Residual life reliability evaluation method, device and equipment of magnetically controlled transformer and medium

Abstract

The invention relates to a residual life reliability evaluation method and device of a magnetic control transformer, computer equipment and a computer readable storage medium. The method comprises the steps of obtaining electrical test data, information of gas dissolved in oil, operation and maintenance record information and accessory operation condition information of the magnetic control transformer, and inputting the obtained information into a pre-established transformer operation state evaluation model to obtain an operation state evaluation result for the magnetic control transformer; obtaining main insulation structure state data and FDS measurement data of the magnetically controlled transformer, and inputting the obtained data into a pre-established transformer insulation life evaluation model to obtain an insulation life evaluation result for the magnetically controlled transformer; and inputting the operation state evaluation result and the insulation life evaluation result into a pre-established transformer residual life reliability evaluation model to obtain a residual life reliability evaluation result for the magnetically controlled transformer. By adopting the method, the comprehensiveness of evaluation can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of transformer reliability assessment, and in particular to a method, device, computer equipment and computer-readable storage medium for assessing the remaining life reliability of a magnetically controlled transformer. Background Art

[0002] With the application and development of computer technology in power grid systems, the operation and inspection mode of power equipment has been transformed into condition-based maintenance, that is, formulating maintenance plans by evaluating the health status of magnetic control transformers. The core of condition-based maintenance is to accurately judge the operating reliability of equipment. Therefore, a comprehensive and accurate reliability assessment of magnetic control transformers has important guiding significance for condition-based maintenance.

[0003] However, the reliability assessment results obtained from the current failure rate model of magnetically controlled transformers are not comprehensive enough. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment and computer-readable storage medium for evaluating the remaining life reliability of a magnetic control transformer, which can comprehensively evaluate the remaining life reliability of the magnetic control transformer, in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a method for evaluating the reliability of the remaining life of a magnetically controlled transformer, comprising:

[0006] Obtaining electrical test data, dissolved gas information in oil, operation and maintenance record information, and accessory operation information of the magnetically controlled transformer, and inputting the acquired information into a pre-established transformer operation status assessment model to obtain an operation status assessment result for the magnetically controlled transformer;

[0007] Obtaining main insulation structure state data and FDS measurement data of the magnetic control transformer, inputting the acquired data into a pre-established transformer insulation life assessment model, and obtaining an insulation life assessment result for the magnetic control transformer; the pre-established transformer insulation life assessment model is obtained based on an initial model for the magnetic control transformer, and the initial model is obtained based on an equivalent circuit of the magnetic control transformer;

[0008] The operating status assessment result and the insulation life assessment result are input into a pre-established transformer remaining life reliability assessment model to obtain a remaining life reliability assessment result for the magnetic control transformer; the pre-established transformer remaining life reliability assessment model is obtained based on the initial model.

[0009] In one embodiment, the step of obtaining the pre-established transformer remaining life reliability assessment model includes:

[0010] Obtain multiple initial models with different model parameters as the initial population;

[0011] Iteratively optimizing the initial population using a snake optimization algorithm, taking a failure rate function corresponding to the initial model as a judgment target, and obtaining a target initial model;

[0012] According to the model parameters corresponding to the target initial model and the corresponding failure rate function, the initial transformer remaining life reliability assessment model is configured to obtain the transformer remaining life reliability assessment model.

[0013] In one embodiment, the iterative optimization of the initial population using the snake optimization algorithm, taking the failure rate function corresponding to the initial model as the evaluation target, and obtaining the target initial model includes:

[0014] Determine the failure rate functions corresponding to a plurality of initial models configured with different model parameters;

[0015] Taking the initial models in the initial population as individuals, adjusting the variables of different individuals in the initial population based on the constraint conditions corresponding to the failure rate function to obtain a first adjustment result;

[0016] Determining the function fitness of the plurality of individuals for the failure rate function based on the first adjustment result; wherein the function fitness is used to quantify the performance of the individuals on the corresponding failure rate function;

[0017] Iteratively optimize the multiple individuals based on the fitness of the function to obtain a target individual as a target initial model.

[0018] In one embodiment, the iterative optimization of the plurality of individuals based on the fitness of the function to obtain a target individual includes:

[0019] Screening multiple individuals in the initial population based on the function fitness to obtain an elite population;

[0020] Searching multiple individuals in the initial population based on a failure rate function to obtain a subpopulation;

[0021] Iterative search is performed on the elite population and sub-population, and when the number of iterations is greater than the preset iteration number threshold, the target individuals included in the final population are obtained.

[0022] In one embodiment, the iterative search of the elite population and the sub-population, when the number of iterations is greater than a preset iteration number threshold, obtains the target individuals included in the final population, including:

[0023] Adjusting the variables of different individuals in the elite population and the sub-population based on the constraint conditions corresponding to the failure rate function to obtain a second adjustment result;

[0024] An iterative search is performed on the elite population and the sub-population based on the second adjustment result and the plurality of failure rate functions, and a target individual is obtained when the number of iterations is greater than a preset threshold number of iterations.

[0025] In one embodiment, the screening of multiple individuals in the initial population based on the function fitness to obtain an elite population includes:

[0026] Screening a plurality of individuals in the initial population based on the fitness of the function to obtain a plurality of initial individuals;

[0027] Determine the crowding degree of the multiple initial individuals in the failure rate function space corresponding to the failure rate function; wherein the crowding degree is used to represent the distribution density of the multiple initial individuals in the failure rate function space;

[0028] The multiple initial individuals are screened based on the crowding degree to obtain an elite population.

