WO2023082298A1

WO2023082298A1 - Transformer health index evaluation method and apparatus, computer device, and storage medium

Info

Publication number: WO2023082298A1
Application number: PCT/CN2021/131052
Authority: WO
Inventors: 林其雄; 刘继平; 段斐; 匡小青; 吴彦伟; 沈志伟; 张科; 刘海宇; 何梓麟; 何一龙; 李辉红; 黄卉
Original assignee: 广东电网有限责任公司广州供电局
Priority date: 2021-11-10
Filing date: 2021-11-17
Publication date: 2023-05-19
Also published as: CN114239681A

Abstract

The present application relates to a transformer health index evaluation method and apparatus, a computer device, a storage medium and a computer program product. The method comprises: constructing a transformer two-level evaluation and determination system, the transformer two-level evaluation and determination system comprising a target layer, an object layer and a feature layer; constructing a transformer health index evaluation model on the basis of the transformer two-level evaluation and determination system and an object element extension principle, and obtaining the degree of correlation of an object element to be evaluated regarding each index evaluation level; obtaining an initial transformer health index and a transformer health correction factor on the basis of the degree of correlation of the object element regarding each index evaluation level; and correcting the initial transformer health index according to the transformer health correction factor to obtain a corrected health index of a transformer. Using the present method, the accuracy of transformer health condition evaluation may be improved.

Description

Transformer health index evaluation method, device, computer equipment and storage medium

technical field

The present application relates to the technical field of transformer detection, in particular to a transformer health index evaluation method, device, computer equipment, storage medium and computer program product.

Background technique

As the key equipment of the power grid, the power transformer is the most expensive and important part of the power grid, which is related to the safe and stable operation of the power grid. The direct and indirect costs generated by planned power outages and maintenance every year are huge, and its social impact is even more difficult to measure. In order to accurately and efficiently find the defects of the commissioning and transportation transformation equipment, reduce the failure rate and reduce the operation risk.

For the maintenance of transformers, the state-of-the-art maintenance method is currently adopted at home and abroad. This maintenance method relies on a scientific and comprehensive evaluation index system and calculation method for the health status and risk of power equipment. Therefore, the assessment of the health status of power transformers is an important link in the life cycle assessment of power transmission and transformation equipment.

In the prior art, most calculation methods of the transformer health index are based on the evaluation of the state of the internal insulation, which has certain limitations and cannot truly reflect the health of the transformer.

Contents of the invention

Based on this, it is necessary to provide a transformer health index evaluation method, device, computer equipment, computer readable storage medium and computer program product that can truly reflect the transformer health status in view of the above technical problems.

In a first aspect, the present application provides a transformer health index evaluation method. The methods include:

Construct a transformer two-level evaluation and judgment system, the transformer two-level evaluation and judgment system includes a target layer, a thing layer and a feature layer; wherein, the target layer is the evaluation result of the transformer operating state; the thing layer is a part of the transformer state Level evaluation factors, including electrical test analysis, oil chromatographic analysis, oily test analysis, maintenance history analysis, operating environment analysis and appearance inspection; the characteristic layer includes the test data of the transformer;

Constructing a transformer health index evaluation model based on the two-level evaluation system of the transformer and the principle of matter-element extension, and obtaining the correlation degree of the matter-element to be evaluated with respect to each index evaluation level;

Based on the correlation degree of the matter elements to be evaluated with respect to the evaluation grades of each index, the initial health index of the transformer and the health correction factor of the transformer are obtained; the health correction factor of the transformer includes a correction factor of operating years and a correction factor of bad working conditions;

The transformer initial health index is corrected according to the transformer health correction factor to obtain a modified transformer health index.

In one of the embodiments, the construction of the transformer health index evaluation model based on the two-level evaluation and judgment system of the transformer and the matter-element extension principle, and obtaining the correlation degree of the matter-element to be evaluated with respect to each index evaluation level includes:

Based on the two-level evaluation and judgment system of the transformer, the classic domain of the model and the matter-element to be evaluated of the transformer state are determined, and the node domain of the transformer state model is constructed;

Determine the weight of each evaluation index in the feature layer by entropy weight method, and obtain the weight matrix of each evaluation index;

Based on the weight matrix of each evaluation index, the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index is obtained.

In one of the embodiments, the acquisition of the transformer initial health index and transformer health correction factor based on the correlation degree of the matter element to be evaluated with respect to each index evaluation level includes:

Obtain the product sum of the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index and the corresponding preset coefficient, and obtain the initial health index of the transformer;

The operating life correction factor is obtained based on the preset amplitude coefficient, the aging coefficient, and the operating life of the transformer; the bad working condition correction factor is obtained based on the preset correction coefficient.

