Method and device for determining health state of transformer bushing and electronic equipment

Abstract

The invention discloses a method and device for determining the health state of a transformer bushing and electronic equipment. The method comprises the steps that parameter values corresponding to a plurality of initial parameters of a bushing of a target transformer and current environment data of an area where the transformer is located are collected, and the initial parameters are used for describing the electrical state and the mechanical state of the bushing; based on the current environment data, determining threshold intervals respectively corresponding to the plurality of initial parameters; abnormal parameters in the multiple initial parameters are determined, and the abnormal parameters are initial parameters with parameter values exceeding the corresponding threshold value intervals; determining an initial health index of the casing based on the abnormal parameter; the initial health index is corrected, the target health index of the casing is determined, and the target health index is used for quantitatively describing the health degree of the casing. According to the invention, the technical problem of low accuracy of the health index determination result of the transformer bushing in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of power systems, and in particular to a method, device, and electronic equipment for determining the health status of a transformer bushing. Background Art

[0002] Transformers are crucial components in power systems. Bushings, a key component connecting the transformer's internal high-voltage windings to the external power grid, are crucial for the transformer's overall safe operation. Bushing failures can lead to serious power outages, such as short circuits and explosions, jeopardizing grid stability and potentially causing casualties and property damage. Therefore, accurate bushing condition assessment can identify potential faults in advance, enabling preventive measures and ensuring safe power system operation.

[0003] The related technologies use parameter detection to determine the health status of the bushing, which has the following shortcomings: first, there are detection blind spots, such as the delayed response of oil chromatography analysis to oil leakage problems caused by failure of the bushing bottom seal, and infrared imaging has difficulty in detecting hidden faults inside the bushing (such as capacitor core stratification); second, the correlation between parameters is weak, and there is a lack of effective fusion of multi-source data, which cannot fully reflect the impact of complex factors such as bushing mechanical stress, ambient temperature and humidity on its performance, which easily leads to low accuracy in determining the health index of the transformer bushing.

[0004] With respect to the problem of low accuracy of the determination result of the health index of the transformer bushing in the above-mentioned related technologies, no effective solution has been proposed so far. Summary of the Invention

[0005] The embodiments of the present application provide a method, device, and electronic device for determining the health status of a transformer bushing, so as to at least solve the technical problem of low accuracy in determining the health index of a transformer bushing in the related art.

[0006] According to one aspect of an embodiment of the present application, a method for determining the health status of a transformer bushing is provided, comprising: collecting parameter values ​​corresponding to multiple initial parameters of a bushing of a target transformer, and current environmental data of an area where the transformer is located, wherein the initial parameters are used to describe the electrical and mechanical states of the bushing; determining threshold intervals corresponding to the multiple initial parameters based on the current environmental data; determining abnormal parameters among the multiple initial parameters, wherein the abnormal parameters are initial parameters whose parameter values ​​exceed the corresponding threshold intervals; determining an initial health index of the bushing based on the abnormal parameters; and correcting the initial health index to determine a target health index of the bushing, wherein the target health index is used to quantitatively describe the health of the bushing.

[0007] According to another aspect of an embodiment of the present application, a device for determining the health status of a transformer bushing is provided, comprising: a data acquisition module for collecting parameter values ​​corresponding to multiple initial parameters of the bushing of a target transformer, and current environmental data of an area where the transformer is located, wherein the initial parameters are used to describe the electrical and mechanical states of the bushing; a first determination module for determining, based on the current environmental data, threshold intervals corresponding to the multiple initial parameters; a second determination module for determining abnormal parameters among the multiple initial parameters, wherein the abnormal parameters are initial parameters whose parameter values ​​exceed the corresponding threshold intervals; a third determination module for determining an initial health index of the bushing based on the abnormal parameters; and a fourth determination module for correcting the initial health index to determine a target health index of the bushing, wherein the target health index is used to quantitatively describe the health of the bushing.

[0008] According to another aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the methods for determining the health status of a transformer bushing.

[0009] In an embodiment of the present application, parameter values ​​corresponding to multiple initial parameters of a target transformer's bushing, as well as current environmental data of the area where the transformer is located, are collected, wherein the initial parameters are used to describe the electrical and mechanical conditions of the bushing; based on the current environmental data, threshold intervals corresponding to the multiple initial parameters are determined; abnormal parameters among the multiple initial parameters are determined, wherein the abnormal parameters are initial parameters whose parameter values ​​exceed the corresponding threshold intervals; based on the abnormal parameters, an initial health index of the bushing is determined; and the initial health index is corrected to determine a target health index for the bushing, wherein the target health index is used to quantitatively describe the health of the bushing. This achieves the purpose of dynamically adjusting the parameter threshold intervals through real-time environmental data and determining the bushing health index through a comprehensive analysis of multiple parameters, thereby achieving the technical effect of improving the accuracy of the bushing health index determination results, thereby resolving the technical problem of low accuracy of transformer bushing health index determination results in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0011] Figure 1 This is a flow chart of a method for determining the health status of a transformer bushing according to an embodiment of the present application;

[0012] Figure 2This is a schematic diagram of an optional fault tree structure provided according to an embodiment of the present application;

[0013] Figure 3 is a flow chart of an optional method for determining the health status of a transformer bushing provided in accordance with an embodiment of the present application;

[0014] Figure 4 This is a schematic diagram of an optional device for determining the health status of a transformer bushing provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0017] According to an embodiment of the present application, a method embodiment of a method for determining the health status of a transformer bushing is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0018] Figure 1 is a flow chart of a method for determining the health status of a transformer bushing according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0019] Step S102: collecting parameter values ​​corresponding to a plurality of initial parameters of the bushing of the target transformer and current environmental data of the area where the transformer is located, wherein the initial parameters are used to describe the electrical and mechanical states of the bushing;

[0020] It is understood that the parameter values ​​corresponding to multiple initial parameters of the bushing of the target transformer and the current environmental data of the area where the transformer is located (such as temperature, humidity, and load rate, etc.) are collected. The above initial parameters are used to describe the electrical and mechanical states of the bushing.