[0029] In one embodiment, the equivalent circuit of the magnetically controlled transformer includes a power supply, a resistor, an inductor, a first coil, a second coil, a third coil, a fourth coil, a diode, a first thyristor, a second thyristor, a high-voltage coil and a low-voltage coil; wherein,

[0030] The first end of the power supply is connected to the first end of the resistor, the second end of the resistor is connected to the first end of the inductor, the second end of the inductor is connected to the first end of the high-voltage coil, the second end of the high-voltage coil is respectively connected to the first end of the first coil and the first end of the second coil, the second end of the first coil is connected to the first end of the fourth coil, the second end of the second coil is connected to the first end of the third coil, and the second end of the power supply is respectively connected to the second end of the fourth coil and the second end of the third coil; the second end of the first coil is connected to the anode of the diode, and the cathode of the diode is connected to the second end of the second coil; the first end of the first thyristor is connected to the midpoint of the first coil, and the second end of the first thyristor is connected to the first end of the third coil; the first end of the second thyristor is connected to the midpoint of the fourth coil, and the second end of the second thyristor is connected to the second end of the second coil.

[0031] In a second aspect, the present application further provides a device for evaluating the reliability of the remaining life of a magnetically controlled transformer, comprising:

[0032] An operation status evaluation module is used to obtain electrical test data, dissolved gas information in oil, operation and maintenance record information, and accessory operation status information of the magnetically controlled transformer, and input the obtained information into a pre-established transformer operation status evaluation model to obtain an operation status evaluation result for the magnetically controlled transformer;

[0033] An insulation life assessment module, used for acquiring the main insulation structure state data and FDS measurement data of the magnetic control transformer, inputting the acquired data into a pre-established transformer insulation life assessment model, and obtaining an insulation life assessment result for the magnetic control transformer; the pre-established transformer insulation life assessment model is obtained based on an initial model for the magnetic control transformer, and the initial model is obtained based on an equivalent circuit of the magnetic control transformer;

[0034] The remaining life reliability assessment module is used to input the operating status assessment result and the insulation life assessment result into a pre-established transformer remaining life reliability assessment model to obtain a remaining life reliability assessment result for the magnetic control transformer; the pre-established transformer remaining life reliability assessment model is obtained based on the initial model.

[0035] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described in the first aspect when executing the computer program.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect.

[0037] The above-mentioned method, device, computer equipment and computer-readable storage medium for assessing the remaining life reliability of the magnetically controlled transformer obtain the electrical test data, dissolved gas information in oil, operation and maintenance record information and accessory operation status information of the magnetically controlled transformer, and input the obtained information into a pre-established transformer operation status assessment model to obtain an operation status assessment result for the magnetically controlled transformer; obtain the main insulation structure status data and FDS measurement data of the magnetically controlled transformer, input the obtained data into a pre-established transformer insulation life assessment model to obtain an insulation life assessment result for the magnetically controlled transformer; the pre-established transformer insulation life assessment model is obtained based on an initial model for the magnetically controlled transformer, and the initial model is obtained based on the equivalent circuit of the magnetically controlled transformer; the operation status assessment result and the insulation life assessment result are input into a pre-established transformer remaining life reliability assessment model to obtain a remaining life reliability assessment result for the magnetically controlled transformer; the pre-established transformer remaining life reliability assessment model is obtained based on the initial model. In an embodiment of the present application, by acquiring electrical test data, dissolved gas information in oil, operation and maintenance records, etc., and inputting an operation status evaluation model, the current working status of the magnetically controlled transformer can be accurately diagnosed; by monitoring the main insulation structure status data and FDS measurement data, and using the corresponding insulation life evaluation model, the remaining service life of the transformer's insulation material can be accurately evaluated; by combining the operating status and the results of the insulation life evaluation, and inputting a remaining life reliability evaluation model, the reliability and safety of the magnetically controlled transformer can be analyzed as a whole; wherein, the pre-established transformer insulation life evaluation model is obtained based on an initial model for the magnetically controlled transformer, the initial model is obtained based on the equivalent circuit of the magnetically controlled transformer, and the pre-established transformer remaining life reliability evaluation model is obtained based on the initial model, and such a transformer remaining life reliability evaluation model can obtain a more comprehensive remaining life reliability evaluation result. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions 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 related drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 It is a flow chart of a method for evaluating the reliability of the remaining life of a magnetically controlled transformer in one embodiment;

[0040] Figure 2 Schematic diagram of the composition of a transformer status evaluation index system in one embodiment;

[0041] Figure 3A schematic diagram of a flow chart of a fuzzy hierarchical analysis method for transformer operation status in one embodiment;

[0042] Figure 4 A schematic flow chart of the steps of obtaining a transformer remaining life reliability assessment model that is pre-established in one embodiment;

[0043] Figure 5 Schematic diagram of the composition of an equivalent circuit of a magnetron transformer in one embodiment;

[0044] Figure 6 A schematic structural diagram of a magnetic circuit structure diagram of a magnetically controlled transformer in one embodiment;

[0045] Figure 7 It is a structural block diagram of a device for evaluating the reliability of the remaining life of a magnetically controlled transformer in one embodiment;

[0046] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] In an exemplary embodiment, Figure 1 As shown, a method for evaluating the reliability of the remaining life of a magnetically controlled transformer is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0049] Step S202, obtaining electrical test data of the magnetically controlled transformer, information on dissolved gas in oil, operation and maintenance record information, and accessory operation status information, and inputting the obtained information into a pre-established transformer operation status assessment model to obtain an operation status assessment result for the magnetically controlled transformer.

[0050] The pre-established transformer operation status evaluation model may be used to evaluate the operation status of the magnetically controlled transformer according to input data and thereby obtain an evaluation result.

[0051] Among them, the above-mentioned magnetically controlled transformer may refer to a device that uses magnetic field control technology to achieve voltage conversion and power transmission. The functions of this device are not limited to voltage regulation, energy transfer, and enhancing the electromagnetic compatibility of the system. Depending on the application scenario, magnetically controlled transformers can be divided into many types, such as magnetron transformers, magnetically controlled current transformers, magnetically controlled voltage transformers, and magnetically controlled power transformers. The specific type of magnetically controlled transformer used depends on the actual application requirements and is not further defined here.

