Method and system for determining full-life-cycle health state of power equipment

Abstract

The invention discloses a method and system for determining the life cycle health state of power equipment, and the method comprises the steps: determining a factor layer and an index layer of a power equipment health state judgment model, and building the power equipment health state judgment model based on the factor layer and the index layer; determining the weight of each specific index in the index layer based on the data of each index in the index layer; performing fuzzy comprehensive evaluation based on the weight of each specific index and the distribution function of the membership function of each index so as to determine the state of each factor in the factor layer; and integrating the states of the factors to determine the overall health state of the power equipment. According to the method, the analytic hierarchy process is adopted to enhance the objectivity of the selected factor and index weight determination, the fuzzy membership function is applied to characterize the mapping relation between each specific index and the health state, and then the evidence synthesis mode is applied, so that various factors influencing the health state of the power equipment can be better fused, and the accurate equipment health state can be obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment health assessment, and more specifically, to a method and system for determining the health status of power equipment throughout its life cycle. Background Art

[0002] The health assessment of power equipment is a complex process. The health assessment of equipment originated from the research on human health assessment. There are similarities between the operating conditions of power equipment and human health. All potential hazards, faults, and other problems have a gradual accumulation process, which is a relatively complex combination of information, with the characteristics of logic and continuity, and is used to determine whether the equipment needs maintenance and can also estimate the remaining life of the equipment.

[0003] Ensuring that power equipment is in good health is the basis for implementing reliability-based maintenance. Currently, accurately and effectively assessing the health status of power equipment throughout its life cycle has become the focus of research. The key to health status assessment lies in determining the health status of the equipment. Although researchers at home and abroad are actively exploring health assessment technologies, the current methods for determining health status mainly focus on qualitative analysis, without more detailed classification of relative advantages and disadvantages, nor a reliable and accurate health status determination system. However, with the development of technology and the in-depth research, it is expected to establish a more perfect power equipment health status determination system in the future to support the implementation of reliability-based maintenance work.

[0004] Therefore, a method for determining the health status of power equipment throughout its life cycle is needed. Summary of the Invention

[0005] The present invention provides a method and system for determining the health status of power equipment throughout its life cycle to solve the problem of how to assess the health status of power equipment.

[0006] To solve the above problems, according to one aspect of the present invention, a method for determining the health status of power equipment throughout its life cycle is provided. The method includes:

[0007] Determine the factor layer and index layer of the power equipment health status judgment model, and establish the power equipment health status judgment model based on the factor layer and index layer;

[0008] Determine the weights of the specific indicators in the index layer based on the data of the indicators in the index layer;

[0009] Perform fuzzy comprehensive evaluation based on the weights of the specific indicators and the distribution functions of the membership functions of the indicators to determine the status of each factor in the factor layer;

[0010] Integrate the status of each factor to determine the overall health status of the power equipment.

[0011] Preferably, determining the weights of the specific indicators in the index layer based on the data of the indicators in the index layer includes:

[0012] Establish a judgment matrix of indicators based on the specific indicators of any one factor in the factor layer;

[0013] Calculate the anti-symmetric matrix of the judgment matrix;

[0014] Calculate the overall standard deviation of the judgment matrix based on the anti-symmetric matrix;

[0015] When the overall standard deviation is less than the preset standard deviation threshold and the judgment matrix is determined to be reasonable, calculate the average matrix of the anti-symmetric matrix;

[0016] Calculate the optimal transfer matrix of the average matrix;

[0017] Determine the weights of the specific indicators based on the optimal transfer matrix.

[0018] Preferably, the method further includes:

[0019] When the overall standard deviation is greater than or equal to the preset standard deviation threshold, adjust the judgment matrix based on a preset value.

[0020] Preferably, performing fuzzy comprehensive evaluation based on the weights of the specific indicators and the distribution functions of the membership functions of the indicators to determine the states of the factors in the factor layer includes:

[0021] Determine the fuzzy intervals corresponding to different health status levels for each specific indicator;

[0022] Establish fuzzy membership functions for each specific indicator in different fuzzy intervals to obtain the distribution functions of the membership functions of the indicators;

[0023] According to the established fuzzy rules, perform fuzzy comprehensive evaluation by combining the distribution functions and the weights of the indicators to determine the states of the factors in the factor layer.

[0024] Preferably, the distribution functions of the membership functions of the indicators include:

[0025]

[0026]

[0027] Among them, f k (x rm ) is the distribution function; s1 to s8 are numerical points, x rm is a certain indicator, μ1(x rm ) to μ5(x rmrespectively represent the membership functions of the index belonging to excellent, good, average, deteriorated, and severe.

[0028] Preferably, the integration of the states of various factors to determine the overall health state of the power equipment includes:

[0029] According to the states of various factors, the membership degrees of various factors belonging to different health state levels are used as the original basic probability assignments in the evidence reasoning decision model;

[0030] Determine the confidence coefficient of each factor, and correct the original basic probability assignment based on the confidence coefficient;

[0031] Based on the corrected basic probability assignment, perform evidence synthesis calculation according to the evidence synthesis algorithm formula in the evidence reasoning method to determine the comprehensive probability assignment of the power equipment health state evaluation level;

[0032] Based on the comprehensive probability assignment, determine the overall health state of the power equipment according to the evidence reasoning decision criterion.

[0033] Preferably, the determination of the confidence coefficient of each factor and the correction of the original basic probability assignment based on the confidence coefficient include:

[0034] m r (H)=α r M r (H)'

[0035] m r (θ)=1 - α r

[0036] Among them, M r (H) is the corrected basic probability assignment of factor f r ; M r (H)' is the original basic probability assignment of factor f r ; α r is the confidence coefficient, r = 1, 2,..., R, R is the number of evaluation factors; m r (θ) is the probability belief assignment of uncertain evidence; θ is the recognition framework of the power equipment health state evaluation level determination result.

[0037] Preferably, the performing of evidence synthesis calculation according to the evidence synthesis algorithm formula in the evidence reasoning method based on the corrected basic probability assignment to determine the comprehensive probability assignment of the power equipment health state evaluation level includes:

[0038] For r evaluation factors, f1, f2, …, fr, considering them as r independent evidences, and the probabilities of them for the proposition Ψ of the power equipment status evaluation level are m1(A1), m2(A2), …, mr(Ar) respectively, then the comprehensive probability assignment m r of the power equipment health status evaluation level is as follows:

[0039]

[0040] where K is the conflict degree of the evidences.

