Life cycle management and maintenance method and device for transformer and GIS

Abstract

The present application relates to a method and device for the life cycle management and maintenance of transformers and GIS. The method sequentially collects multi-source monitoring data of the equipment and preprocesses to build a standardized information library; fault diagnosis and health state assessment are completed respectively to obtain the health level of a single device; the evidence entropy theory is used to fuse the fault diagnosis results of the equipment to obtain a joint diagnosis result; the comprehensive health index is determined by combining the health level of a single device and the joint diagnosis result, and a reliability model is built to predict the remaining life; the integrated life cycle management model is built by integrating the equipment information; the operation and maintenance scheme is determined and the risk and cost quantitative analysis is carried out; and the optimal maintenance decision is determined based on the analysis result. The present application realizes the integrated life cycle management and scientific decision of the equipment, improves the assessment accuracy, fault diagnosis precision and life prediction accuracy, reduces the operation and maintenance cost and fault risk, and is suitable for transformers and GIS equipment of different voltage levels.

Description

Technical Field

[0001] This invention belongs to the field of power equipment operation and maintenance management technology, specifically relating to a method and device for full life cycle management and maintenance of transformers and GIS. Background Technology

[0002] Transformers and gas-insulated switchgear (GIS) are core and critical equipment in power transmission and transformation systems, and their operating status directly affects the safety and stability of the power system. To reduce equipment operation and maintenance costs and improve grid reliability, it is of great significance to conduct full life-cycle management of these devices and formulate scientific and reasonable maintenance and decision-making processes. However, existing technologies still have many shortcomings in the full life-cycle management and maintenance decision-making of transformers and GIS.

[0003] First, in terms of condition monitoring and assessment, existing technologies largely rely on single types of monitoring data, lacking comprehensive utilization of multi-source monitoring parameters such as electrical, chemical, and insulation data. This results in one-sided condition assessment results, making it difficult to accurately reflect the true health status of the equipment. Second, in terms of fault diagnosis, transformers and GIS are typically analyzed independently, without fully considering the operational correlation between the two types of equipment. Furthermore, the diagnostic methods for single equipment lack multi-evidence fusion mechanisms, leading to lower diagnostic accuracy. Third, in terms of lifespan prediction, existing methods mostly estimate remaining lifespan based on single condition indicators, failing to incorporate comprehensive health status to build a reliability model. Moreover, there is a lack of a unified full lifecycle management model applicable to both transformers and GIS, making it difficult to achieve dynamic management of equipment operating status. Finally, in terms of maintenance decision-making, related solutions largely rely on the experience of maintenance personnel, lacking quantitative analysis of the risks and costs of different options such as continued operation, minor repairs, major overhauls, and replacement. This results in insufficient scientific rigor in decision-making, easily leading to problems such as over-maintenance and delayed maintenance.

[0004] In existing technologies, multi-source information fusion can be used to achieve collaborative analysis of different types of monitoring data, evidence entropy theory helps improve the accuracy of fault diagnosis, and comprehensive health index can quantitatively characterize the health status of equipment throughout its entire life cycle. However, there is still a lack of technical solutions that systematically integrate the above-mentioned technologies to construct an integrated life-cycle management and maintenance decision-making method for transformers and GIS. Therefore, it is necessary to propose a new technical solution to address the problems of insufficient information utilization, inadequate diagnostic and assessment accuracy, and lack of quantitative basis for maintenance decisions in existing technologies. Summary of the Invention

[0005] This invention addresses the problems of insufficient information utilization, inaccurate fault diagnosis, disconnect between lifespan prediction and full life cycle management, and lack of quantitative basis for maintenance decisions. It provides a method and device for full life cycle management and maintenance of transformers and GIS, enabling accurate assessment of equipment status, reliable prediction of remaining lifespan, and scientific formulation of maintenance decisions.

