Multi-party coupling consultation scheduling method for maintenance operations of mountain wind turbines

Abstract

The present invention discloses a method for negotiating and scheduling maintenance operations for mountain wind turbines, including the following steps: at a negotiation decision node, each maintenance operation participant formulates a variety of local operation scheduling plans based on scheduling environment information and cost cycle demands, and combines and integrates them to form an initial solution set for a global maintenance operation scheduling plan combination; uses consistency filtering and reduction to pre-process the initial solution set, deletes invalid redundant solutions that do not meet constraints or have conflicting interference, and obtains a feasible global solution set; establishes a sequential serial game negotiation model to assist in obtaining a better decision result that takes both local and global considerations into account. The present invention effectively solves the multi-agent scheduling conflict problem in mountain wind turbine maintenance by negotiating a combined scheduling plan, filtering invalid solutions, and analyzing the game model, enhancing the collaborative efficiency and decision-making scientificity of maintenance operations under complex terrain, and providing a systematic scheduling solution for wind power equipment maintenance.

Description

Technical Field

[0001] The present invention relates to a scheduling operation method, and more particularly to a multi-party coupled maintenance operation negotiation scheduling method for mountain wind turbines. Background Art

[0002] Wind turbine maintenance in complex mountainous environments is a dynamic decision-making process involving multiple decision nodes and coupled negotiation among multiple maintenance participants. At some decision nodes, multiple participants (responsible for addressing detailed maintenance needs at different levels and domains) may experience coupled interference in maintenance operation content, such as cycle, space, object, and goal. This necessitates negotiation, decision-making, and adjustment of relevant content within a comprehensive operation plan (containing sub-operation plans for each participant's maintenance content) (i.e., negotiation and optimization among multiple operation plan combinations). At this point, the multiple participants in the negotiation are prone to asymmetric and inconsistent cognition of local and global desired maintenance objectives (including differing starting points and understandings). This asymmetric conflict in the cognitive judgments of different participants regarding different operation plan combinations regarding predetermined goals such as cost, cycle, and risk, and the expected "value" or "priority" occurs at each decision node, affecting not only the decision outcome at that node but also the evolution of the desired quality and efficiency of the maintenance operations. Summary of the Invention

[0003] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a multi-party coupled maintenance operation negotiation scheduling method for mountain wind turbines that can help promote the expected results of maintenance operations to converge to a better expected quality and efficiency level.

[0004] To achieve the above-mentioned object, the present invention provides the following technical solution: a method for multi-party coupled maintenance and repair negotiation scheduling of mountain wind turbines, comprising the following steps:

[0005] Step 1: At a negotiation decision node, based on the current job scheduling environment and their respective demands for cost and cycle time, each maintenance operation participant in the negotiation, combined with their own understanding, develops multiple acceptable local job scheduling solutions for their respective maintenance needs. These solutions are then combined and integrated to form an initial solution set for the global maintenance operation scheduling solution combination.

[0006] Step 2: Use consistency filtering and reduction to preprocess the initial solution set formed in step 1 to delete local conflict interference invalid redundant solutions that do not meet the job scheduling constraints or cannot form a feasible global job scheduling solution combination, and obtain a feasible global job scheduling solution combination solution set;

[0007] Step three, establish a sequential serial game negotiation model, through which the negotiation process among multiple agents in the combined solution space of multiple feasible job scheduling schemes is characterized and analyzed, to assist in obtaining a relatively optimal decision-making result that takes into account both the local and global aspects.

[0008] As a further improvement of the present invention, the consistency filtering and reduction steps used in step 2 are as follows:

[0009] Step 21: Analyze the correlation between the sub-maintenance requirements, evaluate and calculate the relative importance of each sub-maintenance requirement, and arrange them in descending order of importance to obtain a new sub-maintenance requirement sequence TS, where the requirement Ts i The relative importance is greater than or equal to Ts i +1; Establish demand coupling correlation matrix C n×n , c ij Represents the demand Ts ranked by relative importance i i and the demand Ts ranked as j i The coupling relationship between them:

[0010] ;

[0011] Step 22: Select each item Ts in the maintenance requirement sequence TS obtained in step 21 in turn i , search matrix C n×n And judge c ij The value of c ij =1, j∈i+1,i+2,…,n, then for each solution combination in the initial solution set of the global maintenance operation scheduling solution obtained in step 1, Ts i The corresponding local job scheduling scheme is the current filter reduction comparison reference item, where Ts j The corresponding local operation scheduling schemes are compared and judged for conflicts and interferences. If there is a conflict, the scheme combination solution is deleted from the initial solution set of the global maintenance operation scheduling scheme combination;

[0012] Step 2 and step 3: After the filtering and reduction process is completed, the consistency filtering and reduction results of the initial solution set of the global maintenance operation scheduling scheme combination are output to obtain the feasible global operation scheduling scheme combination solution set.