[0052] Exemplarily, the above step S202 inputs the acquired information into a pre-established transformer operation status assessment model to obtain an operation status assessment result for the magnetically controlled transformer. The specific process may be as follows:

[0053] There are many information characteristics that characterize the operating status of the transformer. These characteristics reflect the operating status of the transformer from different aspects and to different degrees. Therefore, to accurately judge the operating status of the transformer, it is necessary to establish a reasonable and scientific status evaluation index system. According to the "Preventive Test Regulations for Power Equipment" and "Guidelines for Analysis and Judgment of Dissolved Gases in Transformer Oil", the content of characteristic gas in oil (dissolved gas in oil), electrical test data, operation and maintenance records, and accessory operation conditions are used as the transformer status evaluation index system, such as Figure 2 shown.

[0054] The transformer operating status assessment performs statistical analysis on data such as the dissolved gas content in transformer oil, electrical test data, operation and maintenance records, and accessories, so as to accurately calculate the transformer operating status score and judge its health status, providing decision-making for equipment maintenance. Scholars studied the scoring rules and weight calculation of transformers, compared the calculation results with the "Guidelines for Oil-Immersed Transformer Status Evaluation", and established the relationship between health status and operating status scores from a statistical perspective.

[0055] The operating conditions of transformers show complexity and uncertainty. In order to more accurately evaluate their status, a hierarchical processing technique can be used. This method involves analyzing the status of the transformer layer by layer from local to global, and finally calculating a comprehensive score to determine the overall health level of the transformer. Based on this requirement, the fuzzy hierarchical analysis method (such as Figure 3 The comprehensive operating status score of the transformer can be calculated by the following formula:

[0056]

[0057] Among them, W i is the fault type weight related to the fault type in the transformer characteristic quantity; Xi is the fault type status score.

[0058] According to the above formula, combined Figure 3 The process shown can calculate the operating status evaluation result for the magnetic control transformer when the specific data in the transformer status evaluation index system is known; Figure 3 The process shown is to first divide the transformer status evaluation index system into transformer levels, determine the fault type related state quantity and state quantity evaluation matrix r B , calculate the state weight w i , and collect transformer state quantity data at the same time, calculate the unified state score xi of the state quantity, and then calculate the fault type state score Xi based on the above steps, traverse all fault types based on the above steps, determine the state score of each fault type, and then determine the fault type judgment matrix R B , and then calculate the fault type weight W i and transformer status score S (i.e., operating status score); finally, it is necessary to determine whether the obtained transformer status score S is normal. In the case of abnormality, it is necessary to determine the abnormal information and then output the abnormal information and the scoring result; in the normal case, the scoring result (including the operating status score S) is directly output.

[0059] Step S204, obtaining the main insulation structure status data and FDS measurement data of the magnetic control transformer, inputting the obtained data into a pre-established transformer insulation life assessment model, and obtaining an insulation life assessment result for the magnetic control transformer.

[0060] The transformer insulation life assessment model established in advance is obtained based on an initial model for the magnetron transformer, and the initial model is obtained based on an equivalent circuit of the magnetron transformer.

[0061] Among them, the initial model can refer to a basic model framework established based on theoretical analysis and numerical calculation of the equivalent circuit before the formal design of the magnetic control transformer. This model aims to predict the working performance of the magnetic control transformer and provide a scientific basis for the subsequent design optimization process.

[0062] Among them, the main insulation structure status data may refer to multiple characteristic indicators considered in the design process of the magnetic control transformer, such as various insulation performance data and material performance data related to the magnetic control transformer, which can be determined based on the specific performance of the magnetic control transformer and is not specifically limited here.

[0063] The FDS measurement data refers to data obtained by measuring frequency domain dielectric spectroscopy (FDS).

[0064] For example, the state of oil-paper insulation inside the oil-immersed magnetic control transformer directly determines the remaining life of the transformer. The electrical and mechanical properties of the oil-paper gradually decrease under the combined effects of stresses such as electric field, temperature, mechanical vibration and moisture, and moisture and aging degree are important factors affecting the insulation state. The increase in the moisture content of the insulating paperboard will lead to an increase in dielectric loss, while the breakdown voltage will decrease, destroying the oil-paper insulation structure; with the increase in the degree of aging, the insulation paper will also deteriorate, the breakdown voltage and mechanical properties of the insulation system will significantly decrease, and the main insulation system of the magnetic control transformer will completely fail. Therefore, the evaluation of the state of oil-paper insulation of the magnetic control transformer is the key to reliability evaluation. Since the insulation life of the magnetic control transformer is significantly affected by moisture, temperature and the current degree of polymerization, the insulation life of the transformer can be further studied on the basis of obtaining accurate degree of polymerization and moisture content. This example comprehensively considers the moisture content, aging degree and temperature of the magnetic control transformer insulation paperboard and its influence on its life, and establishes a magnetic control transformer insulation life evaluation model that integrates aging, moisture and temperature factors.

[0065] Among them, the cellulose degradation kinetic equation is used to describe the accelerated thermal aging process of oil-paper insulation. By improving the traditional kinetic equation, a fiber polymerization degree cumulative loss kinetic equation is proposed:

[0066]

[0067] Where DP0 represents the initial degree of polymerization, ω DPt represents the degree of polymerization after t time of thermal aging, DPt represents the cumulative loss rate of degree of polymerization, ω*DP represents the ability of degree of polymerization degradation and storage, k DP is the rate of polymerization degradation.

[0068] In the laboratory accelerated thermal aging experiment, the temperature of the insulation paperboard is much higher than the actual operating temperature of the transformer. In order to be consistent with the change law of the insulation performance of the insulation paperboard in actual operation, the time-temperature superposition method is used to extrapolate the high-temperature thermal aging experimental data to the low-temperature environment. Combining the time-temperature superposition method with the above kinetic equation, the temperature translation factor α is obtained. T :

[0069]

[0070] Where, Arrhenius activation energy Ea = 91.4 kJ / mol, gas constant R = 8.314 J / mol / K, T ref is the reference temperature (the lowest test temperature), and T is the hot spot temperature of the transformer.

[0071] In addition to temperature, the effect of moisture on thermal aging must also be considered. Based on the time-temperature superposition, the curve was shifted to obtain the moisture shift factor αM , so that the accelerated thermal aging test data can be extrapolated to the actual moisture content of the insulation paper.

