Method, device and equipment for predicting residual life of transformer, medium and product

The dynamic membership degree offset method with a penalty operator enhances transformer life prediction accuracy by considering operation time and maintenance, addressing inaccuracies in traditional methods.

CN119090047APending Publication Date: 2024-12-06ECONOMIC TECH RES INST OF STATE GRID HENAN ELECTRIC POWER +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411040819.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Traditional methods for predicting the remaining life of transformers are inaccurate due to ignoring the impact of operation time and transformer maintenance on health index, leading to increased prediction errors.

Method used

A method and device that utilize a dynamic membership degree offset method to calculate the health index of transformers, incorporating a penalty operator and considering the relationship between health index, failure rate, and operation time to accurately predict remaining life.

Benefits of technology

The method provides a more accurate prediction of transformer remaining life by accounting for operation time and maintenance, reducing prediction errors and aligning with actual transformer performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090047A_ABST
    Figure CN119090047A_ABST
Patent Text Reader

Abstract

The invention discloses a transformer residual life prediction method, device and equipment, a medium and a product, and relates to the field of power grid equipment asset management. The method comprises the following steps: obtaining normalized index data and index weight according to a transformer health index evaluation index system; based on the normalized index data, calculating the membership degree of the health level to which the target transformer belongs under each index by adopting a dynamic membership degree offset method; calculating a health index of the target transformer according to the membership degree, the index weight and the penalty operator; according to the health index of the target transformer, obtaining a real-time fault rate of the target transformer by using a relational expression between the health index and the fault rate; and the real-time fault rate of the target transformer is substituted into the relational expression of the fault rate and the operation time, the equivalent service age of the target transformer is obtained, and the difference value between the designed service life of the target transformer and the equivalent service age serves as the residual service life of the target transformer. The residual life of the transformer can be predicted more accurately.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of power grid equipment asset management, and in particular to a transformer remaining life prediction method, device, equipment, medium and product. Background Art

[0002] In the field of power grid, the service life of power equipment assets directly affects the provision of depreciation expenses, affects the calculation of transmission and distribution prices, and further affects the reasonable allocation of all power resources. Transformers are a very important part of power equipment assets, and their role and asset value are higher than other equipment. Therefore, it is necessary to carefully study and determine the remaining life of transformers and clarify the reasonable service life of transformers, which is conducive to the unification of physical management and value management of transformers.

[0003] The traditional calculation method of the remaining life of the transformer is based on the relationship between the health index and time. However, traditional methods such as the transformer health index only rely on relevant data, ignoring the impact of the transformer operation time on some implicit and unmeasurable performance. At the same time, the relationship between the health index and the operation time also ignores the impact of transformer maintenance on transformer performance, reducing the accuracy of the prediction of the remaining life of the transformer based on the health index.

[0004] In summary, there is an urgent need for a method that can accurately calculate the transformer health index and fully explore the intrinsic relationship between the transformer health index and the remaining life, so as to reduce the prediction error of the transformer remaining life based on the health index. Summary of the invention

[0005] The purpose of this application is to provide a transformer remaining life prediction method, device, equipment, medium and product, which can more accurately predict the remaining life of the transformer.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for predicting the remaining life of a transformer, including: determining a relationship between a health index and a failure rate of a target transformer; determining a relationship between a failure rate and an operating time of a target transformer; collecting index data of a target transformer according to a transformer health index evaluation index system, and obtaining normalized index data and index weights; based on the normalized index data, using a dynamic membership degree offset method to calculate the membership of a health level of a target transformer under each indicator in the transformer health index evaluation index system; calculating the health index of a target transformer according to the membership of the health level of the target transformer under each indicator, the index weight and a penalty operator; obtaining a real-time failure rate of a target transformer according to the health index of the target transformer using a relationship between the health index and the failure rate; substituting the real-time failure rate of the target transformer into the relationship between the failure rate and the operating time to obtain an equivalent service age of the target transformer, and taking the difference between the design life of the target transformer and the equivalent service age as the remaining life of the target transformer.