[0041] Preferably, based on the comprehensive probability assignment, according to the evidence reasoning decision criterion, to determine the overall health status of the power equipment, including:

[0042] Define θ as the recognition framework for the determination result of the power equipment health status evaluation level. All possible hypotheses in θ form a set H = {H1, …, H2, H n , …, H N}, and the set H is used to represent the evaluation level of the overall health status of the power equipment. The evidence reasoning decision criterion is:

[0043] m r (H N0 ) - m r (H N1 ) > ε0,

[0044] m r (θ) < ε1,

[0045] m r (H N0 ) > m r (θ),

[0046]

[0047] where ε0 and ε1 are preset thresholds, m r (θ) is the probability belief assignment of the uncertain evidence, m r (H N0 ) is the maximum basic probability assignment of the determination result, m r (H N1 ) is any other basic probability assignment except the maximum basic probability assignment, H N0 is the evaluation level determination result with the maximum basic probability amplitude, that is, the power equipment health status evaluation level determination result, H N1 is the other evaluation level determination results except H N0 .

[0048] According to another aspect of the present invention, there is provided a system for determining the health status of the whole life cycle of a power equipment, and the system includes:

[0049] A model establishment unit, configured to determine a factor layer and an index layer of a power equipment health status judgment model, and establish the power equipment health status judgment model based on the factor layer and the index layer;

[0050] An index weight determination unit, configured to determine the weights of specific indexes in the index layer based on the data of each index in the index layer;

[0051] A factor status determination unit, configured to perform fuzzy comprehensive evaluation based on the weights of specific indexes and the distribution functions of membership functions of each index to determine the status of each factor in the factor layer;

[0052] A health status determination unit, configured to integrate the statuses of each factor to determine the overall health status of the power equipment.

[0053] Preferably, the index weight determination unit determines the weights of specific indexes in the index layer based on the data of each index in the index layer, including:

[0054] Establish a judgment matrix of indexes based on specific indexes of any factor in the factor layer;

[0055] Calculate the anti-symmetric matrix of the judgment matrix;

[0056] Calculate the overall standard deviation of the judgment matrix based on the anti-symmetric matrix;

[0057] When the overall standard deviation is less than a preset standard deviation threshold and it is determined that the judgment matrix is reasonable, calculate the average matrix of the anti-symmetric matrix;

[0058] Calculate the optimal transfer matrix of the average matrix;

[0059] Determine the weights of specific indexes based on the optimal transfer matrix.

[0060] Preferably, the index weight determination unit further includes:

[0061] When the overall standard deviation is greater than or equal to the preset standard deviation threshold, adjust the judgment matrix based on a preset value.

[0062] Preferably, the factor status determination unit performs fuzzy comprehensive evaluation based on the weights of specific indexes and the distribution functions of membership functions of each index to determine the status of each factor in the factor layer, including:

[0063] Determine the fuzzy intervals corresponding to different health status levels of specific indexes;

[0064] Establish the fuzzy membership functions of various specific indicators in different fuzzy intervals to obtain the distribution functions of the membership functions of each indicator;

[0065] According to the established fuzzy rules, combined with the distribution function and the weights of various indicators, perform fuzzy comprehensive evaluation to determine the state of each factor in the factor layer.

[0066] Preferably, the distribution functions of the membership functions of various indicators in the factor state determination unit include:

[0067]

[0068] Among them, f k (x rm ) is the distribution function; s1 to s8 are numerical points, x rm is a certain indicator, and μ1(x rm ) to μ5(x rm ) respectively represent the membership functions of this indicator belonging to excellent, good, general, deteriorated, and severe.

[0069] Preferably, the health state determination unit integrates the states of each factor to determine the overall health state of the power equipment, including:

[0070] According to the state of each factor, use the membership degree of each factor belonging to different health state levels as the original basic probability assignment in the evidence reasoning decision model;

[0071] Determine the confidence coefficient of each factor, and modify the original basic probability assignment based on the confidence coefficient;

[0072] Based on the modified basic probability assignment, perform evidence synthesis calculation according to the evidence synthesis algorithm formula in the evidence reasoning method to determine the comprehensive probability assignment of the power equipment health state evaluation level;

[0073] Based on the comprehensive probability assignment, determine the overall health state of the power equipment according to the evidence reasoning decision criterion.

[0074] Preferably, the health state determination unit determines the confidence coefficient of each factor, and modifies the original basic probability assignment based on the confidence coefficient, including:

[0075] m r (H) = α r M r (H)'

[0076] m r (θ) = 1 - α r

[0077] Among them, M r(H) is factor f r The revised basic probability assignment; M r (H)' is the original basic probability assignment of factor f r ; α r is the confidence coefficient, r = 1, 2, …, R, where R is the number of evaluation factors; m r (θ) is the probability belief assignment of uncertain evidence; θ is the identification framework for the determination result of the health state evaluation level of the power equipment.

[0078] Preferably, the health state determination unit, based on the revised basic probability assignment, performs evidence synthesis calculation according to the evidence synthesis algorithm formula in the evidence reasoning method to determine the comprehensive probability assignment of the health state evaluation level of the power equipment, including:

[0079] For r evaluation factors, f1, f2, …, fr, regarding them as r independent pieces of evidence, and determining that their probabilities for the proposition Ψ of the power equipment state evaluation level are m1(A1), m2(A2), …, mr(Ar) respectively, then the comprehensive probability assignment m r (Ψ) is:

[0080]

[0081] where K is the degree of conflict of the evidence.

