Transformer performance evaluation method and system considering scene applicability based on improved AHP

Abstract

The invention discloses a transformer performance evaluation method and system considering scene applicability based on improved AHP, and the method comprises the steps: firstly constructing a comprehensive performance evaluation index system, then correcting a judgment matrix to improve an analytic hierarchy process, obtaining the comprehensive subjective weight of each index, then considering the variable weight theory of a random scene, calculating an index state vector, and finally obtaining the comprehensive subjective weight of each index. The method comprises the steps of obtaining a cloud centroid model, carrying out clustering again through a standard cutting idea to obtain a final variable weight vector, and finally, carrying out calculation based on the cloud centroid model and the final variable weight vector to obtain a weighted deviation degree so as to carry out comprehensive evaluation on the comprehensive performance of the three-phase oil-immersed transformer. According to the method, the comprehensive performance evaluation index system of the three-phase oil-immersed transformer is constructed, the performance of the transformer is investigated from multiple dimensions, the adaptability in different scenes is improved by means of the standard switching thought and the random scene, and finally the uncertainty of information is effectively processed through the cloud centroid model, so that the evaluation accuracy of the comprehensive performance of the three-phase oil-immersed transformer is improved. Therefore, a more accurate and effective basis is provided for the performance evaluation of the transformer.

Description

Technical Field

[0001] The present invention relates to a transformer performance evaluation method, and belongs to the field of transformer comprehensive performance evaluation, and in particular to a transformer performance evaluation method and system based on improved AHP and considering scenario applicability. Background Art

[0002] The establishment of new power systems and power spot markets has resulted in diversified power loads, variable time and space, increased peak-to-valley differences, and soaring loads. However, constrained by the rated load of power equipment, the planning, scheduling, and operation strategies of conventional systems cannot meet actual requirements, resulting in reduced redundancy, lack of flexibility, and weak investment. Therefore, slowing down system investment, ensuring power system safety, and conducting comprehensive performance evaluations of power lines and transformers have become urgent issues to be addressed.

[0003] In the prior art, the difficulty in evaluating the performance of transformers lies mainly in how to determine the evaluation indicators and the weight distribution of the evaluation indicators. Most conventional means need to determine the weights of various indicators based on expert opinions, and all adopt subjective weighting methods, which rely too much on expert experience. Even if there are means of using group decision-making methods and fuzzy mathematics to calculate the indicator weights, and solve the fuzzy uncertainty problem in constructing a comparison judgment matrix, the importance of each indicator is still determined by expert opinions, and the indicator weight is determined only from a single aspect, so that the weight cannot take into account both subjective and objective aspects at the same time, which leads to low accuracy of the evaluation results. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned defects and problems existing in the prior art and to provide a transformer performance evaluation method and system based on improved AHP with high accuracy and considering scenario applicability.

[0005] To achieve the above objectives, the technical solution of the present invention is: a transformer performance evaluation method based on improved AHP considering scenario applicability, comprising:

[0006] S1. Construct a comprehensive performance evaluation index system for three-phase oil-immersed transformers;

[0007] S2, based on the zero deviation matrix, the judgment matrix is ​​modified to improve the analytic hierarchy process and obtain the comprehensive subjective weights of each indicator in the evaluation index system;

[0008] S3. Based on the variable weight theory considering random scenarios, the indicator state vector of the comprehensive subjective weight is calculated, and the indicator state vector is re-clustered through the canonical cutting idea to obtain the final variable weight vector;

[0009] S4. Based on the cloud centroid model and the final variable weight vector, the weighted deviation degree is calculated to comprehensively evaluate the comprehensive performance of the three-phase oil-immersed transformer.

[0010] The step S2 specifically includes:

[0011] S21. Determine the importance of each indicator in the comprehensive performance evaluation index system of three-phase oil-immersed transformers through expert scoring and 1-9 scale method, and construct the judgment matrix A, A=[a ij ] n×n ;

[0012] The expression of the judgment matrix is ​​as follows:

[0013]

[0014] Among them: a ij It is the scale value between indicators;

[0015] S22. Calculate the consistency index CI, which is expressed as follows:

[0016]

[0017] Where: max is the maximum eigenvalue of the judgment matrix A, n is the order of the judgment matrix;

[0018] S23, find the average random consistency index RI and calculate the consistency ratio CR, the expression of which is as follows:

[0019]

[0020] If CR < 0.1, proceed to step S29; if CR ≥ 0.1, proceed to step S24 to modify the judgment matrix;

[0021] S24, the judgment matrix is ​​expressed as:

[0022]

[0023] W=[W ij ]=[w i / w j ],w=(w1...w i ... n ) T ; D = [d ij ];

[0024] Where: A is the judgment matrix, W is the maximum eigenvector of the judgment matrix A, D is the deviation matrix, is the symbol of the Hadamard product;

[0025] When A satisfies the hierarchical analysis method as a consistency matrix, all d ij =1 and λ max (D) = λ max (A) = n; all d ij =1 is called the zero deviation matrix, denoted as DI;

[0026] S25, let the judgment matrix Consistency Ratio Standard CR * =0.1, the number of iterations k=0, and the constant γ is a positive number less than 1 but close to 1;

[0027] S26, calculate the judgment matrix A after the kth iteration (k) The maximum eigenvalue λ max (A (k) ), where the maximum eigenvalue vector w (k) With the priority vector W (k) as follows:

[0028]

[0029] And according to Calculate the deviation matrix D after the kth iteration (k) ;

[0030] S27. Calculate the consistency ratio CR after the kth iteration (k) , and CR (k) With CR * Make comparisons;

[0031] If CR (k) >CR * , then proceed to step S28; if CR (k) ≤CR * , then the output is the judgment matrix A that meets the consistency requirements (k) , the iteration ends;

[0032] S28, Order Correct the judgment matrix; the corrected deviation matrix is ​​as follows:

[0033]

[0034] Then, step S22 is performed until a judgment matrix that meets the consistency requirement is obtained;

[0035] S29, based on the judgment matrix A′=[a′ ij ], use the geometric mean method to calculate the comprehensive indicator weights of each indicator, and construct the initial weight matrix based on the comprehensive indicator weights;

[0036] The expression of the comprehensive index weight is as follows:

[0037]

[0038] Where: i is the comprehensive index weight, a kj is the element in the kth row and jth column of the judgment matrix.