[0021] Alternatively, sensors (such as oil chromatography sensors and partial discharge sensors) and manual inspections can be used to collect values ​​corresponding to multiple initial parameters. By integrating the electrical and mechanical status parameters of the bushing with environmental data for evaluation, a more comprehensive picture of the bushing's true health can be obtained, avoiding misjudgments of health status caused by variations in a single parameter. Furthermore, normalization of heterogeneous data can eliminate dimensional differences.

[0022] Optionally, the above initial parameters may include but are not limited to: dielectric loss (dielectric loss), oil chromatography, ultrasound, infrared, micro-water, oil level, oil pressure, insulation resistance, appearance, capacitance, high-frequency current, partial discharge, ultraviolet, sound, pollution area map, meteorology, creepage distance, contact voltage, load curve, etc.

[0023] In an optional embodiment, before collecting parameter values ​​corresponding to multiple initial parameters of the bushing of the target transformer and current environmental data of the area where the transformer is located, the method further includes: constructing a fault tree model of the bushing based on the structure of the bushing and a preset bushing health status assessment standard, wherein the fault tree model includes: a top event, a secondary event, a bottom event, and a decomposition parameter, wherein the top event is used to describe the most serious fault state of the bushing, the secondary event is used to describe the cause of the top event, the bottom event is used to describe the fault type of the bushing, and the decomposition parameter is used to describe the fault type information corresponding to the bottom event; and determining multiple initial parameters based on the fault tree model.

[0024] As can be understood, a bushing fault tree model is constructed based on the bushing structure and pre-established bushing health assessment criteria. The fault tree model includes the following: top events, secondary events, bottom events, and decomposition parameters. The top event describes the most severe bushing fault condition, such as "bushing insulation breakdown." It serves as the starting point for fault tree analysis and reflects the ultimate consequences of bushing failures that require prevention and control. Secondary events describe the causes of the top event, such as internal insulation failure and external failure. Bottom events describe the type of bushing failure, such as damp insulation, oil deficiency, overheating, insulation aging, internal discharge, pollution flashover, ice flashover, and joint overheating. Each bottom event is associated with a decomposition parameter that describes the corresponding fault type. Multiple initial bushing parameters are determined based on the decomposition parameters in the constructed fault tree model. The bottom events and decomposition parameters of the fault tree effectively integrate data collected by multiple sensors, eliminating the blind spots of single-sensor detection methods and improving the accuracy of health index determination.

[0025] Optionally, the fault tree model may not only include top events, secondary events, bottom events and decomposition parameters, but may also be expanded as required. Figure 2 is a schematic diagram of an optional fault tree structure provided according to an embodiment of the present application, such as Figure 2 As shown in the figure, the fault tree model includes top events, secondary events, bottom events, causes leading to the bottom events, and decomposition parameters. The top event is bushing insulation breakdown; secondary events include internal insulation faults and external faults; bottom events include insulation moisture, oil deficiency, insulation aging due to overheating, internal discharge, pollution flashover, ice flashover, and joint overheating; and the causes leading to the bottom events include poor sealing, large oil leakage, overload, cable contact with copper pipes, uneven voltage distribution, contamination, insufficient insulation margin, loose conductors, and oxidation.

[0026] Optionally, a hierarchical fault tree model can be constructed and fault mode mapping can be used. Taking typical faults of transformer bushings (such as oil shortage, damp insulation, overheating and insulation aging) as the analysis object, a hierarchical fault tree model construction strategy is adopted. First, the most serious fault state of the bushing is taken as the top event, and the secondary events are defined through the historical fault case library and industry standards; secondly, the underlying events are decomposed into quantifiable parameters based on the bushing operation data (i.e., the initial parameter data of the bushing, such as partial discharge, oil chromatography, and ultrasound), and the decomposition parameters corresponding to the underlying time are obtained. Finally, multi-level events are connected in series through the "AND gate" and "OR gate" logical relationships to achieve a systematic association between fault modes and monitoring decomposition parameters, covering complex scenarios such as mechanical, electrical, and environmental.

[0027] Step S104, determining threshold intervals corresponding to the multiple initial parameters based on the current environmental data;

[0028] As can be understood, the threshold ranges corresponding to multiple initial parameters are determined based on the current environmental data collected from the transformer area. The introduction of environmental data and the dynamic adjustment of threshold ranges make the health index determination more accurate to the actual operating environment, reducing errors caused by environmental factors and improving the accuracy of the health index determination.

[0029] In an optional embodiment, based on the current environmental data, threshold intervals corresponding to multiple initial parameters are determined, including: based on a preset casing health status assessment standard, initial parameter thresholds corresponding to the multiple initial parameters are determined; based on the current environmental data, the initial parameter thresholds corresponding to the multiple initial parameters are corrected to obtain threshold intervals corresponding to the multiple initial parameters.

[0030] It can be understood that, based on the preset casing health status assessment criteria, initial parameter thresholds corresponding to multiple initial parameters are determined. Based on the collected current environmental data, the initial parameter thresholds corresponding to each of the multiple initial parameters are modified to ensure that the thresholds match the actual environmental conditions, thereby obtaining threshold ranges corresponding to the multiple initial parameters. The introduction of environmental data and the dynamic adjustment of threshold ranges make the assessment criteria more closely aligned with the actual operating environment, reduce assessment errors caused by environmental factors, and improve the accuracy of health index determination results.

[0031] Optionally, dynamic threshold adjustment can be performed on the initial parameter threshold based on industry standards. Based on industry standards, a static threshold parameter (i.e., initial parameter threshold) is determined for the initial parameter. Based on current environmental data, a dynamic correction algorithm is introduced to expand the static threshold parameter into a threshold interval, enhancing the accuracy of casing fault location.

[0032] Step S106, determining abnormal parameters among the multiple initial parameters, wherein the abnormal parameters are initial parameters whose parameter values ​​exceed corresponding threshold intervals;

[0033] It can be understood that after determining the threshold intervals corresponding to the multiple initial parameters, the parameter values ​​corresponding to the multiple collected initial parameters are compared with the corresponding threshold intervals to determine which initial parameters have values ​​exceeding the corresponding threshold intervals and determine these initial parameters as abnormal parameters. This direct comparison with the dynamic threshold intervals can more promptly and accurately identify abnormal changes in the electrical or mechanical state parameters of the bushing, avoiding misjudgments caused by environmental changes or data fluctuations.