[0082] Preferably, the health state determination unit, based on the comprehensive probability assignment, determines the overall health state of the power equipment according to the evidence reasoning decision criterion, including:

[0083] Define θ as the identification framework for the determination result of the health state evaluation level of the power equipment. All possible hypotheses in θ form a set H = {H1, …, H2, H n , …, H N}, and the set H is used to represent the evaluation level of the overall health state of the power equipment. The evidence reasoning decision criterion is:

[0084] m r (H N0 ) - m r (H N1 ) > ε0,

[0085] m r (θ) < ε1,

[0086] m r (H N0 ) > m r (θ),

[0087]

[0088] where ε0 and ε1 are preset thresholds, and m r (θ) is the probability belief assignment of uncertain evidence, and m r (H N0 ) is the maximum basic probability assignment of the judgment result, and m r (H N1 ) is any other basic probability assignment except the maximum basic probability assignment. H N0 is the evaluation level judgment result with the maximum basic probability amplitude, that is, the evaluation level judgment result of the health state of the power equipment. H N1 is the other evaluation level judgment results except H N0 .

[0089] Based on another aspect of the present invention, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods for determining the health state of the power equipment throughout its life cycle are implemented.

[0090] Based on another aspect of the present invention, the present invention provides an electronic device, including:

[0091] the above-mentioned computer-readable storage medium; and

[0092] one or more processors for executing the program in the computer-readable storage medium.

[0093] The present invention provides a method and system for determining the health state of the power equipment throughout its life cycle, including: determining the factor layer and index layer of the power equipment health state judgment model to establish the power equipment health state judgment model based on the factor layer and index layer; determining the weights of the specific indicators in the index layer based on the data of the indicators in the index layer; performing fuzzy comprehensive evaluation based on the weights of the specific indicators and the distribution functions of the membership functions of the indicators to determine the states of the factors in the factor layer; and integrating the states of the factors to determine the overall health state of the power equipment. The method of the present invention uses the analytic hierarchy process to enhance the objectivity of determining the weights of the selected factors and indicators. Without prior experience, the fuzzy membership function is used to characterize the mapping relationship between each specific indicator and the health state, and then the evidence synthesis method is used to make up for the uncertainty problem brought by the fuzzy membership function, which is more conducive to integrating various factors affecting the health state of the power equipment and obtaining an accurate equipment health state. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] By referring to the following drawings, the exemplary embodiments of the present invention can be more fully understood:

[0095] Figure 1It is a flowchart of a method 100 for determining the health state of a power equipment throughout its life cycle according to an embodiment of the present invention;

[0096] Figure 2 It is a schematic diagram of the distribution function of the membership function according to an embodiment of the present invention;

[0097] Figure 3 It is a schematic structural diagram of a system 300 for determining the health state of a power equipment throughout its life cycle according to an embodiment of the present invention. Detailed implementation manners

[0098] Now, exemplary embodiments of the present invention will be introduced with reference to the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to disclose the present invention in detail and completely, and to fully convey the scope of the present invention to those skilled in the art. The terms in the exemplary embodiments shown in the drawings are not limitations on the present invention. In the drawings, the same unit / element is denoted by the same reference numeral.

[0099] Unless otherwise specified, the terms (including scientific and technical terms) used herein have the ordinary meaning understood by those skilled in the art. In addition, it can be understood that the terms defined in the commonly used dictionary should be understood as having a meaning consistent with the context of their related fields, and should not be understood as idealized or overly formal meanings.

[0100] The present invention provides a method for determining the health state of a power equipment throughout its life cycle, constructs a factor layer and an index layer for judging the health state of the power equipment, uses the analytic hierarchy process to determine the weights of various factors and indexes, applies a fuzzy membership function to characterize the mapping relationship between each index and the health state, applies an evidence synthesis method to make up for the uncertainty problem brought by the fuzzy membership function, and through the combination of the above methods, conducts a fusion analysis on quantitative and qualitative factors such as power equipment defects, faults, abnormal working conditions, maintenance records, and test and monitoring data, so as to realize the judgment of the health state of the power equipment.

[0101] Figure 1 It is a flowchart of a method 100 for determining the health state of a power equipment throughout its life cycle according to an embodiment of the present invention. As Figure 1As shown in the figure, the method for determining the health status of power equipment throughout its life cycle provided by the embodiment of the present invention enhances the objectivity of determining the weights of selected factors and indicators by using the analytic hierarchy process. Without prior experience, the fuzzy membership function is used to characterize the mapping relationship between each specific indicator and the health status, and then the evidence synthesis method is applied to make up for the uncertainty problem brought by the fuzzy membership function, which is more conducive to integrating various factors affecting the health status of power equipment and obtaining the accurate health status of the equipment. The method 100 for determining the health status of power equipment throughout its life cycle provided by the embodiment of the present invention starts from step 101. In step 101, the factor layer and the indicator layer of the power equipment health status judgment model are determined to establish the power equipment health status judgment model based on the factor layer and the indicator layer.

[0102] In the present invention, first, it is necessary to establish a power equipment health status judgment model, define the levels of the power equipment health status, and determine the factor layer and the indicator layer of the power equipment health status judgment model.

[0103] Among them, the factor layer includes the characteristic quantities in the planning and design, procurement and manufacturing, installation and commissioning, and operation and maintenance stages; the indicator layer includes the specific indicators in terms of safety, reliability, and environmental protection corresponding to each factor in the factor layer.

[0104] Among them, the indicators under the planning and design factor include the evaluation results of the standardization of design standards, the grid structure, the evaluation results of the rationality of equipment configuration, and the results of environmental impact analysis;

[0105] The indicators under the procurement and manufacturing factor include the implementation of procurement and manufacturing standards, the evaluation results of supplier performance, and the implementation of standards such as equipment noise and radiation;

[0106] The indicators under the installation and commissioning factor include the evaluation results of the safety of construction operations, the evaluation results of the quality of equipment installation and commissioning, and the implementation of measures such as environmental protection, water and soil conservation, and forest protection;

[0107] The indicators under the operation and maintenance factor include the evaluation results of the equipment operation status, the evaluation results of the equipment reliability, and the monitoring and treatment of noise, radiation, etc.

[0108] In the present invention, the health status levels of power equipment include: healthy, sub-healthy, attention, abnormal, and serious.

[0109] In step 102, based on the data of each indicator in the indicator layer, the weights of each specific indicator in the indicator layer are determined.