[0039] The step S3 specifically includes:

[0040] S31. The initial weight matrix obtained by the improved analytic hierarchy process is W = {w1, w2, ...w n}, the indicator data is X = {x1, x2, ...x n};

[0041] S32, normalize the indicator information of the indicator data to obtain the normalized indicator vector Y={y1, y2…y n};

[0042] The positive indicators are as follows:

[0043]

[0044] The negative indicators are as follows:

[0045]

[0046] Where: x i is the i-th indicator data, y i is the i-th indicator data after normalization;

[0047] S33, the variable weight balance function combining the incentive factor and the penalty factor is calculated to obtain the indicator state vector U i (Y); the expression of the indicator state vector is as follows:

[0048]

[0049] Among them: β is the incentive factor, γ is the penalty factor, C is the passing factor, and k is the adjustment factor;

[0050] S34, based on the initial weight matrix W and the indicator state vector U i (Y), calculate the variable weight vector G i ; The variable weight vector G i The expression is as follows:

[0051]

[0052] S35, calculate variable weight vector G iThe difference vector between the initial weight matrix W and the absolute value of each data of the difference vector is obtained to obtain the absolute difference vector V;

[0053] S36, the absolute difference vector V is regarded as a graph, and based on minimizing the Ncut function, the indexes with relatively drastic weight changes and other indexes are partitioned; the expression of the partition is as follows:

[0054]

[0055]

[0056] Where: A and B are two subgraphs of the partition, and the nodes in the graph are represented by the absolute difference of the index; W u，v is the similarity between nodes u and v; u, v, and p are nodes of graphs A, B, and V respectively; partition A is the indicator with relatively drastic weight changes, and partition B is other indicators;

[0057] S37, for the partition A of the index whose weight changes are relatively drastic, after correcting its corresponding index state vector, proceed to step S34 to obtain the final variable weight vector;

[0058] The modified expression is as follows:

[0059]

[0060] Among them: U i ′ is the correction vector of the index with relatively drastic weight changes, U i A , W i A is the variable weight and constant weight of the index of the i-th index in partition A, λ B It is the volatility index of other indicators in partition B.

[0061] The step S4 specifically includes:

[0062] S41. Determine the standard cloud of the cloud centroid model. The expression of the digital characteristics of the standard cloud is as follows:

[0063]

[0064] Among them: Ex i Expectations for the cloud, En i is the cloud entropy, C i，max is the maximum value of the evaluation level corresponding to the score value interval, C i，min is the minimum value of the scoring interval corresponding to the evaluation level;

[0065] S42. The ideal state of the comprehensive performance of the three-phase oil-immersed transformer is divided into a positive ideal state and a negative ideal state, and the centroid position vector is defined. and the cloud centroid vector are all in a positive ideal state; and define the center of mass position vector and the cloud centroid vector All are in negative ideal state;

[0066] in:

[0067] T + =L + ·G i ; T - =L - ·G i ;

[0068]

[0069] In the above formula: x + is a positive indicator, x - is a negative indicator, N is the number of positive indicators, Ex (i) It is the standard cloud of the secondary indicators in the evaluation indicator system;

[0070] S43, normalizing the cloud centroid vector; the normalized expression is as follows:

[0071]

[0072] Where: T i p is the normalized cloud centroid vector value;

[0073] S44, based on the normalized cloud centroid vector value T of each secondary indicator i p With a variable weight vector G i , and obtain the weighted deviation degree θ; the expression of the weighted deviation degree θ is as follows:

[0074]

[0075] S45. Using the weighted deviation θ as a score value for the comprehensive performance of the three-phase oil-immersed transformer, and matching the score value with a preset evaluation level to obtain a comprehensive performance evaluation of the three-phase oil-immersed transformer.

[0076] The comprehensive performance evaluation index system of the three-phase oil-immersed transformer includes:

[0077] First-level indicators: operational reliability, electrical test indicators, oil test information;

[0078] Secondary indicators: hydrogen content, acetylene content, total hydrocarbon content, methane content, core grounding current, winding DC resistance, winding dielectric loss, winding polarization index, oil breakdown voltage, trace water in oil, oil dielectric loss, and furfural in oil.

[0079] A transformer performance evaluation system based on improved AHP and considering scenario applicability, the system comprising:

[0080] Evaluation index system construction module, used to construct a comprehensive performance evaluation index system for three-phase oil-immersed transformers;

[0081] The comprehensive subjective weight acquisition module is used to modify the judgment matrix based on the zero deviation matrix to improve the hierarchical analysis method and obtain the comprehensive subjective weight of each indicator in the evaluation indicator system;

[0082] The variable weight vector acquisition module is used to calculate the indicator state vector of the comprehensive subjective weight based on the variable weight theory considering random scenarios, and re-cluster the indicator state vector through the canonical cutting idea to obtain the final variable weight vector;

[0083] The comprehensive evaluation module is used to calculate the weighted deviation degree based on the cloud centroid model and the final variable weight vector to comprehensively evaluate the comprehensive performance of the three-phase oil-immersed transformer.

[0084] The comprehensive subjective weight acquisition module is used to obtain the comprehensive subjective weight according to the following steps:

[0085] S21. Determine the importance of each indicator in the comprehensive performance evaluation index system of three-phase oil-immersed transformers through expert scoring and 1-9 scale method, and construct a judgment matrix A, A = [a ij ] n×n ;

[0086] The expression of the judgment matrix is ​​as follows:

[0087]

[0088] Among them: a ij It is the scale value between indicators;

[0089] S22. Calculate the consistency index CI, which is expressed as follows:

[0090]

[0091] Where: max is the maximum eigenvalue of the judgment matrix A, n is the order of the judgment matrix;

[0092] S23, find the average random consistency index RI and calculate the consistency ratio CR, the expression of which is as follows:

[0093]

[0094] If CR < 0.1, proceed to step S29; if CR ≥ 0.1, proceed to step S24 to modify the judgment matrix;

[0095] S24, the judgment matrix is ​​expressed as:

[0096]

[0097] W=[W ij ]=[w i / w j ],w=(w1...w i ... n ) T ; D = [d ij ];

[0098] Where: A is the judgment matrix, W is the maximum eigenvector of the judgment matrix A, D is the deviation matrix, is the symbol of the Hadamard product;

[0099] When A satisfies the hierarchical analysis method as a consistency matrix, all d ij =1 and λ max (D) = λ max (A) = n; all d ij =1 is called the zero deviation matrix, denoted as DI;

[0100] S25, let the judgment matrix Consistency Ratio Standard CR * =0.1, the number of iterations k=0, and the constant γ is a positive number less than 1 but close to 1;

[0101] S26, calculate the judgment matrix A after the kth iteration (k) The maximum eigenvalue λ max (A (k) ), where the maximum eigenvalue vector w (k) With the priority vector W (k) as follows:

[0102]

[0103] And according to Calculate the deviation matrix D after the kth iteration (k) ;

[0104] S27. Calculate the consistency ratio CR after the kth iteration (k) , and CR (k) With CR * Make comparisons;

[0105] If CR (k) >CR *, then proceed to step S28; if CR (k) ≤CR * , then the output is the judgment matrix A that meets the consistency requirements (k) , the iteration ends;

[0106] S28, Order Correct the judgment matrix; the corrected deviation matrix is ​​as follows:

[0107]

[0108] Then, step S22 is performed until a judgment matrix that meets the consistency requirement is obtained;

[0109] S29, based on the judgment matrix A′=[a′ ij ], and the geometric mean method is used to calculate the comprehensive index weight of each index; the expression of the comprehensive index weight is as follows:

[0110]

[0111] Where: i is the comprehensive index weight, a kj is the element in the kth row and jth column of the judgment matrix.