[0034] Step S108, determining the initial health index of the casing based on the abnormal parameters;

[0035] As you can see, based on the identified abnormal parameters, the health of the transformer bushing is assessed and an initial health index is determined. The generation of this initial health index provides a quantitative representation of the bushing's health, facilitating horizontal and vertical comparisons and helping to set trigger conditions for maintenance strategies.

[0036] In an optional embodiment, the initial health index of the casing is determined based on the abnormal parameters, including: based on the abnormal parameters, using a fault tree model of the casing, determining multiple activation cut sets including the abnormal parameters, wherein the activation cut set refers to an event set of underlying events, secondary events and top events that ultimately lead to the occurrence of the top event, the fault tree model includes: top events, secondary events, underlying events and decomposition parameters, the top event is used to describe the most serious fault state of the casing, the secondary event is used to describe the cause of the top event, the underlying event is used to describe the fault type of the casing, and the decomposition parameter is used to describe the fault type information corresponding to the underlying event; determining multiple underlying events corresponding to the multiple activation cut sets, and event weights corresponding to the multiple underlying events, wherein the multiple activation cut sets correspond one-to-one to the multiple underlying events; and determining the initial health index based on the number of the multiple activation cut sets and the event weights corresponding to the multiple underlying events.

[0037] It can be understood that based on the identified abnormal parameters and the fault tree model of the casing, the underlying events including the abnormal parameters are identified. Based on the identified underlying events including the abnormal parameters, multiple activation cut sets are determined. An activation cut set is an event set consisting of the underlying events, secondary events, and top events that ultimately lead to the top event. The event weights corresponding to the multiple underlying events included in the multiple activation cut sets are determined. Based on the number of activation cut sets and the event weights corresponding to the multiple underlying events, the initial health index of the casing is determined. Analyzing the abnormal parameters through the fault tree model can effectively locate the specific underlying event that caused the health index to drop, improve the accuracy of fault identification, and avoid blind maintenance.

[0038] Optionally, a binary decision diagram (BDD) algorithm can be used to calculate activation cut sets and dynamically update fault combination weights (i.e., update the weights of the decomposition parameters of the underlying events included in the activation cut set). This algorithm can be used to mine association rules in historical fault data and optimize the threshold intervals of initial parameters.

[0039] Alternatively, industry standards can be broken down into a structured rule base, with each rule containing the fault type, trigger condition (i.e., initial parameter threshold), and risk level. A fuzzy matching algorithm is used to associate the minimum cut set of the fault tree with the rule base entries. A priority sorting algorithm (TOPSIS) is used to resolve conflicts among multiple rules, ensuring that high-risk defects are prioritized for alerting.

[0040] In an optional embodiment, before determining the initial health index based on the number of multiple activation cut sets and the event weights corresponding to multiple underlying events, the method also includes: for any activation cut set among the multiple activation cut sets, determining the target weights corresponding to multiple decomposition parameters of any underlying event included in any activation cut set; determining the event weight of any underlying event based on the parameter values ​​corresponding to the multiple decomposition parameters and the target weights corresponding to the multiple decomposition parameters; and determining the event weights corresponding to multiple underlying events by adopting the method of determining the event weight of any underlying event.

[0041] It can be understood that the method for determining the event weights of the underlying events included in the activation cut set is explained by taking any activation cut set among multiple activation cut sets as an example. For any underlying event included in any activation cut set, the event weight of any underlying event is determined based on the target weights corresponding to the multiple decomposition parameters of the any underlying event, and the parameter values ​​corresponding to the multiple decomposition parameters. By adopting the method of determining the event weight of any underlying event, the event weights corresponding to the multiple underlying events are determined. Based on the weight calculation of the activation cut set, the fault mode that has the greatest impact on the health status of the casing can be identified, providing a scientific basis for generating customized maintenance strategies.

[0042] In an optional embodiment, the target weights corresponding to the multiple decomposition parameters of any underlying event included in any activation cut set are determined, including: based on the historical fault data of the casing, using statistical analysis to determine the occurrence probabilities corresponding to the multiple decomposition parameters, wherein the occurrence probability is used to represent the possibility of the occurrence of any underlying event due to abnormal parameter values ​​of the decomposition parameters; based on the risk level of any underlying event, the weight addition coefficients corresponding to the multiple decomposition parameters, and the occurrence probabilities corresponding to the multiple decomposition parameters, determining the initial weights corresponding to the multiple decomposition parameters, wherein the weight addition coefficients are used to quantify the degree of influence of the risk level on the initial weights of the decomposition parameters; based on the current environmental data, the initial weights corresponding to the multiple decomposition parameters are corrected to obtain the target weights corresponding to the multiple decomposition parameters.

[0043] It can be understood that statistical analysis is performed on the historical failure data of the casing to determine the probability of occurrence of any underlying event due to abnormal decomposition parameters, and the probability of occurrence corresponding to multiple decomposition parameters is determined. According to the risk level of any underlying event, the probability of occurrence corresponding to multiple decomposition parameters, and the weight addition coefficients corresponding to multiple decomposition parameters, the initial weights corresponding to the multiple decomposition parameters are determined. The above-mentioned weight addition coefficients are used to quantify the degree of influence of the risk level on the initial weights of the decomposition parameters. Combined with the current environmental data, the initial weights corresponding to the multiple decomposition parameters are corrected to determine the target weights corresponding to the multiple decomposition parameters. By incorporating the historical probability of occurrence and risk level of the decomposition parameters into the weight distribution, it is possible to more accurately identify which changes in decomposition parameters have a significant impact on the health status of the casing, improve the accuracy of the casing status assessment, and thereby improve the accuracy of the casing health index determination results.

[0044] Optionally, based on historical bushing failure data, the occurrence probability of the decomposition parameters corresponding to the underlying events in the fault tree model is statistically analyzed. Combined with the risk level of the underlying events specified in industry standards (used to quantify the harm of the fault type of the underlying event to the bushing), the initial weights of the decomposition parameters are determined. A fuzzy logic-driven dynamic weight adaptive algorithm can be used, using current environmental data such as ambient temperature and humidity, ambient humidity, and load rate as inputs to the fuzzy logic weight dynamic adjustment model. A three-dimensional fuzzy rule library for "temperature-humidity-load" is established, and the adjusted target weights of the decomposition parameters are output. Through the above-mentioned fuzzy logic weight dynamic adjustment algorithm, the weight distribution of the decomposition parameters can be automatically adjusted, so that the weights of decomposition parameters closely associated with the underlying events under the current environmental data are increased, and the weights of decomposition parameters less closely associated with the underlying events under the current environmental data are reduced.

