformer under different operating conditions. The concentration of dissolved characteristic gases in the oil under different operating conditions was analyzed based on the oil samples. The generation rate of characteristic gases was calculated based on the concentration of dissolved characteristic gases in the oil at different times.
[0007] The concentrations of dissolved characteristic gases in the oil were incorporated into various fault diagnosis methods based on dissolved gas analysis in oil according to different decision-making approaches to assess and predict the transformer condition, resulting in multiple decision-making assessment results.
[0008] The system statistically analyzes multiple decision evaluation results. If a decision evaluation result is repeated more than twice, the currently repeated decision evaluation result is output. If a decision evaluation result is repeated less than or equal to two times, the system acquires the partial discharge signal corresponding to the oil sample time period. If a partial discharge signal exists, the system performs a fusion judgment based on the amplitude and frequency characteristics of the partial discharge signal and the multiple decision evaluation results, and outputs the discharge fault judgment result. If no partial discharge signal exists, the system performs a fusion judgment based on the characteristic gas generation rate and the multiple decision evaluation results, and outputs the overheating fault judgment result.
[0009] By combining the results of discharge fault determination or overheating fault determination with the ratio of carbon monoxide to carbon dioxide concentration in the oil sample, it is determined whether the insulation system involved in the transformer condition is a pure oil insulation system or an oil-paper insulation system, thus completing the fault classification of the transformer's operating condition.
[0010] Preferred fault diagnosis methods based on dissolved gas analysis in oil include at least five methods: key characteristic gas concentration analysis, Duval Triangle Method, IEC Ratio Method, Rogers Ratio Method, and Dornenburg Gas Ratio Method.
[0011] In the above technical solution, sampling, diagnosis, partial discharge / rate discrimination and insulation system identification are connected in series to form a closed loop, which can locate the transformer fault type and identify the insulation object in real time and accurately. The overall diagnostic accuracy and anti-interference ability are significantly improved, and misjudgment and missed judgment are reduced.
[0012] Preferably, the dissolved characteristic gases in the oil include at least H2, CH4, C2H6, C2H4, C2H2, CO, and CO2.
[0013] Preferably, the generation rate of the characteristic gas is calculated using the following formula:
[0014]
[0015] Where v represents the absolute gas production rate, in mL / h; c i2 This indicates the concentration of a characteristic gas in the insulating oil measured during a second sampling, expressed in pL / L; c i1 The first Δt represents the concentration of a characteristic gas in the transformer insulating oil measured during the first sampling, in μL / L; the second Δt represents the actual operating time between the first and second samplings, in hours (h); the third Δt represents the total mass of the transformer insulating oil, in tons (t); and the fourth ρ represents the density of the transformer insulating oil, in tons per cubic meter (t / m³). 3 .
[0016] The above technical solution introduces oil quantity and density correction to eliminate the impact of sampling interval and oil quantity differences on rate estimation, making the gas production rate more accurate, which is conducive to fault trend monitoring and threshold control, and early warning of potential deterioration.
[0017] A preferred approach is to fuse and determine the partial discharge signal based on its amplitude and frequency characteristics and multiple decision evaluation results, including: if the amplitude or frequency characteristics of the partial discharge signal exceed a preset threshold and at least three diagnostic results indicate the presence of a discharge fault, then outputting a discharge fault determination result; if the amplitude or frequency characteristics of the partial discharge signal do not reach the preset threshold or fewer than three of the multiple diagnostic results indicate the presence of a discharge fault, then comprehensively judging the remaining evaluation information based on pre-set weighted voting or priority rules; if the comprehensive result still indicates the presence of discharge behavior, then outputting a discharge fault determination result; otherwise, determining that the current fault type does not belong to a discharge fault and outputting the corresponding diagnostic result.
[0018] In the above technical solution, electrical signal strength and gas diagnostic results are used simultaneously. When the local discharge signal exceeds the threshold and is consistent with ≥3 methods, the discharge fault is quickly locked. When there is a conflict, the weighted rule is pulled in to ensure the robustness of the conclusion, taking into account both sensitivity and reliability.
[0019] A preferred approach is to fuse the characteristic gas generation rate with multiple decision evaluation results for judgment, which includes: if the characteristic gas generation rate exceeds a preset overheating fault threshold and at least three of the multiple diagnostic results indicate the presence of a thermal fault type, then it is determined to be an overheating fault and the corresponding overheating fault judgment result is output; if the characteristic gas generation rate does not exceed the threshold or fewer than three of the multiple diagnostic results indicate a thermal fault, then the remaining evaluation results are comprehensively judged according to weighted voting or priority rules; if the comprehensive result still points to a thermal fault, then an overheating fault judgment result is output; otherwise, it is determined that the current state does not belong to an overheating fault and the corresponding diagnostic result is output.
[0020] In the above technical solution, the dual thresholds of rate over-threshold and multi-method thermal fault consistency effectively filter false alarms caused by ambient temperature rise or short-term load fluctuations, accurately identify potential continuous overheating hazards, and guide operation and maintenance for cooling or load adjustment.
[0021] A preferred approach is to integrate the discharge fault determination result with the carbon monoxide to carbon dioxide concentration ratio in the oil sample for judgment. This includes: when the overheating fault or discharge fault determination result indicates an abnormal current operating state, determining the insulation system type corresponding to the fault based on a pre-set CO / CO2 concentration ratio threshold; if the actual CO / CO2 concentration ratio is lower than the threshold, it is determined to be a pure oil insulation system fault; if the actual CO / CO2 concentration ratio is equal to or higher than the threshold, it is determined to be an oil-paper insulation system fault; and integrating the aforementioned fault type information with the discharge fault determination result or overheating fault determination result to obtain a complete transformer operating state fault classification and output corresponding diagnostic conclusions.
[0022] In the above technical solution, the insulation medium of the fault source is quickly classified by combining the gas determination results, which can directly guide the subsequent maintenance strategy (replacing oil or treating paper insulation) and avoid over-maintenance or omission of hidden dangers.