In one of the embodiments, the modifying the transformer initial health index according to the transformer health correction factor, and obtaining the modified transformer health index includes:

Calculate the product of the transformer initial health index, the operating life correction factor, and the bad working condition correction factor as the transformer corrected health index.

In one of the embodiments, the entropy weight method is used to determine the weight of each evaluation index in the feature layer, and obtaining the weight matrix of each evaluation index includes:

Obtain the initial data matrix of each evaluation index in the feature layer, and standardize the initial data matrix of each evaluation index in the feature layer to obtain the standardized matrix of each evaluation index;

Obtain the information entropy value of each evaluation index based on the standardized matrix of each evaluation index;

The weight matrix of each evaluation index is obtained based on the information entropy value of each evaluation index.

In one of the embodiments, the acquisition of the correlation degree of the matter element to be evaluated with respect to the evaluation grade of each index based on the weight matrix of each evaluation index includes:

The information utility value of each evaluation index is obtained based on the information entropy value of each evaluation index;

Obtain the entropy weight of each evaluation index based on the information utility value of each evaluation index;

The weight matrix of each evaluation index is obtained based on the entropy weight of each evaluation index.

In the second aspect, the present application also provides a transformer health index evaluation device. The devices include:

The system building module is used to build a two-level evaluation and judgment system for transformers, and the two-level evaluation and judgment system for transformers includes a target layer, a thing layer and a feature layer; wherein, the target layer is the evaluation result of the transformer operating state; the thing The layer is a first-level evaluation factor of the transformer state, including electrical test analysis, oil chromatographic analysis, oil test analysis, maintenance history analysis, operating environment analysis and appearance inspection; the characteristic layer includes the test data of the transformer;

The first acquisition module is used to construct a transformer health index evaluation model based on the two-stage evaluation and judgment system of the transformer and the matter-element extension principle, and obtain the correlation degree of the matter-element to be evaluated about each index evaluation grade;

The second acquisition module is used to obtain the transformer initial health index and the transformer health correction factor based on the correlation degree of the matter element to be evaluated with respect to each index evaluation level; the transformer health correction factor includes the operation years correction factor and the bad working condition correction factor;

An index correction module, configured to correct the transformer initial health index according to the transformer health correction factor, and obtain a modified transformer health index.

In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

The above-mentioned transformer health index evaluation method, device, computer equipment, storage medium and computer program products construct a two-level evaluation and judgment system for transformers. Construct the transformer health index evaluation model based on the principle of matter-element extension, obtain the correlation degree of the matter-element to be evaluated with respect to the evaluation level of each index, and based on the correlation degree of the matter-element to be evaluated with respect to the evaluation level of each index, obtain the initial health index of the transformer and the transformer health Correction factor. Finally, the initial health index of the transformer is corrected according to the transformer health correction factor to obtain the modified health index of the transformer. The health status of the transformer is evaluated through the modified health index of the transformer, which improves the accuracy of the health status evaluation of the transformer.

Description of drawings

Fig. 1 is the application environment diagram of transformer health index evaluation method in an embodiment;

Fig. 2 is a schematic flow chart of a transformer health index evaluation method in an embodiment;

Fig. 3 is a schematic diagram of the composition of the two-stage evaluation and judging system of the transformer in an embodiment;

Fig. 4 is a schematic diagram of the composition of the thing layer in the two-level evaluation and judgment system of the transformer in an embodiment;

FIG. 5 is a schematic diagram of a process for correcting the initial health index of a transformer in an embodiment;

Fig. 6 is a structural block diagram of a transformer health index evaluation device in an embodiment;

Figure 7 is an internal block diagram of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

The transformer health index evaluation method provided in the embodiment of the present application can be applied to the application environment shown in FIG. 1 . Wherein, the terminal 102 communicates with the server 104 through the network. The data storage system can store data that needs to be processed by the server 104 . The data storage system can be integrated on the server 104, or placed on the cloud or other network servers.

In one embodiment, as shown in FIG. 2 , a transformer health index evaluation method is provided, and the method is applied to the server in FIG. 1 as an example for illustration, including the following steps:

Step 202, build a two-level evaluation and judgment system for transformers. The two-level evaluation and judgment system for transformers includes a target layer, a thing layer, and a feature layer; wherein, the target layer is the evaluation result of the transformer operating state; the thing layer is the transformer The first-level evaluation factors of the state include electrical test analysis, oil chromatographic analysis, oily test analysis, maintenance history analysis, operating environment analysis and appearance inspection; the characteristic layer includes test data of the transformer.