[0045] Alternatively, a digital twin-based simulation and verification platform can be constructed to iteratively optimize the fuzzy logic weight dynamic adjustment model. First, typical bushing faults (such as overheating, insulation aging, and insulation moisture) are injected into the virtual twin model to simulate changes in decomposition parameters under different environmental conditions (such as extreme humidity and overload). Second, the evaluation results of the fuzzy logic weight dynamic adjustment model are compared with those of a traditional fixed-weight model, automatically optimizing the model parameters of the three-dimensional fuzzy rule base and the fuzzy logic weight dynamic adjustment model.

[0046] Step S110 : correcting the initial health index to determine a target health index of the casing, wherein the target health index is used to quantitatively describe the health of the casing.

[0047] To further improve the accuracy of the initial health index of the casing, it is corrected to determine a target health index, which is used to quantitatively describe the health of the casing. This corrected health index provides a more accurate basis for fault warning, helping to detect potential faults in advance, reduce unplanned downtime, develop more effective maintenance plans, and improve maintenance efficiency.

[0048] In an optional embodiment, the initial health index is corrected to determine the target health index of the bushing, including: obtaining historical environmental data of the area where the transformer is located and a life curve of the bushing, wherein the life curve is used to describe the change in the service life of the bushing over time; based on the historical environmental data and the life curve, the initial health index is corrected to obtain the target health index.

[0049] It can be understood that historical environmental data of the area where the transformer is located and a life curve used to describe the changes in the service life of the bushing over time are obtained. Among them, the historical environmental data is used to determine the impact of environmental conditions on the health index of the bushing. For example, a long-term high humidity environment may accelerate the penetration of moisture into the capacitor layer, resulting in a decrease in insulation performance, thereby affecting the evaluation of the health index. The life curve is obtained by analyzing the historical operation data and historical fault data of bushings of the same type as the bushing. According to the historical environmental data and the life curve, the initial health index is corrected to obtain the target health index. The correction based on the historical environmental data and the life curve can more accurately reflect the health index of the bushing under specific environmental conditions and reduce the evaluation error caused by environmental changes or equipment aging.

[0050] Optionally, a four-dimensional health index dynamic assessment model can be established to determine the target health index of the casing. A four-dimensional assessment matrix consisting of "parameter dimension - cut set dimension - environmental dimension - historical degradation dimension" is established. The parameter dimension determines initial parameter thresholds based on industry standards and the threshold ranges for these initial parameters based on current environmental data. The cut set dimension determines the initial health index of the casing based on the number of activated cut sets containing abnormal parameters and the event weights of the underlying events included in the activated cut sets. The environmental dimension uses an LSTM (Long Short-Term Memory) model to predict the cumulative impact of environmental data such as temperature, humidity, and load rate on the casing health status, thereby revising the initial health index. The historical dimension analyzes the life curves of similar casings based on the Weibull distribution (a continuous probability distribution) to revise the initial health index. Determining the target health index of the casing based on these four dimensions avoids misjudgments and omissions based on a single dimension, thereby improving the accuracy of the target health index determination.

[0051] In an optional embodiment, after correcting the initial health index and determining the target health index of the casing, the method further includes: based on the abnormal parameters, using a fault tree model of the casing, determining multiple initial underlying events including the abnormal parameters, wherein the fault tree model includes: a top event, a secondary event, a bottom event and a decomposition parameter, the top event is used to describe the most serious fault state of the casing, the secondary event is used to describe the cause of the top event, the bottom event is used to describe the fault type of the casing, and the decomposition parameter is used to describe the fault type information corresponding to the bottom event; determining the initial bottom event with the highest risk level among the multiple initial bottom events as the target bottom event of the casing; determining the target fault type of the casing based on the target bottom event; determining the health level of the casing based on the target health index; and determining the health management strategy of the casing based on the health level and the target fault type.

[0052] It will be appreciated that after determining the target health index of the bushing, a health management strategy can be developed for the bushing based on the target health index and the determined target fault type. First, based on the identified anomaly index, multiple initial underlying events that include the anomaly index are identified from the fault tree model (i.e., underlying events with the same decomposition parameters as the anomaly parameters are found). Prioritize and address the fault with the highest risk to prevent it from escalating to the most severe state. Therefore, the risk levels of the multiple initial underlying events are compared, and the initial underlying event with the highest risk level is determined as the target underlying event for the bushing. Based on the target underlying event, the target fault type of the bushing is determined. Based on the target health index of the bushing, the health level of the bushing is determined. Based on the health level and the target fault type of the bushing, a health management strategy is developed for the bushing. For example, if the bushing is determined to be "abnormal" and the target fault type is "capacitive touch screen moisture," the strategy may include immediate drying, checking the seal, and considering replacing the sealing material. By using fault tree models and risk level classification, we can more accurately pinpoint the root cause of a health index decline, rather than simply identifying surface parameter anomalies, thus improving fault diagnosis accuracy. Furthermore, maintenance strategies developed based on target fault types and health levels are not only highly targeted but also prioritize the severity of faults, helping to optimize the allocation of maintenance resources, avoid ineffective or excessive maintenance, and improve maintenance efficiency.

[0053] Optionally, an integrated "diagnosis-assessment-decision-making" framework can be established based on the analysis results of the fault tree model and industry standards. First, the target bushing fault type (such as thermal insulation aging or insulation moisture) is determined based on the fault tree model. The bushing health level (normal / caution / abnormal / critical) is then determined by combining industry standards and the bushing's target health index. Second, a customized bushing maintenance strategy (i.e., health management strategy) is generated using a rule base of action measures.

[0054] Optionally, an activation cutset containing abnormal parameters is identified through a fault tree model and correlated with industry standards to determine the fault type. When multiple fault groups are triggered simultaneously (i.e., multiple activation cutsets exist), the fault type with the highest risk level is prioritized as the target fault type for the casing, achieving primary and secondary separation of complex defects.