[0023] A preferred approach involves importing the concentration data of different characteristic gas components in the oil sample into five diagnostic methods—key characteristic gas concentration analysis, Duval triangular diagram diagnostic method, IEC gas ratio method, Rogers gas ratio method, and Dornenberg gas ratio method—to assess and predict the transformer's condition, obtaining five decision assessment results. The process includes:
[0024] Obtain the concentration parameters of dissolved gases in the oil, including but not limited to H2, CH4, C2H6, C2H4, C2H2, CO, and CO2;
[0025] In the key characteristic gas concentration analysis method, by identifying the relative proportions of H2, CH4, C2H6, C2H4, C2H2, and CO, a preliminary distinction can be made between discharge faults and overheating faults.
[0026] In the Duval triangle diagnostic method, the percentages of the three combustible gases CH4, C2H4 and C2H2 are projected onto the Duval triangle diagram, and the fault type is determined based on the area where the point falls within the triangle.
[0027] In the International Electrotechnical Commission's gas ratio method, based on the gas ratio coding rules specified in the IEC standard, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are calculated, classified, and the corresponding fault types are output.
[0028] In the Rogers gas ratio method, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are combined and matched with a predetermined range to determine whether a discharge fault or an overheating fault exists.
[0029] In the Dornenberg gas ratio method, the CH4 / H2 concentration ratio, C2H2 / C2H4 concentration ratio, C2H2 / CH4 concentration ratio, and C2H6 / C2H2 concentration ratio are compared with the corresponding criteria to obtain the assessment results of the transformer fault type.
[0030] The fault assessment outputs of the above five diagnostic methods are recorded and summarized to obtain five independent decision assessment results.
[0031] The above technical solutions utilize the complementarity of various methods to achieve redundant verification: Duval provides intuitive graphical representation, IEC / Rogers provides clear standardization, critical gas early warning is provided quickly, and Dornenburg provides auxiliary reinforcement; significantly reducing the diagnostic blind spots caused by a single method "going out of bounds" or "not being coded".
[0032] This invention also provides a transformer condition comprehensive prediction and evaluation system based on decision cascade fusion analysis. The system includes a data acquisition module, an evaluation module, a fault determination module, and a fault classification module.
[0033] The acquisition module is used to collect oil samples from oil-immersed transformers under different operating conditions, analyze the concentration of dissolved characteristic gases in the oil under different operating conditions based on the oil samples, and calculate the generation rate of characteristic gases based on the concentration of dissolved characteristic gases in the oil at different times.
[0034] The evaluation module is used to import the concentration of dissolved characteristic gases in the oil into various fault diagnosis methods based on dissolved gas analysis in oil according to different decision-making methods to evaluate and predict the transformer status, and obtain multiple decision evaluation results respectively.
[0035] The fault determination module is used to statistically analyze multiple decision evaluation results. When a decision evaluation result is repeated more than twice, the currently repeated decision evaluation result is output. When a decision evaluation result is repeated less than or equal to two times, the module acquires the partial discharge signal corresponding to the time period of the oil sample. If a partial discharge signal exists, the module performs a fusion judgment based on the amplitude and frequency characteristics of the partial discharge signal and the multiple decision evaluation results, and outputs the discharge fault determination result. If no partial discharge signal exists, the module performs a fusion judgment based on the characteristic gas generation rate and the multiple decision evaluation results, and outputs the overheating fault determination result.
[0036] The fault classification module is used to integrate the discharge fault determination result or overheating fault determination result with the carbon monoxide to carbon dioxide concentration ratio in the oil sample to determine whether the insulation system involved in the transformer status is a pure oil insulation system or an oil-paper insulation system, thereby completing the fault classification of the transformer operating status.
[0037] Preferred fault diagnosis methods based on dissolved gas analysis in oil include at least five methods: key characteristic gas concentration analysis, Duval Triangle Method, IEC Ratio Method, Rogers Ratio Method, and Dornenburg Gas Ratio Method.
[0038] Preferably, the dissolved characteristic gases in the oil include at least H2, CH4, C2H6, C2H4, C2H2, CO, and CO2.
[0039] Preferably, the generation rate of the characteristic gas is calculated using the following formula:
[0040]
[0041] Where v represents the absolute gas production rate, in mL / h; c i2 This indicates the concentration of a characteristic gas in the insulating oil measured during a second sampling, expressed in pL / L; c i1 The first Δt represents the concentration of a characteristic gas in the transformer insulating oil measured during the first sampling, in μL / L; the second Δt represents the actual operating time between the first and second samplings, in hours (h); the third Δt represents the total mass of the transformer insulating oil, in tons (t); and the fourth ρ represents the density of the transformer insulating oil, in tons per cubic meter (t / m³). 3 .
[0042] A preferred approach is to fuse and determine the partial discharge signal based on its amplitude and frequency characteristics and multiple decision evaluation results, including: if the amplitude or frequency characteristics of the partial discharge signal exceed a preset threshold and at least three diagnostic results indicate the presence of a discharge fault, then outputting a discharge fault determination result; if the amplitude or frequency characteristics of the partial discharge signal do not reach the preset threshold or fewer than three of the multiple diagnostic results indicate the presence of a discharge fault, then comprehensively judging the remaining evaluation information based on pre-set weighted voting or priority rules; if the comprehensive result still indicates the presence of discharge behavior, then outputting a discharge fault determination result; otherwise, determining that the current fault type does not belong to a discharge fault and outputting the corresponding diagnostic result.
[0043] A preferred approach is to fuse the characteristic gas generation rate with multiple decision evaluation results for judgment, which includes: if the characteristic gas generation rate exceeds a preset overheating fault threshold and at least three of the multiple diagnostic results indicate the presence of a thermal fault type, then it is determined to be an overheating fault and the corresponding overheating fault judgment result is output; if the characteristic gas generation rate does not exceed the threshold or fewer than three of the multiple diagnostic results indicate a thermal fault, then the remaining evaluation results are comprehensively judged according to weighted voting or priority rules; if the comprehensive result still points to a thermal fault, then an overheating fault judgment result is output; otherwise, it is determined that the current state does not belong to an overheating fault and the corresponding diagnostic result is output.
