Hydropower station equipment dynamic operation and maintenance management system and method based on variable weight-set pair-extenics fusion model

Abstract

The application provides a hydropower station equipment dynamic operation and maintenance management system and method based on a variable weight-set pair-takable fusion model, wherein the system comprises: a fusion model construction module, which is used for constructing a variable weight-set pair-takable fusion model; a strategy determination module, which is used for determining an operation and maintenance management strategy based on the variable weight-set pair-takable fusion model; and a strategy application module, which is used for applying the operation and maintenance management strategy. The hydropower station equipment dynamic operation and maintenance management system and method based on the variable weight-set pair-takable fusion model can evaluate the safety of the state of the hydropower station equipment by constructing the variable weight-set pair-takable fusion model, can obtain the safety level and possible safety trend of the hydropower station equipment and facilities in a timely manner in the management system, can determine and apply the operation and maintenance management strategy according to the safety evaluation level and the trend, and can accurately evaluate the safety state of the equipment by setting dynamic index weights, so that the timeliness of subsequent operation and maintenance management of the hydropower station is further improved, and the operation and maintenance management is more suitable.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hydropower station equipment management, and particularly relates to a hydropower station equipment dynamic operation and maintenance management system and method based on a variable weight-set pair-extensive fusion model. BACKGROUND

[0002] The occurrence of safety accidents of a hydropower station is a result of the cross action of multiple factors. On the basis of determining a safety evaluation system of hydropower station equipment, the safety level of the hydropower station equipment is divided, so as to quantize the evaluation indexes and perform safety evaluation of the hydropower station equipment.

[0003] The index weight is determined by using a "structure entropy weight method" combining a subjective assignment method and an objective assignment method. The basic idea of the structure entropy weight method is to analyze the system indexes and their mutual relations, decompose them into a plurality of independent hierarchical structures, combine a Delphi expert investigation method of collecting expert opinions and a fuzzy analysis method to form a "typical order" of the importance of the indexes, quantitatively analyze the uncertainty of the "typical order" structure by using an entropy theory, calculate the entropy value and "blinding" analysis, and statistically process the potential deviation data. The relative importance order of each index at the same level is obtained, and the importance value of the same type index at each level is determined, that is, the index weight.

[0004] However, the evaluation index weight of the hydropower station equipment reflects the influence degree of the risk factors on the equipment safety. In the equipment safety evaluation index system, the influence degree of each evaluation index on the equipment safety is not the same compared with other indexes. The fixed index weight cannot accurately determine the safety state of the equipment, and further, it is easy to cause the subsequent operation and maintenance to be not timely and not suitable.

[0005] Therefore, it is urgent to provide a hydropower station equipment dynamic operation and maintenance management system and method based on a variable weight-set pair-extensive fusion model to at least solve the above problems. SUMMARY

[0006] One of the purposes of the present application is to provide a hydropower station equipment dynamic operation and maintenance management system and method based on a variable weight-set pair-extensive fusion model. The safety of the hydropower station equipment is evaluated by constructing a variable weight-set pair-extensive fusion model to obtain a safety evaluation level. The operation and maintenance management strategy is determined and applied according to the safety evaluation level and the operation and maintenance management strategy library. The dynamic index weight of the model can accurately evaluate the safety state of the equipment and further improve the timeliness and suitability of the subsequent operation and maintenance management of the hydropower station.

[0007] The hydropower station equipment dynamic operation and maintenance management system based on the variable weight-set pair-extensive fusion model provided by the embodiment of the present application comprises:

[0008] The fusion model construction module is configured to construct a variable weight-set pair-extensive fusion model.

[0009] a strategy determination module configured to determine the operation and maintenance strategy based on the variable weight-set pair-extensible fusion model, the safety evaluation level of the hydropower station equipment, and the operation and maintenance strategy library;

[0010] a strategy application module configured to apply the operation and maintenance strategy.

[0011] Preferably, the fusion model construction module constructs the variable weight-set pair-extensible fusion model, which comprises the following steps:

[0012] determining the constant weight of the index based on the structural entropy weight method;

[0013] dynamically correcting the constant weight based on the variable weight theory to determine the variable weight of the index;

[0014] coupling the set pair theory and the matter-element extensible method, combining the variable weight, and constructing a variable weight-set pair-extensible coupling evaluation model;

[0015] wherein the index is dynamically updated according to the scoring of experts or staff familiar with the hydropower station equipment and facilities.

[0016] The hydropower station equipment dynamic operation and maintenance management system based on the variable weight-set pair-extensible fusion model provided in the embodiments of the present application further comprises the following:

[0017] an auxiliary operation and maintenance module configured to match the best operation and maintenance personnel and perform auxiliary operation and maintenance based on the corresponding operation and maintenance strategy when manual intervention is performed.

[0018] Preferably, the auxiliary operation and maintenance module matches the best operation and maintenance personnel and performs auxiliary operation and maintenance based on the corresponding operation and maintenance strategy when manual intervention is performed, which comprises the following steps:

[0019] S41: analyzing the operation and maintenance strategy and determining a target operation and maintenance task;

[0020] S42: obtaining the historical operation and maintenance tasks of the idle operation and maintenance personnel in a first time period;

[0021] S43: labeling the first feature of the historical operation and maintenance task of the same task type as the target operation and maintenance task on a preset time axis based on the execution time of the corresponding historical operation and maintenance task, wherein the first feature comprises the safety evaluation level of the hydropower station equipment corresponding to the historical operation and maintenance task and the operation and maintenance evaluation level of the historical operation and maintenance task;

[0022] S44: if the first feature meets a matching trigger condition, obtaining the time axis point existing in each feature distribution corresponding time axis point as a target axis point, wherein the matching trigger condition comprises that the feature distribution of the first feature of the feature type on the time axis meets the standard feature distribution of the feature type;

[0023] S45: If the acquisition is successful, a second feature is extracted according to a historical operation and maintenance task corresponding to the target axis point;

[0024] S46: According to a matching template preset according to the second feature, a second feature corresponding to a maximum matching value is obtained as a best operation and maintenance personnel according to the second feature;

[0025] S47: When the best operation and maintenance personnel intervenes in operation and maintenance, auxiliary operation and maintenance is performed based on a corresponding operation and maintenance management strategy.