Among them, the health index of transformer equipment is mainly reflected from four aspects: theoretical life, aging process, operating life, and current state. Transformer state evaluation is a multi-index decision-making evaluation. Figure 3 is a schematic diagram of the composition of the two-level evaluation and judgment system of the transformer in an embodiment. As shown in Figure 3, the two-level evaluation and evaluation system of the transformer is composed of three levels: the target layer, the object layer and the feature layer. The target layer is the transformer operation The result of the evaluation of the state. The thing layer is the first-level evaluation factor of the transformer state, which is a specific description of the target layer from different sides or structures; the feature layer is the second-level evaluation factor, mainly composed of transformer test data, monitoring data, historical data, etc.; the target layer includes There are four grades of good, good, attention, and serious; Figure 4 is a schematic diagram of the composition of the object layer in the two-stage evaluation and judgment system of the transformer in an embodiment. As shown in Figure 4, the object layer includes electrical test analysis, oil chromatographic analysis, oily Test analysis, maintenance history analysis, operating environment analysis and visual inspection.

Specifically, the electrical test analysis includes winding/bush insulation resistance, winding/bush capacitance value, winding/bush dielectric loss value, winding DC resistance, tap changer transition resistance, tap changer mechanical properties, and core insulation resistance; The oil chromatographic analysis includes hydrogen content, acetylene content, total hydrocarbon absolute gas production rate, total hydrocarbon content, and CO absolute gas production rate. Electrical test analysis includes winding/bush insulation resistance, winding/bush capacitance value, winding/bush dielectric loss value, winding DC resistance, tap changer transition resistance, tap changer mechanical properties, core insulation resistance; the oil Chromatographic analysis includes hydrogen content, acetylene content, total hydrocarbon absolute gas production rate, total hydrocarbon content, and CO absolute gas production rate.

Step 204, constructing a transformer health index evaluation model based on the transformer two-level evaluation system and the matter-element extension principle, and obtaining the correlation degree of the matter-element to be evaluated with respect to each index evaluation level.

Specifically, the principle of matter-element extension is based on the comparison and optimization of a variety of known general decisions, and according to the needs of incompatible and contradictory problems generated at various levels and stages, and then breaks through the conventional and expansive Adopting creative decision-making skills, grasping key strategies, satisfying the main system to the greatest extent, transforming incompatible contradictions into compatible relations, so as to achieve the overall optimal decision-making goal. Based on the transformer two-level evaluation and judgment system and the principle of matter-element extension, the transformer health index evaluation model is constructed, including: determining the classic domain of the model, determining the matter-element of the transformer state to be evaluated, forming the node domain of the transformer state model from the matter-element to be evaluated, and using the entropy weight The weight of each index is determined by the method, and the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index is obtained through the transformer health index evaluation model.

Step 206, based on the correlation degree of the matter element to be evaluated with respect to each index evaluation level, obtain the transformer initial health index and the transformer health correction factor; the transformer health correction factor includes the operating years correction factor and the bad working condition correction factor.

Specifically, for the transformer insulation state health index, according to the evaluation results of the insulation state, the correlation degree of the insulation state to different state levels is converted into a score value, and the uncertainty is considered in the worst case, that is, it is added to the degradation level , get the initial health index of the transformer. For the health status correction factor of the transformer insulation part, in addition to the insulation factor, the transformer health correction factor also has some related factors that directly affect the aging rate of the transformer. These factors are combined to form the operating life correction factor and bad working condition correction factor.

Step 208: Correct the transformer initial health index according to the transformer health correction factor to obtain a modified transformer health index.

Specifically, the initial health index of the transformer is corrected according to the transformer health correction factor, the modified health index of the transformer is obtained, and the health status of the transformer is evaluated according to the modified health index of the transformer. Among them, the bad condition correction factor is generated according to the outlet short-circuit factor, overload factor and over-excitation factor.

In the above transformer health index evaluation method, a two-level evaluation and evaluation system for transformers is constructed. The two-level evaluation and evaluation system for transformers includes the target layer, object layer and feature layer. Based on the two-level evaluation and evaluation system of transformers and the principle of matter-element extension, the transformer health index evaluation is constructed. model, obtain the correlation degree of the matter-element to be evaluated with respect to the evaluation grade of each index, and based on the correlation degree of the matter-element to be evaluated with respect to the evaluation grade of each index, obtain the initial health index of the transformer and the health correction factor of the transformer, and finally calculate the transformer health according to the health correction factor of the transformer The initial health index is corrected to obtain the modified health index of the transformer, and the health status of the transformer is evaluated through the modified health index of the transformer, which improves the accuracy of the health status evaluation of the transformer.

In one embodiment, the construction of a transformer health index evaluation model based on the two-level evaluation system of the transformer and the matter-element extension principle, and obtaining the correlation degree of the matter-element to be evaluated with respect to each index evaluation level includes:

Specifically, firstly, the classic domain of the model is determined based on the transformer two-level evaluation system:

Among them, N _j represents the j-th evaluation level divided by the matter-element of the transformer matter layer; C _i is the i-th evaluation index in the feature layer; V _ji is the value range specified by N _j for the index C _i , < a _ji , b _ji >, that is, the classical domain.