[0110] Preferably, the determining the weights of each specific indicator in the indicator layer based on the data of each indicator in the indicator layer includes:

[0111] Establish a judgment matrix for the indicators based on each specific indicator of any one factor in the factor layer;

[0112] Calculate the skew-symmetric matrix of the said judgment matrix;

[0113] Calculate the overall standard deviation of the said judgment matrix based on the said skew-symmetric matrix;

[0114] When the said overall standard deviation is less than the preset standard deviation threshold, and it is determined that the said judgment matrix is reasonable, calculate the average matrix of the said skew-symmetric matrix;

[0115] Calculate the optimal transfer matrix of the said average matrix;

[0116] Determine the weights of each specific indicator based on the said optimal transfer matrix.

[0117] Preferably, the said method further includes:

[0118] When the said overall standard deviation is greater than or equal to the preset standard deviation threshold, adjust the said judgment matrix based on a preset value.

[0119] In the present invention, the analytic hierarchy process is applied to determine the weights of each specific indicator in the indicator layer. Specifically, it includes:

[0120] S1021. For each specific indicator belonging to any one factor in the factor layer, establish a judgment matrix for the indicators, including:

[0121]

[0122] where n represents the number of indicators, m represents the number of experts for determining the indicator weights, k represents the kth expert, 0 < k < m, a ij represents the comparison result of the importance between indicator i and indicator j, and satisfies a ij > 0, a ij = 1 / a ji a ii = 1, A (k) is the indicator judgment matrix provided by the kth expert, is the matrix element.

[0123] S1022. Calculate the skew-symmetric matrix of the judgment matrix, including:

[0124]

[0125] where B (k) is the skew-symmetric matrix of the judgment matrix A (k) provided by the kth expert, is the matrix element.

[0126] S1023. When the overall standard deviation is less than the preset standard deviation threshold 1, calculate the standard deviation of the judgment matrix from the skew-symmetric matrix of the judgment matrix, including:

[0127]

[0128] where σ ij is the standard deviation of each matrix element in the index judgment matrices provided by different experts.

[0129] S1024. Calculate the average matrix B of the skew-symmetric matrix, including:

[0130]

[0131] where B is the average matrix of the skew-symmetric matrix, and b ij is the matrix element.

[0132] S1025. Calculate the optimal transfer matrix C of the average matrix, including:

[0133]

[0134] where C is the optimal transfer matrix of the average matrix, and c ij is the matrix element, and l represents the l-th index. S1026. Analyze and obtain the weights of specific indicators, including:

[0135]

[0136] where w j is the weight value of each indicator j; c ij is the matrix element, and n is the number of indicators.

[0137] In the present invention, when the overall standard deviation is greater than or equal to the preset standard deviation threshold 1, it is determined that the judgment matrix is unreasonable, and the judgment matrix is adjusted based on a preset value.

[0138] In step 103, perform fuzzy comprehensive evaluation based on the weights of specific indicators and the distribution functions of the membership functions of indicators to determine the states of various factors in the factor layer.

[0139] Preferably, the performing fuzzy comprehensive evaluation based on the weights of specific indicators and the distribution functions of the membership functions of indicators to determine the states of various factors in the factor layer includes:

[0140] Determine the fuzzy intervals corresponding to different health status levels for specific indicators;

[0141] Establish fuzzy membership functions for specific indicators in different fuzzy intervals to obtain the distribution functions of the membership functions of indicators;

[0142] According to the established fuzzy rules, combined with the distribution function and the weights of various indicators, fuzzy comprehensive evaluation is carried out to determine the states of various factors in the factor layer.

[0143] Preferably, the distribution functions of the membership functions of various indicators include:

[0144]

[0145] Among them, f k (x rm ) is the distribution function; s1 to s8 are numerical points, x rm is a certain indicator, and μ1(x rm ) to μ5(x rm ) respectively represent the membership functions of this indicator belonging to excellent, good, general, deteriorated, and serious.

[0146] In the present invention, the fuzzy comprehensive evaluation method is applied to comprehensively evaluate the states of various specific indicators to determine the states of various factors in the factor layer. Specifically, it includes:

[0147] S1031, determining the fuzzy intervals corresponding to different state levels of various specific indicators;

[0148] S1032, establishing the fuzzy membership functions of various specific indicators at different state levels, that is, under different fuzzy intervals, to obtain the distribution functions of the membership functions of various indicators;

[0149] S1033, according to the established fuzzy rules, combined with the weights of various indicators, performing fuzzy comprehensive evaluation to determine the states of various factors in the factor layer.

[0150] In step S1031, considering the fuzziness of the boundaries between adjacent state levels, the fuzzy interval to which the nth-level state of the mth indicator of a certain factor belongs is [y m,n , y m,n+1 , where y m,n ≤ y m,n+1 (m = 1, 2,..., M, n = 1, 2,..., N - 1), and y m,n and y m,n+1 are respectively the lower and upper bounds of the state fuzzy interval.

[0151] In step S1032, a membership function combining a semi-trapezoid and a semi-ridge shape is adopted:

[0152]

[0153] Among them, taking a certain index as an example, after normalizing the specific value of the index, 8 numerical points from s1 to s8 are selected, and the index values are divided into 9 intervals, where: s1 = 1 / 13, s2 = 3 / 13, s3 = 4 / 13, s4 = 6 / 13, s5 = 7 / 13, s6 = 9 / 13, s7 = 10 / 13, s8 = 12 / 13. In the formula, k represents the k-th numerical point, and x rm represents a certain index, and f k (x rm ) is a function combining a semi-trapezoid and a semi-ridge shape. μ1(x rm ) to μ5(x rm ) respectively represent the membership functions of the index belonging to excellent, good, general, deteriorated, and severe. The distribution functions of the membership functions are as Figure 2 shown.

[0154] In step 104, the states of each factor are integrated to determine the overall health state of the power equipment.

[0155] Preferably, the integration of the states of each factor to determine the overall health state of the power equipment includes:

[0156] According to the states of each factor, the membership degrees of each factor belonging to different health state levels are used as the original basic probability assignments in the evidence reasoning decision model;

[0157] Determine the confidence coefficient of each factor, and correct the original basic probability assignment based on the confidence coefficient;

[0158] Based on the corrected basic probability assignment, perform evidence synthesis calculation according to the evidence synthesis algorithm formula in the evidence reasoning method to determine the comprehensive probability assignment of the power equipment health state evaluation level;

[0159] Based on the comprehensive probability assignment, determine the overall health state of the power equipment according to the evidence reasoning decision criterion.