[0026] Preferably, the auxiliary operation and maintenance module performs auxiliary operation and maintenance based on a corresponding operation and maintenance management strategy when the best operation and maintenance personnel intervenes in operation and maintenance, including:

[0027] According to the historical operation and maintenance task corresponding to the second feature with the maximum matching value, a pre-play model is constructed;

[0028] According to a pre-play result of the pre-play model and a management intervention time setting rule, a management intervention time is determined;

[0029] A model slice of the management intervention time is obtained;

[0030] According to the model slice, an intervention queue is obtained;

[0031] According to first intervention operation and maintenance live information, a pre-trigger of an intervention management instruction in the intervention queue is performed;

[0032] According to a model slice corresponding to the pre-trigger successful intervention management instruction, second intervention operation and maintenance live information is obtained;

[0033] According to the second intervention operation and maintenance live information, it is determined whether to determine to trigger the pre-trigger successful intervention management instruction;

[0034] If yes, auxiliary operation and maintenance is performed based on the determined to trigger intervention management instruction.

[0035] The water power station equipment dynamic operation and maintenance management method based on the variable weight-set pair-tubulation fusion model provided by the embodiment of the application comprises:

[0036] Step 1: Construct a variable weight-set pair-tubulation fusion model;

[0037] Step 2: Determine an operation and maintenance management strategy based on a safety evaluation level of a water power station equipment state and an operation and maintenance management strategy library of the variable weight-set pair-tubulation fusion model;

[0038] Step 3: Apply the operation and maintenance management strategy.

[0039] The application has the following beneficial effects:

[0040] The application obtains a safety evaluation grade by constructing a variable weight-set pair-extensive fusion model to evaluate the safety of the equipment of the hydropower station. According to the safety evaluation grade and an operation and maintenance management strategy library, an operation and maintenance management strategy is determined and applied. The model sets dynamic index weights, can accurately evaluate the safety state of the equipment, and further improves the timeliness of subsequent operation and maintenance management of the hydropower station and the suitability of the operation and maintenance management.

[0041] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the application. The objects and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims.

[0042] The technical solutions of the present application will be further described in detail below with the help of the accompanying drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0043] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate the present application and are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation on the present application. In the drawings:

[0044] Figure 1 A schematic diagram of a dynamic operation and maintenance management system for equipment of a hydropower station based on a variable weight-set pair-extensive fusion model in an embodiment of the present application;

[0045] Figure 2 A set pair-extensive set theory domain relationship diagram in an embodiment of the present application;

[0046] Figure 3 A schematic diagram of a dynamic operation and maintenance management method for equipment of a hydropower station based on a variable weight-set pair-extensive fusion model in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The preferred embodiments of the present application will be described below in conjunction with the accompanying drawings, and it should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and do not constitute a limitation on the present application.

[0048] The embodiment of the present application provides a dynamic operation and maintenance management system for equipment of a hydropower station based on a variable weight-set pair-extensive fusion model, as shown in Figure 1 , which comprises:

[0049] A fusion model construction module 1 is configured to construct a variable weight-set pair-extensive fusion model.

[0050] The fusion model construction module comprises:

[0051] The structural entropy weight method is used to determine the constant weight of the index.

[0052] The constant weight is dynamically corrected based on the variable weight theory to determine the variable weight of the index;

[0053] The variable weight-set pair-extenics coupling evaluation model is constructed by coupling the set pair theory and the matter element extenics method and combining the variable weight.

[0054] The index is dynamically updated according to the scoring of experts or staff familiar with the equipment and facilities of the hydropower station.

[0055] The strategy determination module 2 is configured to determine the operation and maintenance strategy based on the variable weight-set pair-extenics fusion model, the safety evaluation level of the equipment of the hydropower station and the operation and maintenance strategy library.

[0056] The strategy application module 3 is configured to apply the operation and maintenance strategy.

[0057] The working principle and beneficial effects of the above technical solution are as follows:

[0058] The variable weight-set pair-extenics fusion model is constructed based on the traditional matter element extenics model, the constant weight is dynamically corrected based on the variable weight theory to determine the weight of the index, then the three principles of "same, different and opposite" in the set pair analysis are used to divide the extension set theory domain, the integrated contact membership and the grade characteristic variable are calculated, and the model for determining the safety evaluation level and the grade transition trend of the equipment of the hydropower station is determined. According to the maximum integrated contact membership principle, the safety level of the equipment of the hydropower station is determined, and the construction method of the variable weight-set pair-extenics fusion model is as follows:

[0059] 1. Determination of the constant weight:

[0060] The "structure entropy weight method" combining the subjective assignment method and the objective assignment method is used to determine the index weight. The basic idea of the structure entropy weight method is to analyze the system index and its mutual relationship, decompose it into several independent hierarchical structures, combine the Delphi expert investigation method collecting expert opinions and the fuzzy analysis method, form a "typical order" for the importance of the index, quantitatively analyze the uncertainty of the "typical order" structure by entropy theory, calculate the entropy value and "blindness" analysis, and statistically process the potential bias data. The relative importance order of each index at the same level is obtained, and the importance value of the same index at each level is determined, that is, the weight of the index.