[0044] A preferred approach is to integrate the discharge fault determination result with the carbon monoxide to carbon dioxide concentration ratio in the oil sample for judgment. This includes: when the overheating fault or discharge fault determination result indicates an abnormal current operating state, determining the insulation system type corresponding to the fault based on a pre-set CO / CO2 concentration ratio threshold; if the actual CO / CO2 concentration ratio is lower than the threshold, it is determined to be a pure oil insulation system fault; if the actual CO / CO2 concentration ratio is equal to or higher than the threshold, it is determined to be an oil-paper insulation system fault; and integrating the aforementioned fault type information with the discharge fault determination result or overheating fault determination result to obtain a complete transformer operating state fault classification and output corresponding diagnostic conclusions.
[0045] A preferred approach involves importing the concentration data of different characteristic gas components in the oil sample into five diagnostic methods—key characteristic gas concentration analysis, Duval triangular diagram diagnostic method, IEC gas ratio method, Rogers gas ratio method, and Dornenberg gas ratio method—to assess and predict the transformer's condition, obtaining five decision assessment results. The process includes:
[0046] Obtain the concentration parameters of dissolved gases in the oil, including but not limited to H2, CH4, C2H6, C2H4, C2H2, CO, and CO2;
[0047] In the key characteristic gas concentration analysis method, by identifying the relative proportions of H2, CH4, C2H6, C2H4, C2H2, and CO, a preliminary distinction can be made between discharge faults and overheating faults.
[0048] In the Duval triangle diagnostic method, the percentages of the three combustible gases CH4, C2H4 and C2H2 are projected onto the Duval triangle diagram, and the fault type is determined based on the area where the point falls within the triangle.
[0049] In the International Electrotechnical Commission's gas ratio method, based on the gas ratio coding rules specified in the IEC standard, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are calculated, classified, and the corresponding fault types are output.
[0050] In the Rogers gas ratio method, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are combined and matched with a predetermined range to determine whether a discharge fault or an overheating fault exists.
[0051] In the Dornenberg gas ratio method, the CH4 / H2 concentration ratio, C2H2 / C2H4 concentration ratio, C2H2 / CH4 concentration ratio, and C2H6 / C2H2 concentration ratio are compared with the corresponding criteria to obtain the assessment results of the transformer fault type.
[0052] The fault assessment outputs of the above five diagnostic methods are recorded and summarized to obtain five independent decision assessment results.
[0053] The present invention also discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of the transformer state comprehensive prediction and evaluation method based on decision cascade fusion analysis.
[0054] This invention, through multi-level fusion decision-making, can effectively achieve accurate, comprehensive, and rapid assessment and decision-making regarding the operating status of transformers, thereby enabling precise prediction of transformer operating conditions. This method has broad practical application potential, significantly improving the accuracy of transformer condition assessment methods and effectively reducing the cost and time required for transformer outage maintenance.
[0055] The method proposed in this invention is practical, reasonable, convenient, accurate, comprehensive and efficient. It can quickly and accurately assess and predict the operating status of transformers, which not only helps to reduce the cost and cycle of on-site maintenance and testing, but also provides a solid foundation for the accurate prediction of transformer operating status in the next stage.
[0056] This invention explores the correspondence between transformer operating status and decision-making methods, continuously improves the depth and breadth of transformer condition monitoring, further enhances the accuracy and robustness of transformer condition monitoring, improves the operational reliability of UHV transformers, and reduces transformer maintenance and replacement costs, transportation costs, etc.
[0057] The overall beneficial effects of this invention specifically include:
[0058] 1. Significantly Improved Diagnostic Accuracy: Through a "five-method parallel" and "decision cascade fusion" mechanism, the complementary advantages of classic methods such as the Duval triangle and IEC / Rogers ratio are fully utilized; combined with partial discharge amplitude and frequency characteristics or gas generation rate thresholds, precise differentiation between electrical discharge and thermal faults is achieved through dual channels. Cross-validation of multi-source information effectively suppresses biases caused by single-method "out-of-bounds," "uncoded," or misjudgments, improving the overall accuracy by 10%–20% or more compared to using any single traditional method alone.
[0059] 2. Enhanced early warning and trend tracking capabilities: The introduction of the concept of absolute gas production rate allows for the quantification of changes in gas generation rate with only two samplings, enabling the detection of potential overheating hazards before gas concentration exceeds warning levels. Real-time online partial discharge signal monitoring and oil sample analysis form two monitoring channels, "fast" and "slow," providing both instantaneous warnings of sudden breakdown risks and long-term tracking of slow degradation, achieving full lifecycle health management.
[0060] 3. More Precise Fault Location and Maintenance Decisions: Utilizing the CO / CO2 ratio, the root cause of faults in pure oil or oil-paper insulation can be quickly identified. Corresponding maintenance strategies can be immediately differentiated into different solutions such as "replace oil" or "dry / replace paper insulation," shortening maintenance and diagnosis time by more than 30%. The discharge and overheating judgment results are coupled with the insulation medium category, directly generating composite tags such as "discharge-oil-paper" and "overheating-pure oil," facilitating the maintenance department to prioritize power outage maintenance or live monitoring.
[0061] 4. Reduce false alarm and false negative rates: Adaptively balance diagnostic conflicts to avoid false alarms triggered by single-point anomalies; while ensuring that the system can still issue alarms when a small number of key indicators are abnormal, reducing false alarms. For early and weak faults such as low-energy partial discharge or slight temperature rise, the fusion algorithm improves the detection rate by approximately 15% compared to the traditional single ratio threshold method.
[0062] 5. High standards compatibility and portability: The key characteristic gas method, Duval diagram, IEC, Rogers, and Dornenburg ratio method adopted are all internationally / industry-standard algorithms, requiring no replacement of existing oil chromatography and partial discharge monitoring hardware; deployment can be achieved solely through software upgrades, resulting in low implementation costs. It can be expanded to include AI models or add new sensors (oil sludge detection, water activity detection, etc.), maintaining compatibility with technological evolution.