[0006] To achieve the above objectives, the present invention adopts one or more of the following technical solutions: In a first aspect, the present invention provides a method for full life-cycle management and maintenance of transformers and GIS, the method comprising the following steps: S1. Collect multi-source monitoring data of the transformer and GIS equipment during operation, and preprocess the multi-source monitoring data; S2. Based on the preprocessed multi-source monitoring data, fault diagnosis is performed on the transformer and GIS equipment respectively to obtain transformer fault diagnosis results and GIS equipment fault diagnosis results. The transformer health status is assessed based on the transformer fault diagnosis results to obtain the transformer health status level. The GIS equipment health status is assessed based on the GIS equipment fault diagnosis results to obtain the GIS equipment health status level. S3. Based on the evidence entropy theory, the transformer fault diagnosis result and the GIS equipment fault diagnosis result are respectively regarded as independent evidence bodies. By constructing a basic trust allocation function for each independent evidence body, the evidence entropy of each evidence body is calculated. The weight coefficient is determined according to the evidence entropy of each independent evidence body. Based on the weight coefficient, the DS evidence combination rule is used to fuse each independent evidence body to obtain the joint fault diagnosis result of the transformer and the GIS equipment. S4. Based on the transformer health status level, the GIS equipment health status level and the joint fault diagnosis result, a comprehensive health index is determined. A reliability model is constructed based on the comprehensive health index. The remaining lifespan of the transformer and the remaining lifespan of the GIS equipment are predicted according to the reliability model. S5. Integrate the basic information, multi-source monitoring data, fault diagnosis results, health status level and remaining life of transformers and GIS equipment to build an integrated full life cycle management model for transformers and GIS equipment. S6. Based on the full life cycle management model, determine the operation and maintenance plan, conduct risk assessment and cost quantification analysis on the operation and maintenance plan, and obtain the risk assessment results and cost quantification analysis results of the operation and maintenance plan. S7. Based on the risk assessment results and the cost quantification analysis results, determine the optimal maintenance decision.

[0007] Furthermore, the multi-source monitoring data of the transformer mentioned in step S1 includes electrical insulation data and dissolved gas chemical data in the oil; The multi-source monitoring data of the GIS equipment includes partial discharge data, SF6 gas characteristic data, and insulation data; The preprocessing includes outlier removal, missing value interpolation, and dimensional normalization. This is used to eliminate noise and data bias, form a standardized monitoring information database, and support subsequent fault diagnosis and health status assessment. A standardized monitoring information database is constructed based on the preprocessed multi-source monitoring data to provide data support for subsequent fault diagnosis and health status assessment.

[0008] Furthermore, the electrical insulation data includes absorption ratio, dielectric loss, insulation resistance to ground, and oil breakdown voltage; the dissolved gas chemical data in the oil includes hydrogen hydrocarbon content and CO and CO2 gas content. The partial discharge data includes electrical and chemical parameters; the SF6 gas characteristic data includes moisture content and gas leakage; and the insulation data includes insulation resistance to ground.

[0009] Furthermore, step S2 specifically includes the following steps: S201. Based on the electrical insulation data of the transformer and the chemical data of dissolved gases in the oil, feature indicators are extracted. Based on the feature indicators, fault diagnosis is performed through threshold comparison and trend analysis to identify the fault type and fault degree. According to the feature indicators, the fault type and the fault degree, a percentage scoring method is used to assess the health status and obtain the corresponding health status level. S202. Based on the partial discharge data, SF6 gas characteristic data and insulation data of the GIS equipment, extract characteristic indicators, perform abnormal characteristic analysis based on the characteristic indicators, complete fault diagnosis and identify fault type and fault degree, and use a percentage scoring method to evaluate the health status according to the characteristic indicators, the fault type and the fault degree to obtain the corresponding health status level. The health status level is divided into four levels: healthy, slightly deteriorated, moderately deteriorated, and severely deteriorated.

[0010] Furthermore, step S3 specifically includes the following steps: S301. Treat the single-device fault diagnosis results of transformers and GIS equipment as independent evidence bodies, and construct a basic trust allocation function for different fault diagnosis results. S302. Calculate the evidence entropy of each piece of evidence, quantify the uncertainty of each piece of evidence, and assign weight coefficients to each piece of evidence based on the evidence entropy, assigning low weights to evidence with high uncertainty and high weights to evidence with low uncertainty. S303. Based on the aforementioned weighting coefficients, D is used. The S-evidence combination rule fuses various pieces of evidence to obtain a joint fault diagnosis result for both the transformer and GIS equipment. This is used to achieve collaborative fault identification between the transformer and GIS equipment, correct biases in single-equipment diagnosis, and improve the overall accuracy of fault diagnosis.