[0013] As a further improvement of the present invention, a sequential serial game negotiation model established in the step three includes two serial game negotiation stages, specifically a first-stage Nash equilibrium candidate solution set acquisition stage based on non-cooperative game and a second-stage global job scheduling scheme combination solution negotiation and optimization decision-making stage based on cooperative game. In the first-stage non-cooperative game, the comprehensive expected realization level of the local maintenance goals associated with the sub-maintenance demands undertaken by each negotiating subject is used as a measure to coordinate the demands conflicts between the subjects. At the same time, considering the fault tolerance of fuzzy cognitive evaluation data, the feasible combination solution set with utility value exceeding a specific threshold is retained as the candidate solution set of the second-stage cooperative game; in the second-stage cooperative game, the alliance game model of the cooperative game is used to negotiate and optimize a maintenance job scheduling solution with the optimal compromise of the comprehensive expected realization level of the global maintenance goal from the candidate solution set output in the first stage.

[0014] As a further improvement of the present invention, the negotiation game in the first stage of step 3 is modeled using a non-cooperative game model and represented as G=(P i ;S i ;U i ), i∈1,2,3,…,n, including the three elements of game subject, game subject strategy, and game subject utility; among them, the game subject P i Corresponding to the negotiation subjects who undertake the coupling-related maintenance requirements; the game subject strategy S i The combined solution of the feasible operation scheduling scheme after filtering and reduction corresponding to the subset of maintenance requirements undertaken by each negotiating subject; the utility of the game subject Ui corresponds to the satisfaction degree of the maintenance operation scheduling expectations of each subject, by measuring the satisfaction and expected realization level of their respective local maintenance goals Carry out characterization of it.

[0015] As a further improvement of the present invention, the game subject P p The overall expected level of achievement of all associated local maintenance objectives for each sub-maintenance requirement undertaken The calculation formula for measuring is:

[0016]

[0017] Among them, dg p is the total number of associated local maintenance objectives, is the relative weight of the associated local maintenance objective j, is the expected level of achievement of the associated local maintenance target j, To divide P p The content of the operation scheduling plan for the maintenance and repair requirements undertaken by other game entities other than the game entity P p The impact of the expected level of achievement of local maintenance target j associated with the undertaken maintenance needs.

[0018] As a further improvement of the present invention, the The calculation formula for measuring is:

[0019]

[0020] Among them, dv p For the game subject P p The number of maintenance and repair requirements undertaken. To define the game subject P p The degree of influence of the optional operation scheduling scheme k of the sub-maintenance demand i in the sub-maintenance demand undertaken on the expected level of achievement of the associated local maintenance target j is The value of is obtained by using a finite The evaluation language term set H for odd-numbered labels is (extremely negative impact, strong negative impact, moderate negative impact, weak negative impact, no impact, weak positive impact, moderate positive impact, strong positive impact, extremely strong positive impact) and the cloud model is used for quantitative analysis and calculation. When the optional operation scheduling scheme k of the maintenance demand i negatively affects the expected level of realization of the associated local maintenance target j, When , the optional job scheduling scheme k for the maintenance demand i positively affects the expected achievement level of the associated local maintenance target j.

[0021] As a further improvement of the present invention, the The calculation formula for measuring is:

[0022]

[0023] Among them, m is the total number of tasks, Cc i,j It quantifies the positive and negative correlations between local maintenance objectives and characterizes the dependency or conflict relationship between them.

[0024] As a further improvement of the present invention, the Cc i,j By introducing covariance and correlation coefficient to measure the positive and negative correlation Cc between local maintenance targets i and j i,j The measurement calculation formula is:

[0025]

[0026]

[0027]

[0028] Among them, RO iis the correlation vector between local target i and all global targets, RO i =(ro i,1 ,ro i,2 ,…,ro i,k ),ro i,q Represents the correlation between the local target i and the global target q; Cov(.) is the covariance; E[.] is the expectation; RO i Standard deviation; is the mean of the correlation between local target i and all global targets.