[0072]

[0073] In the formula, the moisture translation factor parameter b = 0.773, the reference moisture content M ref =0.5%, M is the moisture content in the insulation paper. At this point, we can get the time-temperature-moisture translation factor α T，M :

[0074]

[0075] Therefore, at any temperature T and moisture content M, the degree of polymerization decreases from DP0 to DP t The time required t T，M The extrapolation formula, that is, the transformer insulation life assessment model is as follows:

[0076]

[0077] Where, the degree of polymerization degradation storage capacity =0.699, cellulose polymerization degree degradation rate =2.04*10 -3 From the above formula, we can know that given the initial polymerization degree DP0 of the transformer, the water content M and the hot spot temperature T, we can calculate the polymerization degree from DP0 to any polymerization degree DP t To facilitate further research, we simplify the formula to the following: the running time is related to the degree of polymerization, water content and temperature.

[0078]

[0079] Step S206, inputting the operating status assessment result and the insulation life assessment result into a pre-established transformer remaining life reliability assessment model to obtain a remaining life reliability assessment result for the magnetic control transformer.

[0080] Among them, the pre-established transformer remaining life reliability assessment model is obtained based on the initial model.

[0081] For example, after the operation status evaluation result of the magnetically controlled transformer is calculated in step S202, the calculation result is compared with the formulated "Oil-immersed Transformer Status Evaluation Guidelines" to determine the health status of the transformer. Studies have shown that the health status of the transformer is directly related to the probability of its failure. In the "Guidelines for Risk Assessment of Power Transmission and Transformation Equipment", a failure rate model based on the health status of the equipment is provided, and the mathematical expression of the model is:

[0082]

[0083] Among them, K represents the scale parameter; C represents the curvature parameter.

[0084] However, since the transformer operating status is an evaluation result based on a large amount of statistical data, it may not fully reflect the individual differences of each transformer. Therefore, comprehensive consideration of the transformer operating status and main insulation status will help improve the accuracy of transformer reliability evaluation.

[0085] The transformer aging process is often described by Weibull distribution, and its failure rate function is shown as follows:

[0086]

[0087] Among them, β represents the shape parameter and η represents the characteristic life parameter.

[0088] The transformer will be affected by load fluctuations during actual operation, resulting in temperature changes. Considering the impact of temperature on Weibull distribution, the concept of "equivalent operating time" is introduced, and the "hot spot temperature calculation model" is used to convert the actual service time into the benchmark hot spot temperature θ H Based on the Arrhenius reaction principle, a temperature-related transformer aging failure model was established. However, in addition to temperature, moisture and degree of polymerization in oil-paper insulation are also important factors that accelerate transformer aging. Therefore, the transformer insulation life model established only based on temperature is not completely accurate. On this basis, the ontological parameters (i.e., the model parameters corresponding to the initial model) are introduced to obtain a new failure rate formula:

[0089]

[0090] In the model corresponding to the new failure rate formula, in order to further explore the relationship between the operating status and the expected life, the parameter η is first defined as the expected life of the transformer L(S,DP). The exponential function is more flexible and adaptable than the logarithmic function or the quadratic function, and can simultaneously cover the characteristics of linear, concave and convex functions. Therefore, referring to the transformer failure rate model based on the operating status (i.e., the failure rate model based on the health status of the equipment), it is assumed that the following exponential relationship is satisfied between L(S,DP) and S:

[0091]

[0092] Among them, n, m, and K are coefficients in the exponential relationship expression, and the operating status score S is used as the independent variable.

[0093] According to the basic working principle and operation analysis of the transformer, as the operating status decreases, the expected life will also decrease monotonically; when the operating status score drops to 0, the life will also decrease to 0; and when the operating status score reaches 1, that is, the transformer is under ideal working conditions and external environmental conditions, the expected life of the transformer at this time depends only on its insulation aging state, recorded as L0. Assuming the degree of aggregation at the end of the transformer life is 250, the calculated t T,M The value is L0. Therefore, the function L(S,DP) must satisfy the following conditions:

[0094] (1) L decreases monotonically with S.

[0095] (2) When S=0, L=0.

[0096] (3) When S=1, L=L0.

[0097] Substituting the above conditions into the equation, we get:

[0098]

[0099] By bringing the new expected life function L(S,DP|m) into the aging failure model, a new failure rate model function (i.e., transformer remaining life reliability assessment model) can be obtained:

[0100]

[0101] Among them, it is assumed that the parameters β and m remain unchanged with temperature changes, which can be determined by the nonlinear least squares method through historical data; the operating time t (i.e., the remaining insulation life in the insulation life assessment result) and the operating status score S (i.e., the status score S in the operating status assessment result) are independent variables. According to the historical data of different transformers, different β and m parameters can be obtained to avoid the influence of individual differences on the failure rate results. On the other hand, in order to further reduce the influence between individuals, the operating time t is calculated, and the influence of temperature, moisture and DP differences of different transformers during operation on the measurement results is fully considered. The above new failure rate model function can be used to obtain the remaining life reliability assessment results for the magnetic control transformer.

[0102] In the above-mentioned remaining life reliability assessment method of the magnetic control transformer, by obtaining electrical test data, dissolved gas information in oil, operation and maintenance records, etc., and inputting the operation status assessment model, the current working state of the magnetic control transformer can be accurately diagnosed; by monitoring the main insulation structure status data and FDS measurement data, and using the corresponding insulation life assessment model, the remaining service life of the transformer's insulation material can be accurately assessed; by combining the operating status and the results of the insulation life assessment, and inputting the remaining life reliability assessment model, the reliability and safety of the magnetic control transformer can be analyzed as a whole; wherein, the pre-established transformer insulation life assessment model is obtained based on an initial model for the magnetic control transformer, the initial model is obtained based on the equivalent circuit of the magnetic control transformer, and the pre-established transformer remaining life reliability assessment model is obtained based on the initial model. Such a transformer remaining life reliability assessment model can obtain a more comprehensive remaining life reliability assessment result.