[0011] Furthermore, step S4 specifically includes the following steps: S401. Based on the transformer health status level, the GIS equipment health status level, and the joint fault diagnosis results, the health status level scores of the transformer and GIS equipment, fault severity, equipment operating years, and maintenance history are integrated to determine a comprehensive health index; this is used to achieve a global quantitative representation of the health status. S402. Using the comprehensive health index as the core variable, and combining the manufacturing parameters, operating environment, and load characteristics of transformers and GIS equipment, construct a reliability model for power transmission and transformation equipment based on Weibull distribution. S403. Substitute the comprehensive health index into the reliability model to predict the remaining lifespan of the transformer and GIS equipment.

[0012] Furthermore, step S6 specifically includes: S601. Based on the full life cycle management model, determine the operation and maintenance plan, which includes four options: continued operation, minor repair, major repair, and replacement; this is used to clarify the implementation content, process requirements, and cycle of each operation and maintenance plan. S602. The risk matrix method is used to conduct a risk assessment of the operation and maintenance scheme, quantify the probability of transformer and GIS equipment failure and the severity of failure consequences under each operation and maintenance scheme, obtain the comprehensive risk value of each operation and maintenance scheme, and divide the risk value into three risk levels: low, medium and high. S603. The operation and maintenance plan is quantitatively analyzed using a full life cycle cost model. Direct and indirect costs are calculated to obtain the total life cycle cost of each operation and maintenance plan.

[0013] Furthermore, the direct costs include the cost of repairing or replacing consumables, labor costs, and equipment costs; the indirect costs include power outage losses, fault maintenance costs, and subsequent maintenance costs.

[0014] Furthermore, step S7 specifically includes: S701. Normalize the risk assessment results and cost quantification analysis results of the operation and maintenance plan, set the risk indicator weights and cost indicator weights according to the power grid safety priority, and calculate the comprehensive score. S702. The maintenance plan with the highest comprehensive score is determined as the optimal maintenance decision; this is used to determine the implementation time, specific measures, and control requirements of each maintenance plan. S703. Feed the optimal maintenance decision back to the full life cycle management model, update the multi-source monitoring data and health status assessment results of transformers and GIS equipment in real time, and when the multi-source monitoring data and health status assessment results change significantly, re-evaluate the risk assessment and cost quantification analysis of the operation and maintenance plan, and dynamically adjust the maintenance decision.

[0015] Secondly, the present invention provides a device for full life-cycle management and maintenance of transformers and GIS, the device being used to implement the above-mentioned method, comprising: The data processing and status assessment module is used to collect multi-source monitoring data of transformers and GIS equipment, preprocess the multi-source monitoring data, and perform fault diagnosis and health status assessment of transformers and GIS equipment based on the preprocessed multi-source monitoring data to obtain the corresponding single equipment health status level. The joint fault diagnosis module is used to treat the fault diagnosis results of transformers and GIS equipment as independent evidence bodies based on the evidence entropy theory. The weight coefficients are determined according to the evidence entropy of each evidence body. Based on the weight coefficients, the DS evidence combination rules are used to fuse the evidence bodies to obtain the joint fault diagnosis results of transformers and GIS equipment. The health assessment and life prediction module is used to determine a comprehensive health index based on the health status level of the transformer, the health status level of the GIS equipment, and the joint fault diagnosis results; to construct a reliability model based on the comprehensive health index; and to predict the remaining life of the transformer and the GIS equipment based on the reliability model. The whole life cycle management and decision-making module is used to integrate the basic information of transformers and GIS equipment, multi-source monitoring data, fault diagnosis results, health status assessment results and remaining lifespan to build an integrated whole life cycle management model. Based on the whole life cycle management model, the module determines the operation and maintenance plan, performs risk assessment and cost quantification analysis on the operation and maintenance plan, and outputs the optimal maintenance decision.

[0016] Thirdly, the present invention provides a life-cycle management and maintenance device for transformers and GIS, comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory has instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the above-described method.

[0017] Fourthly, the present invention provides a non-volatile computer storage medium storing computer-executable instructions configured to implement the above-described method.