[0008] In a second aspect, the present application provides a transformer remaining life prediction device, including: a first relationship determination module, used to determine the relationship between the health index and the failure rate of the target transformer; a second relationship determination module, used to determine the relationship between the failure rate and the operating time of the target transformer; a collection module, used to collect the index data of the target transformer according to the transformer health index evaluation index system, and obtain the normalized index data and index weight; a membership calculation module, used to calculate the membership of the health level of the target transformer under each indicator in the transformer health index evaluation index system based on the normalized index data using a dynamic membership offset method; a health index calculation module, used to calculate the health index of the target transformer according to the membership of the health level of the target transformer under each indicator, the index weight and the penalty operator; a real-time failure rate acquisition module, used to obtain the real-time failure rate of the target transformer according to the health index of the target transformer and the relationship between the health index and the failure rate; a remaining life acquisition module, used to bring the real-time failure rate of the target transformer into the relationship between the failure rate and the operating time, obtain the equivalent service age of the target transformer, and use the difference between the design life and the equivalent service age of the target transformer as the remaining life of the target transformer.

[0009] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned transformer remaining life prediction method.

[0010] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned transformer remaining life prediction method when executed by a processor.

[0011] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the above-mentioned transformer remaining life prediction method when executed by a processor.

[0012] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0013] The present application provides a method, device, equipment, medium and product for predicting the remaining life of a transformer. The dynamic membership offset method is used to make up for the deficiency of the traditional method that does not consider the influence of the transformer operation time on some implicit and unmeasurable performances. At the same time, a penalty operator that takes into account the exceeding of the index value is introduced to make the membership calculation result of the transformer health status to each health level more in line with the actual situation. In addition, considering the improvement of transformer performance by maintenance, the relationship between health index and operation time is disassembled into the relationship between health index and failure rate and the relationship between failure rate and operation time. Based on the relationship between health index and failure rate and the relationship between failure rate and operation time, the equivalent service age of the target transformer, i.e., the equivalent operation time, is calculated. Finally, the remaining life of the target transformer is calculated by the equivalent service age, so that the prediction of the remaining life of the transformer is more in line with the actual situation, the prediction error is reduced, and the remaining life prediction result is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 This is an application environment diagram of a transformer remaining life prediction method in one embodiment of the present application;

[0016] Figure 2 A schematic diagram of a flow chart of a method for predicting the remaining life of a transformer provided in one embodiment of the present application;

[0017] Figure 3 A schematic diagram of the original membership function corresponding to each health level provided in another embodiment of the present application;

[0018] Figure 4 A schematic diagram of the membership function after correction of each health level provided in another embodiment of the present application;

[0019] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0022] The transformer remaining life prediction method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the index data of the target transformer to the server 104. After the server 104 receives the index data of the target transformer, for the target transformer, the server 104 determines the relationship between the health index and the failure rate of the target transformer; determines the relationship between the failure rate and the running time of the target transformer; collects the index data of the target transformer according to the transformer health index evaluation index system, and obtains the normalized index data and index weight; based on the normalized index data, the dynamic membership degree offset method is used to calculate the membership of the health level of the target transformer under each indicator in the transformer health index evaluation index system; according to the membership of the health level of the target transformer under each indicator, the index weight and the penalty operator, the health index of the target transformer is calculated; according to the health index of the target transformer, the relationship between the health index and the failure rate is used to obtain the real-time failure rate of the target transformer; the real-time failure rate of the target transformer is brought into the relationship between the failure rate and the running time to obtain the equivalent service age of the target transformer, and the difference between the design life of the target transformer and the equivalent service age is used as the remaining life of the target transformer. The server 104 can feedback the remaining life of the target transformer obtained to the terminal 102. In addition, in some embodiments, the transformer remaining life prediction method can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly predict the transformer remaining life based on the index data of the target transformer, or the server 104 can obtain the index data of the target transformer from the data storage system and predict the transformer remaining life based on the index data of the target transformer.