[0063] 6. Improved Operation and Maintenance Economy and Safety: Detecting potential faults 1-3 maintenance cycles in advance can reduce unplanned power outages by approximately 40%, directly saving on power outage losses and major repair costs. Systematic health assessments avoid over-maintenance, extending the life of oil-paper insulation by more than 5 years and reducing the overall asset life cycle cost (LCC) by approximately 8%.
[0064] 7. Data Closed Loop and Intelligent Management: The multi-dimensional fault labels output by the method can be directly written into the transformer digital twin or asset management system, forming a closed-loop data chain of status-decision-execution-feedback. This provides high-quality training samples for subsequent big data analysis, fault root cause mining, and network-wide health index (HI) assessment, assisting in the intelligent operation and maintenance upgrade of distribution networks, main grids, and new energy power plants. Attached Figure Description
[0065] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0066] Figure 1 This is a flowchart illustrating Embodiment 1 of the transformer condition comprehensive prediction and evaluation method based on decision cascade fusion analysis of the present invention;
[0067] Figure 2 This is a schematic diagram of the functional modules of Embodiment 2 of the Transformer Condition Comprehensive Prediction and Evaluation System based on Decision Cascade Fusion Analysis of the present invention. Detailed Implementation
[0068] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems and methods are omitted so as not to obscure the description of the invention with unnecessary detail.
[0069] Example 1
[0070] like Figure 1 As shown, a comprehensive prediction and evaluation method for transformer condition based on decision cascade fusion analysis includes...
[0071] Oil samples were collected from the oil-immersed transformer under different operating conditions. The concentration of dissolved characteristic gases in the oil under different operating conditions was analyzed based on the oil samples. The generation rate of characteristic gases was calculated based on the concentration of dissolved characteristic gases in the oil at different times.
[0072] The concentrations of dissolved characteristic gases in the oil were incorporated into various fault diagnosis methods based on dissolved gas analysis in oil according to different decision-making approaches to assess and predict the transformer condition, resulting in multiple decision-making assessment results.
[0073] The system statistically analyzes multiple decision evaluation results. If a decision evaluation result is repeated more than twice, the currently repeated decision evaluation result is output. If a decision evaluation result is repeated less than or equal to two times, the system acquires the partial discharge signal corresponding to the oil sample time period. If a partial discharge signal exists, the system performs a fusion judgment based on the amplitude and frequency characteristics of the partial discharge signal and the multiple decision evaluation results, and outputs the discharge fault judgment result. If no partial discharge signal exists, the system performs a fusion judgment based on the characteristic gas generation rate and the multiple decision evaluation results, and outputs the overheating fault judgment result.
[0074] By combining the results of discharge fault determination or overheating fault determination with the ratio of carbon monoxide to carbon dioxide concentration in the oil sample, it is determined whether the insulation system involved in the transformer condition is a pure oil insulation system or an oil-paper insulation system, thus completing the fault classification of the transformer's operating condition.
[0075] Multiple fault diagnosis methods based on dissolved gas analysis in oil include at least five methods: key characteristic gas concentration analysis, Duval Triangle Method, IEC Ratio Method, Rogers Ratio Method, and Dornenburg Gas Ratio Method.
[0076] The characteristic dissolved gases in the oil include at least H2, CH4, C2H6, C2H4, C2H2, CO, and CO2.
[0077] The generation rate of the characteristic gas is calculated using the following formula:
[0078]
[0079] Where v represents the absolute gas production rate, in mL / h; c i2 This indicates the concentration of a characteristic gas in the insulating oil measured during a second sampling, expressed in pL / L; c i1 The first Δt represents the concentration of a characteristic gas in the transformer insulating oil measured during the first sampling, in μL / L; the second Δt represents the actual operating time between the first and second samplings, in hours (h); the third Δt represents the total mass of the transformer insulating oil, in tons (t); and the fourth ρ represents the density of the transformer insulating oil, in tons per cubic meter (t / m³). 3 .
[0080] The fusion judgment based on the amplitude and frequency characteristics of partial discharge signals and multiple decision evaluation results includes: if the amplitude or frequency characteristics of the partial discharge signal exceed a preset threshold and at least three diagnostic results indicate the presence of a discharge fault, then a discharge fault judgment result is output; if the amplitude or frequency characteristics of the partial discharge signal do not reach the preset threshold or fewer than three of the multiple diagnostic results indicate the presence of a discharge fault, then the remaining evaluation information is comprehensively judged based on pre-set weighted voting or priority rules. If the comprehensive result still indicates the presence of discharge behavior, then a discharge fault judgment result is output; otherwise, it is determined that the current fault type does not belong to a discharge fault and the corresponding diagnostic result is output.
[0081] The fusion judgment based on the characteristic gas generation rate and multiple decision evaluation results includes: if the characteristic gas generation rate exceeds the preset overheating fault threshold and at least three of the multiple diagnostic results indicate the presence of a thermal fault type, then it is determined to be an overheating fault and the corresponding overheating fault judgment result is output; if the characteristic gas generation rate does not exceed the threshold or fewer than three of the multiple diagnostic results indicate a thermal fault, then the remaining evaluation results are comprehensively judged according to weighted voting or priority rules. If the comprehensive result still points to a thermal fault, then the overheating fault judgment result is output; otherwise, it is determined that the current state does not belong to an overheating fault and the corresponding diagnostic result is output.
[0082] The fusion judgment of discharge fault determination results with the carbon monoxide to carbon dioxide concentration ratio in the oil sample includes: when the overheating fault or discharge fault determination results indicate that the current operating state is abnormal, the insulation system type corresponding to the fault is determined based on a pre-set CO / CO2 concentration ratio threshold. If the actual CO / CO2 concentration ratio is lower than the threshold, it is determined to be a pure oil insulation system fault; if the actual CO / CO2 concentration ratio is equal to or higher than the threshold, it is determined to be an oil-paper insulation system fault. The aforementioned fault type information is integrated with the discharge fault determination results or overheating fault determination results to obtain a complete transformer operating state fault classification and output the corresponding diagnostic conclusion.