[0018] This invention achieves integrated full lifecycle management and scientific maintenance decision-making for transformers and GIS equipment through multi-source monitoring information fusion, evidence entropy-based joint fault diagnosis, comprehensive health index lifespan prediction, and risk-cost dual-dimensional decision-making. Compared with existing technologies, it has the following significant advantages: (1) Achieve deep integration of multi-source monitoring data and improve the accuracy of condition assessment: Collect and preprocess multi-source monitoring data such as transformer electrical insulation, dissolved gas in oil, partial discharge of GIS equipment, SF6 gas characteristics, and insulation, and build a standardized monitoring information database to avoid the one-sidedness of single data assessment, truly reflect the actual health status of equipment, and improve the accuracy of condition assessment by more than 20%. (2) Based on evidence entropy, joint fault diagnosis is achieved to improve fault discrimination accuracy: The fault diagnosis results of transformer and GIS equipment are used as independent evidence bodies. The uncertainty is quantified and weights are assigned by evidence entropy. The DS evidence combination rule is used to achieve multi-evidence fusion, which breaks through the limitation of independent diagnosis of single equipment. The fault diagnosis accuracy is improved by 15%~25% compared with traditional methods. (3) Construct a reliability model based on the comprehensive health index to achieve accurate prediction of remaining life: integrate the health status level of a single device, the joint fault diagnosis results, the equipment's operating years and maintenance history to determine the comprehensive health index, construct a reliability model with the comprehensive health index as the core variable, complete the prediction of remaining life, and control the prediction error within 10%, providing a quantitative basis for full life cycle management. (4) Achieve dual-dimensional quantitative analysis of risk and cost to improve the scientific nature of maintenance decisions: Conduct risk matrix assessment and full life cycle cost quantitative analysis of four maintenance options: continue operation, minor repair, major repair, and replacement. Avoid excessive maintenance delays caused by experience-based decision-making. This can reduce the full life cycle maintenance cost of equipment by 10% to 30% and significantly reduce the risk of equipment failure. (5) Construct an integrated full life cycle management model to achieve dynamic control and decision-making: Integrate basic equipment information, multi-source monitoring data, fault diagnosis, health assessment and remaining life information to form an integrated full life cycle management model for transformers and GIS equipment, support dynamic adjustment and real-time updates of maintenance decisions, and improve the intelligence and refinement of power transmission and transformation system operation and maintenance. Attached Figure Description

[0019] Figure 1 This is a flowchart of a method for full life cycle management and maintenance of transformers and GIS according to the present invention; Figure 2This is a schematic diagram of the overall architecture of a method for full life cycle management and maintenance of transformers and GIS according to the present invention; Figure 3 This is a schematic diagram of the structure of a life-cycle management and maintenance device for transformers and GIS according to the present invention; Figure 4 This is a structural schematic diagram of a life-cycle management and maintenance device for transformers and GIS according to the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will now be described in detail and completely with reference to the accompanying drawings. It should be noted that the described embodiments are merely some examples of the present invention and do not represent all possible implementations of the present invention. Any other implementations obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the protection scope of the present invention.

[0021] This embodiment uses a 220kV main transformer (operating for 10 years) and a 220kV GIS device (operating for 10 years) of a hydropower station as the application objects. Both devices are in a long-term continuous operation state.

[0022] Figure 1 , Figure 2 The present invention provides a flowchart and overall architecture diagram of a method for full life cycle management and maintenance of transformers and GIS, the method comprising the following steps: S1. Collect multi-source monitoring data of transformers and GIS equipment during operation, preprocess the multi-source monitoring data, and construct a standardized monitoring information database.

[0023] Specifically, for transformers, electrical insulation data and dissolved gas chemical data in oil are collected during their operation, and parameters such as absorption ratio, dielectric loss, and hydrogen content are monitored; for GIS equipment, partial discharge data, SF6 gas characteristic data, and insulation data are collected during their operation, and parameters such as partial discharge amount, SF6 moisture content, and gas leakage amount are monitored.

[0024] In this embodiment, no fewer than 8 monitoring parameters are selected for the transformer, and no fewer than 6 monitoring parameters are selected for the GIS equipment.

[0025] The collected multi-source monitoring data are preprocessed by removing outliers, interpolating missing values, and normalizing dimensions to construct a standardized monitoring information database.

[0026] The results showed that the transformer's hydrogen content and dielectric loss exceeded the normal threshold, the GIS equipment had high partial discharge and a trace amount of SF6 leakage.

[0027] S2. Based on the preprocessed multi-source monitoring data, fault diagnosis is performed on the transformer and GIS equipment respectively to obtain the transformer fault diagnosis results and the GIS equipment fault diagnosis results. The transformer health status is assessed according to the transformer fault diagnosis results to obtain the transformer health status level. The GIS equipment health status is assessed according to the GIS equipment fault diagnosis results to obtain the GIS equipment health status level.