[0023] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0024] In an exemplary embodiment, Figure 2 As shown, a method for predicting the remaining life of a transformer is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate, including the following steps 201 to 207. Among them:

[0025] Step 201: Determine a relationship between a health index and a failure rate of a target transformer.

[0026] Step 202: Determine a relationship between the failure rate and the operating time of the target transformer.

[0027] Step 203: According to the transformer health index evaluation index system, the index data of the target transformer is collected, and the normalized index data and index weight are obtained.

[0028] Step 204: Based on the normalized index data, a dynamic membership degree offset method is used to calculate the membership degree of the health level of the target transformer under each indicator in the transformer health index evaluation index system.

[0029] Step 205: Calculate the health index of the target transformer according to the degree of membership of the health level to which the target transformer belongs under each of the indicators, the indicator weight and the penalty operator.

[0030] Step 206: According to the health index of the target transformer, the real-time failure rate of the target transformer is obtained by using the relationship between the health index and the failure rate.

[0031] Step 207: Substitute the real-time failure rate of the target transformer into the relationship between the failure rate and the operating time to obtain the equivalent service age of the target transformer, and use the difference between the design life of the target transformer and the equivalent service age as the remaining life of the target transformer.

[0032] By implementing the above steps 201 to 207, the present application uses the membership offset method to make up for the deficiency of the traditional method that does not consider the influence of the transformer operation time on some implicit and unmeasurable performances, and at the same time introduces a penalty operator that takes into account the situation where the index value exceeds the standard, so that the membership calculation results of the transformer health status to each health level are more in line with the actual situation. At the same time, considering the improvement of transformer performance by maintenance, the present application disassembles the relationship between health index and operation time, calculates the equivalent service age of the transformer, that is, the equivalent operation time, through the relationship between health index and failure rate and the relationship between failure rate and operation time, and calculates the remaining life of the transformer based on the equivalent service age, so that the remaining life prediction of the transformer is more in line with reality and reduces the prediction error.

[0033] In another exemplary embodiment of the present application, the relationship between the health index and the real-time failure rate is determined according to the historical fault information of the target transformer and the health index calculation result. The relationship between the health index and the failure rate in the above step 201 is:

[0034] λ=Ke C·(100-HI)

[0035] Where λ is the failure rate of the target transformer, K is the proportionality coefficient, C is the curvature coefficient, and HI is the health index of the target transformer.

[0036] In another exemplary embodiment of the present application, the specific implementation method of the above step 202 is: according to the historical fault data of the target transformer, an exponential function is used to fit the curve of the fault rate and the operating time, and the relationship between the fault rate and the operating time is obtained as follows: λ = W × e qt ; In the formula, λ is the failure rate of the target transformer, t is the operating time of the target transformer, W and q are the first parameter and the second parameter.

[0037] In another exemplary embodiment of the present application, the detailed process of the above step 203 is as follows:

[0038] The influencing factors of transformer health index are analyzed, and a transformer health index evaluation index system is constructed. The index data of the target transformer are collected according to the transformer health index evaluation index system. After normalizing the index data, the hierarchical analysis method and entropy weight method are used to obtain the weights of each index.

[0039] In another exemplary embodiment of the present application, the above step 204 can be replaced by the following steps 301 to 303:

[0040] Step 301: Divide the transformer into health levels and construct a membership function for each health level of the transformer.

[0041] Step 302: According to the formula The boundary values ​​of each membership function are offset to obtain the membership function after correction for each health level; where x ij- and x ij+ They represent the two boundary values ​​of the membership function corresponding to the transformer health level j under index i; x' ij- and x' ij+ They represent the two boundary values ​​of the membership function corresponding to the transformer health level j under the offset index i; D represents the degree of transformer degradation, θ is the initial degradation degree of the transformer, β is the threshold ratio of the transformer degradation degree, T n Indicates the service life of the transformer, T d Represents the design life of the transformer. β is the ratio of the degree of degradation of the transformer when it is retired to the initial degree of degradation, which can be obtained through historical data.

[0042] Step 303: Based on the normalized index data, the membership function after correction of each health level is used to obtain the membership of the health level of the target transformer under each indicator in the transformer health index evaluation index system.