[0061] Suppose that k experts participate in the consultation investigation, and k consultation tables are obtained, each table corresponds to an index set, denoted as U={u1, u2, …, u n}, the "typical order" array corresponding to the index set is denoted as (a i1 , a i2 , …, a in ), and the ordering matrix of the index obtained from the k tables is denoted as A (A=(a ij ) k×n, i = 1, 2, ..., k; j = 1, 2, ..., n, are called the "typical ranking" matrix of the indicators. Where a ij This indicates that the i-th expert's opinion on the j-th indicator u j Evaluation. i1 a i2 , ..., a in Take any number from the natural numbers {1, 2, ..., n}. For example, if you need to sort four indicators, then the indicator "typical sorting" array {a i1 a i2 , ..., a in In the sequence {}, n=4 can take any number from {1, 2, 3, 4}. The qualitative and quantitative transformation of the above "typical sorting" can be defined by the membership function of the qualitative sorting transformation, which can be transformed into:

[0062] μ(I)=ln(mI) / ln(m-1) (1)

[0063] Where I is the qualitative ranking number given by experts after evaluating a certain indicator according to the "typical ranking" format. If A is considered the "first choice" among the four indicators A, B, C, and D, then I is 1; if it is considered the "second choice," then I is 2; and so on. m is a variable defined on [0, 1], μ(I) is the membership function value corresponding to I, I = 1, 2, ..., j, j+1, where j is the actual maximum sequence number. For example, when j = 4, it means that 4 indicators are participating in the ranking, so the maximum sequence number is 4. m is the transformation parameter, which is taken as m = j + 2, i.e., m = 6.

[0064] When I = 1,

[0065] When I = j + 1, take the maximum index. Let I=a i Substituting into equation (1), we can obtain a ij Quantitative conversion value b ij (μ(a ij )=b ij ), b ij The membership degree is called the order number I. The matrix μ(a) ij )=b ij This is called the membership matrix. It considers the k experts' views on the index u. j The "discourse power" is the same, and the calculation of k experts' opinions on indicator u j The "consensus" is called the average level of awareness, denoted as b. j ,make:

[0066] b j =(b 1j +b 2j +…+b kj) / k (2)

[0067] Definition of expert z i For factor u j The uncertainty generated by cognition is called "cognitive blindness" and is denoted as Q j Let:

[0068] Q j = |{[max(b 1j ,b 2j ,…b kj )-b j ]+[min(b 1j ,b 2j ,…b kj )-b j ]} / 2 (3)

[0069] Obviously Q j ≥ 0.

[0070] For each factor u j , the overall cognitive degree x j of k experts about u j is defined as:

[0071] x j = b j (1-Q j ) (4)

[0072] The evaluation vector X = (x1, x2, …, x n ) of the overall k experts about the index u j is obtained from x j .

[0073] To obtain the weight of the index u j , the normalization processing of x j = b j (1-Q j ) is performed, and let:

[0074]

[0075] Obviously, α n (j = 1, 2, …, n) > 0, and (α1, α2, …, α n ) is the overall judgment of the consistency of the importance of the k "expert opinions" about the factor set U = {u1, u2, …, u n}, which conforms to the will or cognition of the k expert groups. W = {α1, α2, …, α n} is called the weight vector of the factor set U = {u1, u2, …, u m}.

[0076] 2. Determining the variable weights:

[0077] The weights of evaluation indicators for hydropower station equipment reflect the degree of impact of risk factors on the safety of hydropower station equipment. In the hydropower station equipment safety evaluation indicator system, since the degree of impact of each evaluation indicator on the safety of hydropower station equipment varies compared to other indicators, different weights must be assigned to each indicator according to its degree of impact. Only by rationally determining the weights of each evaluation indicator for hydropower station equipment can the safety status of the hydropower station equipment be determined more accurately. Considering that in the actual operation of hydropower station equipment, if the safety status of a certain indicator is poor, even if its weight is low, the overall safety status of the hydropower station equipment will decrease. To avoid fixed indicator weights affecting the effectiveness of the evaluation, variable weight theory is introduced. The indicator values ​​are used to determine the state variable weight vector, thereby correcting the constant weights of the indicators, making the determination of indicator weights more scientific, and laying the foundation for the rational determination of the safety status of hydropower station equipment.

[0078] Let X = (x1, x2, ..., x m ) is the factor state variable, W = (w1, w2, ..., w m ) is a constant weighted variable of the factor, S(X)=(S1(X),S2(X),…,S m (X) is the state-variable weight vector, W(X)=(W1(X),W2(X),…,W m (X)) is the variable weight vector. The variable weight W of the i-th index is... i (X) can be represented as:

[0079]

[0080] Compared to empirical and summative state-weighted vectors, exponential state-weighted vectors have advantages such as good fitting properties, clear principles, and easy parameter determination. They can be set as follows:

[0081]

[0082] In the formula, x i α is the value of the i-th evaluation indicator; α is the variable factor. When α > 0, an incentive-type state-weighted vector is generated, which aims to highlight the evaluation indicators with larger values ​​and does not have high requirements for the balance of indicators; when α < 0, a penalty-type state-weighted vector is generated, which aims to highlight the evaluation indicators with smaller values ​​and has certain requirements for the balance of each evaluation indicator; when α = 0, it is a constant weight model.

[0083] In the safety evaluation of hydropower station equipment, the smaller the value of each evaluation index, the lower the safety level of the structure. Considering that in actual engineering, even if a certain evaluation index has a low weight, a small evaluation value can still significantly reduce the safety of the hydropower station equipment, a penalty-type state-variable weighted variable is adopted to reflect the balance of evaluation indicators in the safety evaluation of hydropower station equipment and to highlight the evaluation indicators with smaller values. Furthermore, since α < -1 indicates that the evaluator has gone to an extreme, this invention takes α = -1.

[0084] 3. Establishment of the set-pair-extension coupling model:

[0085] To fully understand the overall risk level of hydropower station equipment, a scientific safety evaluation model must be adopted based on the established evaluation index system to comprehensively analyze the risks of hydropower station equipment. The evaluation results can then be used to identify weak points in the project and ultimately determine the safety status of the hydropower station equipment. As can be seen from the evaluation index system established above, the safety evaluation indicators for hydropower station equipment involve numerous uncertainties. Previous hydropower station equipment evaluation models have all converted the uncertainty of the safety evaluation indicators into determinism for analysis, without considering the conversion between the two, which has certain limitations. Therefore, in order to effectively characterize the uncertainty of the evaluation indicators and accurately determine the safety level of small and medium-sized hydropower station equipment and the trend of transformation to other safety levels, this invention leverages the advantage of using the tripartite principle in set pair theory for inverse analysis of similarities and differences, which can effectively characterize the uncertainties in the safety evaluation of hydropower station equipment. This invention couples set pair theory and the matter-element extension method to construct a set pair-extension coupled evaluation model.