[0160] Preferably, determining the confidence coefficient of each factor and correcting the original basic probability assignment based on the confidence coefficient includes:

[0161] m r (H) = α r M r (H)'

[0162] m r (θ) = 1 - α r

[0163] Among them, M r (H) is the corrected basic probability assignment of factor f r ; M r(H)' is factor f r of the original basic probability assignment; α r is the confidence coefficient, r = 1, 2, …, R, where R is the number of evaluation factors; m r (θ) is the probability belief assignment of uncertain evidence; θ is the identification framework for the determination result of the health state evaluation level of power equipment.

[0164] Preferably, based on the revised basic probability assignment, evidence combination calculation is performed according to the evidence combination algorithm formula in the evidence reasoning method to determine the comprehensive probability assignment of the health state evaluation level of power equipment, including:

[0165] For r evaluation factors, f1, f2, …, fr, regarding them as r independent pieces of evidence, the probabilities of them for the proposition Ψ of the power equipment state evaluation level are determined as m1(A1), m2(A2), …, mr(Ar) respectively. Then the comprehensive probability assignment m r (Ψ) is:

[0166]

[0167] where K is the degree of conflict of evidence.

[0168] Preferably, based on the comprehensive probability assignment, according to the evidence reasoning decision criterion, the overall health state of power equipment is determined, including:

[0169] Define θ as the identification framework for the determination result of the health state evaluation level of power equipment. All possible hypotheses in θ form a set H = {H1, …, H2, H n , …, H N}. The set H is used to represent the evaluation level of the overall health state of power equipment. The evidence reasoning decision criterion is:

[0170] m r (H N0 ) - m r (H N1 ) > ε0,

[0171] m r (θ) < ε1,

[0172] m r (H N0 ) > m r (θ),

[0173]

[0174] where ε0 and ε1 are preset thresholds, m r (θ) is the probability belief assignment of uncertain evidence, m r(H N0 ) assigns the maximum basic probability to the determination result, m r (H N1 ) is any other basic probability assignment except the maximum basic probability assignment, H N0 is the evaluation level determination result with the maximum basic probability amplitude, that is, the power equipment health status evaluation level determination result, H N1 is the other evaluation level determination results except H N0 .

[0175] In the present invention, after determining the states of various factors, the evidence reasoning method is applied to integrate the states of each factor to determine the overall health state of the power equipment. Specifically, it includes:

[0176] S1041. According to the states of each factor in the factor layer determined by the fuzzy comprehensive evaluation method, the membership degrees of each factor belonging to different health state levels obtained in step S103 are used as the original basic probability assignments in the evidence reasoning decision model.

[0177] S1042. Before performing evidence fusion, determine the confidence coefficient of each factor and correct the original basic probability assignment.

[0178] In the present invention, let M r (H) be the original basic probability assignment of factor f r . Considering that the relative importance of different factors is different, the confidence coefficient α r (r = 1, 2,..., R} is introduced to correct the probability assignment before evidence synthesis

[0179] m r (H) = α r M r (H)

[0180] m r (θ) = 1 - α r

[0181] Among them, m r (H) is the revised basic probability assignment, and m r (θ) is the probability confidence assignment of uncertain evidence. The confidence coefficient α r is measured by the weight value of the factor and determined by the following formula. Suppose the weights of factors {f1,..., f r ,..., f R} are {w1,..., w r ,..., w R}, let w K be the maximum value in {w1,..., w r ,..., w R}, then

[0182]

[0183] Among them, α K is the priority confidence coefficient.

[0184] S1043. According to the evidence combination algorithm formula in the evidence reasoning method, perform evidence combination calculation to determine the comprehensive probability assignment of the health state evaluation level of the power equipment.

[0185] In the present invention, for r evaluation factors, f1, f2, …, fr, considering them as r independent evidences, and determining their probabilities for the proposition Ψ of the power equipment state evaluation level as m1(A1), m2(A2), …, mr(Ar) respectively, then the comprehensive probability assignment m r (Ψ) is:

[0186]

[0187] Among them, K is the conflict degree of the evidences.

[0188] S1044. According to the evidence reasoning decision criterion, determine the judgment result of the health state evaluation level of the power equipment.

[0189] Define θ as the recognition framework of the judgment result of the power equipment health state evaluation level. All possible hypotheses in θ form a set H = {H1, …, H2, H n , …, H N}, and the set H is used to represent the evaluation level of the overall health state of the power equipment. The evidence reasoning decision criterion is:

[0190] m r (H N0 ) - m r (H N1 ) > ε0,

[0191] m r (θ) < ε1,

[0192] m r (H N0 ) > m r (θ),

[0193]

[0194] Among them, ε0 and ε1 are preset thresholds, m r (θ) is the probability belief assignment of the uncertain evidence, m r (H N0 ) is the maximum basic probability assignment of the judgment result, m r (H N1) is any basic probability assignment other than the maximum basic probability assignment, H N0 is the evaluation level determination result with the maximum basic probability amplitude, that is, the evaluation result of the health state of the power equipment, H N1 is other than H N0 of the other evaluation level determination results.

[0195] Compared with the prior art, the method of the present invention has at least the following advantages:

[0196] A method for determining the health state of a power equipment throughout its life cycle regards the determination of the health state of the power equipment as a multi-attribute decision-making problem, measures the health state of the power equipment from the characteristic quantities in the planning and design, procurement and manufacturing, installation and commissioning, and operation and maintenance stages, uses multiple factors for evidence fusion, has a relatively high credibility, and finally obtains a clear and accurate conclusion of the health state, so as to be able to timely grasp the health state of the power equipment. In practical applications, it has very important practical significance for reducing the occurrence probability of equipment accidents and improving the safe operation level of the power grid.

[0197] Further, defects, faults, abnormal operating conditions, maintenance records, and test and monitoring data are selected to measure the health state of the power equipment, which can comprehensively cover various specific indicators in terms of safety, reliability, and environmental protection throughout the life cycle of the power equipment, fully consider the influencing factors of the equipment health state and the parameters that can characterize the health state, and fuse them for the evaluation of the health state.