[0055] Optionally, a four-dimensional health status grading standard can be established. Based on the threshold range corresponding to the abnormal parameter (such as dielectric loss factor tanδ ≤ 0.7%), the number of active cut sets in the fault tree, and environmental data, the target health index of the bushing is determined. Based on the target health index, the bushing health level is determined to be one of the four health levels: "normal / caution / abnormal / critical".

[0056] Optionally, the health management strategy in the industry standard can be automatically matched based on the health level and target fault type: Dynamic maintenance strategy generation and optimization. Based on the casing health level and target fault type, the following health management strategies are matched: Caution Level: Automatically issue a "retest within 72 hours + infrared tracking" work order and link it to a library of similar fault handling cases; Abnormal Level: Utilize a fault tree model to locate the fault and generate a customized solution; Severity Level: Link the Production Management System (PMS) to generate a shutdown work order and push spare parts inventory information. Monte Carlo simulation is used to optimize maintenance paths and reduce the probability of unnecessary downtime.

[0057] Through the above steps S102 to S110, the purpose of dynamically adjusting the threshold range of the parameter through real-time environmental data and determining the health index of the bushing in combination with a comprehensive analysis of multiple parameters can be achieved, thereby achieving the technical effect of improving the accuracy of the bushing health index determination result, thereby solving the technical problem of low accuracy of the transformer bushing health index determination result existing in the related art.

[0058] Based on the above embodiments and optional embodiments, the present application proposes an optional implementation of a method for determining the health status of a transformer bushing. The method can be understood as a method for assessing the health status of a transformer bushing based on a fault tree and evaluation guidelines. The method includes the following steps:

[0059] In step S21, a fault tree model covering typical bushing failure modes (such as oil deficiency, insulation moisture, and insulation aging due to overheating) is first constructed. By combining historical fault data with threshold parameters (i.e., initial parameter thresholds) defined by industry standards (i.e., pre-set bushing health status assessment standards), the underlying events of the fault tree model are dynamically associated with quantitative indicators defined by industry standards (i.e., decomposition parameters corresponding to the underlying events). This forms a logical "AND / OR" relationship, enabling precise location of bushing faults.

[0060] Step S211, hierarchical fault tree model construction and fault mode mapping. Taking the typical faults of transformer bushings (such as oil shortage, damp insulation, overheating and insulation aging) as the analysis object, a hierarchical fault tree model construction strategy is adopted. First, the most serious fault state of the bushing is taken as the top event, and the secondary events are defined through the historical fault case library and industry standards; secondly, the underlying events are decomposed into quantifiable parameters in combination with the bushing operation data (i.e. the initial parameter data of the bushing, such as partial discharge, oil chromatography, and ultrasound), and the decomposition parameters corresponding to the underlying time are obtained. Finally, multi-level events are connected in series through the logical relationship of "AND gate" and "OR gate" to achieve a systematic association between fault modes and monitoring decomposition parameters, covering complex scenarios such as mechanical, electrical, and environmental. The above process is used to construct the following Figure 2 The fault tree model shown.

[0061] Step S212: Initial parameter threshold and dynamic threshold adjustment mechanism based on industry standards. Based on industry standards, static threshold parameters of the initial parameters (i.e., initial parameter thresholds) are determined. Based on current environmental data, a dynamic correction algorithm is introduced to expand the static threshold parameters into threshold intervals, enhancing the accuracy of casing fault location.

[0062] Step S213: Casing fault location and fault path visualization. A minimum cut set algorithm is used to identify the critical path in the fault tree model and generate a three-dimensional visual diagnostic map. The diagnostic results are presented as a tree topology diagram, allowing interactive clicks to view parameter historical trends, maintenance records, and associated industry standards for each node (i.e., event in the fault tree model), enabling one-click tracing from "parameter anomaly" to "fault location."

[0063] Step S22: Dynamically and adaptively adjust the target weights of the decomposition parameters. First, the initial weights of the decomposition parameters are calculated based on the probability of occurrence of the decomposition parameters corresponding to each underlying event in the fault tree model and the risk level specified by industry standards. Second, the current environmental data (such as load rate, ambient temperature, and ambient humidity) are introduced, and the initial weights are dynamically modified using a fuzzy logic algorithm to obtain the target weights of the decomposition parameters.

[0064] In step S221, based on the historical failure data of the casing, the occurrence probability of the decomposition parameters corresponding to the bottom-level events in the fault tree model is statistically analyzed. In combination with the risk level of the bottom-level events specified in the industry standard (which is used to quantitatively describe the harm of the fault type of the bottom-level event to the casing), the initial weights of the decomposition parameters are determined.

[0065] Step S222: A fuzzy logic-driven dynamic weight adaptation algorithm. Current environmental data, such as ambient temperature and humidity, ambient humidity, and load rate, are used as inputs for the fuzzy logic weight dynamic adjustment model. A three-dimensional fuzzy rule base for "temperature-humidity-load" is established, and the adjusted target weights for the decomposition parameters are output. This fuzzy logic weight dynamic adjustment algorithm automatically adjusts the weight distribution of the decomposition parameters, increasing the weights of decomposition parameters that are closely associated with the underlying events in the current environmental data, while decreasing the weights of decomposition parameters that are less closely associated with the underlying events in the current environmental data.

[0066] Step S223: Build a digital twin-based simulation and verification platform to iteratively optimize the fuzzy logic weight dynamic adjustment model. First, inject typical bushing faults (such as overheating, insulation aging, and insulation moisture) into the virtual twin model to simulate changes in decomposition parameters under different environmental conditions (such as extreme humidity and overload). Second, compare the evaluation results of the fuzzy logic weight dynamic adjustment model with those of a traditional fixed weight model, and automatically optimize the model parameters of the three-dimensional fuzzy rule base and the fuzzy logic weight dynamic adjustment model.

[0067] Step S23: Industry-standard driven multi-dimensional bushing health status decision-making and maintenance strategy generation. Based on the analysis results of the fault tree model and industry standards, an integrated "diagnosis-assessment-decision-making" framework is established. First, the target bushing fault type (such as thermal insulation aging or insulation moisture) is determined based on the fault tree model. The bushing health level (normal / caution / abnormal / critical) is determined by combining industry standards and the bushing's target health index. Second, a customized bushing maintenance strategy (i.e., health management strategy) is generated using a rule library of action measures.