[0112] The variable weight vector acquisition module is used to obtain the variable weight vector according to the following steps:

[0113] S31. The initial weight matrix obtained by the improved analytic hierarchy process is W = {w1, w2, ...w m}, the indicator data is X = {x1, x2, ...x n};

[0114] S32, normalize the indicator information of the indicator data to obtain the normalized indicator vector Y={y1, y2…y n};

[0115] The positive indicators are as follows:

[0116]

[0117] The negative indicators are as follows:

[0118]

[0119] Where: x i is the i-th indicator data, y i is the i-th indicator data after normalization;

[0120] S33, the variable weight balance function combining the incentive factor and the penalty factor is calculated to obtain the indicator state vector U i(Y); the expression of the indicator state vector is as follows:

[0121]

[0122] Among them: β is the incentive factor, γ is the penalty factor, C is the passing factor, and k is the adjustment factor;

[0123] S34, based on the initial weight matrix W and the indicator state vector U i (Y), calculate the variable weight vector G i ; The variable weight vector G i The expression is as follows:

[0124]

[0125] S35, calculate variable weight vector G i The difference vector between the initial weight matrix W and the absolute value of each data of the difference vector is obtained to obtain the absolute difference vector V;

[0126] S36, the absolute difference vector V is regarded as a graph, and based on minimizing the Ncut function, the indexes with relatively drastic weight changes and other indexes are partitioned; the expression of the partition is as follows:

[0127]

[0128]

[0129] Where: A and B are two subgraphs of the partition, and the nodes in the graph are represented by the absolute difference of the index; W u，v is the similarity between nodes u and v; u, v, and p are nodes of graphs A, B, and V respectively; partition A is the indicator with relatively drastic weight changes, and partition B is other indicators;

[0130] S37, for the partition A of the index whose weight changes are relatively drastic, after correcting its corresponding index state vector, proceed to step S34 to obtain the final variable weight vector;

[0131] The modified expression is as follows:

[0132]

[0133] Among them: U i ′ is the correction vector of the index with relatively drastic weight changes, U i A , W i A is the variable weight and constant weight of the index of the i-th index in partition A, λ B It is the volatility index of other indicators in partition B.

[0134] The comprehensive evaluation module is used to obtain a comprehensive evaluation according to the following steps:

[0135] S41. Determine the standard cloud of the cloud centroid model. The expression of the digital characteristics of the standard cloud is as follows:

[0136]

[0137] Among them: Ex i Expectations for the cloud, En i is the cloud entropy, C i，max is the maximum value of the evaluation level corresponding to the score value interval, C i，min is the minimum value of the scoring interval corresponding to the evaluation level;

[0138] S42. The ideal state of the comprehensive performance of the three-phase oil-immersed transformer is divided into a positive ideal state and a negative ideal state, and the centroid position vector is defined. and the cloud centroid vector are all in a positive ideal state; and define the center of mass position vector and the cloud centroid vector All are in negative ideal state;

[0139] in:

[0140] T+=L+·G i ; T-=L-·G i ;

[0141]

[0142] In the above formula: x + is a positive indicator, x - is a negative indicator, N is the number of positive indicators, Ex (i) It is the standard cloud of the secondary indicators in the evaluation indicator system;

[0143] S43, normalizing the cloud centroid vector; the normalized expression is as follows:

[0144]

[0145] Where: T i p is the normalized cloud centroid vector value;

[0146] S44, based on the normalized cloud centroid vector value T of each secondary indicator i p With a variable weight vector G i , and obtain the weighted deviation degree θ; the expression of the weighted deviation degree θ is as follows:

[0147]

[0148] S45. Using the weighted deviation θ as a score value for the comprehensive performance of the three-phase oil-immersed transformer, and matching the score value with a preset evaluation level to obtain a comprehensive performance evaluation of the three-phase oil-immersed transformer.

[0149] A transformer performance evaluation device based on improved AHP and considering scenario applicability, the device comprising a processor 5 and a memory 6;

[0150] The processor 6 is used to store the computer program code 61 and transmit the computer program code 61 to the processor 5;

[0151] The processor 5 is used to execute the above-mentioned transformer performance evaluation method based on improved AHP and considering scenario applicability according to the instructions in the computer program code 61.

[0152] Compared with the prior art, the present invention has the following beneficial effects:

[0153] The present invention discloses a transformer performance evaluation method and system based on improved AHP considering scenario applicability. The method first constructs a comprehensive performance evaluation index system for a three-phase oil-immersed transformer, then corrects a judgment matrix based on a zero deviation matrix to improve the analytic hierarchy process, and obtains the comprehensive subjective weights of various indicators in the evaluation index system. Then, the variable weight theory of random scenarios is considered to calculate the indicator state vector, and re-clustering is performed through the canonical cut idea to obtain the final variable weight vector. Finally, based on a cloud centroid model and the final variable weight vector, a weighted deviation degree is calculated to comprehensively evaluate the comprehensive performance of the three-phase oil-immersed transformer. In the application of the present design, a relatively comprehensive comprehensive performance evaluation index system for a three-phase oil-immersed transformer is constructed to examine the transformer performance from multiple dimensions, and with the help of the canonical cut idea and random scenarios, the adaptability under different scenarios is improved. Finally, the uncertainty of information is effectively processed through the cloud centroid model, thereby providing a more accurate and effective basis for the performance evaluation of the transformer. BRIEF DESCRIPTION OF THE DRAWINGS

[0154] Figure 1 It is a flow chart of the method steps of the present invention.

[0155] Figure 2 It is a flow chart of the transformer performance evaluation method in Example 1 of the present invention.

[0156] Figure 3 It is a schematic diagram of the evaluation index system in Example 1 of the present invention.

[0157] Figure 4 It is the average random consistency index table in Example 1 of the present invention.

[0158] Figure 5This is a comparative analysis table of evaluation results of different evaluation models in Example 1 of the present invention.

[0159] Figure 6 It is a schematic diagram of the system structure of the present invention.

[0160] Figure 7 It is a schematic diagram of the device structure of the present invention.

[0161] In the figure: evaluation index system construction module 1, comprehensive subjective weight acquisition module 2, variable weight vector acquisition module 3, comprehensive evaluation module 4, processor 5, memory 6, computer program code 61. DETAILED DESCRIPTION

[0162] The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0163] Embodiment 1:

[0164] See also Figure 1 , a transformer performance evaluation method considering scenario applicability based on improved AHP, including:

[0165] S1. Construct a comprehensive performance evaluation index system for three-phase oil-immersed transformers;

[0166] Furthermore, an evaluation index system consisting of 3 primary indicators and 12 secondary indicators was constructed in this proposal;

[0167] See also Figure 3 Among them, three first-level indicators include operation reliability, electrical test indicators and oil test information to jointly reflect the comprehensive performance of three-phase oil-immersed transformers; 12 second-level indicators are subordinate to the first-level indicators, including hydrogen content, acetylene content, total hydrocarbon content, methane content, core grounding current, winding DC resistance, winding dielectric loss, winding polarization index, oil breakdown voltage, micro-water in oil, oil dielectric loss, and aldehyde in oil.

[0168] Operation reliability is mainly reflected by monitoring the status evaluation indicators obtained by the monitoring device when the oil-immersed transformer is not powered off to reflect the real-time status of the transformer. The main status evaluation indicators are the hydrogen content, acetylene content, total hydrocarbon content and methane content in the oil.

[0169] Hydrogen content: When the inside of the oil-immersed transformer is damp, the water decomposes into a large amount of hydrogen under the action of high temperature and high pressure. Therefore, the hydrogen content mainly reflects the moisture condition or insulation status of the oil-immersed transformer during operation.