[0103] In an exemplary embodiment, Figure 4 As shown, the steps of obtaining the above-mentioned pre-established transformer remaining life reliability assessment model may include:

[0104] Step S302, obtaining a plurality of initial models configured with different model parameters as an initial population.

[0105] Step S304, using the snake optimization algorithm to iteratively optimize the initial population, taking the failure rate function corresponding to the initial model as the evaluation target, and obtaining the target initial model.

[0106] Step S306, configuring the initial transformer remaining life reliability assessment model according to the model parameters corresponding to the target initial model and the corresponding failure rate function, to obtain the transformer remaining life reliability assessment model.

[0107] Among them, the initial model may refer to a model established based on the known characteristics and configuration parameters of the transformer. Model parameters may be variables used to define the characteristics of these initial models, and different initial models correspond to different model parameters. The types of these model parameters may include but are not limited to the input variables of the model, algorithm parameters, environmental settings, etc. The specific types of model parameters will be determined according to the actual needs of the initial model, and are not further limited here. The snake optimization algorithm can be used to iteratively optimize the initial model to minimize the failure rate function. The failure rate function can be a mathematical function used to evaluate the failure probability of the transformer during use. The initial transformer remaining life reliability assessment model can be used to evaluate the reliability of the transformer based on the operating conditions, historical data and failure rate of the equipment. Taking the failure rate function corresponding to the initial model as the evaluation target can mean taking the failure rate function as the evaluation criterion, and adjusting the parameters continuously so that the output of the failure rate function reaches the expected optimal point, for example, making the failure rate output by the failure rate function less than the preset lower limit failure rate, or making the failure rate output by the failure rate function meet the preset failure rate value interval.

[0108] In this embodiment, an initial population consisting of multiple initial models is created, wherein each initial model corresponds to a specific parameter configuration representing the output failure rate of the magnetically controlled transformer. After the initial population is generated, iterative updates are performed to continuously optimize the parameter configuration of the transformer remaining life reliability assessment model corresponding to the failure rate, thereby improving the assessment accuracy of the transformer remaining life reliability assessment model.

[0109] In an exemplary embodiment, the above-mentioned step S304, i.e., using the snake optimization algorithm to iteratively optimize the initial population, taking the failure rate function corresponding to the initial model as the evaluation target, to obtain the target initial model, may specifically include:

[0110] Step S11, determining failure rate functions corresponding to a plurality of initial models configured with different model parameters.

[0111] Step S12: taking the initial model in the initial population as an individual, adjusting the variables of different individuals in the initial population based on the constraint conditions corresponding to the failure rate function to obtain a first adjustment result.

[0112] Step S13, determining the function fitness of the plurality of individuals for the failure rate function based on the first adjustment result; wherein the function fitness is used to quantify the performance of the individuals on the corresponding failure rate function.

[0113] Step S14, iteratively optimize multiple individuals based on the function fitness to obtain a target individual as a target initial model.

[0114] Among them, the individual can refer to an element in the initial population, that is, a specific instance of the initial model, and its parameter configuration represents a possible operating state. Constraints can refer to conditions or rules that limit parameter changes during the optimization process. Function fitness can be an indicator used to quantify the performance of an individual on a failure rate function. Iterative optimization can refer to the process of gradually improving and optimizing individual models through repeated methods. In each iteration, the variables of different individuals, that is, the parameters of the individuals are adjusted according to the previously evaluated function fitness in order to find the optimal solution. The target individual can be the individual that exhibits the best function fitness after iterative optimization, that is, the individual has the best performance characteristics under a given failure rate function, and is finally determined as the target initial model.

[0115] In this embodiment, by accurately evaluating the failure rate function of multiple initial models configured with different model parameters, it can be ensured that the evaluation model is more in line with the actual situation and its prediction accuracy is improved.

[0116] In an exemplary embodiment, the iterative optimization of multiple individuals based on the function fitness performed in the above step S14 to obtain the target individual may include:

[0117] Step S21, screening multiple individuals in the initial population based on the function fitness to obtain an elite population.

[0118] Step S22, searching multiple individuals in the initial population based on the failure rate function to obtain a sub-population.

[0119] Step S23, performing iterative search on the elite population and the sub-population, and obtaining the target individuals included in the final population when the number of iterations is greater than a preset iteration number threshold.

[0120] Among them, the elite population can be a subset formed by screening individuals with the best fitness. These individuals are selected in the hope of retaining excellent features so that they can continue to be optimized in subsequent iterations. The subpopulation can be a set of individuals obtained by searching based on the failure rate function. It may contain individuals that do not perform as well as the elite population, but potential excellent features or parameter configurations are discovered through the search mechanism. Iterative search can be an iterative process that selects, crosses, mutates, and other operations on individuals in the population in order to obtain better individuals. The process will continuously adjust individuals according to fitness.

[0121] In this embodiment, by screening the elite population, individuals with the best performance can be effectively retained, so that the excellent characteristics of these individuals can be further utilized in subsequent iterations to improve the performance of the entire population, thereby improving the selection accuracy of the target individuals included in the final population.

[0122] In an exemplary embodiment, the iterative search of the elite population and the sub-population performed in the above step S23, when the number of iterations is greater than a preset iteration number threshold, obtains the target individuals included in the final population, including:

[0123] Step S31, adjusting the variables of different individuals in the elite population and the sub-population based on the constraint conditions corresponding to the failure rate function to obtain a second adjustment result;

[0124] Step S32, performing iterative search on the elite population and the sub-population based on the second adjustment result and multiple failure rate functions, and obtaining the target individual when the number of iterations is greater than a preset iteration number threshold.

[0125] Among them, the second adjustment result can be the output obtained after adjusting the individual variables in the elite population and sub-population according to the constraints of the failure rate function, which reflects the optimization of individual variables to further improve their performance in terms of failure rate. Iterative search can be a process of gradually improving and optimizing the population in each round of iteration by continuously adjusting individual parameters, evaluating fitness, selecting high-performance individuals, and performing operations such as crossover and mutation. Constraints can refer to a series of rules that limit the adjustment range of model parameters and variables. These conditions are used to ensure that adjustments during the optimization process do not exceed the physical or operational limitations of the equipment, thereby maintaining its reliability and safety.