[0086] The matter-element-extension theory is based on extension sets and matter-element theory. Extension sets describe the "dynamics" of things, that is, the transformation of the properties of the research object, while the matter-element concept overcomes the incompatibility problem in evaluation. Considering that the safety influencing factors of hydropower station equipment are mostly qualitative indicators and belong to multiple dimensions, this invention uses the matter-element concept to describe the problem, transforming the complex, multi-dimensional, and incompatible problem of hydropower station equipment safety evaluation into a quantitative and solvable problem model.

[0087] For the safety evaluation of hydropower station equipment, let the safety level set of hydropower station equipment be N = [N1, N2, ..., N]. j ,…,N n The set of safety evaluation indicators for the frame is C = [C1, C2, ..., C]. i C m Based on the above classification and quantification of the safety levels of hydropower station equipment, the classical domains of each safety level of hydropower station equipment are determined, and the classical domain R is obtained as follows:

[0088]

[0089] In the formula, ij b​ij >This is evaluation index C i Regarding security level N j The range of values.

[0090] The corresponding evaluation index's domain R m Represented as:

[0091]

[0092] In the formula, N represents all safety levels of the hydropower station equipment to be evaluated; m b m Under all safety levels of hydropower station equipment, evaluation index C m The range of values ​​for .

[0093] The matter element R0 to be evaluated is:

[0094]

[0095] In the formula, N0 represents the level of safety risk to be evaluated for the hydropower station equipment; V i The evaluation index C is the expert evaluation value of the level N0 to be evaluated.

[0096] This paper combines set pair analysis and extension theory. The domain of extension sets is divided using the ternary triad principle (identity, difference, and inverse) of set pair analysis. The relationship between set pair and extension set domains is shown in the diagram below. Figure 2 As shown.

[0097] Determine the relationship between the value V of evaluation index C and the various safety levels of hydropower station equipment: When the value V of evaluation index C... i When the evaluation index C is located within the standard positive region of the extension set of the discussion level j, the relationship between the evaluation index C and the safety level j is identical, indicating that from the perspective of this evaluation index, the hydropower station equipment is at the j-th safety level. The membership formula is as follows:

[0098]

[0099] In the formula, F ij+1 F ij It is the threshold value for the evaluation level; μ j (V i ) represents the membership degree of the framework to the standard positive domain formed by the i index in the safety level j under discussion.

[0100] When evaluation index C is within the adjacent level j-1 (j>1) or j+1 of discussion level j and V i Located in the positive transition region X1 of the extension set = (F ij－1 F ij ) or X2 = (F ij+1 F ij+2 ​Within this range, its relationship with the discussed safety level j is one of difference. This indicates that, from the perspective of this evaluation index, hydropower station equipment has a tendency to transform towards the j-th safety level. The membership formula is as follows:

[0101]

[0102] In the formula, F ij－1 F ij+2 It is the threshold value of the evaluation level, ρ(V) i V0) is the distance between the value V of evaluation index C and the standard positive region and the extension positive region formed by the standard of index i in evaluation level j. When j = 1, then F is taken. ij－1 =F ij When j = n, then take F. ij+2 =F in .

[0103] When evaluation index C i If a value falls within the adjacent levels j-2 (>2) or j+2 of the discussion level j, or is not within any evaluation level, then it lies in the negative domain of the extension set composed of the safety evaluation levels, and the evaluation index C is... i The relationship with security level j is one of independence. In this case, the membership degree is as follows:

[0104] μ j (V i )=-1 (15)

[0105] This indicates that, from the perspective of this evaluation index, the hydropower station equipment is not at the i-th safety level and has no possibility of being converted to that safety level.

[0106] The following formula is used to calculate the safety level N of the hydropower station equipment. j The membership degree μ of the framework integration relationship for (j = 1, 2, 3, 4, 5) j :

[0107]

[0108] In the formula, w i (X) represents the variable weight of the evaluation index.

[0109] Based on the calculation of the integration and membership degree of hydropower station equipment, and in accordance with the principle of maximum integration and membership degree, the safety level of hydropower station equipment is determined as follows:

[0110] j = Max{μ1,μ2,...μ n} (17)

[0111] In practical engineering, the safety status of hydropower station equipment changes with the safety management of the project. To more scientifically determine the safety status of hydropower station equipment, this invention utilizes the integrated membership degree of hydropower station equipment across different safety levels to establish the level characteristic variable j of the hydropower station equipment to be evaluated. * .

[0112]

[0113] In the formula, n represents the number of evaluation levels for hydropower station equipment; j represents the level name, j = (1, 2, 3, 4, 5), using j * This is to determine the trend of hydropower station equipment transitioning to a nearby safety level. The management system can dynamically obtain the safety level of hydropower station equipment and facilities and the potential safety trends of their transition in a timely manner.

[0114] The operation and maintenance (O&M) management strategy library pre-stores multiple one-to-one correspondences between hydropower station equipment evaluation levels and their corresponding O&M management strategies. When determining the O&M management strategy, the hydropower station equipment status (e.g., limit switch status, brake gate status, pressure gauge counts, and integrated brake valve group IoT data) is first input into the variable weight-set-extension fusion model to obtain the hydropower station equipment evaluation level output by the model (e.g., the safety level of the braking device is level 3). The hydropower station equipment evaluation level is then matched with the hydropower station equipment evaluation levels in the O&M management strategy library to determine the O&M management strategy (e.g., the braking device's safety level is level 3, the level description is that the equipment and facilities have safety hazards, corresponding control measures need to be formulated, and rectification must be carried out within a specified time limit; the O&M management strategy is: arrange personnel to inspect the braking device and restore its safety level to level 1 within 48 hours).