[0043] The purpose of the modified membership function is to ensure that the longer the transformer is in operation, the higher its membership of the worse level under the same indicator data. For example, a transformer that has been in operation for 10 years and a transformer that has been in operation for 30 years, even if their indicator data are the same, belong to level 2 before the offset. After the offset, the 30-year-old transformer will belong to level 3, which is a worse level. The purpose of doing this is to fully consider that the increase in the operating life of the transformer may increase the decline of some implicit indicators, which may be unmeasurable.

[0044] In this embodiment, the membership function constructed in step 301 may adopt a semi-trapezoidal and semi-ridge membership function, such as Figure 3 When the health levels of the transformer are normal, caution, abnormal, and severe, the membership functions of each health level are:

[0045]

[0046] Where μ1, μ2, μ3, and μ4 are the membership functions of the four levels of normal, caution, abnormal, and severe, respectively. i is the normalized index data of index i.

[0047] The modified membership function is as follows: Figure 3 shown.

[0048] In another exemplary embodiment of the present application, the above step 205 can be replaced by the following steps 401 to 404:

[0049] Step 401: According to the membership degree of the health level of the target transformer under each indicator and the indicator weight, the formula Calculate the comprehensive membership of the target transformer to each health level; where b j is the comprehensive membership degree of the target transformer belonging to health level j, a i is the weight of index i, r ij is the membership degree of the target transformer belonging to health level j under indicator i.

[0050] Step 402: According to the comprehensive membership of the target transformer to each health level, use the formula Calculate the initial health index of the target transformer; where HI0 is the initial health index of the target transformer, s j is the score corresponding to the target transformer health level j.

[0051] Step 403: Introduce a penalty operator for correcting the initial health index; the formula of the penalty operator is: In the formula, p is the penalty operator, k is the number of indicators in the transformer health index evaluation index system whose index data exceeds the index threshold, and N is the total number of indicators involved in the evaluation. The index threshold can be obtained through the relevant guidelines or standards for transformer operation. When k = 0, the penalty function p = 1, when k = N, the penalty function p = 0. When the number of exceeding indicators is certain, the more the total number of indicators involved in the evaluation N, the smaller the penalty.

[0052] Step 404: Based on the penalty operator and the initial health index of the target transformer, the final health index of the target transformer is obtained using the formula HI=p×HI0; wherein HI is the final health index of the target transformer.

[0053] The following is a process of predicting the remaining life of a 110kV transformer, taking a 110kV transformer as the target transformer:

[0054] S1: According to the historical fault information of the transformer and the calculation results of the health index, the relationship between the health index and the real-time failure rate is determined. The relationship between the transformer health index and the failure rate is:

[0055] λ=Ke C·(100-HI)

[0056] Wherein λ and HI are the failure rate and health index of the transformer; K is the proportionality coefficient; C is the curvature coefficient. In this embodiment, K=0.0085, C=0.0544, and λ=0.0467.

[0057] S2: According to the historical fault information of the transformer, an exponential function is used to fit the fault rate-operating time curve to determine the relationship between the fault rate and the operating time. In this embodiment, the relationship between the fault rate and the operating time is:

[0058] λ(t)=0.0026*e 0.1451t

[0059] S3: Analyze the influencing factors of the transformer health index, and construct a transformer health index evaluation index system (hereinafter referred to as the index). According to the index system, collect transformer related data, normalize the data and calculate the index weight based on the normalized data. Specifically, first select the health index evaluation index of a 110kV transformer, normalize the index data, and use the hierarchical analysis method and entropy weight method to jointly obtain the weight of each index. The specific index, the weight of each index, the measured value, the warning value and the normalized value are shown in Table 1:

[0060] Table 1 Selected indicators and related data

[0061] index Indicator weight Measurements Warning value Normalized value <![CDATA[H2 content / (μL·L -1 )]]> 0.1327 180.33 150.00 0 <![CDATA[C2H2 content / (μL·L -1 )]]> 0.1637 0.14 5 0.972 <![CDATA[Total hydrocarbon content / (μL·L -1 )]]> 0.0941 27.88 150.00 0.8164 <![CDATA[Micro water in oil / (mg·L -1 )]]> 0.0839 15 35 0.7407 Oil dielectric loss / % 0.0453 2.8 4 0.7384 Breakdown voltage / kV 0.0496 56 35 0.8400 Winding DC resistance difference / % 0.0468 0.8 2.00 0.6000 Winding absorption ratio 0.0984 1.8 1.00 0.8000 Winding dielectric loss / % 0.0901 0.21 0.80 0.9077 Capacitive bushing dielectric loss % 0.1327 0.3 0.8 1.0000 Core grounding current / mA 0.1637 1 100.0 0.9900

[0062] S4: Based on the normalized data, the membership of the health level of the transformer under each indicator is calculated by using a dynamic membership offset method, and the transformer health index is calculated by combining the membership value of the health level of the transformer under each indicator and the indicator weight and the penalty operator, as follows:

[0063] S41: The transformer health level is divided into four levels, namely normal, caution, abnormal and severe, and a semi-trapezoidal and semi-ridge membership function is used, such as Figure 3 As shown, its expression is as follows:

[0064]

[0065]

[0066] Among them, μ1, μ2, μ3, and μ4 correspond to the membership functions of the four levels of normal, attention, abnormal, and severe, respectively.

[0067] S42: Using a dynamic offset algorithm to correct the boundary values ​​of each membership function constructed, the specific steps are:

[0068] Let x ij- and x ij+ They represent the two boundary values ​​of the membership function corresponding to the transformer health level j under index i, that is, the intersection of the membership function under index i and the x-axis. The following formula is used to offset the boundary values ​​of each membership function:

[0069]

[0070] Where: x' ij- and x' ij+ Respectively represent the two boundary values ​​after the offset,

[0071]

[0072] Where D represents the degree of transformer degradation, T n Indicates the service life of the transformer, T d represents the design life of the transformer, θ is the initial degradation degree of the transformer, and β is the threshold ratio of the degradation degree of the transformer, that is, the ratio of the degradation degree of the transformer when it is retired to the initial degradation degree, which can be obtained through historical data. In this embodiment, θ=0.5, β=13. For transformers with different operating times, the improved membership function (corrected membership function) is shown in the following figure: Figure 4 As shown, in this embodiment, the transformer operation time is 15 years, so its membership diagram is as follows Figure 4 As shown in part (a) of . Figure 4 Part (a) shows the modified membership function when the transformer is in operation for 15 years. Figure 4 Part (b) shows the modified membership function when the transformer is in operation for 20 years. Figure 4 Part (c) shows the modified membership function when the transformer is in operation for 25 years. Figure 4 Part (d) shows the modified membership function when the transformer is in operation for 30 years. Figure 4 The four membership functions shown in parts (a), (b), (c) and (d) correspond to the health levels of severe, abnormal, caution and normal from left to right.

[0073] S43: Calculate the initial health index of the transformer using the following method:

[0074]

[0075] Where HI0 is the initial health index of the transformer, s j is the score corresponding to the transformer health level j. In this embodiment, the scores corresponding to the four levels of normal, caution, abnormal, and severe are 100, 80, 60, and 40 respectively. j is the comprehensive membership of the transformer to health level j, and its calculation formula is:

[0076]

[0077] In the formula, a i is the weight of indicator i, as shown in Table 1. ij is the membership degree of the transformer belonging to health level j under indicator i.

[0078] S44: A penalty operator is introduced to correct the initial health index. The penalty operator formula is:

[0079]

[0080] Among them, p represents a penalty operator, k is the number of indicators whose index values ​​exceed the index threshold, the index threshold is obtained through transformer operation related guidelines or standards, N represents the total number of indicators involved in the evaluation, in this embodiment, k=1 (H2 content exceeds the standard), N=11.

[0081] S45: Calculate the transformer health index. The calculation method is as follows:

[0082] HI=p×HI0

[0083] In this embodiment, p=0.7677, HI0=89.46, HI=68.68.