Secondly, the matter-element to be evaluated expresses the obtained data or analysis results in matter-element R:

Among them, p ₀ is the matter element to be evaluated.

Afterwards, the node domain of the transformer state model is composed of matter-elements to be evaluated:

Among them, j={1,2,3,4} in N _j , respectively: good, good, attention, serious four evaluation grades; p is the whole evaluation grade, v _pi is what p refers to the project index C _i The value range to take, that is, the section field.

For determining the weight of each evaluation index in the feature layer through the entropy weight method, a weight matrix of each evaluation index is obtained.

First, construct a standardized matrix. For the evaluation of the transformer health index, it is assumed that the initial data matrix V={v _il }m×n of m indicators C _i in n stages has been obtained. The orientations are very different, and the initial data of each indicator is standardized, and the standardized matrix V' of the indicator data is obtained.

Among them, the formula for standardizing the initial data of each indicator is:

The formula for obtaining the standardization matrix V' of the index data is:

V'={v' _il } _m×n

Obtain the information entropy value of the i-th indicator according to the indicator data normalization matrix V':

Among them, k is a constant, and its value is related to the number of system samples m.

For a system with completely disordered information, the degree of order is zero, and its entropy value is the largest, e=1.

When the data of n stages are all in a completely disordered distribution state, v ^' _il =1/n.

It can be obtained: k=(lnm) ^-1 , 0≤e≤1.

Information entropy e _i can measure the utility value of the i-th index information (index data), and when the information is completely out of order, e _i =1. At this time, the utility value of the information of e _i (that is, the information contained in the data of the i-th indicator) to the comprehensive evaluation is zero.

The information utility value of an evaluation index depends on the difference h _i between the information entropy e _i of the evaluation index and 1, namely:

h _i =1-e _i

The essence of the entropy weight method is to use the value coefficient contained in the evaluation index data to estimate the index weight. When the index value coefficient is higher, the importance and contribution to the evaluation conclusion are greater, and the entropy weight of the i-th evaluation index is calculated as:

Finally, the weight matrix of each evaluation index is: μ=[μ ₁ ,μ ₂ ,…,μ _m ],

Based on the weight matrix of each evaluation index, the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index is obtained, specifically including:

K _j(vi) indicates the correlation degree of the i-th feature with respect to the j-th state level, which is used to describe the degree of attribution of each indicator of the system to be evaluated with respect to the four evaluation levels j, and K _j (v _i )≥0 means that the indicator belongs to the level j, the larger its value is, the more attributes this indicator has at level j. ρ(v _i , v _ji ), ρ(v _i , v _pi ) represent the distances between point v _i and intervals v _ji and v _pi respectively.

For the matter-element to be evaluated, the correlation degree of each level j is:

Among them: K _j(p0) is the combined value of the correlation degree of each index in the matter-element to be evaluated with respect to each level considering the importance of the index, indicating the degree to which the matter-element to be evaluated p ₀ belongs to the set K.

In this embodiment, based on the transformer two-level evaluation and judgment system, the classic domain of the model and the matter-element of the transformer state to be evaluated are determined, and the node domain of the transformer state model is constructed. The weight of each evaluation index in the feature layer is determined by the entropy weight method, and each evaluation index is obtained. Finally, based on the weight matrix of each evaluation index, the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index is obtained, which realizes the acquisition of the correlation degree of each index evaluation level, in order to further obtain the transformer initial health index and transformer health correction Factor and access to the modified health index of the transformer create the conditions.

In one embodiment, the acquisition of the transformer initial health index and transformer health correction factor based on the correlation degree of the matter element to be evaluated with respect to each index evaluation level includes:

Specifically, when obtaining the transformer initial health index and transformer health correction factor based on the correlation degree of the matter-elements to be evaluated with respect to the evaluation grades of each index, the initial health index of the transformer is obtained by obtaining the evaluation grades of the matter-elements to be evaluated with respect to each index The correlation degree and the product sum of the corresponding preset coefficients are obtained to obtain the initial health index of the transformer. The formula for obtaining the initial health index of the transformer is:

H _Ia ＝K _1(p0) ×10+K _2(p0) ×30+K _3(p0) ×50+K _4(p0) ×100+K _θ(p0) ×100

Among them, K _θ(p0) is the uncertainty, H _Ia is the initial health index of the transformer, the range is 0-100, the larger the value, the worse the state (0-20 is excellent, 20-50 is good, 50-80 is attention , 80-100 is serious).

The acquisition of the operating life correction factor is based on the preset amplitude coefficient, aging coefficient and the operating life of the transformer; the operating life correction factor is obtained by the following formula:

a ₁ = Ae ^BT

Among them, a ₁ is the correction coefficient of operating life; A is the amplitude coefficient; B is the aging coefficient; according to the expert experience, A=0.9531, B=0.01917; T is the operating life of the transformer.