[0083] The process of importing concentration data of different characteristic gas components in oil samples into five diagnostic methods—key characteristic gas concentration analysis, Duval triangular diagram diagnostic method, IEC gas ratio method, Rogers gas ratio method, and Dornenberg gas ratio method—to assess and predict transformer condition, and obtaining five decision assessment results, includes:
[0084] Obtain the concentration parameters of dissolved gases in the oil, including but not limited to H2, CH4, C2H6, C2H4, C2H2, CO, and CO2;
[0085] In the key characteristic gas concentration analysis method, by identifying the relative proportions of H2, CH4, C2H6, C2H4, C2H2, and CO, a preliminary distinction can be made between discharge faults and overheating faults.
[0086] In the Duval triangle diagnostic method, the percentages of the three combustible gases CH4, C2H4 and C2H2 are projected onto the Duval triangle diagram, and the fault type is determined based on the area where the point falls within the triangle.
[0087] In the International Electrotechnical Commission's gas ratio method, based on the gas ratio coding rules specified in the IEC standard, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are calculated, classified, and the corresponding fault types are output.
[0088] In the Rogers gas ratio method, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are combined and matched with a predetermined range to determine whether a discharge fault or an overheating fault exists.
[0089] In the Dornenberg gas ratio method, the CH4 / H2 concentration ratio, C2H2 / C2H4 concentration ratio, C2H2 / CH4 concentration ratio, and C2H6 / C2H2 concentration ratio are compared with the corresponding criteria to obtain the assessment results of the transformer fault type.
[0090] The fault assessment outputs of the above five diagnostic methods are recorded and summarized to obtain five independent decision assessment results.
[0091] Example 2
[0092] like Figure 2 As shown, a transformer condition comprehensive prediction and evaluation system based on decision cascade fusion analysis is presented. This system includes a data acquisition module, an evaluation module, a fault determination module, and a fault classification module.
[0093] The data acquisition module is used to collect oil samples from oil-immersed transformers under different operating conditions. Based on the oil samples, the concentration of dissolved characteristic gases in the oil under different operating conditions is analyzed, and the generation rate of characteristic gases is calculated based on the concentration of dissolved characteristic gases in the oil at different times.
[0094] The evaluation module is used to import the concentration of dissolved characteristic gases in the oil into various fault diagnosis methods based on dissolved gas analysis in oil according to different decision-making methods to evaluate and predict the transformer condition, and obtain multiple decision evaluation results.
[0095] The fault determination module is used to statistically analyze multiple decision evaluation results. When a decision evaluation result is repeated more than twice, the currently repeated decision evaluation result is output. When a decision evaluation result is repeated less than or equal to two times, the module acquires the partial discharge signal corresponding to the time period of the oil sample. If a partial discharge signal exists, the module performs a fusion judgment based on the amplitude and frequency characteristics of the partial discharge signal and the multiple decision evaluation results, and outputs the discharge fault determination result. If no partial discharge signal exists, the module performs a fusion judgment based on the characteristic gas generation rate and the multiple decision evaluation results, and outputs the overheating fault determination result.
[0096] The fault classification module is used to integrate the discharge fault judgment result or overheating fault judgment result with the carbon monoxide to carbon dioxide concentration ratio in the oil sample to determine whether the insulation system involved in the transformer status is a pure oil insulation system or an oil-paper insulation system, thus completing the fault classification of the transformer operating status.
[0097] Multiple fault diagnosis methods based on dissolved gas analysis in oil include at least five methods: key characteristic gas concentration analysis, Duval Triangle Method, IEC Ratio Method, Rogers Ratio Method, and Dornenburg Gas Ratio Method.
[0098] The characteristic dissolved gases in the oil include at least H2, CH4, C2H6, C2H4, C2H2, CO, and CO2.
[0099] The generation rate of the characteristic gas is calculated using the following formula:
[0100]
[0101] Where v represents the absolute gas production rate, in mL / h; c i2 This indicates the concentration of a characteristic gas in the insulating oil measured during a second sampling, expressed in pL / L; c i1 The first Δt represents the concentration of a characteristic gas in the transformer insulating oil measured during the first sampling, in μL / L; the second Δt represents the actual operating time between the first and second samplings, in hours (h); the third Δt represents the total mass of the transformer insulating oil, in tons (t); and the fourth ρ represents the density of the transformer insulating oil, in tons per cubic meter (t / m³). 3 .
[0102] The fusion judgment based on the amplitude and frequency characteristics of partial discharge signals and multiple decision evaluation results includes: if the amplitude or frequency characteristics of the partial discharge signal exceed a preset threshold and at least three diagnostic results indicate the presence of a discharge fault, then a discharge fault judgment result is output; if the amplitude or frequency characteristics of the partial discharge signal do not reach the preset threshold or fewer than three of the multiple diagnostic results indicate the presence of a discharge fault, then the remaining evaluation information is comprehensively judged based on pre-set weighted voting or priority rules. If the comprehensive result still indicates the presence of discharge behavior, then a discharge fault judgment result is output; otherwise, it is determined that the current fault type does not belong to a discharge fault and the corresponding diagnostic result is output.
[0103] The fusion judgment based on the characteristic gas generation rate and multiple decision evaluation results includes: if the characteristic gas generation rate exceeds the preset overheating fault threshold and at least three of the multiple diagnostic results indicate the presence of a thermal fault type, then it is determined to be an overheating fault and the corresponding overheating fault judgment result is output; if the characteristic gas generation rate does not exceed the threshold or fewer than three of the multiple diagnostic results indicate a thermal fault, then the remaining evaluation results are comprehensively judged according to weighted voting or priority rules. If the comprehensive result still points to a thermal fault, then the overheating fault judgment result is output; otherwise, it is determined that the current state does not belong to an overheating fault and the corresponding diagnostic result is output.