[0029] As a further improvement of the present invention, the process of obtaining the candidate solution set for the second-stage cooperative game through non-cooperative game negotiation analysis in the first stage is:

[0030] Step 3.1: Select each feasible strategy combination of each game player in turn, calculate the utility value of each game player under the strategy, and use the following formula to calculate the utility value of the corresponding combination:

[0031] ;

[0032] Step 32: Use the combination comparison procedure to determine whether the selected strategy combination satisfies Nash equilibrium according to the following formula. If Nash equilibrium is satisfied, any individual change to the strategy combination by each player will reduce their own benefits:

[0033]

[0034] in, and They are the strategy of the game subject Pi and the strategies of other game subjects at the Nash equilibrium;

[0035] Step 33: Obtain all strategy combinations that satisfy the Nash equilibrium, using the predefined combination utility threshold To select a set of candidate solutions for the two-stage cooperative game;

[0036]

[0037] in, and are the maximum and minimum combined utilities respectively, and α takes the empirical value of 0.8.

[0038] As a further improvement of the present invention, the second-stage global job scheduling solution combination solution negotiation optimization decision phase based on cooperative game in step 3 is modeled using the coalition game model and represented as G=(N,v), where N is the set of game entities, v is the utility function of all possible game coalitions, and satisfies And for all and Both , the negotiation and optimization process of the best combination solution is as follows:

[0039] Steps 3 and 4: Calculate the utility vector U(Xi) of each game subject under different feasible strategy combinations. The utility of each subject uses the expected realization level ST corresponding to the global maintenance goal. i To characterize, the measurement calculation formula is.

[0040]

[0041] Among them, Ncvi is the number of lower-level targets associated with the upper-level target i, and there are ;

[0042] Step 35: Calculate the alliance benefit function v;

[0043] Step 36: Allocate utility to the alliance. The utility allocation method in the alliance is determined using the Shapley value method. The components in the Shapley value vector are The calculation is as follows:

[0044]

[0045] Where alliance S is any subset of the set of game players N; |S| represents the number of game players contained in S, and v(S\{i}) represents the utility of the alliance composed of other game players in alliance S except game player i.

[0046] Step 37: Based on the solution of the Shapley value Φ and the utility vector U(Xi) of each player corresponding to the strategy combination Xi, the global expected return evaluation value βi corresponding to the strategy combination Xi can be calculated:

[0047] ;

[0048] Step 38: Select the strategy combination corresponding to the maximum βi value as the optimal combination solution for the global maintenance operation scheduling plan of the current negotiation decision node.

[0049] The beneficial effects of the present invention are as follows: the present invention addresses the problem that the existing technical solutions have largely ignored the asymmetric cognitive characteristics among multiple subjects in the maintenance negotiation decision-making process, and have also rarely considered the information ambiguity characteristics of the decision-making environment. The present invention has the advantages that the analytical model is closer to the actual situation of complex engineering, and the sequential decision-making results dynamically take into account both the local and the global aspects. While taking into account the satisfaction of the demands of various negotiation subjects under asymmetric cognition, the expected quality and efficiency level of the final maintenance operation is maximized, which can effectively help improve the quality and efficiency of remote health management and operation and maintenance decision-making response of wind turbine groups in complex mountainous environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a schematic diagram of the framework of the sequential negotiation decision-making method;

[0051] Figure 2 Schematic diagram of non-cooperative game problem model conversion. DETAILED DESCRIPTION

[0052] The present invention will be further described below with reference to the embodiments shown in the accompanying drawings.

[0053] Reference Figures 1 to 2 As shown, a multi-party coupled maintenance operation negotiation scheduling method for mountain wind turbines in this embodiment includes consistency filtering and reduction of maintenance operation scheduling scheme combination solutions, and sequential serial game negotiation decision-making of maintenance operation scheduling schemes, so as to achieve, at a certain negotiation decision node, a plurality of acceptable operation scheduling schemes determined by multiple negotiation subjects according to their respective maintenance needs, and the integrated combination is converted into an operation scheduling scheme combination solution set, that is, the initial solution space of the negotiation decision; then, in the consistency filtering and reduction link of the maintenance operation scheduling scheme combination solution in the method of the present invention, the initial solution space is reduced to obtain a combination solution set of multiple feasible operation scheduling schemes; then, in the sequential serial game negotiation decision link of the maintenance operation scheduling scheme in the method of the present invention, the best global operation scheduling scheme combination is selected from the multiple feasible operation scheduling scheme combination solution set through two-stage game negotiation.