The correction factor for bad working conditions is obtained based on the preset correction coefficient, and the formula for obtaining the bad working condition correction factor is:

Among them, a ₂₁ , a ₂₂ , and a ₂₃ are all determined according to the correction coefficient reference value. Every time a bad working condition occurs, the corresponding score is deducted from the health index score according to its severity as a correction to the final score.

In this embodiment, the initial health index of the transformer is obtained by obtaining the product sum of the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index and the corresponding preset coefficient; based on the preset amplitude coefficient, aging coefficient and operating life of the transformer, Obtain the operating life correction factor; based on the preset correction coefficient, the bad working condition correction factor is obtained, which realizes the acquisition of the initial health index of the transformer, the operating life correction factor and the bad working condition correction factor, and realizes the evaluation of the state of the internal insulation. The correction creates the conditions for further obtaining the modified health index of the transformer.

In one embodiment, the modifying the transformer initial health index according to the transformer health correction factor, and obtaining the modified transformer health index includes:

Calculate the product of the initial health index of the transformer, the operating life correction factor, and the bad working condition correction factor as a modified transformer health index.

Specifically, when obtaining the modified health index of the transformer, the product of the initial health index of the transformer, the correction factor of the operating life, and the correction factor of bad working conditions is calculated as the modified health index of the transformer. Figure 5 shows the process of correcting the initial health index of the transformer in an embodiment. Schematic diagram, the formula for obtaining the modified health index of the transformer is:

TH＝HI _a ×a ₁ ×a ₂

Among them, TH is the modified health index of the transformer.

In this embodiment, by calculating the product of the initial health index of the transformer and the correction factor of the operating life and the correction factor of the bad working condition, as the modified health index of the transformer, the correction of the initial health index of the transformer is realized, and the evaluation of the health status of the transformer is improved. accuracy.

In one embodiment, the determination of the weight of each evaluation index in the feature layer by the entropy weight method, and obtaining the weight matrix of each evaluation index includes:

Specifically, the initial data matrix of each evaluation index in the feature layer is obtained, and the initial data matrix of each evaluation index in the feature layer is standardized to obtain the normalization matrix of each evaluation index, and then based on the normalization matrix of each evaluation index, the initial data matrix of each evaluation index is obtained. Information entropy value, the information utility value of an evaluation index depends on the difference between the evaluation index information entropy and 1, through the obtained information utility value of an evaluation index, and finally obtain each evaluation index based on the information entropy value of each evaluation index The weight matrix of .

In this embodiment, the initial data matrix of each evaluation index in the feature layer is obtained, the initial data matrix of each evaluation index in the feature layer is standardized to obtain the standardized matrix of each evaluation index, and each evaluation index is obtained based on the standardized matrix of each evaluation index Based on the information entropy value of each evaluation index, the weight matrix of each evaluation index is obtained based on the information entropy value of each evaluation index, which realizes the acquisition of the weight matrix of each evaluation index, and creates an conditions.

In one embodiment, the acquisition of the correlation degree of the matter element to be evaluated with respect to the evaluation grade of each index based on the weight matrix of each evaluation index includes:

Specifically, when obtaining the correlation degree of the matter-element to be evaluated with respect to the evaluation level of each index based on the weight matrix of each evaluation index, firstly, the information utility value of each evaluation index is obtained based on the information entropy value of each evaluation index, and then based on the information of each evaluation index The utility value obtains the entropy weight of each evaluation index, and finally obtains the weight matrix of each evaluation index based on the entropy weight of each evaluation index.

In this embodiment, the information utility value of each evaluation index is obtained based on the information entropy value of each evaluation index, and the entropy weight value of each evaluation index is obtained based on the information utility value of each evaluation index, and the entropy weight value of each evaluation index is obtained based on the entropy weight value of each evaluation index. The weight matrix of each evaluation index realizes the acquisition of the weight matrix of each evaluation index, which is beneficial to evaluate the health status of the transformer by modifying the health index of the transformer, and improves the accuracy of the evaluation of the health status of the transformer.

It should be understood that although the steps in the flow charts involved in the above embodiments are shown sequentially as indicated by the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flow charts involved in the above-mentioned embodiments may include multiple steps or stages, and these steps or stages are not necessarily executed at the same time, but may be performed at different times For execution, the execution sequence of these steps or stages is not necessarily performed sequentially, but may be performed in turn or alternately with other steps or at least a part of steps or stages in other steps.

Based on the same inventive concept, an embodiment of the present application further provides a transformer health index evaluation device for implementing the above-mentioned transformer health index evaluation method. The solution to the problem provided by the device is similar to the implementation described in the above method, so the specific limitations in one or more embodiments of the transformer health index evaluation device provided below can be referred to above for transformer health index evaluation The limitation of the method will not be repeated here.