[0104] The fusion judgment of discharge fault determination results with the carbon monoxide to carbon dioxide concentration ratio in the oil sample includes: when the overheating fault or discharge fault determination results indicate that the current operating state is abnormal, the insulation system type corresponding to the fault is determined based on a pre-set CO / CO2 concentration ratio threshold. If the actual CO / CO2 concentration ratio is lower than the threshold, it is determined to be a pure oil insulation system fault; if the actual CO / CO2 concentration ratio is equal to or higher than the threshold, it is determined to be an oil-paper insulation system fault. The aforementioned fault type information is integrated with the discharge fault determination results or overheating fault determination results to obtain a complete transformer operating state fault classification and output the corresponding diagnostic conclusion.
[0105] The process of importing concentration data of different characteristic gas components in oil samples into five diagnostic methods—key characteristic gas concentration analysis, Duval triangular diagram diagnostic method, IEC gas ratio method, Rogers gas ratio method, and Dornenberg gas ratio method—to assess and predict transformer condition, and obtaining five decision assessment results, includes:
[0106] Obtain the concentration parameters of dissolved gases in the oil, including but not limited to H2, CH4, C2H6, C2H4, C2H2, CO, and CO2;
[0107] In the key characteristic gas concentration analysis method, by identifying the relative proportions of H2, CH4, C2H6, C2H4, C2H2, and CO, a preliminary distinction can be made between discharge faults and overheating faults.
[0108] In the Duval triangle diagnostic method, the percentages of the three combustible gases CH4, C2H4 and C2H2 are projected onto the Duval triangle diagram, and the fault type is determined based on the area where the point falls within the triangle.
[0109] In the International Electrotechnical Commission's gas ratio method, based on the gas ratio coding rules specified in the IEC standard, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are calculated, classified, and the corresponding fault types are output.
[0110] In the Rogers gas ratio method, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are combined and matched with a predetermined range to determine whether a discharge fault or an overheating fault exists.
[0111] In the Dornenberg gas ratio method, the CH4 / H2 concentration ratio, C2H2 / C2H4 concentration ratio, C2H2 / CH4 concentration ratio, and C2H6 / C2H2 concentration ratio are compared with the corresponding criteria to obtain the assessment results of the transformer fault type.
[0112] The fault assessment outputs of the above five diagnostic methods are recorded and summarized to obtain five independent decision assessment results.
[0113] The above schemes mainly refer to the most widely used assessment methods in practice, including key characteristic gas concentration analysis (H2, CH4, C2H6, C2H4, C2H2, CO), as shown in Table 1; the Dornenburg gas ratio method (CH4 / H2, C2H2 / C2H4, C2H2 / CH4, C2H6 / C2H2); the Rogers ratio method (CH4 / H2, C2H2 / C2H4, C2H4 / C2H6); the IEC method (CH4 / H2, C2H2 / C2H4, C2H4 / C2H6); and the Duval triangle method, as shown in Tables 2-5. These five methods were simultaneously used for transformer condition assessment based on the concentration of dissolved characteristic gases in oil, and the results of each assessment method were recorded.
[0114] Table 1 Key Feature Gas Concentration Thresholds
[0115] Key characteristic gas types Gas concentration (ppm) <![CDATA[H2]]> 100 <![CDATA[CH4]]> 120 <![CDATA[C2H2]]> 35 <![CDATA[C2H4]]> 50 <![CDATA[C2H6]]> 65 CO 350
[0116] Table 2. Dornenburg Gas Ratio Method and Coding
[0117]
[0118] Table 3 Rogers' ratio method and coding
[0119]
[0120] Table 4 IEC Methods and Coding
[0121]
[0122] Table 5 Duval Triangle Method
[0123] area Fault type feature PD Partial discharge <![CDATA[98%CH4]]> D1 Low-energy discharge <![CDATA[23%C2H4;13%C2H2]]> D2 High-energy discharge <![CDATA[23%C2H4;13%C2H2;38%C2H4;29%C2H2]]> T1 Low temperature failure <![CDATA[4%C2H2;20%C2H4]]> T2 Medium temperature fault <![CDATA[2%C2H2;20%C2H4;50%C2H4]]> T3 High temperature fault <![CDATA[15%C2H2;50%C2H4]]>
[0124] Example 3
[0125] The present invention also discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of the transformer state comprehensive prediction and evaluation method based on decision cascade fusion analysis.
[0126] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0127] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0128] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0129] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading the present invention, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the scope of protection of the pending claims of the invention.
[0131] The contents not described in detail in this specification are existing technologies known to those skilled in the art.
Claims
1. A method for comprehensive prediction and evaluation of transformer condition based on decision cascade fusion analysis, characterized in that: include Oil samples were collected from the oil-immersed transformer under different operating conditions. The concentration of dissolved characteristic gases in the oil under different operating conditions was analyzed based on the oil samples. The generation rate of characteristic gases was calculated based on the concentration of dissolved characteristic gases in the oil at different times. The concentrations of dissolved characteristic gases in the oil were incorporated into various fault diagnosis methods based on dissolved gas analysis in oil according to different decision-making approaches to assess and predict the transformer condition, resulting in multiple decision-making assessment results. The results of multiple decision evaluations are statistically analyzed. If a decision evaluation result is repeated more than twice, the currently repeated decision evaluation result is output. If a decision evaluation result is repeated less than or equal to two times, the partial discharge signal corresponding to the oil sample time period is obtained. If a partial discharge signal exists, the amplitude and frequency characteristics of the partial discharge signal and the results of multiple decision evaluations are fused and judged to output the discharge fault judgment result. If no partial discharge signal is present, the overheating fault determination result is output based on the fusion of the characteristic gas generation rate and the results of multiple decision evaluations. By combining the results of discharge fault determination or overheating fault determination with the ratio of carbon monoxide to carbon dioxide concentration in the oil sample, it is determined whether the insulation system involved in the transformer condition is a pure oil insulation system or an oil-paper insulation system, thus completing the fault classification of the transformer's operating condition.
2. The transformer condition comprehensive prediction and evaluation method based on decision cascade fusion analysis according to claim 1, characterized in that: Multiple fault diagnosis methods based on dissolved gas analysis in oil include at least five methods: key characteristic gas concentration analysis, Duval triangular diagram diagnosis, IEC gas ratio method, Rogers gas ratio method, and Dornenberg gas ratio method.