[0068] In step S231, the fault tree model is used to determine the active cutsets containing the abnormal parameters and, in conjunction with industry standards, to determine the fault type. When multiple faults are triggered simultaneously (i.e., multiple active cutsets exist), the fault type with the highest risk is prioritized as the target fault type for the casing, achieving a primary and secondary separation of complex defects. Experimental results show that this method has an accuracy rate exceeding 94% for identifying complex faults.

[0069] Step S232: Establish a four-dimensional health status grading standard. Based on the threshold range corresponding to the abnormal parameter (e.g., dielectric loss factor tanδ ≤ 0.7%), the number of active cut sets in the fault tree, and environmental data, determine the target health index of the bushing. Based on the target health index, determine which of the four health levels (normal / caution / abnormal / critical) the bushing belongs to.

[0070] Step S233: Dynamic maintenance strategy generation mechanism automatically matches the health management strategy in the row standard according to the health level and target fault type:

[0071] Note: Trigger 72-hour retest + infrared tracking;

[0072] Abnormal: push customized solutions (such as insulation getting damp and requiring vacuum oiling);

[0073] Serious: Generate a shutdown work order and associate it with the equipment maintenance record.

[0074] Experiments show that after application, maintenance efficiency increased by 50% and the unplanned downtime rate decreased by 22%.

[0075] Step S234, digital twin maintenance verification.

[0076] Simulate maintenance effects in a virtual model (such as changes in moisture content after replacing a seal). If the simulation results deviate from expectations (such as insufficient reduction in moisture content), optimize the disposal measure rule base (such as adding cleanliness detection items).

[0077] The above method is used to determine the specific implementation method of casing health detection. Figure 3 is a flow chart of an optional method for determining the health status of a transformer bushing according to an embodiment of the present application, such as Figure 3 As shown, the steps of the implementation method include:

[0078] Step S31: Multi-source data collection and standardization preprocessing. Using a sensor network (such as oil chromatography sensors and partial discharge sensors) and manual inspection records, the system collects bushing operating parameters (i.e., initial parameters, such as dielectric loss factor tanδ, oil level, and partial discharge), environmental data (temperature, humidity, and load factor), and historical defect database information (including historical bushing failure data). Heterogeneous data is normalized to eliminate dimensional differences.

[0079] Step S32: Fault tree model construction and dynamic generation of activation cut sets. Based on the bushing structure and industry standards, the top event of the fault tree model (e.g., bushing insulation breakdown) is constructed and layer-by-layer decomposition is performed to obtain underlying events (e.g., insulation moisture, oil shortage, etc.). A binary decision diagram (BDD) algorithm is used to calculate the activation cut sets, and the fault combination weights (i.e., the weights of the decomposition parameters of the underlying events included in the activation cut sets) are dynamically updated. The algorithm mines association rules from historical fault data and optimizes the threshold intervals of the initial parameters.

[0080] Step S33: Intelligently map industry standard rule bases to fault types. Industry standards are broken down into a structured rule base, where each rule includes the fault type, trigger condition (i.e., initial parameter threshold), and risk level. A fuzzy matching algorithm is used to associate the minimum cut set of the fault tree with the rule base entries. A priority sorting algorithm (TOPSIS) is used to resolve multi-rule conflicts, ensuring that high-risk defects are prioritized for alerting.

[0081] Step S34: Construct a four-dimensional health index dynamic assessment model. A four-dimensional assessment matrix consisting of "parameter dimension - cut set dimension - environmental dimension - historical degradation dimension" is established. The parameter dimension determines the initial parameter threshold according to industry standards and the threshold range of the initial parameter based on current environmental data. The cut set dimension determines the initial health index of the bushing based on the number of activated cut sets containing abnormal parameters and the event weights of the underlying events included in the activated cut sets. The environmental dimension uses an LSTM (Long Short-Term Memory) model to predict the cumulative impact of environmental data such as temperature, humidity, and load rate on the bushing health status, which is used to correct the initial health index. The historical dimension analyzes the life curves of similar bushings based on the Weibull distribution (a continuous probability distribution) to correct the initial health index. Determining the bushing's target health index based on these four dimensions avoids misjudgments and missed judgments based on a single dimension, and improves the accuracy of the target health index determination.

[0082] Step S35: Dynamic maintenance strategy generation and optimization. Based on the casing health level and target fault type, the health management strategy specified in the row standard is matched: For the Caution level, a "retest within 72 hours + infrared tracking" work order is automatically issued and linked to a library of similar fault handling cases; for the Abnormal level, a fault tree model is used to locate the fault and generate a customized solution; for the Severity level, a shutdown work order is generated in conjunction with the Production Management System (PMS) and spare parts inventory information is pushed. Monte Carlo simulation is used to optimize maintenance paths and reduce the probability of unnecessary downtime.

[0083] Step S36: adaptive adjustment of dynamic event weights and model iteration.

[0084] A fuzzy logic controller is used to dynamically adjust the model parameters and decomposition parameter weights of the model by adjusting the fuzzy logic weights in real time according to environmental changes, and to adjust the event weights of the underlying events according to the adjusted hierarchical parameter weights.

[0085] Model input: ambient humidity, ambient temperature, load rate, equipment operation years, etc.

[0086] Three-dimensional fuzzy rule base: For example, "When humidity is greater than 85%, the event weight of the underlying event corresponding to insulation moisture is increased from 0.3 to 0.5";

[0087] Output Optimization: The health index calculation formula is updated through a Bayesian network to ensure model adaptability. Model validation is performed monthly using historical data. Gradient descent is used to optimize fuzzy logic weights to dynamically adjust model parameters and decompose parameter weights, improving the stability of health status assessment by 40%.

[0088] Step S37: Full-process closed-loop verification and operation and maintenance data feedback.

[0089] Establish an "implementation-monitoring-feedback" closed-loop mechanism, whereby on-site personnel receive work orders through mobile terminals and record operation details (such as oil injection pressure value and sealing ring batch); continuously monitor key parameters (such as water content and partial discharge) within 72 hours after maintenance, and transmit the data back to the central platform; analyze the data, and if the assessment results do not meet the standards, initiate root cause analysis (RCA) and correct the minimum cut set of the fault tree model or the industry standard mapping logic; and store verified maintenance cases in a database to support future decision-making.