[0028] Specifically, S201. Based on the electrical insulation data of the transformer and the chemical data of dissolved gases in the oil, feature indicators are extracted. Based on the feature indicators, fault diagnosis is performed through threshold comparison and trend analysis to identify the fault type and fault degree. According to the feature indicators, the fault type and the fault degree, a percentage scoring method is used to assess the health status and obtain the corresponding health status level. S202. Based on the partial discharge data, SF6 gas characteristic data and insulation data of the GIS equipment, extract characteristic indicators, perform abnormal characteristic analysis based on the characteristic indicators, complete fault diagnosis and identify fault type and fault degree, and use a percentage scoring method to evaluate the health status according to the characteristic indicators, the fault type and the fault degree to obtain the corresponding health status level.

[0029] The health status level is divided into four levels: healthy, slightly deteriorated, moderately deteriorated, and severely deteriorated.

[0030] The diagnostic results showed that the transformer had a minor insulation deterioration fault, with a health score of 75, corresponding to a minor deterioration level; the GIS equipment had a partial discharge and minor leakage fault, with a health score of 70, corresponding to a minor deterioration level.

[0031] S3. Based on the evidence entropy theory, the transformer fault diagnosis result and the GIS equipment fault diagnosis result are respectively regarded as independent evidence bodies. By constructing a basic trust allocation function for each independent evidence body, the evidence entropy of each evidence body is calculated. The weight coefficient is determined according to the evidence entropy of each independent evidence body. Based on the weight coefficient, the DS evidence combination rule is used to fuse each independent evidence body to obtain the joint fault diagnosis result of the transformer and the GIS equipment.

[0032] Specifically, S301. Treat the single-device fault diagnosis results of transformers and GIS equipment as independent evidence bodies, and construct a basic trust allocation function for different fault diagnosis results. S302. Calculate the evidence entropy of each piece of evidence, quantify the uncertainty of each piece of evidence, and assign weight coefficients to each piece of evidence based on the evidence entropy. Assign low weights to evidence with high uncertainty and high weights to evidence with low uncertainty. The transformer is assigned 0.45 and the GIS equipment is assigned 0.55. S303. Based on the aforementioned weighting coefficients, D is used. The S-evidence combination rule merges the various evidence bodies to obtain a joint fault diagnosis result for the transformer and GIS equipment.

[0033] The diagnostic results indicate that the substation insulation system as a whole is in a state of slight deterioration, thus correcting the individual equipment fault diagnosis results and reducing the impact of local diagnostic biases on the overall judgment.

[0034] S4. Based on the transformer health status level, the GIS equipment health status level and the joint fault diagnosis results, a comprehensive health index is determined. Based on the comprehensive health index, a reliability model is constructed. Based on the reliability model, the remaining lifespan of the transformer and the remaining lifespan of the GIS equipment are predicted respectively.

[0035] Specifically, S401. Based on the transformer health status level, the GIS equipment health status level, and the joint fault diagnosis results, the comprehensive health index is determined by integrating the health status level scores, fault severity, equipment operating years, and maintenance history of the transformer and GIS equipment. The comprehensive health index of the transformer is 72, and the comprehensive health index of the GIS equipment is 68. S402. Using the comprehensive health index as the core variable, and combining the manufacturing parameters, operating environment, and load characteristics of transformers and GIS equipment, construct a reliability model for power transmission and transformation equipment based on Weibull distribution. S403. Substitute the comprehensive health index into the reliability model to predict the remaining lifespan of the transformer and GIS equipment. The predicted remaining lifespan of the transformer is 8 years and the remaining lifespan of the GIS equipment is 6 years.

[0036] S5. Integrate the basic information, multi-source monitoring data, fault diagnosis results, health status level and remaining life of transformers and GIS equipment to construct an integrated full life cycle management model for transformers and GIS equipment.

[0037] S6. Based on the full life cycle management model, determine the operation and maintenance plan, conduct risk assessment and cost quantification analysis on the operation and maintenance plan, and obtain the risk assessment results and cost quantification analysis results of the operation and maintenance plan.

[0038] Specifically, S601. Based on the full life cycle management model, determine the operation and maintenance plan, which includes four options: continue operation, minor repair, major repair, and replacement. S602. The risk matrix method is used to conduct a risk assessment of the operation and maintenance scheme, quantify the probability of transformer and GIS equipment failure and the severity of failure consequences under each operation and maintenance scheme, obtain the comprehensive risk value of each operation and maintenance scheme, and divide the risk value into three risk levels: low, medium and high. S603. The operation and maintenance plan is quantitatively analyzed using a full life cycle cost model. Direct and indirect costs are calculated to obtain the total life cycle cost of each operation and maintenance plan.