3. The transformer condition comprehensive prediction and evaluation method based on decision cascade fusion analysis according to claim 1, characterized in that: The oil contains at least the following dissolved characteristic gases: H2, CH4, C2H6, C2H4, C2H2, CO, and CO2.
4. The transformer condition comprehensive prediction and evaluation method based on decision cascade fusion analysis according to claim 1, characterized in that: The generation rate of the characteristic gas is calculated using the following formula: ; in, Indicates the absolute gas production rate; This indicates the concentration of a certain characteristic gas in the insulating oil as measured in a second sample. This indicates the concentration of a certain characteristic gas in the insulating oil as measured in the first sample. This indicates the actual operating time between the first and second sampling; m represents the total mass of the transformer insulating oil. This indicates the density of the transformer insulating oil.
5. The transformer condition comprehensive prediction and evaluation method based on decision cascade fusion analysis according to claim 1, characterized in that: The fusion judgment based on the amplitude and frequency characteristics of partial discharge signals and multiple decision evaluation results includes: if the amplitude or frequency characteristics of the partial discharge signal exceed a preset threshold and at least three diagnostic results indicate the presence of a discharge fault, then a discharge fault judgment result is output; if the amplitude or frequency characteristics of the partial discharge signal do not reach the preset threshold or fewer than three of the multiple diagnostic results indicate the presence of a discharge fault, then the remaining evaluation information is comprehensively judged based on pre-set weighted voting or priority rules. If the comprehensive result still indicates the presence of discharge behavior, then a discharge fault judgment result is output; otherwise, it is determined that the current fault type does not belong to a discharge fault and the corresponding diagnostic result is output.
6. The transformer condition comprehensive prediction and evaluation method based on decision cascade fusion analysis according to claim 1, characterized in that: The fusion judgment based on the characteristic gas generation rate and multiple decision evaluation results includes: if the characteristic gas generation rate exceeds the preset overheating fault threshold and at least three of the multiple diagnostic results indicate the presence of a thermal fault type, then it is determined to be an overheating fault and the corresponding overheating fault judgment result is output; if the characteristic gas generation rate does not exceed the threshold or fewer than three of the multiple diagnostic results indicate a thermal fault, then the remaining evaluation results are comprehensively judged according to weighted voting or priority rules. If the comprehensive result still points to a thermal fault, then the overheating fault judgment result is output; otherwise, it is determined that the current state does not belong to an overheating fault and the corresponding diagnostic result is output.
7. The transformer condition comprehensive prediction and evaluation method based on decision cascade fusion analysis according to claim 1, characterized in that: The fusion judgment of discharge fault determination results with the carbon monoxide to carbon dioxide concentration ratio in the oil sample includes: when the overheating fault or discharge fault determination results indicate that the current operating state is abnormal, the insulation system type corresponding to the fault is determined based on a pre-set CO / CO2 concentration ratio threshold. If the actual CO / CO2 concentration ratio is lower than the threshold, it is determined to be a pure oil insulation system fault; if the actual CO / CO2 concentration ratio is equal to or higher than the threshold, it is determined to be an oil-paper insulation system fault. The determined insulation system type is integrated with the discharge fault determination results or overheating fault determination results to obtain a complete transformer operating state fault classification and output the corresponding diagnostic conclusion.
8. The transformer condition comprehensive prediction and evaluation method based on decision cascade fusion analysis according to claim 2, characterized in that: The process of importing concentration data of different characteristic gas components in oil samples into five diagnostic methods—key characteristic gas concentration analysis, Duval triangular diagram diagnostic method, IEC gas ratio method, Rogers gas ratio method, and Dornenberg gas ratio method—to assess and predict transformer condition, and obtaining five decision assessment results, includes: Obtain the concentration parameters of dissolved gases in the oil, including H2, CH4, C2H6, C2H4, C2H2, CO, and CO2; In the key characteristic gas concentration analysis method, by identifying the relative proportions of H2, CH4, C2H6, C2H4, C2H2, and CO, a preliminary distinction can be made between discharge faults and overheating faults. In the Duval triangle diagnostic method, the percentages of the three combustible gases CH4, C2H4 and C2H2 are projected onto the Duval triangle diagram, and the fault type is determined based on the area where the point falls within the triangle. In the International Electrotechnical Commission's gas ratio method, based on the gas ratio coding rules specified in the IEC standard, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are calculated, classified, and the corresponding fault types are output. In the Rogers gas ratio method, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are combined and matched with a predetermined range to determine whether a discharge fault or an overheating fault exists. In the Dornenberg gas ratio method, the CH4 / H2 concentration ratio, C2H2 / C2H4 concentration ratio, C2H2 / CH4 concentration ratio, and C2H6 / C2H2 concentration ratio are compared with the corresponding criteria to obtain the assessment results of the transformer fault type. The fault assessment outputs of the above five diagnostic methods are recorded and summarized to obtain five independent decision assessment results.
9. A transformer condition comprehensive prediction and evaluation system based on decision cascade fusion analysis, characterized in that: The transformer condition comprehensive prediction and evaluation system based on decision cascade fusion analysis includes a data acquisition module, an evaluation module, a fault determination module, and a fault classification module. The acquisition module is used to collect oil samples from oil-immersed transformers under different operating conditions, analyze the concentration of dissolved characteristic gases in the oil under different operating conditions based on the oil samples, and calculate the generation rate of characteristic gases based on the concentration of dissolved characteristic gases in the oil at different times. The evaluation module is used to import the concentration of dissolved characteristic gases in the oil into various fault diagnosis methods based on dissolved gas analysis in oil according to different decision-making methods to evaluate and predict the transformer status, and obtain multiple decision evaluation results respectively. The fault determination module is used to statistically analyze multiple decision evaluation results. When a decision evaluation result is repeated more than twice, the currently repeated decision evaluation result is output. When a decision evaluation result is repeated less than or equal to two times, the partial discharge signal corresponding to the oil sample time period is obtained. If a partial discharge signal exists, the amplitude and frequency characteristics of the partial discharge signal and multiple decision evaluation results are fused and judged to output the discharge fault determination result. If no partial discharge signal is present, the overheating fault determination result is output based on the fusion of the characteristic gas generation rate and the results of multiple decision evaluations. The fault classification module is used to integrate the discharge fault determination result or overheating fault determination result with the carbon monoxide to carbon dioxide concentration ratio in the oil sample to determine whether the insulation system involved in the transformer status is a pure oil insulation system or an oil-paper insulation system, thereby completing the fault classification of the transformer operating status.