[0170] Acetylene content: The oil-immersed transformer itself and new oil will not produce acetylene, but the process is not perfect when the oil-immersed transformer oil is injected into the transformer tank; there are leaks in the sealed test tank and defects in the transformer test process, which will lead to discharge accompanied by the production of acetylene. Therefore, the acetylene content mainly reflects the safety performance of the oil-immersed transformer during operation.

[0171] Total hydrocarbon content: The generation of total hydrocarbons is related to the thermal decomposition, oxidation or degradation of the insulating oil of the oil-immersed transformer at high temperature. The total hydrocarbon content can reflect the impact of the thermal load on the insulating oil during the operation of the oil-immersed transformer and the aging level of the insulating oil.

[0172] Methane content: Methane can be produced by arc discharge, thermal decomposition or oxidation reaction of insulating oil at high temperature. The methane content level of the insulation system during the operation of oil-immersed transformers.

[0173] The electrical experimental indicators mainly include four test items: core grounding current, winding DC resistance, winding dielectric loss and winding polarization index.

[0174] Core grounding current: When the core grounding current is too large, there will be a large circulating current inside the equipment, which may cause the core to heat up and affect the operation of the equipment. Therefore, timely and accurate judgment of whether there is multi-point grounding in the core is of great significance to ensure the safe operation of the power transformer.

[0175] Winding DC resistance: Winding DC resistance is used to test the welding quality of transformer windings and determine whether there are abnormal phenomena such as broken strands and short circuits between winding layers and turns. It reflects the longitudinal insulation stability of the windings and the current loop connection status in the evaluation of oil-immersed transformers.

[0176] Winding dielectric loss: The winding dielectric loss factor in the oil-immersed transformer evaluation mainly reflects whether the oil-immersed transformer is damp, has oil aging and failure, has a penetrating discharge channel, and has severe local damage.

[0177] Winding polarization index: In the evaluation of oil-immersed transformers, the winding polarization index mainly reflects whether the insulation of the oil-immersed transformer winding is damp, aged, and the main insulation level.

[0178] The oiling experiment information is mainly used to judge the insulation condition and physical and chemical properties of the oil in the oil-immersed transformer. As the internal insulating medium, the transformer oil is the main factor to ensure the insulation state between windings, between windings and iron cores, and between windings and shells; the present invention selects oil breakdown voltage, micro-water in oil, oil dielectric loss and furfural in oil to judge the degree of deterioration of the insulating oil performance of the oil-immersed transformer.

[0179] Oil breakdown voltage: The oil breakdown voltage test of power transformers is mainly to determine the ability of the equipment to withstand voltage; when the quality of oil-immersed transformer oil deteriorates, its ability to withstand voltage will weaken. Therefore, the size of the oil breakdown voltage can comprehensively reflect the insulation performance of the oil-immersed transformer oil.

[0180] Water in oil: To ensure that the insulation performance of transformer oil meets the requirements of stable operation, the oil should not contain water. When the water content in the oil exceeds a certain limit, the insulating oil's withstand voltage capability will decrease, the dielectric loss will increase, and other oil quality deterioration problems will occur, which may threaten the stable operation of the oil-immersed transformer.

[0181] Oil dielectric loss: It can reflect the degree of oil deterioration and contamination, and is an important indicator affecting transformer oil performance.

[0182] Furfural in oil: When exposed to external electric fields, mechanical stress, etc., the cellulose chains of solid insulating materials break to produce urfural that dissolves in transformer oil. Therefore, the concentration of urfural in oil-immersed transformer oil can reveal the state of the transformer insulation system.

[0183] S2, based on the zero deviation matrix, the judgment matrix is ​​modified to improve the analytic hierarchy process and obtain the comprehensive subjective weights of each indicator in the evaluation index system;

[0184] See also Figure 2 The present invention proposes a heuristic algorithm, which can automatically generate a consistent matrix from the original inconsistent judgment matrix, and can avoid the need for experts to re-score due to inconsistent judgment matrices. The main steps of improving AHP to calculate the subjective weights of various indicators are as follows:

[0185] S21. Determine the importance of each first-level indicator and each second-level indicator under each first-level indicator through expert scoring and 1-9 scale method. n , then construct the judgment matrix A, A=[a ij ] n×n ;

[0186] The expression of the judgment matrix is ​​as follows:

[0187]

[0188] Among them: a ij is the scale value between indicators, and

[0189] S22. Calculate the consistency index CI, which is expressed as follows:

[0190]

[0191] Where: max is the maximum eigenvalue of the judgment matrix A, n is the order of the judgment matrix;

[0192] S23, find the average random consistency index RI and calculate the consistency ratio CR; the consistency index RI corresponds to the order of the judgment matrix, and RI can be found by searching the average random consistency index table; the average random consistency index table can be found in Figure 4 .

[0193] The expression of the consistency ratio CR is as follows:

[0194]

[0195] If CR < 0.1, proceed to step S29; if CR ≥ 0.1, proceed to step S24 to modify the judgment matrix;

[0196] S24, the judgment matrix is ​​expressed as:

[0197]

[0198] W=[W ij ]=[w i / w j ],w=(w1...w i ... n ) T ; D = [d ij ];

[0199] Where: A is the judgment matrix, W is the maximum eigenvector of the judgment matrix A, D is the deviation matrix, is the symbol of the Hadamard product;

[0200] When A satisfies the hierarchical analysis method as a consistency matrix, all d ij =1 and λ max (D) = λ max (A) = n; otherwise there exists d ij ≠1 and λ max (D) = λ max (A)>n; all d ij =1 is called the zero deviation matrix, denoted as DI;

[0201] Then, the consistency ratio is improved by modifying the deviation matrix. The main steps are as follows:

[0202] S25, Initialization parameters: Let the judgment matrix Consistency Ratio Standard CR * =0.1, the number of iterations k=0, and the constant γ is a positive number less than 1 but close to 1;

[0203] S26, variable calculation: calculate the judgment matrix A after the kth iteration (k) The maximum eigenvalue λ max (A (k) ), where the maximum eigenvalue vector w (k) With the priority vector W (k) as follows:

[0204]

[0205] And according to Calculate the deviation matrix D after the kth iteration (k) ;

[0206] S27, judge the consistency of the matrix: calculate the consistency ratio CR after the kth iteration (k) , and CR (k) With CR * Make comparisons;

[0207] If CR (k) >CR * , then proceed to step S28; if CR (k) ≤CR * , then the output is the judgment matrix A that meets the consistency requirements (k) , the iteration ends;

[0208] S28. Modify the judgment matrix: Correct the judgment matrix; the corrected deviation matrix is ​​as follows:

[0209]

[0210] Then, step S22 is performed until a judgment matrix that meets the consistency requirement is obtained;

[0211] S29, based on the judgment matrix A′=[a′ ij ], and the geometric mean method is used to calculate the comprehensive index weight of each index; the expression of the comprehensive index weight is as follows:

[0212]

[0213] Where: i is the comprehensive index weight, a kj is the element in the kth row and jth column of the judgment matrix.