[0084] S5: Substitute the calculated transformer health index into the health index-failure rate relationship to obtain the real-time failure rate, and then substitute the real-time failure rate into the failure rate-operating time relationship to obtain its equivalent service age t. Subtract the equivalent service age from the design life of the transformer to obtain the remaining life of the transformer. In this example, the equivalent service age of the transformer is 19.91 years, and the design life of the transformer is 30 years, so the remaining life of the transformer is 30-19.91=10.09 years.

[0085] This application takes into account the internal and external health influencing factors of the transformer throughout its life cycle to establish a transformer health index indicator system. By introducing a dynamic membership function offset in the fuzzy comprehensive evaluation mathematical method, a time-based dynamic transformer health index calculation model is realized. At the same time, a penalty function that takes into account the number of alarm indicators exceeding the standard is introduced as a correction operator to further realize the accurate calculation of the transformer health index. Then, the equivalent service age of the transformer is calculated through the health index-failure rate relationship and the failure rate-operating time relationship, making the transformer remaining life prediction result more accurate.

[0086] Based on the same inventive concept, the embodiment of the present application also provides a transformer remaining life prediction device for implementing the transformer remaining life prediction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more transformer remaining life prediction device embodiments provided below can refer to the limitations of the transformer remaining life prediction method above, and will not be repeated here.

[0087] In an exemplary embodiment, a transformer remaining life prediction device is provided, comprising: a first relationship determination module, a second relationship determination module, a collection module, a membership calculation module, a health index calculation module, a real-time failure rate acquisition module and a remaining life acquisition module.

[0088] The first relationship determination module is used to determine the relationship between the health index and the failure rate of the target transformer. The second relationship determination module is used to determine the relationship between the failure rate and the operating time of the target transformer. The collection module is used to collect the index data of the target transformer according to the transformer health index evaluation index system, and obtain the normalized index data and index weight. The membership calculation module is used to calculate the membership of the health level of the target transformer under each indicator in the transformer health index evaluation index system by using the dynamic membership offset method based on the normalized index data. The health index calculation module is used to calculate the health index of the target transformer according to the membership of the health level of the target transformer under each indicator, the index weight and the penalty operator. The real-time failure rate acquisition module is used to obtain the real-time failure rate of the target transformer according to the health index of the target transformer and the relationship between the health index and the failure rate. The remaining life acquisition module is used to bring the real-time failure rate of the target transformer into the relationship between the failure rate and the operating time, obtain the equivalent service age of the target transformer, and use the difference between the design life and the equivalent service age of the target transformer as the remaining life of the target transformer.

[0089] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the remaining life of the target transformer. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the remaining life of a transformer is implemented.

[0090] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0091] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0092] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0093] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0094] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0095] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0096] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0097] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for predicting the remaining life of a transformer, characterized in that: include: Determine the relationship between the health index and failure rate of the target transformer; Determine the relationship between the failure rate and the operating time of the target transformer; According to the transformer health index evaluation index system, the index data of the target transformer is collected, and the normalized index data and index weights are obtained; Based on the normalized index data, a dynamic membership degree offset method is used to calculate the membership degree of the health level of the target transformer under each indicator in the transformer health index evaluation index system; Calculate the health index of the target transformer according to the degree of membership of the health level of the target transformer under each indicator, the indicator weight and the penalty operator; According to the health index of the target transformer, the real-time failure rate of the target transformer is obtained by using the relationship between the health index and the failure rate; The real-time failure rate of the target transformer is substituted into the relationship between the failure rate and the operating time to obtain the equivalent service age of the target transformer, and the difference between the design life of the target transformer and the equivalent service age is taken as the remaining life of the target transformer; the equivalent service age is the equivalent operating time.

2. The transformer remaining life prediction method according to claim 1, characterized in that: The relationship between the health index and the failure rate is: λ=Ke C·(100-HI) , Where λ is the failure rate of the target transformer, K is the proportionality coefficient, C is the curvature coefficient, and HI is the health index of the target transformer.