[0039] Based on risk assessment and cost quantification analysis, the specific results of each operation and maintenance plan are as follows: Continue operating: Overall risk value 0.7, corresponding to medium risk level, total life cycle cost 1.2 million yuan; Minor repair: Comprehensive risk value 0.3, corresponding to low risk level, total life cycle cost 1.5 million yuan; Overhaul: Comprehensive risk value 0.2, corresponding to low risk level, total life cycle cost 2.8 million yuan; Replacement: Overall risk value 0.1, corresponding to a low risk level, with a total life cycle cost of 6.5 million yuan.

[0040] S7. Based on the risk assessment results and the cost quantification analysis results, determine the optimal maintenance decision.

[0041] Specifically, S701. Normalize the risk assessment results and cost quantification analysis results of the operation and maintenance plan. Combined with the operation and maintenance requirements of this embodiment (power grid safety priority is high), set the risk index weight and cost index weight, where the risk index weight is 0.6 and the cost index weight is 0.4. Calculate the comprehensive score of each operation and maintenance plan based on the above weights. S702. Compare the comprehensive scores of each operation and maintenance plan, and determine the operation and maintenance plan with the highest comprehensive score as the optimal maintenance decision. In this embodiment, the minor repair plan with the highest score of 86 points becomes the optimal decision. Based on this, it is determined that targeted minor repairs will be carried out on the transformer and GIS equipment within one month, focusing on addressing insulation degradation, partial discharge and SF6 leakage issues. S703. Feed the optimal maintenance decision back to the full life cycle management model, update the multi-source monitoring data and health status assessment results of transformers and GIS equipment in real time, and when the multi-source monitoring data and health status assessment results change significantly, re-evaluate the risk assessment and cost quantification analysis of the operation and maintenance plan, and dynamically adjust the maintenance decision.

[0042] This embodiment utilizes the method provided by the present invention to achieve full lifecycle management and scientific maintenance decision-making for 220kV transformers and GIS equipment. Compared to traditional experience-based decision-making, it effectively avoids the problems of continued operation leading to higher failure risks and major overhauls or replacements resulting in wasted maintenance costs. After the implementation of the minor repair plan, the health scores of the transformer and GIS equipment increased to 88 and 85 points respectively, the remaining lifespan was extended to 10 years and 8 years respectively, the equipment failure risk was reduced by more than 60%, and the full lifecycle maintenance cost was reduced by 25%, fully verifying the scientific nature and practicality of the method of the present invention.

[0043] Figure 3 This invention provides a structural diagram of a life-cycle management and maintenance system for transformers and GIS, the system comprising: The data processing and status assessment module is used to collect multi-source monitoring data of transformers and GIS equipment, preprocess the multi-source monitoring data, and perform fault diagnosis and health status assessment of transformers and GIS equipment based on the preprocessed multi-source monitoring data to obtain the corresponding single equipment health status level. The joint fault diagnosis module is used to treat the fault diagnosis results of transformers and GIS equipment as independent evidence bodies based on the evidence entropy theory. The weight coefficients are determined according to the evidence entropy of each evidence body. Based on the weight coefficients, the DS evidence combination rules are used to fuse the evidence bodies to obtain the joint fault diagnosis results of transformers and GIS equipment. The health assessment and life prediction module is used to determine a comprehensive health index based on the health status level of the transformer, the health status level of the GIS equipment, and the joint fault diagnosis results; to construct a reliability model based on the comprehensive health index; and to predict the remaining life of the transformer and the GIS equipment based on the reliability model. The whole life cycle management and decision-making module is used to integrate the basic information of transformers and GIS equipment, multi-source monitoring data, fault diagnosis results, health status assessment results and remaining lifespan to build an integrated whole life cycle management model. Based on the whole life cycle management model, the module determines the operation and maintenance plan, performs risk assessment and cost quantification analysis on the operation and maintenance plan, and outputs the optimal maintenance decision.

[0044] Figure 4 A schematic diagram of a life-cycle management and maintenance device for transformers and GIS provided by the present invention includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory has instructions that can be executed by the at least one processor, which enables the at least one processor to perform a life-cycle management and maintenance method for transformers and GIS provided in Embodiment 1.