[0115] After determining the operation and maintenance management strategy, it is then implemented. For example, dispatching maintenance personnel to the braking system for maintenance, while clearly defining the task deadlines.

[0116] This invention conducts a safety assessment of hydropower station equipment status by constructing a variable weight-set pair-extension fusion model to obtain a safety assessment level. Based on the safety assessment level and an operation and maintenance management strategy library, operation and maintenance management strategies are determined and applied. The model sets dynamic indicator weights, enabling accurate assessment of equipment safety status and further improving the timeliness and suitability of subsequent hydropower station operation and maintenance management.

[0117] In one embodiment, the method for obtaining the status of hydropower station equipment in the strategy determination module includes:

[0118] Data from hydropower station equipment is acquired using industrial IoT technology.

[0119] By aggregating all data of the same hydropower station equipment, the status of the hydropower station equipment can be obtained.

[0120] The working principle and beneficial effects of the above technical solution are as follows:

[0121] The hydropower station equipment data is collected based on Industrial Internet of Things (IIoT) technology, including data such as limit switch status, brake gate status, pressure gauge counts, and integrated brake valve group IoT data. By aggregating all equipment data from the same hydropower station, the overall equipment status is obtained. For example, the limit switch status, brake gate status, pressure gauge counts, and integrated brake valve group IoT data represent the "braking device" status of the hydropower station equipment. This invention utilizes IIoT technology to obtain hydropower station equipment status, making the process more efficient.

[0122] This invention provides a dynamic operation and maintenance management system for hydropower station equipment based on a variable weight-set pair-extension fusion model, and further includes:

[0123] The auxiliary operation and maintenance module is used to match the best operation and maintenance personnel and provide auxiliary operation and maintenance based on the corresponding operation and maintenance management strategy when manual operation and maintenance is involved.

[0124] The auxiliary operation and maintenance module performs the following operations:

[0125] S41: Analyze the operation and maintenance management strategy and determine the target operation and maintenance tasks;

[0126] S42: Obtain the historical maintenance tasks of idle maintenance personnel within the first time period;

[0127] S43: Mark the first feature of the historical operation and maintenance task of the same task type as the target operation and maintenance task on the preset time axis based on the execution time of the corresponding historical operation and maintenance task. The first feature includes: the safety evaluation level of the hydropower station equipment corresponding to the historical operation and maintenance task and the operation and maintenance evaluation level of the historical operation and maintenance task.

[0128] S44: If the first feature satisfies the matching triggering condition, obtain the time axis point that exists in the time axis point corresponding to each feature distribution as the target axis point; the matching triggering condition includes: the feature distribution of the first feature of the feature type on the time axis satisfies the preset standard feature distribution of the feature type;

[0129] S45: If successful, extract the second feature based on the historical maintenance tasks corresponding to the target axis point;

[0130] S46: Based on the preset matching template of the second feature and the second feature, obtain the idle maintenance personnel corresponding to the second feature with the largest matching value as the best maintenance personnel;

[0131] S47: When the best operations and maintenance personnel are involved in operations and maintenance, assist operations and maintenance based on the corresponding operations and maintenance management strategies.

[0132] The working principle and beneficial effects of the above technical solution are as follows:

[0133] The optimal maintenance personnel are defined as the staff best suited for the maintenance management strategy of the hydropower station equipment. This refers to the optimal maintenance personnel for the hydropower station equipment requiring maintenance management and the corresponding maintenance management strategy for that equipment. Assisted maintenance refers to the process of assisting the optimal maintenance personnel in the maintenance of hydropower station equipment, such as demonstrating a virtual 3D model of the problem to be solved to the optimal maintenance personnel.

[0134] When matching the best maintenance personnel, the first step is to determine the target maintenance tasks based on the maintenance management strategy. The target maintenance tasks are the tasks that need to be performed by humans, which are the ultimate goal of maintenance management. For example, the braking device is inspected and its safety level is adjusted from level 3 to level 1.

[0135] The first time period is a period of time that goes back from the current time to the past time. The length of this time period is preset by the operator, such as 30 days. The historical maintenance tasks are all maintenance tasks that have been completed by the idle maintenance personnel during this period.

[0136] The task type is defined as the type of task, such as: maintenance of braking devices, maintenance of speed governor hydraulic devices, etc. The preset timeline starts at the beginning of the aforementioned time period and ends at the midpoint of that time period. The first feature is extracted based on a preset feature extraction template corresponding to the feature type. For example, if the feature type is safety evaluation, the corresponding preset feature extraction template is: a template for extracting the safety evaluation level of relevant hydropower station equipment for comparison with historical maintenance tasks. The execution time of the corresponding historical maintenance task is marked on the timeline for the first feature.

[0137] The matching trigger condition is: the feature distribution of the first feature of the feature type on the time axis meets the preset standard feature distribution of the feature type. The preset standard feature distribution of the feature type is set manually in advance. For example, when the feature type is safety evaluation, the standard feature distribution is: the distribution of the first feature (historical safety evaluation level) less than or equal to the safety evaluation level of the hydropower station equipment status on the time axis; or, for example, when the feature type is operation and maintenance evaluation, the standard feature distribution is: the distribution of the first feature (historical operation and maintenance evaluation level) greater than or equal to the evaluation level threshold on the time axis.

[0138] When determining whether the matching trigger condition is met, it is determined whether the feature distribution of the first feature of the feature type on the time axis meets the preset standard feature distribution of the feature type. For example, when the feature type is safety evaluation, the first feature of the feature type is used as the y-axis and the time axis as the x-axis. A line parallel to the x-axis is drawn according to the safety evaluation level of the hydropower station equipment status. If there is a marked first feature below the line, then the feature distribution of the corresponding first feature when the feature type is safety evaluation meets the standard feature distribution. Similarly, when the feature type is operation and maintenance evaluation, the first feature of the feature type is used as the y-axis and the time axis as the x-axis. A line parallel to the x-axis is drawn according to the evaluation level threshold. If there is a marked first feature above the line, then the feature distribution of the corresponding first feature when the feature type is operation and maintenance evaluation meets the standard feature distribution. When the feature distribution of the first feature of all feature types meets the preset standard feature distribution of the corresponding feature type, the time axis point that exists in the time axis point corresponding to each feature distribution is obtained as the target axis point. If the acquisition is successful, the second feature is extracted according to the historical operation and maintenance task corresponding to the target axis point. The second feature is the historical evaluation index value of the historical operation and maintenance task. Introducing matching trigger conditions to trigger the extraction of the second feature greatly reduces the resources required for extracting the second feature.