[0214] S3. Based on the variable weight theory considering random scenarios, the indicator state vector of the comprehensive subjective weight is calculated, and the indicator state vector is re-clustered through the canonical cutting idea to reduce the drastic change of the weight change and obtain the final variable weight vector;

[0215] Normalized Cut is an algorithm framework for image segmentation and clustering. It finds the optimal segmentation by minimizing the ratio of inter-class and intra-class similarity. The core of this idea is to transform the clustering problem into an optimization problem by finding a partition (cut) to maximize the ratio of intra-class similarity to inter-class similarity.

[0216] Furthermore, considering that the adaptability of three-phase oil-immersed transformers is different in different scenarios, a variable weight theory considering random scenarios is proposed, and the steps are as follows:

[0217] S31. The initial weight matrix obtained by the improved analytic hierarchy process is W = {w1, w2, ...w n}, the indicator data is X = {x1, x2, ...x n};

[0218] S32, normalize the indicator information of the indicator data to obtain the normalized indicator vector Y={y1, y2…y n};

[0219] The positive and negative indicators are as follows:

[0220]

[0221] Where: x i is the i-th indicator data, y i is the i-th indicator data after normalization;

[0222] S33, the variable weight balance function combining the incentive factor and the penalty factor is calculated to obtain the indicator state vector U i (Y); the expression of the indicator state vector is as follows:

[0223]

[0224] Wherein: β is the incentive factor, γ is the penalty factor, C is the pass factor, and k is the adjustment factor; they all satisfy α, β, γ, C∈[0,1]. Without loss of generality, in this embodiment, α=0.2, β=0.6, γ=0.9, and C=0.2 are set.

[0225] S34, based on the initial weight matrix W and the indicator state vector U i (Y), calculate the variable weight vector G i ; The variable weight vector G i The expression is as follows:

[0226]

[0227] S35, calculate variable weight vector Gi The difference vector between the initial weight matrix W and the absolute value of each data of the difference vector is obtained to obtain the absolute difference vector V;

[0228] S36, the absolute difference vector V is regarded as a graph, and based on minimizing the Ncut function, the indexes with relatively drastic weight changes and other indexes are partitioned; the expression of the partition is as follows:

[0229]

[0230]

[0231] Where: A and B are two subgraphs of the partition, and the nodes in the graph are represented by the absolute difference of the index; W u，v is the similarity between nodes u and v; u, v, and p are nodes of graphs A, B, and V respectively; partition A is the indicator with relatively drastic weight changes, and partition B is other indicators;

[0232] S37, for the partition A of the index whose weight changes are relatively drastic, after correcting its corresponding index state vector, proceed to step S34 to obtain the final variable weight vector;

[0233] The modified expression is as follows:

[0234]

[0235] Among them: U i ′ is the correction vector of the index with relatively drastic weight changes, U i A , W i A is the variable weight and constant weight of the index of the i-th index in partition A, λ B It is the volatility index of other indicators in partition B.

[0236] S4. Based on the cloud centroid model and the final variable weight vector, the weighted deviation degree is calculated to comprehensively evaluate the comprehensive performance of the three-phase oil-immersed transformer.

[0237] Furthermore, the cloud centroid model is used in this technical solution for comprehensive evaluation. The specific steps are as follows:

[0238] S41. Determine the standard cloud of the cloud centroid model. The expression of the digital characteristics of the standard cloud is as follows:

[0239]

[0240] Among them: Ex i Expectations for the cloud, En i is the cloud entropy, C i，maxis the maximum value of the evaluation level corresponding to the score value interval, C i，min is the minimum value of the scoring interval corresponding to the evaluation level;

[0241] S42. The ideal state of the comprehensive performance of the three-phase oil-immersed transformer is divided into a positive ideal state and a negative ideal state, and the centroid position vector is defined. and the cloud centroid vector are all in a positive ideal state; and define the center of mass position vector and the cloud centroid vector All are in negative ideal state;

[0242] in:

[0243] T+=L+·G i ; T-=L-·G i ;

[0244]

[0245] In the above formula: x + is a positive indicator, x - is a negative indicator, N is the number of positive indicators, Ex (i) It is the standard cloud of the secondary indicators in the evaluation indicator system;

[0246] S43, normalizing the cloud centroid vector; the normalized expression is as follows:

[0247]

[0248] Where: T i p is the normalized cloud centroid vector value;

[0249] S44, based on the normalized cloud centroid vector value T of each secondary indicator i p With a variable weight vector G i , and obtain the weighted deviation degree θ; the expression of the weighted deviation degree θ is as follows:

[0250]

[0251] S45. Using the weighted deviation θ as a score value for the comprehensive performance of the three-phase oil-immersed transformer, and matching the score value with a preset evaluation level to obtain a comprehensive performance evaluation of the three-phase oil-immersed transformer.

[0252] In this technical solution, the quality level of oil-immersed transformers is divided into level I (0.75≤θ<1), level II (0.5≤θ<0.75), level III (0.25≤θ<0.5) and level IV (0≤θ≤0.25) from high to low according to the scoring results. The preset evaluation levels are {I, II, III, IV}; where: I is the highest level, II is a high level, III is a medium level, and IV is a low level;

[0253] In this example, the accuracy of the evaluation method of this solution is compared with other existing methods. Figure 5 The evaluation method of this scheme has the highest accuracy, reaching 86.2%. Compared with the entropy weight method, fuzzy comprehensive evaluation method, and grey correlation method, the evaluation accuracy is increased by 13.7%, 8% and 15.9% respectively. It can be seen from the figure that the method proposed in this scheme effectively improves the accuracy of the comprehensive performance of the three-phase oil-immersed transformer.

[0254] Embodiment 2:

[0255] See also Figure 6 , a transformer performance evaluation system considering scenario applicability based on improved AHP, the system comprising:

[0256] Evaluation index system construction module 1 is used to construct a comprehensive performance evaluation index system for three-phase oil-immersed transformers;

[0257] Furthermore, the evaluation index system constructed by the evaluation index system construction module 1 includes:

[0258] First-level indicators: operational reliability, electrical test indicators, oil test information;

[0259] Secondary indicators: hydrogen content, acetylene content, total hydrocarbon content, methane content, core grounding current, winding DC resistance, winding dielectric loss, winding polarization index, oil breakdown voltage, trace water in oil, oil dielectric loss, and furfural in oil.

[0260] Comprehensive subjective weight acquisition module 2 is used to modify the judgment matrix based on the zero deviation matrix to improve the hierarchical analysis method and obtain the comprehensive subjective weight of each indicator in the evaluation indicator system;

[0261] Furthermore, the comprehensive subjective weight acquisition module 2 is used to obtain the comprehensive subjective weight according to the following steps:

[0262] S21. Determine the importance of each indicator in the comprehensive performance evaluation index system of three-phase oil-immersed transformers through expert scoring and 1-9 scale method, and construct a judgment matrix A, A = [a ij ] n×n ;

[0263] The expression of the judgment matrix is ​​as follows:

[0264]

[0265] Among them: a ij It is the scale value between indicators;

[0266] S22. Calculate the consistency index CI, which is expressed as follows:

[0267]

[0268] Where: max is the maximum eigenvalue of the judgment matrix A, n is the order of the judgment matrix;

[0269] S23, find the average random consistency index RI and calculate the consistency ratio CR, the expression of which is as follows:

[0270]

[0271] If CR < 0.1, proceed to step S29; if CR ≥ 0.1, proceed to step S24 to modify the judgment matrix;