10. The transformer condition comprehensive prediction and evaluation system based on decision cascade fusion analysis according to claim 9, characterized in that: Multiple fault diagnosis methods based on dissolved gas analysis in oil include at least five methods: key characteristic gas concentration analysis, Duval triangular diagram diagnosis, IEC gas ratio method, Rogers gas ratio method, and Dornenberg gas ratio method.
11. The transformer condition comprehensive prediction and evaluation system based on decision cascade fusion analysis according to claim 9, characterized in that: The oil contains at least the following dissolved characteristic gases: H2, CH4, C2H6, C2H4, C2H2, CO, and CO2.
12. The transformer condition comprehensive prediction and evaluation method based on decision cascade fusion analysis according to claim 9, characterized in that: The generation rate of the characteristic gas is calculated using the following formula: ; in, Indicates the absolute gas production rate; This indicates the concentration of a certain characteristic gas in the insulating oil as measured in a second sample. This indicates the concentration of a certain characteristic gas in the insulating oil as measured in the first sample. This indicates the actual operating time between the first and second sampling; m represents the total mass of the transformer insulating oil. This indicates the density of the transformer insulating oil.
13. The transformer condition comprehensive prediction and evaluation system based on decision cascade fusion analysis according to claim 9, characterized in that: The fusion judgment based on the amplitude and frequency characteristics of partial discharge signals and multiple decision evaluation results includes: if the amplitude or frequency characteristics of the partial discharge signal exceed a preset threshold and at least three diagnostic results indicate the presence of a discharge fault, then a discharge fault judgment result is output; if the amplitude or frequency characteristics of the partial discharge signal do not reach the preset threshold or fewer than three of the multiple diagnostic results indicate the presence of a discharge fault, then the remaining evaluation information is comprehensively judged based on pre-set weighted voting or priority rules. If the comprehensive result still indicates the presence of discharge behavior, then a discharge fault judgment result is output; otherwise, it is determined that the current fault type does not belong to a discharge fault and the corresponding diagnostic result is output.
14. The transformer condition comprehensive prediction and evaluation system based on decision cascade fusion analysis according to claim 9, characterized in that: The fusion judgment based on the characteristic gas generation rate and multiple decision evaluation results includes: if the characteristic gas generation rate exceeds the preset overheating fault threshold and at least three of the multiple diagnostic results indicate the presence of a thermal fault type, then it is determined to be an overheating fault and the corresponding overheating fault judgment result is output; if the characteristic gas generation rate does not exceed the threshold or fewer than three of the multiple diagnostic results indicate a thermal fault, then the remaining evaluation results are comprehensively judged according to weighted voting or priority rules. If the comprehensive result still points to a thermal fault, then the overheating fault judgment result is output; otherwise, it is determined that the current state does not belong to an overheating fault and the corresponding diagnostic result is output.
15. The transformer condition comprehensive prediction and evaluation system based on decision cascade fusion analysis according to claim 9, characterized in that: The fusion judgment of discharge fault determination results with the carbon monoxide to carbon dioxide concentration ratio in the oil sample includes: when the overheating fault or discharge fault determination results indicate that the current operating state is abnormal, the insulation system type corresponding to the fault is determined based on a pre-set CO / CO2 concentration ratio threshold. If the actual CO / CO2 concentration ratio is lower than the threshold, it is determined to be a pure oil insulation system fault; if the actual CO / CO2 concentration ratio is equal to or higher than the threshold, it is determined to be an oil-paper insulation system fault. The determined insulation system type is integrated with the discharge fault determination results or overheating fault determination results to obtain a complete transformer operating state fault classification and output the corresponding diagnostic conclusion.
16. The transformer condition comprehensive prediction and evaluation system based on decision cascade fusion analysis according to claim 10, characterized in that: The process of importing concentration data of different characteristic gas components in oil samples into five diagnostic methods—key characteristic gas concentration analysis, Duval triangular diagram diagnostic method, IEC gas ratio method, Rogers gas ratio method, and Dornenberg gas ratio method—to assess and predict transformer condition, and obtaining five decision assessment results, includes: Obtain the concentration parameters of dissolved gases in the oil, including H2, CH4, C2H6, C2H4, C2H2, CO, and CO2; In the key characteristic gas concentration analysis method, by identifying the relative proportions of H2, CH4, C2H6, C2H4, C2H2, and CO, a preliminary distinction can be made between discharge faults and overheating faults. In the Duval triangle diagnostic method, the percentages of the three combustible gases CH4, C2H4 and C2H2 are projected onto the Duval triangle diagram, and the fault type is determined based on the area where the point falls within the triangle. In the International Electrotechnical Commission's gas ratio method, based on the gas ratio coding rules specified in the IEC standard, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are calculated, classified, and the corresponding fault types are output. In the Rogers gas ratio method, the concentration ratios of CH4 / H2, C2H2 / C2H4, and C2H4 / C2H6 are combined and matched with a predetermined range to determine whether a discharge fault or an overheating fault exists. In the Dornenberg gas ratio method, the CH4 / H2 concentration ratio, C2H2 / C2H4 concentration ratio, C2H2 / CH4 concentration ratio, and C2H6 / C2H2 concentration ratio are compared with the corresponding criteria to obtain the assessment results of the transformer fault type. The fault assessment outputs of the above five diagnostic methods are recorded and summarized to obtain five independent decision assessment results.
17. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the transformer condition comprehensive prediction and evaluation method based on decision cascade fusion analysis as described in any one of claims 1 to 8.
Citation Information
Patent Citations
Internal transformer composite-defect fuzzy diagnostic method based on gas dissolved in oil
CN104730378A
Systems and methods for dissolved gas analysis
US20210270797A1