[0139] The second feature pre-sets a matching template for calculating the similarity value of historical evaluation index values ​​and evaluation index values ​​of hydropower equipment that triggers the target maintenance task. For example, it compares the limit switch status, brake gate status, pressure gauge count value, and integrated brake valve group IoT data in the historical maintenance task corresponding to the target axis point with the similarity value (matching value) of the limit switch status, brake gate status, pressure gauge count value, and integrated brake valve group IoT data of hydropower equipment in the target maintenance task. It adaptively obtains the corresponding matching template according to the second feature, improving the matching efficiency of the best maintenance personnel.

[0140] Once the best maintenance personnel are identified, they are reminded to go to the corresponding hydropower station equipment that needs maintenance. After the best maintenance personnel are connected to the maintenance team, they will provide auxiliary maintenance based on the corresponding maintenance management strategy.

[0141] This invention extracts the first feature of historical maintenance tasks of the same task type as the target maintenance task. When the first feature meets the matching trigger condition, the second feature is then extracted. The second feature is the historical evaluation index value of the historical maintenance task, which includes multiple index types. Directly matching the historical evaluation index values ​​of all historical maintenance tasks would waste a lot of computing resources. Introducing the matching trigger condition to make condition judgments in advance greatly improves the efficiency of determining the best maintenance personnel and consumes less computing resources.

[0142] In one embodiment, the auxiliary operation and maintenance module also performs the following operations:

[0143] When the first feature does not meet the matching trigger condition or the target axis point fails to be obtained, the first time period is extended based on the preset time period extension rule to obtain the second time period. The second time period replaces the first time period in S42 and S42-S47 are executed until the best maintenance personnel are matched.

[0144] The working principle and beneficial effects of the above technical solution are as follows:

[0145] When the first feature does not meet the matching trigger condition or the target axis point fails to be acquired, the first time period is extended based on the preset time period extension rule (e.g., 30 days each time) to obtain the second time period. The second time period replaces the first time period in S42 and S42-S47 are executed until the best maintenance personnel are matched, which improves the comprehensiveness of matching situation identification.

[0146] In one embodiment, the auxiliary operation and maintenance module provides auxiliary operation and maintenance based on the corresponding operation and maintenance management strategy when the best operation and maintenance personnel intervene in operation and maintenance, including:

[0147] Based on the historical operation and maintenance tasks corresponding to the second feature with the largest matching value, a pre-simulation model is constructed.

[0148] Based on the results of the pre-simulation model and the rules for determining the timing of management intervention, the timing of management intervention is determined.

[0149] Model slices for obtaining the timing of management intervention;

[0150] Based on the model slices, obtain the intervention queue;

[0151] Pre-trigger intervention management commands in the intervention queue based on the first intervention operation and maintenance status information;

[0152] Based on the model slice corresponding to the pre-triggered successful intervention management instruction, obtain the second intervention operation and maintenance real-time information;

[0153] Determine whether the pre-triggered intervention management command has been successfully triggered based on the second intervention and maintenance status information.

[0154] If so, assist in operation and maintenance based on intervention management commands that are triggered by certain factors.

[0155] The working principle and beneficial effects of the above technical solution are as follows:

[0156] Generally, when performing similar historical maintenance tasks, operations and maintenance personnel will perform the tasks according to their personal experience. However, even if the tasks are the same, the management expectations for the maintenance tasks may be different. For example, historical maintenance tasks may require completion within 48 hours, while current maintenance tasks may require completion within 24 hours.

[0157] Therefore, a pre-simulation model is constructed based on the historical maintenance tasks corresponding to the second feature with the largest matching value. The pre-simulation model is a 3D model of the best maintenance personnel performing the hydropower station equipment maintenance tasks, built based on the task records of historical maintenance tasks (e.g., on-site video of the best maintenance personnel performing the task). The pre-simulation result is the task progress of each task stage simulated by the pre-simulation model.

[0158] The rules for setting the timing of management intervention are determined based on the operation and maintenance management strategy. The operation and maintenance management strategy predicts the extent to which the operation and maintenance tasks should be executed in each task phase. For example, personnel should arrive on site within 2 hours, the preliminary arrangement of operation and maintenance work should be completed within 3 hours, and the initial inspection of equipment should be completed within 5 hours. If the execution level of a task phase does not meet the management expectations, the starting point of that task phase is set as the timing for management intervention.

[0159] Based on the timing of management intervention, model slices are extracted from the pre-simulation model. These slices include all slices from the pre-simulation model after the management intervention timing to the end point of the task phase, encompassing all influencing factors affecting the management expectations for that task phase. The intervention queue includes multiple intervention management instructions, each associated with the management intervention timing. These instructions are generated based on all the aforementioned influencing factors, such as detecting that the optimal maintenance personnel in the model only complete the initial equipment inspection 6 hours after task assignment. The management intervention timing is the starting point of the initial equipment inspection phase (e.g., the moment the initial deployment of maintenance work has just ended). Model slices representing the management intervention timing are obtained (e.g., model slices of the initial equipment inspection task phase). All influencing factors affecting the management expectations for that task phase are extracted from these model slices (factors affecting the initial inspection speed, such as maintenance personnel chatting or unreasonable initial inspection strategies). An intervention queue is determined, for example: [issuing reminders during chatter or planning reasonable strategies when the initial inspection strategy is inappropriate].

[0160] The first intervention and maintenance real-time information is the video footage of the maintenance work captured by the engineering recorder worn by the maintenance personnel themselves. Although there are other monitoring devices on site at the hydropower station, these devices also perform other monitoring tasks and cannot be used continuously. Therefore, intervention management commands are pre-triggered.