[0272] S24, the judgment matrix is ​​expressed as:

[0273]

[0274] W=[W ij ]=[w i / w j ],w=(w1...w i ... n ) T ; D = [d ij ];

[0275] Where: A is the judgment matrix, W is the maximum eigenvector of the judgment matrix A, D is the deviation matrix, and ○ is the symbol of the Hadamard product;

[0276] When A satisfies the hierarchical analysis method as a consistency matrix, all d ij =1 and λ max (D) = λ max (A) = n; all d ij =1 is called the zero deviation matrix, denoted as DI;

[0277] S25, let the judgment matrix Consistency Ratio Standard CR * =0.1, the number of iterations k=0, and the constant γ is a positive number less than 1 but close to 1;

[0278] S26, calculate the judgment matrix A after the kth iteration (k) The maximum eigenvalue λ max (A (k) ), where the maximum eigenvalue vector w (k) With the priority vector W (k) as follows:

[0279]

[0280] And according to Calculate the deviation matrix D after the kth iteration (k) ;

[0281] S27. Calculate the consistency ratio CR after the kth iteration (k) , and CP (k) With CR * Make comparisons;

[0282] If CR (k) >CR * , then proceed to step S28; if CR (k) ≤CR * , then the output is the judgment matrix A that meets the consistency requirements (k) , the iteration ends;

[0283] S28, Order Correct the judgment matrix; the corrected deviation matrix is ​​as follows:

[0284]

[0285] Then, step S22 is performed until a judgment matrix that meets the consistency requirement is obtained;

[0286] S29, based on the judgment matrix A′=[a′ ij ], and the geometric mean method is used to calculate the comprehensive index weight of each index; the expression of the comprehensive index weight is as follows:

[0287]

[0288] Where: i is the comprehensive index weight, a kj is the element in the kth row and jth column of the judgment matrix.

[0289] The variable weight vector acquisition module 3 is used to calculate the indicator state vector of the comprehensive subjective weight based on the variable weight theory considering random scenarios, and re-cluster the indicator state vector through the canonical cutting idea to obtain the final variable weight vector;

[0290] Furthermore, the variable weight vector acquisition module 3 is used to obtain the variable weight vector according to the following steps:

[0291] S31. The initial weight matrix obtained by the improved analytic hierarchy process is W = {w1, w2, ...w n}, the indicator data is X={x1, x2, …x n};

[0292] S32, normalize the indicator information of the indicator data to obtain the normalized indicator vector X={y1, y2, ...y n};

[0293] The positive and negative indicators are as follows:

[0294]

[0295] Where: x i is the i-th indicator data, y i is the i-th indicator data after normalization;

[0296] S33, the variable weight balance function combining the incentive factor and the penalty factor is calculated to obtain the indicator state vector U i (Y); the expression of the indicator state vector is as follows:

[0297]

[0298] Among them: β is the incentive factor, γ is the penalty factor, C is the passing factor, and k is the adjustment factor;

[0299] S34, based on the initial weight matrix W and the indicator state vector U i (Y), calculate the variable weight vector G i ; The variable weight vector G i The expression is as follows:

[0300]

[0301] S35, calculate variable weight vector G i The difference vector between the initial weight matrix W and the absolute value of each data of the difference vector is obtained to obtain the absolute difference vector V;

[0302] S36, the absolute difference vector V is regarded as a graph, and based on minimizing the Ncut function, the indexes with relatively drastic weight changes and other indexes are partitioned; the expression of the partition is as follows:

[0303]

[0304]

[0305] Where: A and B are two subgraphs of the partition, and the nodes in the graph are represented by the absolute difference of the index; W u，v is the similarity between nodes u and v; u, v, and p are nodes of graphs A, B, and V respectively; partition A is the indicator with relatively drastic weight changes, and partition B is other indicators;

[0306] S37, for the partition A of the index whose weight changes are relatively drastic, after correcting its corresponding index state vector, proceed to step S34 to obtain the final variable weight vector;

[0307] The modified expression is as follows:

[0308]

[0309] Among them: U i ′ is the correction vector of the index with relatively drastic weight changes, U i A , W i A is the variable weight and constant weight of the index of the i-th index in partition A, λ B It is the volatility index of other indicators in partition B.

[0310] The comprehensive evaluation module 4 is used to calculate the weighted deviation degree based on the cloud centroid model and the final variable weight vector to comprehensively evaluate the comprehensive performance of the three-phase oil-immersed transformer.

[0311] Furthermore, the comprehensive evaluation module 4 is used to obtain a comprehensive evaluation according to the following steps:

[0312] S41. Determine the standard cloud of the cloud centroid model. The expression of the digital characteristics of the standard cloud is as follows:

[0313]

[0314] Among them: Ex i Expectations for the cloud, En i is the cloud entropy, C i，max is the maximum value of the evaluation level corresponding to the score value interval, C i，min is the minimum value of the scoring interval corresponding to the evaluation level;

[0315] S42. The ideal state of the comprehensive performance of the three-phase oil-immersed transformer is divided into a positive ideal state and a negative ideal state, and the centroid position vector is defined. and the cloud centroid vector are all in a positive ideal state; and define the center of mass position vector and the cloud centroid vector All are in negative ideal state;

[0316] in:

[0317] T+=L+·G i ; T-=L-·G i ;

[0318]

[0319] In the above formula: x + is a positive indicator, x - is a negative indicator, N is the number of positive indicators, Ex (i) It is the standard cloud of the secondary indicators in the evaluation indicator system;

[0320] S43, normalizing the cloud centroid vector; the normalized expression is as follows:

[0321]

[0322] Where: T i p is the normalized cloud centroid vector value;

[0323] S44, based on the normalized cloud centroid vector value T of each secondary indicator i p With a variable weight vector G i , and obtain the weighted deviation degree θ; the expression of the weighted deviation degree θ is as follows:

[0324]

[0325] S45. Using the weighted deviation θ as a score value for the comprehensive performance of the three-phase oil-immersed transformer, and matching the score value with a preset evaluation level to obtain a comprehensive performance evaluation of the three-phase oil-immersed transformer.

[0326] Embodiment 3:

[0327] See also Figure 7 , In this embodiment, a transformer performance evaluation device considering scenario applicability based on improved AHP is also included, and the device includes a processor 5 and a memory 6;

[0328] The memory 6 is used to store the computer program code 61 and transmit the computer program code 61 to the processor 5;

[0329] The processor 5 is configured to execute the transformer performance evaluation method based on improved AHP and considering scenario applicability described in Example 1 according to the instructions in the computer program code 61 .

[0330] This embodiment also includes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed on a computer, the transformer performance evaluation method based on improved AHP considering scenario applicability described in Example 1 is implemented.

[0331] Generally speaking, the computer instructions for implementing the method of the present invention may be carried in any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media may include any computer-readable media, except for the signal itself that is temporarily propagating.

[0332] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EKROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0333] Computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, SMalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages, in particular, Python suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. can be used. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer or to an external computer (for example, using an Internet service provider to connect via the Internet) through any type of network, including a local area network (LAN) or a wide area network (WAN).

[0334] The above-mentioned device and non-transitory computer-readable storage medium can refer to the specific description of a transformer performance evaluation method considering scenario applicability based on improved AHP and its beneficial effects, which will not be repeated here.