In one embodiment, as shown in Figure 6, a transformer health index evaluation device is provided, including: a system construction module 601, a first acquisition module 602, a second acquisition module 603 and an index correction module 604, wherein:

The system construction module 601 is used to construct a two-level evaluation and judgment system for transformers, and the two-level evaluation and judgment system for transformers includes a target layer, a thing layer and a feature layer; wherein, the target layer is the evaluation result of the transformer operating state; the The matter layer is the first-level evaluation factor of the transformer state, including electrical test analysis, oil chromatographic analysis, oil test analysis, maintenance history analysis, operating environment analysis and appearance inspection; the feature layer includes test data of the transformer;

The first acquisition module 602 is configured to construct a transformer health index evaluation model based on the transformer two-level evaluation and judgment system and the matter-element extension principle, and obtain the correlation degree of the matter-element to be evaluated with respect to each index evaluation level;

The second acquisition module 603 is used to acquire the transformer initial health index and the transformer health correction factor based on the correlation degree of the matter element to be evaluated with respect to each index evaluation grade; the transformer health correction factor includes the operating years correction factor and the bad working condition correction factor ;

The index correction module 604 is configured to correct the initial health index of the transformer according to the transformer health correction factor, and obtain a revised transformer health index.

In one embodiment, the first acquisition module 602 is also used to: determine the classical domain of the model and the matter-element of the transformer state to be evaluated based on the two-level evaluation system of the transformer, and construct the node domain of the transformer state model; The method determines the weight of each evaluation index in the feature layer, and obtains the weight matrix of each evaluation index; based on the weight matrix of each evaluation index, the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index is obtained.

In one embodiment, the second acquisition module 603 is further configured to: acquire the product sum of the correlation degree of the object element to be evaluated with respect to each index evaluation level and the corresponding preset coefficient to obtain the initial health index of the transformer; based on the preset The amplitude coefficient, aging coefficient and operating life of the transformer are used to obtain the operating life correction factor; based on the preset correction coefficient, the bad working condition correction factor is obtained.

In one embodiment, the index correction module 604 is further configured to: calculate the product of the transformer initial health index, the operating life correction factor, and the bad working condition correction factor as a transformer corrected health index.

In one embodiment, the first acquisition module 602 is further configured to: acquire the initial data matrix of each evaluation index in the feature layer, and standardize the initial data matrix of each evaluation index in the feature layer to obtain the normalization of each evaluation index matrix; obtain the information entropy value of each evaluation index based on the standardized matrix of each evaluation index; obtain the weight matrix of each evaluation index based on the information entropy value of each evaluation index.

In one embodiment, the first acquisition module 602 is further configured to: obtain the information utility value of each evaluation index based on the information entropy value of each evaluation index; obtain the entropy weight of each evaluation index based on the information utility value of each evaluation index value; the weight matrix of each evaluation index is obtained based on the entropy weight of each evaluation index.

The above-mentioned transformer health index evaluation device constructs a two-level evaluation and judgment system for transformers. The two-level evaluation and judgment system for transformers includes the target layer, object layer and feature layer. Based on the two-level evaluation and judgment system of transformers and the principle of matter-element extension, a transformer health index evaluation model is constructed. , to obtain the correlation degree of the matter-element to be evaluated with respect to the evaluation grade of each index, and based on the correlation degree of the matter-element to be evaluated with respect to the evaluation grade of each index, obtain the initial health index of the transformer and the health correction factor of the transformer, and finally calculate the initial value of the transformer according to the health correction factor of the transformer The health index is corrected to obtain the modified health index of the transformer, and the health status of the transformer is evaluated through the modified health index of the transformer, thereby improving the accuracy of evaluating the health status of the transformer.

Each module in the above transformer health index evaluation device can be fully or partially realized by software, hardware and combinations thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure may be as shown in FIG. 7 . The computer device includes a processor, memory and a network interface connected by a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs and databases. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a transformer health index evaluation method is realized.

Those skilled in the art can understand that the structure shown in Figure 7 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation to the computer equipment on which the solution of this application is applied. The specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.

In one embodiment, a computer device is provided, including a memory and a processor, a computer program is stored in the memory, and the processor implements the following steps when executing the computer program:

In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the transformer two-level evaluation and evaluation system, the classic domain of the model and the matter-element to be evaluated in the transformer state are determined, and the node domain of the transformer state model is constructed; through the entropy weight method The weight of each evaluation index in the feature layer is determined, and the weight matrix of each evaluation index is obtained; based on the weight matrix of each evaluation index, the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index is obtained.