[0161] When pre-triggering intervention management commands, the pre-triggering factors are obtained. For example, the pre-triggering factor for issuing a reminder during casual conversation is the identification of multiple semantics unrelated to the operation and maintenance scenario; another example is the pre-triggering factor for planning a reasonable strategy when the initial inspection strategy is inappropriate, which is the identification of the wrong testing tool being used. Pre-triggering factors are collected and identified through the engineering recorder.

[0162] However, the limited availability of a single data collection device for the first intervention and maintenance (O&M) information can lead to limited collection of pre-triggering factors. Therefore, upon successful pre-triggering of an intervention management command, the model slice corresponding to the command is identified. The "corresponding" in the model slice indicates that the basis for the intervention management command's formulation (information on expected influencing factors) originates from that model slice. Following successful pre-triggering, the data source device for constructing the corresponding model slice is activated. The configuration information of the source device is obtained based on the model slice corresponding to the intervention management command, and the collected data after configuration is used as the second intervention and O&M information. The second intervention and O&M information is used to determine whether a successfully pre-triggered intervention management command has been triggered. If so, O&M is assisted based on the confirmed trigger (e.g., reminding O&M personnel not to engage in frequent idle chat via a mobile terminal configured by the personnel), significantly improving the efficiency of intervention command determination.

[0163] This invention provides a dynamic operation and maintenance management method for hydropower station equipment based on a variable weight-set pair-extension fusion model, such as... Figure 3 As shown, it includes:

[0164] Step 1: Construct a variable weight-set pair-extension fusion model;

[0165] Step 2: Based on the variable weight-set pair-extension fusion model, determine the safety evaluation level of hydropower station equipment status and the operation and maintenance management strategy library, and then determine the operation and maintenance management strategy.

[0166] Step 3: Apply operation and maintenance management strategies;

[0167] Step 4: Match the best maintenance personnel and provide auxiliary maintenance based on the corresponding maintenance management strategy when manual maintenance is required;

[0168] Step 1: Constructing a variable-weight-set-extension fusion model, including:

[0169] The constant weights of the indicators are determined based on the structural entropy weighting method;

[0170] Based on the theory of variable weights, the constant weights are dynamically adjusted to determine the variable weights of the indicators.

[0171] By coupling set pair theory and matter-element extension method and combining them with variable weights, a variable weight-set pair-extension coupled evaluation model is constructed.

[0172] The indicators are dynamically updated based on scores from experts or staff familiar with hydropower station equipment and facilities.

[0173] Step 4: Matching the best maintenance personnel, and providing assisted maintenance based on corresponding maintenance management strategies when manual intervention is required, including:

[0174] S41: Analyze the operation and maintenance management strategy and determine the target operation and maintenance tasks;

[0175] S42: Obtain the historical maintenance tasks of idle maintenance personnel within the first time period;

[0176] S43: Mark the first feature of the historical operation and maintenance task of the same task type as the target operation and maintenance task on the preset time axis based on the execution time of the corresponding historical operation and maintenance task. The first feature includes: the safety evaluation level of the hydropower station equipment corresponding to the historical operation and maintenance task and the operation and maintenance evaluation level of the historical operation and maintenance task.

[0177] S44: If the first feature satisfies the matching triggering condition, obtain the time axis point that exists in the time axis point corresponding to each feature distribution as the target axis point; the matching triggering condition includes: the feature distribution of the first feature of the feature type on the time axis satisfies the preset standard feature distribution of the feature type;

[0178] S45: If successful, extract the second feature based on the historical maintenance tasks corresponding to the target axis point;

[0179] S46: Based on the preset matching template of the second feature and the second feature, obtain the idle maintenance personnel corresponding to the second feature with the largest matching value as the best maintenance personnel;

[0180] S47: When the best maintenance personnel are involved in maintenance, assist maintenance based on the corresponding maintenance management strategy;

[0181] When the best maintenance personnel intervene in maintenance, the auxiliary maintenance based on the corresponding maintenance management strategy includes:

[0182] Based on the historical operation and maintenance tasks corresponding to the second feature with the largest matching value, a pre-simulation model is constructed.

[0183] Based on the results of the pre-simulation model and the rules for determining the timing of management intervention, the timing of management intervention is determined.

[0184] Model slices for obtaining the timing of management intervention;

[0185] Based on the model slices, obtain the intervention queue;

[0186] Pre-trigger intervention management commands in the intervention queue based on the first intervention operation and maintenance status information;

[0187] Based on the model slice corresponding to the pre-triggered successful intervention management instruction, obtain the second intervention operation and maintenance real-time information;

[0188] Determine whether the pre-triggered intervention management command has been successfully triggered based on the second intervention and maintenance status information.

[0189] If so, assist in operation and maintenance based on intervention management commands that are triggered by certain factors.

[0190] In one embodiment, the method for obtaining the status of the hydropower station equipment in step 2 includes:

[0191] Data from hydropower station equipment is acquired using industrial IoT technology.

[0192] By aggregating all data of the same hydropower station equipment, the status of the hydropower station equipment can be obtained.

[0193] In one embodiment, step 4: matching the best maintenance personnel and providing assisted maintenance based on the corresponding maintenance management strategy when manual intervention is required, further includes:

[0194] When the first feature does not meet the matching trigger condition or the target axis point fails to be obtained, the first time period is extended based on the preset time period extension rule to obtain the second time period. The second time period replaces the first time period in S42 and S42-S47 are executed until the best maintenance personnel are matched.