[0045] This invention also provides a non-volatile computer storage medium storing computer-executable instructions, which are configured to implement the full life-cycle management and maintenance method for transformers and GIS provided in Embodiment 1.

[0046] The embodiments described above are only used to illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention. For transformers and GIS equipment of other voltage levels such as 110kV and 500kV, only the monitoring parameter thresholds, comprehensive health index calculation coefficients, and risks need to be adjusted. By applying cost weighting, the method of this invention can be used to achieve full life-cycle management and maintenance decisions. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0047] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for full life-cycle management and maintenance of transformers and GIS, characterized in that, The method includes the following steps: S1. Collect multi-source monitoring data of the transformer and GIS equipment during operation, and preprocess the multi-source monitoring data; S2. Based on the preprocessed multi-source monitoring data, fault diagnosis is performed on the transformer and GIS equipment respectively to obtain transformer fault diagnosis results and GIS equipment fault diagnosis results. The transformer health status is assessed based on the transformer fault diagnosis results to obtain the transformer health status level. The GIS equipment health status is assessed based on the GIS equipment fault diagnosis results to obtain the GIS equipment health status level. S3. Based on the evidence entropy theory, the transformer fault diagnosis result and the GIS equipment fault diagnosis result are respectively regarded as independent evidence bodies. By constructing a basic trust allocation function for each independent evidence body, the evidence entropy of each evidence body is calculated. The weight coefficient is determined according to the evidence entropy of each independent evidence body. Based on the weight coefficient, the DS evidence combination rule is used to fuse each independent evidence body to obtain the joint fault diagnosis result of the transformer and the GIS equipment. S4. Based on the transformer health status level, the GIS equipment health status level and the joint fault diagnosis result, a comprehensive health index is determined. A reliability model is constructed based on the comprehensive health index. The remaining lifespan of the transformer and the remaining lifespan of the GIS equipment are predicted according to the reliability model. S5. Integrate the basic information, multi-source monitoring data, fault diagnosis results, health status level and remaining life of transformers and GIS equipment to build an integrated full life cycle management model for transformers and GIS equipment. S6. Based on the full life cycle management model, determine the operation and maintenance plan, conduct risk assessment and cost quantification analysis on the operation and maintenance plan, and obtain the risk assessment results and cost quantification analysis results of the operation and maintenance plan. S7. Based on the risk assessment results and the cost quantification analysis results, determine the optimal maintenance decision.

2. The method for full life-cycle management and maintenance of transformers and GIS according to claim 1, characterized in that, The multi-source monitoring data of the transformer mentioned in step S1 includes electrical insulation data and dissolved gas chemical data in oil; The multi-source monitoring data of the GIS equipment includes partial discharge data, SF6 gas characteristic data, and insulation data. The preprocessing includes outlier removal, missing value interpolation, and dimensional normalization. A standardized monitoring information database is constructed based on the preprocessed multi-source monitoring data to provide data support for subsequent fault diagnosis and health status assessment.

3. The method for full life-cycle management and maintenance of transformers and GIS according to claim 2, characterized in that, Step S2 specifically includes: S201. Based on the electrical insulation data of the transformer and the chemical data of dissolved gases in the oil, feature indicators are extracted. Based on the feature indicators, fault diagnosis is performed through threshold comparison and trend analysis to identify the fault type and fault degree. According to the feature indicators, the fault type and the fault degree, a percentage scoring method is used to assess the health status and obtain the corresponding health status level. S202. Based on the partial discharge data, SF6 gas characteristic data and insulation data of the GIS equipment, extract characteristic indicators, perform abnormal characteristic analysis based on the characteristic indicators, complete fault diagnosis and identify fault type and fault degree, and use a percentage scoring method to evaluate the health status according to the characteristic indicators, the fault type and the fault degree to obtain the corresponding health status level. The health status level is divided into four levels: healthy, slightly deteriorated, moderately deteriorated, and severely deteriorated.

4. The method for full life-cycle management and maintenance of transformers and GIS according to claim 1, characterized in that, Step S3 specifically includes the following steps: S301. Treat the single-device fault diagnosis results of transformers and GIS equipment as independent evidence bodies, and construct a basic trust allocation function for different fault diagnosis results. S302. Calculate the evidence entropy of each piece of evidence, quantify the uncertainty of each piece of evidence, and assign weight coefficients to each piece of evidence based on the evidence entropy, assigning low weights to evidence with high uncertainty and high weights to evidence with low uncertainty. S303. Based on the aforementioned weighting coefficients, D is used. The S-evidence combination rule merges the various evidence bodies to obtain a joint fault diagnosis result for the transformer and GIS equipment.