[0198] Further, the analytic hierarchy process is used to determine the weights of the indicators at the index layer, which can avoid the subjectivity of artificially determining the weights. For the comprehensive evaluation application scenarios of multi-factor and multi-level indicators, the analytic hierarchy process is more suitable for weight assignment of indicators that are not convenient for quantitative analysis such as defects and faults.

[0199] Further, since the functional relationship between the specific indicators in the planning and design, procurement and manufacturing, installation and commissioning, and operation and maintenance stages and the equipment health state has not been established yet, for a certain specific indicator, such as the supplier performance evaluation result, it is more suitable to be represented by a fuzzy membership function to solve the problems of lack of functional relationship and prior experience.

[0200] Further, in the way of evidence synthesis, the D-S evidence theory is applied, which can make up for the uncertainty problem brought by the fuzzy membership function. By performing synthesis calculations on multiple evidence sources (factors), the inference result integrating multi-factor information can be obtained.

[0201] Figure 3 is a schematic structural diagram of a system 300 for determining the health state of a power equipment throughout its life cycle according to an embodiment of the present invention. As Figure 3As shown in the figure, the determination system 300 for the health status of the entire life cycle of a power device provided by the embodiment of the present invention includes: a model establishment unit 301, an index weight determination unit 302, a factor status determination unit 303, and a health status determination unit 304.

[0202] Preferably, the model establishment unit 301 is configured to determine the factor layer and the index layer of the power device health status judgment model, and establish the power device health status judgment model based on the factor layer and the index layer.

[0203] Preferably, the index weight determination unit 302 is configured to determine the weights of the specific indicators in the index layer based on the data of the indicators in the index layer.

[0204] Preferably, the index weight determination unit 302 determines the weights of the specific indicators in the index layer based on the data of the indicators in the index layer, including:

[0205] [[ID=*12]]Establish a judgment matrix of the indicators based on the specific indicators of any one factor in the factor layer;

[0206] [[ID=*15]]Calculate the anti-symmetric matrix of the judgment matrix;

[0207] [[ID=*18]]Calculate the overall standard deviation of the judgment matrix based on the anti-symmetric matrix;

[0208] [[ID=*21]]When the overall standard deviation is less than the preset standard deviation threshold and the judgment matrix is determined to be reasonable, calculate the average matrix of the anti-symmetric matrix;

[0209] [[ID=*24]]Calculate the optimal transfer matrix of the average matrix;

[0210] [[ID=*27]]Determine the weights of the specific indicators based on the optimal transfer matrix.

[0211] Preferably, the index weight determination unit 302 further includes:

[0212] [[ID=*33]]When the overall standard deviation is greater than or equal to the preset standard deviation threshold, adjust the judgment matrix based on a preset value.

[0213] Preferably, the factor status determination unit 303 is configured to perform fuzzy comprehensive evaluation based on the weights of the specific indicators and the distribution functions of the membership functions of the indicators to determine the status of each factor in the factor layer.

[0214] Preferably, the factor status determination unit 303 performs fuzzy comprehensive evaluation based on the weights of the specific indicators and the distribution functions of the membership functions of the indicators to determine the status of each factor in the factor layer, including:

[0215] Determine the fuzzy intervals corresponding to various specific indicators at different health status levels;

[0216] Establish the fuzzy membership functions of various specific indicators under different fuzzy intervals to obtain the distribution functions of the membership functions of each indicator;

[0217] According to the established fuzzy rules, combine the distribution function and the weights of each indicator to conduct a fuzzy comprehensive evaluation to determine the status of each factor in the factor layer.

[0218] Preferably, the distribution functions of the membership functions of each indicator in the factor status determination unit 303 include:

[0219]

[0220] Among them, f k (x rm ) is the distribution function; s1 to s8 are numerical points, x rm is a certain indicator, and μ1(x rm ) to μ5(x rm ) respectively represent the membership functions of the indicator belonging to excellent, good, general, deteriorated, and serious.

[0221] Preferably, the health status determination unit 304 is used to integrate the status of each factor to determine the overall health status of the power equipment.

[0222] Preferably, the health status determination unit 304 integrates the status of each factor to determine the overall health status of the power equipment, including:

[0223] According to the status of each factor, use the membership degrees of each factor belonging to different health status levels as the original basic probability assignments in the evidence reasoning decision model;

[0224] Determine the confidence coefficient of each factor, and correct the original basic probability assignment based on the confidence coefficient;

[0225] Based on the corrected basic probability assignment, perform evidence synthesis calculation according to the evidence synthesis algorithm formula in the evidence reasoning method to determine the comprehensive probability assignment of the power equipment health status evaluation level;

[0226] Based on the comprehensive probability assignment, determine the overall health status of the power equipment according to the evidence reasoning decision criterion.

[0227] Preferably, the health status determination unit 304 determines the confidence coefficient of each factor and corrects the original basic probability assignment based on the confidence coefficient, including:

[0228] m r (H) = αr M r (H)'

[0229] m r (θ) = 1 - α r

[0230] where M r (H) is the revised basic probability assignment for factor f r ; M r (H)' is the original basic probability assignment for factor f r ; α r is the confidence coefficient, r = 1, 2, …, R, where R is the number of evaluation factors; m r (θ) is the probability belief assignment of uncertain evidence; θ is the identification framework for the determination result of the health state evaluation level of the power equipment.

[0231] Preferably, the health state determination unit 304, based on the revised basic probability assignment, performs evidence combination calculation according to the evidence combination algorithm formula in the evidence reasoning method to determine the comprehensive probability assignment of the health state evaluation level of the power equipment, including:

[0232] For r evaluation factors, f1, f2, …, fr, regarding them as r independent evidences, and determining their probabilities for the proposition Ψ of the power equipment state evaluation level as m1(A1), m2(A2), …, mr(Ar), then the comprehensive probability assignment m r (Ψ) is:

[0233]

[0234] where K is the conflict degree of the evidences.