[0195] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A dynamic operation and maintenance management system for hydropower station equipment based on a variable weight-set pair-extension fusion model, characterized in that, include: The fusion model building module is used to construct a variable weight-set pair-extension fusion model; The strategy determination module is used to determine the operation and maintenance management strategy based on the safety evaluation level of the hydropower station equipment status and the operation and maintenance management strategy library, based on the variable weight-set pair-extension fusion model. The strategy application module is used to apply operation and maintenance management strategies. The auxiliary operation and maintenance module is used to match the best operation and maintenance personnel and provide auxiliary operation and maintenance based on the corresponding operation and maintenance management strategies when manual intervention is required. This includes: S41: Analyze the operation and maintenance management strategy and determine the target operation and maintenance tasks; S42: Obtain the historical maintenance tasks of idle maintenance personnel within the first time period; S43: Mark the first feature of the historical operation and maintenance task of the same task type as the target operation and maintenance task on the preset time axis based on the execution time of the corresponding historical operation and maintenance task. The first feature includes: the safety evaluation level of the hydropower station equipment corresponding to the historical operation and maintenance task and the operation and maintenance evaluation level of the historical operation and maintenance task. S44: If the first feature satisfies the matching triggering condition, obtain the time axis point that exists in the time axis point corresponding to each feature distribution as the target axis point; the matching triggering condition includes: the feature distribution of the first feature of the feature type on the time axis satisfies the preset standard feature distribution of the feature type; S45: If successful, extract the second feature based on the historical maintenance tasks corresponding to the target axis point; S46: Based on the preset matching template of the second feature and the second feature, obtain the idle maintenance personnel corresponding to the second feature with the largest matching value as the best maintenance personnel; S47: When the best maintenance personnel are involved in maintenance, assist maintenance based on the corresponding maintenance management strategy; S47: When the best maintenance personnel intervene in maintenance, auxiliary maintenance is carried out based on the corresponding maintenance management strategy, including: Based on the historical operation and maintenance tasks corresponding to the second feature with the largest matching value, a pre-simulation model is constructed. Based on the results of the pre-simulation model and the rules for determining the timing of management intervention, the timing of management intervention is determined. Model slices for obtaining the timing of management intervention; Based on the model slices, obtain the intervention queue; Pre-trigger intervention management commands in the intervention queue based on the first intervention operation and maintenance status information; Based on the model slice corresponding to the pre-triggered successful intervention management instruction, obtain the second intervention operation and maintenance real-time information; Determine whether the pre-triggered intervention management command has been successfully triggered based on the second intervention and maintenance status information. If so, assist in operation and maintenance based on intervention management commands that are triggered by certain factors.

2. The dynamic operation and maintenance management system for hydropower station equipment based on the variable weight-set pair-extension fusion model as described in claim 1, characterized in that, The fusion model building module constructs a variable weight-set pair-extension fusion model, including: The constant weights of the indicators are determined based on the structural entropy weighting method; Based on the theory of variable weights, the constant weights are dynamically adjusted to determine the variable weights of the indicators. By coupling set pair theory and matter-element extension method and combining them with variable weights, a variable weight-set pair-extension coupled evaluation model is constructed. The indicators are dynamically updated based on scores from experts or staff familiar with hydropower station equipment and facilities.

3. A dynamic operation and maintenance management method for hydropower station equipment based on a variable weight-set pair-extension fusion model, characterized in that, include: Step 1: Construct a variable weight-set pair-extension fusion model; Step 2: Based on the variable weight-set pair-extension fusion model, determine the safety evaluation level of hydropower station equipment status and the operation and maintenance management strategy library, and then determine the operation and maintenance management strategy. Step 3: Apply operation and maintenance management strategies; Step 4: Match the best operations and maintenance personnel to assist in operations and maintenance based on the corresponding operations and maintenance management strategies when manual intervention is required, including: S41: Analyze the operation and maintenance management strategy and determine the target operation and maintenance tasks; S42: Obtain the historical maintenance tasks of idle maintenance personnel within the first time period; S43: Mark the first feature of the historical operation and maintenance task of the same task type as the target operation and maintenance task on the preset time axis based on the execution time of the corresponding historical operation and maintenance task. The first feature includes: the safety evaluation level of the hydropower station equipment corresponding to the historical operation and maintenance task and the operation and maintenance evaluation level of the historical operation and maintenance task. S44: If the first feature satisfies the matching triggering condition, obtain the time axis point that exists in the time axis point corresponding to each feature distribution as the target axis point; the matching triggering condition includes: the feature distribution of the first feature of the feature type on the time axis satisfies the preset standard feature distribution of the feature type; S45: If successful, extract the second feature based on the historical maintenance tasks corresponding to the target axis point; S46: Based on the preset matching template of the second feature and the second feature, obtain the idle maintenance personnel corresponding to the second feature with the largest matching value as the best maintenance personnel; S47: When the best maintenance personnel are involved in maintenance, assist maintenance based on the corresponding maintenance management strategy; S47: When the best maintenance personnel intervene in maintenance, auxiliary maintenance is carried out based on the corresponding maintenance management strategy, including: Based on the historical operation and maintenance tasks corresponding to the second feature with the largest matching value, a pre-simulation model is constructed. Based on the results of the pre-simulation model and the rules for determining the timing of management intervention, the timing of management intervention is determined. Model slices for obtaining the timing of management intervention; Based on the model slices, obtain the intervention queue; Pre-trigger intervention management commands in the intervention queue based on the first intervention operation and maintenance status information; Based on the model slice corresponding to the pre-triggered successful intervention management instruction, obtain the second intervention operation and maintenance real-time information; Determine whether the pre-triggered intervention management command has been successfully triggered based on the second intervention and maintenance status information. If so, assist in operation and maintenance based on intervention management commands that are triggered by certain factors.

4. The dynamic operation and maintenance management method for hydropower station equipment based on the variable weight-set pair-extension fusion model as described in claim 3, characterized in that, Step 1: Construct a variable weight-set pair-extension fusion model, including: The constant weights of the indicators are determined based on the structural entropy weighting method; Based on the theory of variable weights, the constant weights are dynamically adjusted to determine the variable weights of the indicators. By coupling set pair theory and matter-element extension method and combining them with variable weights, a variable weight-set pair-extension coupled evaluation model is constructed. The indicators are dynamically updated based on scores from experts or staff familiar with hydropower station equipment and facilities.

Images