In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining the product sum of the correlation degree of the object element to be evaluated with respect to the evaluation level of each index and the corresponding preset coefficient to obtain the initial health index of the transformer; based on the preset The amplitude coefficient, the aging coefficient and the operating life of the transformer are used to obtain the operating life correction factor; the bad working condition correction factor is obtained based on the preset correction coefficient.

In one embodiment, when the processor executes the computer program, the following steps are further implemented: calculating the product of the transformer initial health index, the operating life correction factor, and the bad working condition correction factor as the transformer corrected health index.

In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining the initial data matrix of each evaluation index in the feature layer, and standardizing the initial data matrix of each evaluation index in the feature layer to obtain the standardized matrix of each evaluation index ; The information entropy value of each evaluation index is obtained based on the standardized matrix of each evaluation index; the weight matrix of each evaluation index is obtained based on the information entropy value of each evaluation index.

In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining the information utility value of each evaluation index based on the information entropy value of each evaluation index; obtaining the entropy weight value of each evaluation index based on the information utility value of each evaluation index ; Obtain the weight matrix of each evaluation index based on the entropy weight of each evaluation index.

The above-mentioned computer equipment builds a two-level evaluation and judgment system for transformers. The two-level evaluation and evaluation system for transformers includes the target layer, the object layer and the feature layer. Evaluate the correlation degree of the matter-element with respect to the evaluation grade of each index, and based on the correlation degree of the matter-element to be evaluated with respect to the evaluation grade of each index, obtain the initial health index of the transformer and the health correction factor of the transformer, and finally calculate the initial health index of the transformer according to the health correction factor of the transformer Correction, obtaining the modified health index of the transformer, evaluating the health status of the transformer through the modified health index of the transformer, and improving the accuracy of the evaluation of the health status of the transformer.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the classical domain of the model and the matter-elements to be evaluated in the state of the transformer based on the two-level evaluation system of the transformer, and constructing the node domain of the state model of the transformer; using the entropy weight The method determines the weight of each evaluation index in the feature layer, and obtains the weight matrix of each evaluation index; based on the weight matrix of each evaluation index, the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index is obtained.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the product sum of the correlation degree of the object element to be evaluated with respect to each index evaluation level and the corresponding preset coefficient, and obtaining the initial health index of the transformer; based on the preset The amplitude coefficient, aging coefficient and operating life of the transformer are used to obtain the operating life correction factor; based on the preset correction coefficient, the bad working condition correction factor is obtained.

In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: calculating the product of the transformer initial health index, the operating life correction factor, and the bad working condition correction factor as the transformer corrected health index.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the initial data matrix of each evaluation index in the feature layer, and standardizing the initial data matrix of each evaluation index in the feature layer to obtain the normalization of each evaluation index matrix; obtain the information entropy value of each evaluation index based on the standardized matrix of each evaluation index; obtain the weight matrix of each evaluation index based on the information entropy value of each evaluation index.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the information utility value of each evaluation index based on the information entropy value of each evaluation index; obtaining the entropy weight of each evaluation index based on the information utility value of each evaluation index value; the weight matrix of each evaluation index is obtained based on the entropy weight of each evaluation index.

The above-mentioned storage medium builds a transformer two-level evaluation and judgment system. The transformer two-level evaluation and judgment system includes the target layer, the object layer and the feature layer. Evaluate the correlation degree of the matter-element with respect to the evaluation grade of each index, and based on the correlation degree of the matter-element to be evaluated with respect to the evaluation grade of each index, obtain the initial health index of the transformer and the health correction factor of the transformer, and finally calculate the initial health index of the transformer according to the health correction factor of the transformer Correction, obtaining the modified health index of the transformer, evaluating the health status of the transformer through the modified health index of the transformer, and improving the accuracy of the evaluation of the health status of the transformer.

In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

The above computer program product constructs a two-level evaluation and judgment system for transformers. The two-level evaluation and evaluation system for transformers includes target layer, thing layer and feature layer. Based on the two-level evaluation and evaluation system of transformers and the principle of matter-element extension, a transformer health index evaluation model is constructed to obtain The correlation degree of the matter-elements to be evaluated with respect to the evaluation grades of each index, and based on the correlation degree of the matter-elements to be evaluated with respect to the evaluation grades of each index, the initial health index of the transformer and the health correction factor of the transformer are obtained, and finally the initial health index of the transformer is calculated according to the health correction factor of the transformer. Correction is performed to obtain the modified health index of the transformer, and the health status of the transformer is evaluated through the modified health index of the transformer, thereby improving the accuracy of evaluating the health status of the transformer.

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

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments can be completed by instructing related hardware through computer programs, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any reference to storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile and volatile storage. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive variable memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory, MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (Phase Change Memory, PCM), graphene memory, etc. The volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a blockchain-based distributed database, etc., but is not limited thereto. The processors involved in the various embodiments provided by this application can be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., and are not limited to this.