[0090] The above optional implementations achieve at least the following effects: Accurate identification and prioritization of complex faults are achieved through an intelligent mapping mechanism between the fault tree model and industry standards. A four-dimensional dynamic health index assessment breaks through the limitations of a single parameter threshold and improves the accuracy of health index determination results based on multi-source detection data (oil chromatography / ultrasound / infrared) and the synergistic effects of environmental dimensions and historical degradation dimensions. A dynamic adaptive adjustment mechanism for the target weights of decomposition parameters, using a fuzzy logic-based weight dynamic adjustment model to adjust the weights of decomposition parameters in real time, improves the stability of the health index assessment model under complex working conditions and reduces the false alarm rate.

[0091] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0092] This embodiment also provides a device for determining the health status of a transformer bushing. This device is used to implement the aforementioned embodiments and preferred implementations, and details already described will not be repeated. As used below, the terms "module" and "device" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented using software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0093] According to an embodiment of the present application, there is also provided an embodiment of a device for implementing a method for determining the health status of a transformer bushing. Figure 4 is a schematic diagram of a device for determining the health status of a transformer bushing according to an embodiment of the present application. Figure 4 As shown, the above-mentioned device for determining the health status of a transformer bushing includes a data acquisition module 402, a first determination module 404, a second determination module 406, a third determination module 408, and a fourth determination module 410. The device is described below.

[0094] The data acquisition module 402 is used to collect parameter values ​​corresponding to multiple initial parameters of the bushing of the target transformer, as well as current environmental data of the area where the transformer is located, wherein the initial parameters are used to describe the electrical and mechanical conditions of the bushing;

[0095] A first determination module 404, connected to the data acquisition module 402, is used to determine the threshold intervals corresponding to the multiple initial parameters based on the current environmental data;

[0096] A second determining module 406, connected to the first determining module 404, is configured to determine an abnormal parameter among the multiple initial parameters, wherein the abnormal parameter is an initial parameter whose parameter value exceeds a corresponding threshold range;

[0097] A third determination module 408, connected to the second determination module 406, is configured to determine an initial health index of the casing based on the abnormal parameters;

[0098] The fourth determining module 410 is connected to the third determining module 408 and is configured to modify the initial health index to determine a target health index of the casing, wherein the target health index is used to quantitatively describe the health of the casing.

[0099] In a device for determining the health status of a transformer bushing provided in an embodiment of the present application, a data acquisition module 402 is set to collect parameter values ​​corresponding to multiple initial parameters of the bushing of a target transformer, as well as current environmental data of the area where the transformer is located, wherein the initial parameters are used to describe the electrical and mechanical states of the bushing; a first determination module 404 is connected to the data acquisition module 402 and is used to determine threshold intervals corresponding to the multiple initial parameters based on the current environmental data; a second determination module 406 is connected to the first determination module 404 and is used to determine abnormal parameters among the multiple initial parameters, wherein the abnormal parameters are initial parameters whose parameter values ​​exceed the corresponding threshold intervals; a third determination module 408 is connected to the second determination module 406 and is used to determine an initial health index of the bushing based on the abnormal parameters; and a fourth determination module 410 is connected to the third determination module 408 and is used to correct the initial health index and determine a target health index of the bushing, wherein the target health index is used to quantitatively describe the health of the bushing. The purpose of dynamically adjusting the threshold range of parameters through real-time environmental data and determining the health index of the bushing by combining comprehensive analysis of multiple parameters is achieved, thereby achieving the technical effect of improving the accuracy of the results of determining the health index of the bushing, thereby solving the technical problem of low accuracy of the health index determination results of the transformer bushing existing in the related art.

[0100] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0101] It should be noted that the data acquisition module 402, first determination module 404, second determination module 406, third determination module 408, and fourth determination module 410 correspond to steps S102 to S110 in the embodiment. The examples and application scenarios implemented by the modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the modules, as part of the device, can be run on a computer terminal.

[0102] It should be noted that the optional or preferred implementation of this embodiment can be found in the relevant description in the embodiment, which will not be repeated here.

[0103] The above-mentioned transformer bushing health status determination device may further include a processor and a memory. The data acquisition module 402, the first determination module 404, the second determination module 406, the third determination module 408, the fourth determination module 410, etc. are all stored in the memory as program units. The processor executes the above-mentioned program units stored in the memory to implement corresponding functions.

[0104] The processor includes a kernel, which retrieves the corresponding program unit from memory. There can be one or more kernels. Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0105] An embodiment of the present application provides a non-volatile storage medium having a program stored thereon, which, when executed by a processor, implements a method for determining the health status of a transformer bushing.

[0106] An embodiment of the present application provides an electronic device comprising a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are performed: collecting parameter values ​​corresponding to multiple initial parameters of a target transformer's bushing, as well as current environmental data of the area where the transformer is located, wherein the initial parameters are used to describe the electrical and mechanical conditions of the bushing; determining threshold intervals corresponding to the multiple initial parameters based on the current environmental data; determining abnormal parameters among the multiple initial parameters, wherein the abnormal parameters are initial parameters whose parameter values ​​exceed the corresponding threshold intervals; determining an initial health index of the bushing based on the abnormal parameters; and correcting the initial health index to determine a target health index for the bushing, wherein the target health index is used to quantitatively describe the health of the bushing. The device herein may be a server, a PC, or the like.

[0107] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: collecting parameter values ​​corresponding to multiple initial parameters of the bushing of a target transformer, and current environmental data of the area where the transformer is located, wherein the initial parameters are used to describe the electrical and mechanical states of the bushing; based on the current environmental data, determining threshold intervals corresponding to the multiple initial parameters; determining abnormal parameters among the multiple initial parameters, wherein the abnormal parameters are initial parameters whose parameter values ​​exceed the corresponding threshold intervals; determining an initial health index of the bushing based on the abnormal parameters; and correcting the initial health index to determine a target health index of the bushing, wherein the target health index is used to quantitatively describe the health of the bushing.