[0126] In this embodiment, by adjusting the variables of the elites and sub-populations based on the constraints corresponding to the failure rate function, the model can not only meet the theoretical optimal solution, but also adapt to the actual use environment and conditions, thereby improving the application effectiveness of the model.

[0127] In an exemplary embodiment, multiple individuals in the initial population are screened based on the function fitness to obtain an elite population, including:

[0128] Step S41, screening multiple individuals in the initial population based on the function fitness to obtain multiple initial individuals.

[0129] Step S42, determining the crowding degree of the multiple initial individuals in the failure rate function space corresponding to the failure rate function; wherein the crowding degree is used to represent the distribution density of the multiple initial individuals in the failure rate function space.

[0130] Step S43, screening multiple initial individuals based on the crowding degree to obtain an elite population.

[0131] The failure rate function space can be a multidimensional space used to represent the failure rates corresponding to different parameter combinations, where each dimension represents a parameter and a point in the space corresponds to a specific failure rate value. Crowding can be an indicator used to represent the distribution density of multiple initial individuals in the failure rate function space. It measures the number of other individuals around an individual. A high crowding indicates that the individuals in the area are concentrated, while a low crowding indicates relative dispersion.

[0132] In this embodiment, through crowding-based screening, it can be ensured that the elite population not only retains individuals with high fitness, but also avoids concentration in too narrow areas, promotes the diversity of model parameters, and by screening out elite individuals that are well distributed in the failure rate function space, the optimization process can focus on high-potential areas more quickly, thereby improving the overall search efficiency.

[0133] The above steps S302 to S306, as well as specific steps related to the above steps, can be calculated by the following snake optimization algorithm:

[0134] Snake Optimizer (SO) is used to simulate the foraging and reproduction behavior of snakes. Compared with traditional optimization algorithms, it has the remarkable characteristics of novel ideas, fast and efficient. Its mathematical model is as follows:

[0135] (1) Initialization of the snake population.

[0136] The mathematical description of snake population initialization is as follows:

[0137]

[0138] Among them, X i is the position of the i-th snake, rand is a random number between 0 and 1, X max and X min are the upper and lower bounds of the independent variable.

[0139] (2) The snake population was divided into two groups according to sex.

[0140] Assuming that the number of male snakes and female snakes is 50% each, and they are divided into two groups: male group and female group, the population is divided as follows:

[0141]

[0142] Where N is the snake population size, N m is the number of male snakes, N f is the number of female snakes.

[0143] (3) Evaluate the temperature and food quantity of each group of snakes.

[0144] The temperature of each group of snakes can be defined as:

[0145]

[0146] Among them, t is the current iteration number, and Tmax is the maximum iteration number.

[0147] The amount of food for each snake group can be defined by the formula:

[0148]

[0149] Among them, C1 is a constant, and here it is taken as 0.5.

[0150] (4) Exploration stage of the snake group in a state of food shortage.

[0151] If Q < Td (Td is the threshold), the snakes search for food by choosing any random position and update their positions. To simulate the exploration stage, as follows:

[0152]

[0153] Among them, X i,m is the position of the male; X rand,f is the position of a randomly selected female; rand is a random number within the range of [0, 1].

[0154] The ability of the male to find food is shown in the following formula:

[0155]

[0156] Among them, f rand,f is the fitness value of the position X rand,f of a randomly selected female; f i,f is the fitness value of the female position X i,f

[0157] (5) The exploitation stage when the snake group has abundant food is:

[0158]

[0159]

[0160] Among them, (a) The combat mode of the snake group is:

[0161]

[0162]

[0163]

[0164]

[0165] Among them, (b) The mating mode of the snake group is:​

[0166]

[0167]

[0168]

[0169]

[0170]

[0171]

[0172] The above-mentioned snake optimization algorithm can realize the optimization of the evaluation of the magnetic control transformer by outputting the failure rate function and based on the single optimization goal, so as to ensure the accuracy of the remaining life reliability evaluation of the magnetic control transformer.

[0173] In an exemplary embodiment, Figure 5 As shown, the equivalent circuit of the magnetically controlled transformer includes a power supply U, a resistor R, an inductor L, a first coil Q1, a second coil Q2, a third coil Q3, a fourth coil Q4, a diode D, a first thyristor TH1, a second thyristor TH2, a high-voltage coil LH and a low-voltage coil LL; wherein:

[0174] A first end of a power source U is connected to a first end of a resistor R, a second end of the resistor R is connected to a first end of an inductor L, a second end of the inductor L is connected to a first end of a high-voltage coil LH, a second end of the high-voltage coil LH is respectively connected to a first end of a first coil Q1 and a first end of a second coil Q2, a second end of the first coil Q1 is connected to a first end of a fourth coil Q4, a second end of the second coil Q2 is connected to a first end of a third coil Q3, and a second end of the power source U is respectively connected to a second end of the fourth coil Q4 and a second end of the third coil Q3; a second end of the first coil Q1 is connected to an anode of a diode D, a cathode of the diode D is connected to a second end of the second coil Q2; a first end of a first thyristor TH1 is connected to a midpoint of the first coil Q1, a second end of the first thyristor TH1 is connected to a first end of the third coil Q3; a first end of a second thyristor TH2 is connected to a midpoint of the fourth coil Q4, a second end of the second thyristor TH2 is connected to a second end of the second coil Q2. Figure 5 In the figure, r is the load connected to the magnetron transformer.