[0235] Preferably, the health state determination unit 304, based on the comprehensive probability assignment, determines the overall health state of the power equipment according to the evidence reasoning decision criterion, including:

[0236] Define θ as the identification framework for the determination result of the health state evaluation level of the power equipment. All possible hypotheses in θ form a set H = {H1, …, H2, H n , …, H N}, and the set H is used to represent the evaluation level of the overall health state of the power equipment. The evidence reasoning decision criterion is:

[0237] m r (H N0 ) - m r (H N1 ) > ε0,

[0238] m r(θ) < ε1,

[0239] m r (H N0 ) > m r (θ),

[0240]

[0241] where ε0 and ε1 are preset thresholds, m r (θ) is the probability belief assignment of uncertain evidence, m r (H N0 ) is the maximum basic probability assignment of the determination result, m r (H N1 ) is any other basic probability assignment except the maximum basic probability assignment, H N0 is the evaluation level determination result with the maximum basic probability amplitude, that is, the evaluation level determination result of the health state of the power equipment, H N1 is the other evaluation level determination results except H N0 outside.

[0242] The determination system 300 of the health state of the power equipment throughout the life cycle in the embodiment of the present invention corresponds to the determination method 100 of the health state of the power equipment throughout the life cycle in another embodiment of the present invention, which will not be elaborated here.

[0243] Based on another aspect of the present invention, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steps of any one of the methods for determining the health state of a power equipment throughout its life cycle.

[0244] Based on another aspect of the present invention, the present invention provides an electronic device, including:

[0245] the above-mentioned computer-readable storage medium; and

[0246] one or more processors for executing the program in the computer-readable storage medium.

[0247] The present invention has been described by referring to a few embodiments. However, as is known to those skilled in the art, other embodiments equivalent to those disclosed above of the present invention equally fall within the scope of the present invention.

[0248] Generally, all terms used in the present invention are interpreted according to their ordinary meanings in the technical field, unless otherwise explicitly defined therein. All references to "a / the [device, component, etc.]" are to be interpreted openly as at least one instance of the device, component, etc., unless otherwise explicitly stated. The steps of any method disclosed herein do not necessarily have to be run in the exact order disclosed, unless explicitly stated.

[0249] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0250] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0251] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0252] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0253] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that it is still possible to modify the specific implementation manners of the present invention or make equivalent replacements. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the protection scope of the present invention.

Claims

1. A method for determining the health state of a power equipment throughout its life cycle, characterized in that, The method includes: Determining the factor layer and index layer of the power equipment health status judgment model, and establishing the power equipment health status judgment model based on the factor layer and index layer; Determining the weights of the specific indicators in the index layer based on the data of the indicators in the index layer; Performing fuzzy comprehensive evaluation based on the weights of the specific indicators and the distribution functions of the membership functions of the indicators to determine the status of each factor in the factor layer; Integrating the status of each factor to determine the overall health status of the power equipment.

2. The method according to claim 1, wherein The determining the weights of the specific indicators in the index layer based on the data of the indicators in the index layer includes: Establishing a judgment matrix of the indicators based on the specific indicators of any one factor in the factor layer; Calculating the anti-symmetric matrix of the judgment matrix; Calculating the overall standard deviation of the judgment matrix based on the anti-symmetric matrix; When the overall standard deviation is less than the preset standard deviation threshold and the judgment matrix is determined to be reasonable, calculating the average matrix of the anti-symmetric matrix; Calculating the optimal transfer matrix of the average matrix; Determining the weights of the specific indicators based on the optimal transfer matrix.

3. The method according to claim 2, characterized in that, The method further includes: When the overall standard deviation is greater than or equal to the preset standard deviation threshold, adjusting the judgment matrix based on a preset value.

4. The method according to claim 1, wherein The performing fuzzy comprehensive evaluation based on the weights of the specific indicators and the distribution functions of the membership functions of the indicators to determine the status of each factor in the factor layer includes: Determining the fuzzy intervals corresponding to different health status levels of the specific indicators; Establishing fuzzy membership functions of the specific indicators under different fuzzy intervals to obtain the distribution functions of the membership functions of the indicators; According to the established fuzzy rules, combining the distribution functions and the weights of the indicators to perform fuzzy comprehensive evaluation to determine the status of each factor in the factor layer.

5. The method according to claim 4, characterized in that, The distribution functions of the membership functions of the indicators include: Among them, f k (x rm ) is the distribution function; s1 to s8 are numerical points, x rm is a certain index, and μ1(x rm ) to μ5(x rm ) respectively represent the membership functions of this index belonging to excellent, good, general, deterioration, and severe.

6. The method according to claim 1, characterized in that, The integrating the status of each factor to determine the overall health status of the power equipment includes: According to the status of each factor, using the membership degrees of each factor belonging to different health status levels as the original basic probability assignments in the evidence reasoning decision model; Determining the confidence coefficient of each factor and correcting the original basic probability assignment based on the confidence coefficient; Based on the corrected basic probability assignment, performing evidence synthesis calculation according to the evidence synthesis algorithm formula in the evidence reasoning method to determine the comprehensive probability assignment of the power equipment health status evaluation level; Based on the comprehensive probability assignment, determining the overall health status of the power equipment according to the evidence reasoning decision criterion.

7. The method according to claim 6, characterized in that, Determining the confidence coefficient of each factor and correcting the original basic probability assignment based on the confidence coefficient includes: m r (H) = α r M r (H)' m r (θ) = 1 - α r Among them, M r (H) is the revised basic probability assignment of factor f r ; M r (H)' is the original basic probability assignment of factor f r ; α r is the confidence coefficient, r = 1, 2, …, R, where R is the number of evaluation factors; m r (θ) is the probability belief assignment of uncertain evidence; θ is the recognition framework for the determination result of the health state evaluation level of power equipment.

8. The method according to claim 6, wherein The performing evidence synthesis calculation according to the evidence synthesis algorithm formula in the evidence reasoning method based on the corrected basic probability assignment to determine the comprehensive probability assignment of the power equipment health status evaluation level includes: For r evaluation factors, f1, f2, …, fr, regarded as r independent pieces of evidence, if the probabilities that they determine the proposition Ψ of the power equipment status evaluation level are m1(A1), m2(A2), …, mr(Ar) respectively, then the combined probability assignment m r (Ψ) is as follows: where K is the conflict degree of the evidence.