5. The method for full life-cycle management and maintenance of transformers and GIS according to claim 1, characterized in that, Step S4 specifically includes the following steps: S401. Based on the transformer health status level, the GIS equipment health status level, and the joint fault diagnosis results, the comprehensive health index is determined by integrating the health status level scores of the transformer and GIS equipment, the severity of the fault, the equipment's operating years, and the maintenance history. S402. Using the comprehensive health index as the core variable, and combining the manufacturing parameters, operating environment, and load characteristics of transformers and GIS equipment, construct a reliability model for power transmission and transformation equipment based on Weibull distribution. S403. Substitute the comprehensive health index into the reliability model to predict the remaining lifespan of the transformer and GIS equipment.

6. The method for full life-cycle management and maintenance of transformers and GIS according to claim 1, characterized in that, Step S6 specifically includes: S601. Determine the operation and maintenance plan based on the full life cycle management model. The operation and maintenance plan includes four options: continue operation, minor repair, major repair, and replacement. S602. The risk matrix method is used to conduct a risk assessment of the operation and maintenance scheme, quantify the probability of transformer and GIS equipment failure and the severity of failure consequences under each operation and maintenance scheme, obtain the comprehensive risk value of each operation and maintenance scheme, and divide the risk value into three risk levels: low, medium and high. S603. The operation and maintenance plan is quantitatively analyzed using a full life cycle cost model. Direct and indirect costs are calculated to obtain the total life cycle cost of each operation and maintenance plan.

7. The method for full life-cycle management and maintenance of transformers and GIS according to claim 1, characterized in that, Step S7 specifically includes: S701. Normalize the risk assessment results and cost quantification analysis results of the operation and maintenance plan, set the risk index weights and cost index weights according to the power grid safety priority, and calculate the comprehensive score. S702. The maintenance solution with the highest comprehensive score is determined as the optimal maintenance decision. S703. Feed the optimal maintenance decision back to the full life cycle management model, update the multi-source monitoring data and health status assessment results of transformers and GIS equipment in real time, and when the multi-source monitoring data and health status assessment results change significantly, re-evaluate the risk assessment and cost quantification analysis of the operation and maintenance plan, and dynamically adjust the maintenance decision.

8. A device for full life-cycle management and maintenance of transformers and GIS, characterized in that, The device is used to implement the full life-cycle management and maintenance method for transformers and GIS as described in any one of claims 1-7, including: The data processing and status assessment module is used to collect multi-source monitoring data of transformers and GIS equipment, preprocess the multi-source monitoring data, and perform fault diagnosis and health status assessment of transformers and GIS equipment based on the preprocessed multi-source monitoring data to obtain the corresponding single equipment health status level. The joint fault diagnosis module is used to treat the fault diagnosis results of transformers and GIS equipment as independent evidence bodies based on the evidence entropy theory. The weight coefficients are determined according to the evidence entropy of each evidence body. Based on the weight coefficients, the DS evidence combination rules are used to fuse the evidence bodies to obtain the joint fault diagnosis results of transformers and GIS equipment. The health assessment and life prediction module is used to determine a comprehensive health index based on the health status level of the transformer, the health status level of the GIS equipment, and the joint fault diagnosis results; to construct a reliability model based on the comprehensive health index; and to predict the remaining life of the transformer and the GIS equipment based on the reliability model. The whole life cycle management and decision-making module is used to integrate the basic information of transformers and GIS equipment, multi-source monitoring data, fault diagnosis results, health status assessment results and remaining lifespan to build an integrated whole life cycle management model. Based on the whole life cycle management model, the module determines the operation and maintenance plan, performs risk assessment and cost quantification analysis on the operation and maintenance plan, and outputs the optimal maintenance decision.

9. A life-cycle management and maintenance device for transformers and GIS, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory has instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the life-cycle management and maintenance method for transformers and GIS as described in any one of claims 1-7.

10. A non-volatile computer storage medium, characterized in that, The device stores computer-executable instructions configured to implement the full life-cycle management and maintenance method for transformers and GIS as described in any one of claims 1-7.

Images