[0175] In an exemplary embodiment, Figure 6As shown, a magnetic circuit structure diagram of a magnetic control transformer is provided, and the equivalent circuit of the magnetic control transformer can be obtained through the magnetic circuit structure diagram of the magnetic control transformer. In the above magnetic circuit structure diagram, the magnetic control transformer includes 4 core columns, 1 diode, 2 thyristors, a high-voltage coil, a low-voltage coil, a sinusoidal AC voltage Us and a load voltage U2, wherein the 4 core columns include core column 1, core column 2, core column 3 and core column 4, and the 2 thyristors include thyristor TH1 and thyristor TH2. In the above magnetic circuit structure diagram, the magnetic control transformer is composed of a magnetic saturation reactor and a transformer connected together. N / 2 turns of coils are wound around the upper and lower parts of the core column 1 and the core column 2, and the upper coil of the core column 1 has a tap, which is connected to the head end of the lower coil through the thyristor TH1. Similarly, the lower coil of the core column 2 also has a tap, which is connected to the end of the upper coil through the thyristor TH2. The upper and lower coils of the core column 1 and the core column 2 are cross-connected, and a diode D is connected between the upper coils of the core column 1 and the core column 2 to achieve continuous current flow. The core column 1 and the core column 2 and their corresponding coils constitute a part of the magnetic saturation reactor. The core column 3 is wound with N turns of coils on the upper and lower sides to form the transformer part. The upper coil of the core column 3 is a low-voltage coil, and the two ends are connected to the load, so the middle of the two ends is the load voltage. The lower coil is a high-voltage coil, one end of which is connected to the first end of the upper coil of the core column 1 and the core column 2, and the other end is connected to the sinusoidal AC power supply of the power grid, so the middle of the two ends is the sinusoidal AC voltage.

[0176] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0177] Based on the same inventive concept, the embodiment of the present application also provides a device for evaluating the remaining life reliability of a magnetically controlled transformer for implementing the above-mentioned method for evaluating the remaining life reliability of a magnetically controlled transformer. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of the device for evaluating the remaining life reliability of one or more magnetically controlled transformers provided below can refer to the limitations of the method for evaluating the remaining life reliability of a magnetically controlled transformer in the above text, and will not be repeated here.

[0178] In an exemplary embodiment, Figure 7 As shown, a device 900 for evaluating the reliability of the remaining life of a magnetically controlled transformer is provided, comprising: an operating state evaluation module 901, an insulation life evaluation module 902 and a remaining life reliability evaluation module 903, wherein:

[0179] The operation status evaluation module 901 is used to obtain the electrical test data, dissolved gas information in oil, operation and maintenance record information, and accessory operation information of the magnetic control transformer, and input the obtained information into a pre-established transformer operation status evaluation model to obtain the operation status evaluation result for the magnetic control transformer;

[0180] The insulation life evaluation module 902 is used to obtain the main insulation structure state data and FDS measurement data of the magnetic control transformer, and input the obtained data into a pre-established transformer insulation life evaluation model to obtain an insulation life evaluation result for the magnetic control transformer; the pre-established transformer insulation life evaluation model is obtained based on an initial model for the magnetic control transformer, and the initial model is obtained based on an equivalent circuit of the magnetic control transformer;

[0181] The remaining life reliability assessment module 903 is used to input the operating status assessment results and the insulation life assessment results into a pre-established transformer remaining life reliability assessment model to obtain a remaining life reliability assessment result for the magnetically controlled transformer; the pre-established transformer remaining life reliability assessment model is obtained based on the initial model.

[0182] In an exemplary embodiment, the remaining life reliability assessment device of the above-mentioned magnetically controlled transformer also includes a model acquisition module, which is used to obtain multiple initial models configured with different model parameters as an initial population; the above-mentioned initial population is iteratively optimized using a snake optimization algorithm, and the failure rate function corresponding to the above-mentioned initial model is used as an evaluation target to obtain a target initial model; according to the model parameters corresponding to the above-mentioned target initial model and the corresponding failure rate function, the initial transformer remaining life reliability assessment model is configured to obtain the above-mentioned transformer remaining life reliability assessment model.

[0183] In an exemplary embodiment, the above-mentioned model acquisition module is also used to determine the failure rate function corresponding to multiple initial models configured with different model parameters; taking the initial model in the above-mentioned initial population as an individual, adjusting the variables of different individuals in the above-mentioned initial population based on the constraint conditions corresponding to the above-mentioned failure rate function, and obtaining a first adjustment result; determining the function fitness of the above-mentioned multiple individuals for the above-mentioned failure rate function based on the above-mentioned first adjustment result; wherein the above-mentioned function fitness is used to quantify the performance of the above-mentioned individuals on the corresponding failure rate function; and iteratively optimizing the above-mentioned multiple individuals based on the above-mentioned function fitness to obtain a target individual as the target initial model.

[0184] In an exemplary embodiment, the above-mentioned model acquisition module is also used to screen multiple individuals in the above-mentioned initial population based on the fitness of the above-mentioned function to obtain an elite population; search multiple individuals in the above-mentioned initial population based on the failure rate function to obtain a sub-population; iteratively search the elite population and the sub-population, and when the number of iterations is greater than a preset iteration number threshold, obtain the target individual included in the final population.

[0185] In an exemplary embodiment, the above-mentioned model acquisition module is also used to adjust the variables of different individuals in the elite population and the sub-population based on the constraints corresponding to the above-mentioned failure rate function to obtain a second adjustment result; based on the second adjustment result and multiple above-mentioned failure rate functions, the elite population and the sub-population are iteratively searched, and the target individual is obtained when the number of iterations is greater than a preset iteration number threshold.

[0186] In an exemplary embodiment, the above-mentioned model acquisition module is also used to screen multiple individuals in the above-mentioned initial population based on the above-mentioned function fitness to obtain multiple initial individuals; determine the crowding of the multiple initial individuals in the failure rate function space corresponding to the above-mentioned failure rate function; wherein the crowding is used to represent the distribution density of the multiple initial individuals in the failure rate function space; based on the above-mentioned crowding, the above-mentioned multiple initial individuals are screened to obtain an elite population.

[0187] Each module in the above-mentioned device for assessing the reliability of the remaining life of a magnetically controlled transformer can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0188] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8As 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 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 evaluating the reliability of the remaining life of a magnetically controlled transformer is implemented.