[0108] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0109] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0110] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0112] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0113] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0114] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0115] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0116] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for determining the health status of a transformer bushing, characterized in that: include: Collect parameter values ​​corresponding to multiple initial parameters of the bushing of the target transformer, as well as current environmental data of the area where the transformer is located, wherein the initial parameters are used to describe the electrical and mechanical states of the bushing; Determining, based on the current environmental data, threshold intervals corresponding to the multiple initial parameters respectively; Determining an abnormal parameter among the multiple initial parameters, wherein the abnormal parameter is an initial parameter whose parameter value exceeds a corresponding threshold range; determining an initial health index of the casing based on the abnormal parameters; The initial health index is corrected to determine a target health index of the casing, wherein the target health index is used to quantitatively describe the health of the casing.

2. The method according to claim 1, characterized in that Before collecting parameter values ​​corresponding to a plurality of initial parameters of the bushing of the target transformer and current environmental data of the area where the transformer is located, the method further includes: Based on the structure of the casing and a preset casing health status assessment standard, a fault tree model of the casing is constructed, wherein the fault tree model includes: a top event, a secondary event, a bottom event, and a decomposition parameter, wherein the top event is used to describe the most serious fault state of the casing, the secondary event is used to describe the cause of the top event, the bottom event is used to describe the fault type of the casing, and the decomposition parameter is used to describe the fault type information corresponding to the bottom event; Based on the fault tree model, the plurality of initial parameters are determined.

3. The method according to claim 1, characterized in that The determining, based on the current environment data, threshold intervals corresponding to the multiple initial parameters respectively includes: Based on a preset casing health status assessment standard, determining initial parameter thresholds corresponding to the multiple initial parameters respectively; Based on the current environment data, the initial parameter thresholds corresponding to the multiple initial parameters are corrected to obtain the threshold intervals corresponding to the multiple initial parameters.

4. The method according to claim 1, wherein The determining of the initial health index of the casing based on the abnormal parameter includes: Based on the abnormal parameters, a fault tree model of the casing is used to determine multiple activation cut sets including the abnormal parameters, wherein the activation cut set refers to an event set of bottom-level events, secondary events, and top events that ultimately lead to the occurrence of a top event. The fault tree model includes: a top event, a secondary event, a bottom-level event, and a decomposition parameter. The top event is used to describe the most serious fault state of the casing, the secondary event is used to describe the cause of the top event, the bottom-level event is used to describe the fault type of the casing, and the decomposition parameter is used to describe the fault type information corresponding to the bottom-level event. Determining a plurality of underlying events corresponding to the plurality of activation cut sets and event weights respectively corresponding to the plurality of underlying events, wherein the plurality of activation cut sets correspond to the plurality of underlying events in a one-to-one manner; The initial health index is determined based on the number of the multiple activated cut sets and the event weights corresponding to the multiple underlying events.

5. The method according to claim 4, characterized in that Before determining the initial health index based on the number of the multiple activated cut sets and the event weights corresponding to the multiple underlying events, the method further includes: For any activation cut set among the multiple activation cut sets, determining target weights corresponding to multiple decomposition parameters of any underlying event included in the any activation cut set; Determining an event weight of any of the underlying events based on the parameter values ​​corresponding to the multiple decomposition parameters and the target weights corresponding to the multiple decomposition parameters; The event weights corresponding to the multiple underlying events are determined in a manner of determining the event weight of any of the underlying events.

6. The method according to claim 5, characterized in that The determining of target weights corresponding to a plurality of decomposition parameters of any underlying event included in any activation cut set includes: Based on the historical fault data of the casing, using a statistical analysis method, determining the occurrence probabilities corresponding to the multiple decomposition parameters, wherein the occurrence probability is used to represent the possibility of occurrence of any underlying event due to abnormal parameter values ​​of the decomposition parameters; Determining initial weights corresponding to the multiple decomposition parameters based on the risk level of any underlying event, the weight addition coefficients corresponding to the multiple decomposition parameters, and the occurrence probabilities corresponding to the multiple decomposition parameters, wherein the weight addition coefficients are used to quantitatively represent the degree of influence of the risk level on the initial weights of the decomposition parameters; Based on the current environmental data, the initial weights corresponding to the multiple decomposition parameters are corrected to obtain the target weights corresponding to the multiple decomposition parameters.

7. The method according to claim 1, characterized in that The correcting the initial health index to determine the target health index of the casing includes: Obtaining historical environmental data of the area where the transformer is located, and a life curve of the bushing, wherein the life curve is used to describe changes in the service life of the bushing over time; Based on the historical environmental data and the life curve, the initial health index is corrected to obtain the target health index.

8. The method according to any one of claims 1 to 7, characterized in that After the initial health index is corrected to determine the target health index of the casing, the method further includes: Based on the abnormal parameters, a fault tree model of the casing is used to determine multiple initial bottom-level events including the abnormal parameters, wherein the fault tree model includes: a top event, a secondary event, a bottom-level event, and a decomposition parameter, the top event is used to describe the most serious fault state of the casing, the secondary event is used to describe the cause of the top event, the bottom-level event is used to describe the fault type of the casing, and the decomposition parameter is used to describe the fault type information corresponding to the bottom-level event; determining the initial bottom-layer event with the highest risk level among the multiple initial bottom-layer events as the target bottom-layer event of the casing; determining a target fault type of the casing based on the target underlying event; determining a health level of the casing based on the target health index; A health management strategy for the bushing is determined based on the health level and the target fault type.

9. A device for determining the health status of a transformer bushing, characterized in that: include: a data acquisition module, configured to acquire parameter values ​​corresponding to a plurality of initial parameters of the bushing of a target transformer, and current environmental data of an area where the transformer is located, wherein the initial parameters are used to describe the electrical and mechanical states of the bushing; A first determining module is configured to determine, based on the current environmental data, threshold intervals corresponding to the multiple initial parameters; A second determining module is configured to determine an abnormal parameter among the plurality of initial parameters, wherein the abnormal parameter is an initial parameter whose parameter value exceeds a corresponding threshold range; a third determining module, configured to determine an initial health index of the casing based on the abnormal parameter; The fourth determination module is configured to modify the initial health index to determine a target health index of the casing, wherein the target health index is used to quantitatively describe the health of the casing.

10. An electronic device, characterized in that: include: One or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the health status of a transformer bushing according to any one of claims 1 to 8.

Images