3. The transformer remaining life prediction method according to claim 1, characterized in that: Determine the relationship between the failure rate and operating time of the target transformer, including: According to the historical fault data of the target transformer, an exponential function is used to fit the curve of the fault rate and the operating time, and the relationship between the fault rate and the operating time is obtained as follows: λ = W × e qt ; Where λ is the failure rate of the target transformer, t is the operating time of the target transformer, W and q are the first parameter and the second parameter.

4. The transformer remaining life prediction method according to claim 1, characterized in that: Based on the normalized index data, the dynamic membership degree offset method is used to calculate the membership degree of the health level of the target transformer under each indicator in the transformer health index evaluation index system, specifically including: Divide the transformer health level and construct the membership function of each transformer health level; According to the formula The boundary values ​​of each membership function are offset to obtain the membership function after correction for each health level; where x ij- and x ij+ They represent the two boundary values ​​of the membership function corresponding to the transformer health level j under index i; x' ij- and x' ij+ They represent the two boundary values ​​of the membership function corresponding to the transformer health level j under the offset index i; D represents the degree of transformer degradation, θ is the initial degradation degree of the transformer, β is the threshold ratio of the transformer degradation degree, T n Indicates the service life of the transformer, T d Indicates the design life of the transformer; Based on the normalized index data, the membership function after correction of each health level is used to obtain the membership of the health level to which the target transformer belongs under each indicator in the transformer health index evaluation index system.

5. The transformer remaining life prediction method according to claim 4, characterized in that: When the health levels of the transformer are normal, caution, abnormal, and severe, the membership functions of each health level are: Where μ1, μ2, μ3, and μ4 are the membership functions of the four levels of normal, caution, abnormal, and severe, respectively. i is the normalized index data of index i.

6. The transformer remaining life prediction method according to claim 1, characterized in that: According to the membership degree of the health level of the target transformer under each indicator, the indicator weight and the penalty operator, the health index of the target transformer is calculated, specifically including: According to the membership degree of the target transformer health level under each indicator and the indicator weight, the formula is used Calculate the comprehensive membership of the target transformer to each health level; where b j is the comprehensive membership degree of the target transformer belonging to health level j, a i is the weight of index i, r ij is the membership degree of the target transformer belonging to health level j under indicator i; According to the comprehensive membership of the target transformer to each health level, the formula Calculate the initial health index of the target transformer; where HI0 is the initial health index of the target transformer, s j is the score corresponding to the target transformer health level j; A penalty operator is introduced to correct the initial health index; the formula of the penalty operator is: In the formula, p is the penalty operator, k is the number of indicators whose index data exceeds the index threshold in the transformer health index evaluation index system, and N is the total number of indicators involved in the evaluation; According to the penalty operator and the initial health index of the target transformer, the final health index of the target transformer is obtained using the formula HI=p×HI0; wherein HI is the final health index of the target transformer.

7. A transformer remaining life prediction device, characterized in that: include: A first relationship determination module is used to determine a relationship between the health index and the failure rate of the target transformer; A second relationship determination module, used to determine a relationship between the failure rate and the operating time of the target transformer; A collection module is used to collect the index data of the target transformer according to the transformer health index evaluation index system, and obtain the normalized index data and index weight; A membership calculation module, used to calculate the membership of the health level of the target transformer under each indicator in the transformer health index evaluation index system based on the normalized index data by using a dynamic membership offset method; A health index calculation module, used to calculate the health index of the target transformer according to the membership degree of the health level to which the target transformer belongs under each of the indicators, the indicator weight and the penalty operator; A real-time fault rate acquisition module is used to obtain the real-time fault rate of the target transformer according to the health index of the target transformer and the relationship between the health index and the fault rate; The remaining life acquisition module is used to substitute the real-time failure rate of the target transformer into the relationship between the failure rate and the operating time, obtain the equivalent service age of the target transformer, and take the difference between the design life of the target transformer and the equivalent service age as the remaining life of the target transformer.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the transformer remaining life prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the remaining life of a transformer according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting the remaining life of a transformer according to any one of claims 1 to 6 is implemented.