[0189] Those skilled in the art will understand that Figure 8 The 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.

[0190] In one embodiment, a computer device is further 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 method embodiments when executing the computer program.

[0191] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0192] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0193] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method 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 memory 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. 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, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0194] 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 application.

[0195] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for evaluating the reliability of the remaining life of a magnetic control transformer, characterized in that: The method comprises: Obtaining electrical test data, dissolved gas information in oil, operation and maintenance record information, and accessory operation information of the magnetically controlled transformer, and inputting the acquired information into a pre-established transformer operation status assessment model to obtain an operation status assessment result for the magnetically controlled transformer; Obtaining main insulation structure state data and FDS measurement data of the magnetic control transformer, inputting the acquired data into a pre-established transformer insulation life assessment model, and obtaining an insulation life assessment result for the magnetic control transformer; the pre-established transformer insulation life assessment model is obtained based on an initial model for the magnetic control transformer, and the initial model is obtained based on an equivalent circuit of the magnetic control transformer; The operating status assessment result and the insulation life assessment result are input into a pre-established transformer remaining life reliability assessment model to obtain a remaining life reliability assessment result for the magnetic control transformer; the pre-established transformer remaining life reliability assessment model is obtained based on the initial model.

2. The method according to claim 1, characterized in that: The step of obtaining the pre-established transformer remaining life reliability assessment model includes: Obtain multiple initial models with different model parameters as the initial population; Iteratively optimizing the initial population using a snake optimization algorithm, taking a failure rate function corresponding to the initial model as a judgment target, and obtaining a target initial model; According to the model parameters corresponding to the target initial model and the corresponding failure rate function, the initial transformer remaining life reliability assessment model is configured to obtain the transformer remaining life reliability assessment model.

3. The method according to claim 2, characterized in that The snake optimization algorithm is used to iteratively optimize the initial population, and the failure rate function corresponding to the initial model is used as the evaluation target to obtain the target initial model, including: Determine the failure rate functions corresponding to a plurality of initial models configured with different model parameters; Taking the initial models in the initial population as individuals, adjusting the variables of different individuals in the initial population based on the constraint conditions corresponding to the failure rate function to obtain a first adjustment result; Determining the function fitness of the plurality of individuals for the failure rate function based on the first adjustment result; wherein the function fitness is used to quantify the performance of the individuals on the corresponding failure rate function; Iteratively optimize the multiple individuals based on the fitness of the function to obtain a target individual as a target initial model.

4. The method according to claim 3, characterized in that The iterative optimization of the plurality of individuals based on the fitness of the function to obtain a target individual includes: Screening multiple individuals in the initial population based on the function fitness to obtain an elite population; Searching multiple individuals in the initial population based on a failure rate function to obtain a subpopulation; Iterative search is performed on the elite population and sub-population, and when the number of iterations is greater than the preset iteration number threshold, the target individuals included in the final population are obtained.

5. The method according to claim 4, characterized in that The iterative search of the elite population and the sub-population, when the number of iterations is greater than a preset iteration number threshold, obtains the target individuals included in the final population, including: Adjusting the variables of different individuals in the elite population and the sub-population based on the constraint conditions corresponding to the failure rate function to obtain a second adjustment result; An iterative search is performed on the elite population and the sub-population based on the second adjustment result and the plurality of failure rate functions, and a target individual is obtained when the number of iterations is greater than a preset threshold number of iterations.

6. The method according to claim 4, characterized in that The step of screening a plurality of individuals in the initial population based on the function fitness to obtain an elite population includes: Screening a plurality of individuals in the initial population based on the fitness of the function to obtain a plurality of initial individuals; Determine the crowding degree of the multiple initial individuals in the failure rate function space corresponding to the failure rate function; wherein the crowding degree is used to represent the distribution density of the multiple initial individuals in the failure rate function space; The multiple initial individuals are screened based on the crowding degree to obtain an elite population.

7. The method according to claim 1, characterized in that The equivalent circuit of the magnetically controlled transformer includes a power supply, a resistor, an inductor, a first coil, a second coil, a third coil, a fourth coil, a diode, a first thyristor, a second thyristor, a high-voltage coil and a low-voltage coil; wherein, The first end of the power supply is connected to the first end of the resistor, the second end of the resistor is connected to the first end of the inductor, the second end of the inductor is connected to the first end of the high-voltage coil, the second end of the high-voltage coil is respectively connected to the first end of the first coil and the first end of the second coil, the second end of the first coil is connected to the first end of the fourth coil, the second end of the second coil is connected to the first end of the third coil, and the second end of the power supply is respectively connected to the second end of the fourth coil and the second end of the third coil; the second end of the first coil is connected to the anode of the diode, and the cathode of the diode is connected to the second end of the second coil; the first end of the first thyristor is connected to the midpoint of the first coil, and the second end of the first thyristor is connected to the first end of the third coil; the first end of the second thyristor is connected to the midpoint of the fourth coil, and the second end of the second thyristor is connected to the second end of the second coil.

8. A device for evaluating the reliability of the remaining life of a magnetically controlled transformer, characterized in that: The device comprises: An operation status evaluation module is used to obtain electrical test data, dissolved gas information in oil, operation and maintenance record information, and accessory operation status information of the magnetically controlled transformer, and input the obtained information into a pre-established transformer operation status evaluation model to obtain an operation status evaluation result for the magnetically controlled transformer; An insulation life assessment module, used for acquiring the main insulation structure state data and FDS measurement data of the magnetic control transformer, inputting the acquired data into a pre-established transformer insulation life assessment model, and obtaining an insulation life assessment result for the magnetic control transformer; the pre-established transformer insulation life assessment model is obtained based on an initial model for the magnetic control transformer, and the initial model is obtained based on an equivalent circuit of the magnetic control transformer; The remaining life reliability assessment module is used to input the operating status assessment result and the insulation life assessment result into a pre-established transformer remaining life reliability assessment model to obtain a remaining life reliability assessment result for the magnetic control transformer; the pre-established transformer remaining life reliability assessment model is obtained based on the initial model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images