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

The above-mentioned embodiments only express several implementation modes of the present application, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be determined by the appended claims.

Claims

A transformer health index evaluation method is characterized in that the method comprises:

Construct a transformer two-level evaluation and judgment system, the transformer two-level evaluation and judgment system includes a target layer, a thing layer and a feature layer; wherein, the target layer is the evaluation result of the transformer operating state; the thing layer is a part of the transformer state Level evaluation factors, including electrical test analysis, oil chromatographic analysis, oily test analysis, maintenance history analysis, operating environment analysis and appearance inspection; the characteristic layer includes the test data of the transformer;

Constructing a transformer health index evaluation model based on the two-level evaluation system of the transformer and the principle of matter-element extension, and obtaining the correlation degree of the matter-element to be evaluated with respect to each index evaluation level;

Based on the correlation degree of the matter elements to be evaluated with respect to the evaluation grades of each index, the initial health index of the transformer and the health correction factor of the transformer are obtained; the health correction factor of the transformer includes a correction factor of operating years and a correction factor of bad working conditions;

The transformer initial health index is corrected according to the transformer health correction factor to obtain a modified transformer health index.
The method according to claim 1, characterized in that, the transformer health index evaluation model is constructed based on the transformer two-level evaluation and judgment system and the matter-element extension principle, and the correlation degree of the matter-element to be evaluated with respect to each index evaluation level is obtained include:

Based on the two-level evaluation and judgment system of the transformer, the classic domain of the model and the matter-element to be evaluated of the transformer state are determined, and the node domain of the transformer state model is constructed;

Determine the weight of each evaluation index in the feature layer by entropy weight method, and obtain the weight matrix of each evaluation index;

Based on the weight matrix of each evaluation index, the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index is obtained.
The method according to claim 2, wherein the obtaining of the initial health index of the transformer and the health correction factor of the transformer based on the correlation degree of the matter element to be evaluated with respect to each index evaluation grade includes:

Obtain the product sum of the correlation degree of the matter element to be evaluated with respect to the evaluation level of each index and the corresponding preset coefficient, and obtain the initial health index of the transformer;

The operating life correction factor is obtained based on the preset amplitude coefficient, the aging coefficient, and the operating life of the transformer; the bad working condition correction factor is obtained based on the preset correction coefficient.
The method according to claim 1, characterized in that, modifying the transformer initial health index according to the transformer health correction factor, and obtaining the modified transformer health index includes:

Calculate the product of the transformer initial health index, the operating life correction factor, and the bad working condition correction factor as the transformer corrected health index.
The method according to claim 2, wherein the determination of the weight of each evaluation index in the feature layer by the entropy weight method, and obtaining the weight matrix of each evaluation index includes:

Obtain the initial data matrix of each evaluation index in the feature layer, and standardize the initial data matrix of each evaluation index in the feature layer to obtain the standardized matrix of each evaluation index;

Obtain the information entropy value of each evaluation index based on the standardized matrix of each evaluation index;

The weight matrix of each evaluation index is obtained based on the information entropy value of each evaluation index.
The method according to claim 2, wherein said obtaining the correlation degree of the matter element to be evaluated with respect to each index evaluation grade based on the weight matrix of each evaluation index comprises:

The information utility value of each evaluation index is obtained based on the information entropy value of each evaluation index;

Obtain the entropy weight of each evaluation index based on the information utility value of each evaluation index;

The weight matrix of each evaluation index is obtained based on the entropy weight of each evaluation index.
A transformer health index evaluation device is characterized in that the device comprises:

The system building module is used to build a two-level evaluation and judgment system for transformers, and the two-level evaluation and judgment system for transformers includes a target layer, a thing layer and a feature layer; wherein, the target layer is the evaluation result of the transformer operating state; the thing The layer is a first-level evaluation factor of the transformer state, including electrical test analysis, oil chromatographic analysis, oil test analysis, maintenance history analysis, operating environment analysis and appearance inspection; the characteristic layer includes the test data of the transformer;

The first acquisition module is used to construct a transformer health index evaluation model based on the two-level evaluation and judgment system of the transformer and the matter-element extension principle, and obtain the correlation degree of the matter-element to be evaluated with respect to each index evaluation level;

The second acquisition module is used to obtain the transformer initial health index and the transformer health correction factor based on the correlation degree of the matter element to be evaluated with respect to each index evaluation level; the transformer health correction factor includes the operation years correction factor and the bad working condition correction factor;

An index correction module, configured to correct the transformer initial health index according to the transformer health correction factor, and obtain a modified transformer health index.
A computer device, comprising a memory and a processor, the memory stores a computer program, wherein the processor implements the steps of the method according to any one of claims 1 to 6 when executing the computer program.
A computer-readable storage medium, on which a computer program is stored, wherein, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are realized.
A computer program product, comprising a computer program, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.