[0335] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A transformer performance evaluation method based on improved AHP considering scenario applicability, characterized in that: include: S1. Construct a comprehensive performance evaluation index system for three-phase oil-immersed transformers; S2, based on the zero deviation matrix, the judgment matrix is ​​modified to improve the analytic hierarchy process and obtain the comprehensive subjective weights of each indicator in the evaluation index system; S3. Based on the variable weight theory considering random scenarios, the indicator state vector of the comprehensive subjective weight is calculated, and the indicator state vector is re-clustered through the canonical cutting idea to obtain the final variable weight vector; S4. Based on the cloud centroid model and the final variable weight vector, the weighted deviation degree is calculated to comprehensively evaluate the comprehensive performance of the three-phase oil-immersed transformer.

2. The transformer performance evaluation method considering scenario applicability based on improved AHP according to claim 1 is characterized in that: The step S2 specifically includes: S21. Determine the importance of each indicator in the comprehensive performance evaluation index system of three-phase oil-immersed transformers through expert scoring and 1-9 scale method, and construct a judgment matrix A, A = [a ij ] n×n ; The expression of the judgment matrix is ​​as follows: Among them: a ij It is the scale value between indicators; S22. Calculate the consistency index CI, which is expressed as follows: Where: max is the maximum eigenvalue of the judgment matrix A, n is the order of the judgment matrix; S23, find the average random consistency index RI and calculate the consistency ratio CR, the expression of which is as follows: If CR<0.1, proceed to step S29; if CR≥0.1, proceed to step S24 to modify the judgment matrix; S24, the judgment matrix is ​​expressed as: W=[W ij ]=[w i / w j ],w=(w1...w i ...w n ) T ; D=[d ij ]; Where: A is the judgment matrix, W is the maximum eigenvector of the judgment matrix A, D is the deviation matrix, is the symbol of the Hadamard product; When A satisfies the hierarchical analysis method as a consistency matrix, all d ij =1 and λ max (D) = λ max (A) = n; all d ij =1 is called the zero deviation matrix, denoted as DI; S25, let the judgment matrix Consistency Ratio Standard CR * =0.1, the number of iterations k=0, and the constant γ is a positive number less than 1 but close to 1; S26, calculate the judgment matrix A after the kth iteration (k) The maximum eigenvalue λ max (A (k) ), where the maximum eigenvalue vector w (k) With the priority vector W (k) as follows: And according to Calculate the deviation matrix D after the kth iteration (k) ; S27. Calculate the consistency ratio CR after the kth iteration (k) , and CR (k) With CR * Make comparisons; If CR (k) >CR * , then proceed to step S28; if CR (k) ≤CR * , then the output is the judgment matrix A that meets the consistency requirements (k) , the iteration ends; S28, Order Correct the judgment matrix; the corrected deviation matrix is ​​as follows: Then, step S22 is performed until a judgment matrix that meets the consistency requirement is obtained; S29, based on the judgment matrix A′=[a′ ij ], use the geometric mean method to calculate the comprehensive indicator weights of each indicator, and construct the initial weight matrix based on the comprehensive indicator weights; The expression of the comprehensive index weight is as follows: Where: i is the comprehensive index weight, a kj is the element in the kth row and jth column of the judgment matrix.

3. The transformer performance evaluation method considering scenario applicability based on improved AHP according to claim 2 is characterized by: The step S3 specifically includes: S31. The initial weight matrix obtained by the improved analytic hierarchy process is W = {w1, w2, ...w n }, the indicator data is X = {x1, x2, ...x n }; S32, normalize the indicator information of the indicator data to obtain the normalized indicator vector Y={y1, y2…y n }; The positive indicators are as follows: The negative indicators are as follows: Where: x i is the i-th indicator data, y i is the i-th indicator data after normalization; S33, the variable weight balance function combining the incentive factor and the penalty factor is calculated to obtain the indicator state vector U i (Y); the expression of the indicator state vector is as follows: Among them: β is the incentive factor, γ is the penalty factor, C is the passing factor, and k is the adjustment factor; S34, based on the initial weight matrix W and the indicator state vector U i (Y), calculate the variable weight vector G i ; The variable weight vector G i The expression is as follows: S35, calculate variable weight vector G i The difference vector between the initial weight matrix W and the absolute value of each data of the difference vector is obtained to obtain the absolute difference vector V; S36, the absolute difference vector V is regarded as a graph, and based on minimizing the Ncut function, the indexes with relatively drastic weight changes and other indexes are partitioned; the expression of the partition is as follows: Where: A and B are two subgraphs of the partition, and the nodes in the graph are represented by the absolute difference of the index; W u，v is the similarity between nodes u and v; u, v, and p are nodes of graphs A, B, and V respectively; partition A is the indicator with relatively drastic weight changes, and partition B is other indicators; S37, for the partition A of the index whose weight changes are relatively drastic, after correcting its corresponding index state vector, proceed to step S34 to obtain the final variable weight vector; The modified expression is as follows: Among them: U i ′ is the correction vector of the index whose weight changes are relatively drastic, is the variable weight and constant weight of the index of the i-th index in partition A, λ B It is the volatility index of other indicators in partition B.

4. The transformer performance evaluation method considering scenario applicability based on improved AHP according to claim 3 is characterized by: The step S4 specifically includes: S41. Determine the standard cloud of the cloud centroid model. The expression of the digital characteristics of the standard cloud is as follows: Among them: Ex i Expectations for the cloud, En i is the cloud entropy, Ci,max is the maximum value of the scoring interval corresponding to the evaluation level, and Ci,min is the minimum value of the scoring interval corresponding to the evaluation level; S42. The ideal state of the comprehensive performance of the three-phase oil-immersed transformer is divided into a positive ideal state and a negative ideal state, and the centroid position vector is defined. and the cloud centroid vector are all in a positive ideal state; and define the center of mass position vector and the cloud centroid vector All are in negative ideal state; in: T + =L + ·G i ;T - =L - ·G i ; In the above formula: x + is a positive indicator, x - is a negative indicator, N is the number of positive indicators, Ex (i) It is the standard cloud of the secondary indicators in the evaluation indicator system; S43, normalizing the cloud centroid vector; the normalized expression is as follows: in: is the normalized cloud centroid vector value; S44, Normalized cloud centroid vector value based on each secondary indicator With a variable weight vector G i , and obtain the weighted deviation degree θ; the expression of the weighted deviation degree θ is as follows: S45. Using the weighted deviation θ as a score value for the comprehensive performance of the three-phase oil-immersed transformer, and matching the score value with a preset evaluation level to obtain a comprehensive performance evaluation of the three-phase oil-immersed transformer.

5. The transformer performance evaluation method considering scenario applicability based on improved AHP according to claim 1 is characterized by: The comprehensive performance evaluation index system of the three-phase oil-immersed transformer includes: First-level indicators: operational reliability, electrical test indicators, oil test information; Secondary indicators: hydrogen content, acetylene content, total hydrocarbon content, methane content, core grounding current, winding DC resistance, winding dielectric loss, winding polarization index, oil breakdown voltage, trace water in oil, oil dielectric loss, and furfural in oil.