9. The method according to claim 6, wherein Based on the comprehensive probability assignment, determining the overall health status of the power equipment according to the evidence reasoning decision criterion includes: Define θ as the recognition framework for the determination result of the health status evaluation level of power equipment. All possible hypotheses in θ form a set H = {H1, …, H2, H n , …, H N}, and the set H is used to represent the evaluation level of the overall health status of power equipment. The evidence reasoning decision criterion is as follows: m r (H N0 ) - m r (H N1 ) > ε0, m r (θ) < ε1, m r (H N0 )>m r (θ), where ε0 and ε1 are preset thresholds, and m r (θ) is the probability belief assignment of uncertain evidence, and m r (H N0 ) is the maximum basic probability assignment of the determination result, and m r (H N1 ) is any other basic probability assignment except the maximum basic probability assignment, and H N0 is the evaluation level determination result with the maximum basic probability amplitude, that is, the evaluation level determination result of the health state of the power equipment, and H N1 is the other evaluation level determination results except H N0 .

10. A system for determining the health state of a power equipment throughout its life cycle, characterized in that, The system includes: A model establishment unit for determining the factor layer and index layer of the power equipment health status judgment model, and establishing the power equipment health status judgment model based on the factor layer and index layer; An index weight determination unit for determining the weights of specific indicators in the index layer based on the data of each indicator in the index layer; A factor status determination unit for performing fuzzy comprehensive evaluation based on the weights of specific indicators and the distribution function of the membership function of each indicator to determine the status of each factor in the factor layer; A health status determination unit for integrating the status of each factor to determine the overall health status of the power equipment.

11. The system according to claim 10, wherein The index weight determination unit determines the weights of specific indicators in the index layer based on the data of each indicator in the index layer, including: Establishing a judgment matrix of indicators based on specific indicators of any factor in the factor layer; Calculating the anti-symmetric matrix of the judgment matrix; Calculating the overall standard deviation of the judgment matrix based on the anti-symmetric matrix; When the overall standard deviation is less than the preset standard deviation threshold and the judgment matrix is determined to be reasonable, calculating the average matrix of the anti-symmetric matrix; Calculating the optimal transfer matrix of the average matrix; Determining the weights of specific indicators based on the optimal transfer matrix.

12. The system according to claim 11, characterized in that, The index weight determination unit further includes: When the overall standard deviation is greater than or equal to the preset standard deviation threshold, adjusting the judgment matrix based on a preset value.

13. The system according to claim 10, wherein The factor status determination unit performs fuzzy comprehensive evaluation based on the weights of specific indicators and the distribution function of the membership function of each indicator to determine the status of each factor in the factor layer, including: Determining the fuzzy intervals corresponding to different health status levels of specific indicators; Establishing the fuzzy membership function of specific indicators under different fuzzy intervals to obtain the distribution function of the membership function of each indicator; According to the established fuzzy rules, combining the distribution function and the weights of each indicator to perform fuzzy comprehensive evaluation to determine the status of each factor in the factor layer.

14. The system according to claim 13, wherein The distribution function of the membership function of each indicator in the factor status determination unit includes: Among them, f k (x rm ) is a distribution function; s1 to s8 are numerical points, x rm is a certain index, and μ1(x rm ) to μ5(x rm ) respectively represent the membership functions of this index belonging to excellent, good, average, deterioration, and severe.

15. The system according to claim 10, wherein The health status determination unit integrates the status of each factor to determine the overall health status of the power equipment, including: According to the status of each factor, using the membership degree of each factor belonging to different health status levels as the original basic probability assignment in the evidence reasoning decision model; Determining the confidence coefficient of each factor and correcting the original basic probability assignment based on the confidence coefficient; Based on the corrected basic probability assignment, performing evidence synthesis calculation according to the evidence synthesis algorithm formula in the evidence reasoning method to determine the comprehensive probability assignment of the power equipment health status evaluation level; Based on the comprehensive probability assignment, determining the overall health status of the power equipment according to the evidence reasoning decision criterion.

16. The system according to claim 6, wherein The health status determination unit determines the confidence coefficient of each factor and corrects the original basic probability assignment based on the confidence coefficient, including: m r (H) = α r M r (H)' m r (θ) = 1 - α r Among them, M r (H) is the revised basic probability assignment of factor f r ; M r (H)' is the original basic probability assignment of factor f r ; α r is the confidence coefficient, r = 1, 2, …, R, where R is the number of evaluation factors; m r (θ) is the probability belief assignment of uncertain evidence; θ is the recognition framework for the determination result of the health state evaluation level of power equipment.

17. The system according to claim 15, wherein The health status determination unit performs evidence combination calculation based on the revised basic probability assignment according to the evidence combination algorithm formula in the evidence reasoning method to determine the comprehensive probability assignment of the health status evaluation level of the power equipment, including: For r evaluation factors, f1, f2, …, fr, regarded as r independent pieces of evidence, if the probabilities of them for the proposition Ψ of the power equipment status evaluation level are m1(A1), m2(A2), …, mr(Ar) respectively, then the combined probability assignment m r (Ψ) is as follows: where K is the conflict degree of the evidence.

18. The system according to claim 15, wherein The health status determination unit determines the overall health status of the power equipment based on the comprehensive probability assignment according to the evidence reasoning decision criterion, including: Define θ as the recognition framework for the determination result of the health status evaluation level of power equipment. All possible hypotheses in θ form a set H = {H1, …, H2, H n , …, H N}, …, H}, and the set H is used to represent the evaluation level of the overall health status of power equipment. The evidential reasoning decision criterion is as follows: m r (H N0 ) - m r (H N1 ) > ε0, m r (θ) < ε1, m r (H N0 )>m r (θ), where ε0 and ε1 are preset thresholds, and m r (θ) is the probability belief assignment of uncertain evidence, and m r (H N0 ) is the maximum basic probability assignment of the judgment result, and m r (H N1 ) is any other basic probability assignment except the maximum basic probability assignment, and H N0 is the evaluation level judgment result with the maximum basic probability amplitude, that is, the evaluation level judgment result of the health state of the power equipment, and H N1 is the other evaluation level judgment results except H N0 .

19. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method according to any one of claims 1-9.

20. An electronic device, characterized in that, Including: The computer-readable storage medium described in claim 19; And One or more processors for executing the program in the computer-readable storage medium.

Images