6. A transformer performance evaluation system based on improved AHP considering scenario applicability, characterized in that: The system comprises: An evaluation index system construction module (1) is used to construct a comprehensive performance evaluation index system for three-phase oil-immersed transformers; A comprehensive subjective weight acquisition module (2) is used to modify the judgment matrix based on the zero deviation matrix to improve the hierarchical analysis method and obtain the comprehensive subjective weight of each indicator in the evaluation indicator system; A variable weight vector acquisition module (3) is used to calculate the indicator state vector of the comprehensive subjective weight based on the variable weight theory considering random scenarios, and re-cluster the indicator state vector through the canonical cutting idea to obtain the final variable weight vector; The comprehensive evaluation module (4) is used to calculate the weighted deviation based on the cloud centroid model and the final variable weight vector to comprehensively evaluate the comprehensive performance of the three-phase oil-immersed transformer.

7. The transformer performance evaluation system based on improved AHP considering scenario applicability according to claim 6 is characterized by: The comprehensive subjective weight acquisition module (2) is used to obtain the comprehensive subjective weight according to the following steps: S21. Determine the importance of each indicator in the comprehensive performance evaluation index system of three-phase oil-immersed transformers through expert scoring and 1-9 scale method, and construct a judgment matrix A, A = [a ij ] n×n ; The expression of the judgment matrix is ​​as follows: Among them: a ij It is the scale value between indicators; S22. Calculate the consistency index CI, which is expressed as follows: Where: max is the maximum eigenvalue of the judgment matrix A, n is the order of the judgment matrix; S23, find the average random consistency index RI and calculate the consistency ratio CR, the expression of which is as follows: If CR<0.1, proceed to step S29; if CR≥0.1, proceed to step S24 to modify the judgment matrix; S24, the judgment matrix is ​​expressed as: W=[W ij ]=[w i / w j ],w=(w1…w i ...w n ) T ; D=[d ij ]; Where: A is the judgment matrix, W is the maximum eigenvector of the judgment matrix A, D is the deviation matrix, is the symbol of the Hadamard product; When A satisfies the hierarchical analysis method as a consistency matrix, all d ij =1 and λ max (D) = λ max (A) = n; all d ij =1 is called the zero deviation matrix, denoted as DI; S25, let the judgment matrix Consistency Ratio Standard CR * =0.1, the number of iterations k=0, and the constant γ is a positive number less than 1 but close to 1; S26, calculate the judgment matrix A after the kth iteration (k) The maximum eigenvalue λ max (A (k) ), where the maximum eigenvalue vector w (k) With the priority vector W (k) as follows: And according to Calculate the deviation matrix D after the kth iteration (k) ; S27. Calculate the consistency ratio CR after the kth iteration (k) , and CR (k) With CR * Make comparisons; If CR (k) >CR * , then proceed to step S28; if CR (k) ≤CR * , then the output is the judgment matrix A that meets the consistency requirements (k) , the iteration ends; S28, Order Correct the judgment matrix; the corrected deviation matrix is ​​as follows: Then, step S22 is performed until a judgment matrix that meets the consistency requirement is obtained; S29, based on the judgment matrix A′=[a′ ij ], use the geometric mean method to calculate the comprehensive indicator weights of each indicator, and construct the initial weight matrix based on the comprehensive indicator weights; The expression of the comprehensive index weight is as follows: Where: i is the comprehensive index weight, a kj is the element in the kth row and jth column of the judgment matrix.

8. The transformer performance evaluation system based on improved AHP and considering scenario applicability according to claim 7 is characterized in that: The variable weight vector acquisition module (3) is used to obtain the variable weight vector according to the following steps: S31. The initial weight matrix obtained by the improved analytic hierarchy process is W = {w1, w2, ...w n }, the indicator data is X = {x1, x2, ... xn}; S32, normalize the indicator information of the indicator data to obtain the normalized indicator vector Y={y1, y2…y n }; The positive indicators are as follows: The negative indicators are as follows: Where: x i is the i-th indicator data, y i is the i-th indicator data after normalization; S33, the variable weight balance function combining the incentive factor and the penalty factor is calculated to obtain the indicator state vector U i (Y); the expression of the indicator state vector is as follows: Among them: β is the incentive factor, γ is the penalty factor, C is the passing factor, and k is the adjustment factor; S34, based on the initial weight matrix W and the indicator state vector U i (Y), calculate the variable weight vector G i ; The variable weight vector G i The expression is as follows: S35, calculate variable weight vector G i The difference vector between the initial weight matrix W and the absolute value of each data of the difference vector is obtained to obtain the absolute difference vector V; S36, the absolute difference vector V is regarded as a graph, and based on minimizing the Ncut function, the indexes with relatively drastic weight changes and other indexes are partitioned; the expression of the partition is as follows: Where: A and B are two subgraphs of the partition, and the nodes in the graph are represented by the absolute difference of the index; W u，v is the similarity between nodes u and v; u, v, and p are nodes of graphs A, B, and V respectively; partition A is the indicator with relatively drastic weight changes, and partition B is other indicators; S37, for the partition A of the index whose weight changes are relatively drastic, after correcting its corresponding index state vector, proceed to step S34 to obtain the final variable weight vector; The modified expression is as follows: Among them: U i ′ is the correction vector of the index whose weight changes are relatively drastic, is the variable weight and constant weight of the index of the i-th index in partition A, λ B It is the volatility index of other indicators in partition B.

9. The transformer performance evaluation system based on improved AHP considering scenario applicability according to claim 8, characterized in that: The comprehensive evaluation module (4) is used to obtain a comprehensive evaluation according to the following steps: S41. Determine the standard cloud of the cloud centroid model. The expression of the digital characteristics of the standard cloud is as follows: Among them: Ex i Expectations for the cloud, En i is the cloud entropy, Ci,max is the maximum value of the scoring interval corresponding to the evaluation level, and Ci,min is the minimum value of the scoring interval corresponding to the evaluation level; S42. The ideal state of the comprehensive performance of the three-phase oil-immersed transformer is divided into a positive ideal state and a negative ideal state, and the centroid position vector is defined. and the cloud centroid vector are all in a positive ideal state; and define the center of mass position vector and the cloud centroid vector All are in negative ideal state; in: T + =L + ·G i ;T - =L - ·G i ; In the above formula: x + is a positive indicator, x - is a negative indicator, N is the number of positive indicators, Ex (i) It is the standard cloud of the secondary indicators in the evaluation indicator system; S43, normalizing the cloud centroid vector; the normalized expression is as follows: in: is the normalized cloud centroid vector value; S44, Normalized cloud centroid vector value based on each secondary indicator With a variable weight vector G i , and obtain the weighted deviation degree θ; the expression of the weighted deviation degree θ is as follows: S45. Using the weighted deviation θ as a score value for the comprehensive performance of the three-phase oil-immersed transformer, and matching the score value with a preset evaluation level to obtain a comprehensive performance evaluation of the three-phase oil-immersed transformer.

10. A transformer performance evaluation device based on improved AHP considering scenario applicability, characterized by: The device comprises a processor (5) and a memory (6); The memory (6) is used to store computer program code (61) and transmit the computer program code (61) to the processor (5); The processor (5) is used to execute the transformer performance evaluation method based on improved AHP and considering scenario applicability according to any one of claims 1 to 5 according to the instructions in the computer program code (61).

Images