[0054] The specific solution of this embodiment is as follows:

[0055] 1. Consistency filtering and reduction of maintenance operation scheduling scheme combination solutions

[0056] At a negotiation decision point, based on the current job scheduling environment and their respective demands for cost and cycle time, each participating maintenance operator, combined with their own understanding, develops multiple acceptable local job scheduling solutions for their respective maintenance needs. These solutions are then combined to form an initial set of combined solutions for the global maintenance job scheduling solution. Due to asymmetric cognition between the operators, some combined solutions in this initial set exhibit conflicts in local scheduling arrangements due to factors such as time, space, and resource usage, making them infeasible and unworkable global job scheduling solutions.

[0057] The method proposed in the present invention uses consistency filtering and reduction as a preprocessing step to delete local conflict interference invalid redundant solutions that do not meet the job scheduling constraints or cannot form a feasible global job scheduling solution combination, and obtains a feasible global job scheduling solution combination solution set, which is reduced and used as the preferred feasible solution search space for subsequent negotiation decisions.

[0058] The steps of consistency filtering reduction are as follows:

[0059] 1) Analyze the correlation between the sub-maintenance requirements, evaluate and calculate the relative importance of each sub-maintenance requirement, and arrange them in descending order of importance to obtain a new sub-maintenance requirement sequence TS, where the requirement Ts i The relative importance is greater than or equal to Ts i+1 ; Establish demand coupling association matrix C n×n , c ij Represents the demand Ts ranked by relative importance i i and the demand Ts ranked as j j The coupling relationship between them.

[0060] (1)

[0061] 2) Initialization: let i=1, j=i+1.

[0062] 3) Select maintenance requirements Ts i For the current filter reduction comparison reference, search matrix C n×n And judge c ij If the value of c ij =0, let j=j+1 and continue to judge c ij The value of c ij = 1, then select each item in the initial solution set of the global maintenance operation scheduling scheme combination in turn, with the demand Ts i The corresponding acceptable local job scheduling solution is priority guarantee, and the demand Ts j The corresponding acceptable local job scheduling solutions are compared and judged for conflicts and interferences. i The acceptable local job scheduling solution constitutes a feasible global job scheduling solution, which is deleted from the initial solution set, and then j=j+1 is set and c is judged. ij The value of .

[0063] 4) When j = n (n is the number of maintenance requirements in the sequence TS), set i = i + 1 and return to step 3.

[0064] 5) When i = n and j = n, the filtering and reduction process is completed, and the consistent filtering and reduction results of the initial solution set of the global maintenance operation scheduling scheme combination are output to obtain the feasible global operation scheduling scheme combination solution set.

[0065] 2. Serial game negotiation decision-making for maintenance operation scheduling

[0066] Taking into account the asymmetric cognition problem of job scheduling expectations and maintenance goals among multiple negotiating subjects, the method proposed in this invention establishes a sequential serial game negotiation model to characterize and analyze the negotiation process among multiple subjects in the combined solution space of multiple feasible job scheduling solutions, thereby assisting in obtaining relatively optimal decision-making results that take into account both local and global considerations.

[0067] The established sequential serial game negotiation model includes two serial game negotiation stages. In the first stage of non-cooperative game, the comprehensive expected realization level of the local maintenance goals associated with the sub-maintenance demands undertaken by each negotiating subject is used as a measure to coordinate the demands conflicts among the subjects. At the same time, the fault tolerance of fuzzy cognitive evaluation data is taken into account, and the feasible combination solution set with utility value exceeding a specific threshold is retained as the candidate solution set of the second stage cooperative game. In the second stage cooperative game, the alliance game model of cooperative game is used to negotiate and select a maintenance operation scheduling solution that compromises the comprehensive expected realization level of the global maintenance goal from the candidate solution set output in the first stage. The process schematic framework of the sequential serial game negotiation model is shown as follows. Figure 1 shown.

[0068] Furthermore, the one-stage solution for obtaining the Nash equilibrium candidate solution set based on non-cooperative game is as follows:

[0069] The one-stage negotiation game is modeled using the non-cooperative game model as G=(P i ;S i ;U i ), i∈1,2,3,…,n, including the three elements of game subject, game subject strategy, and game subject utility. i Corresponding to the negotiation subjects who undertake the coupling-related maintenance requirements; the game subject strategy S i The combined solution of the feasible operation scheduling scheme after filtering and reduction corresponding to the subset of maintenance requirements undertaken by each negotiation subject; the utility of the game subject U i Corresponding to the maintenance operation scheduling expectations of each subject, the satisfaction and expected realization level of each related local maintenance goal are measured to characterize the load. Considering the impact of different strategic choices of each game subject on each other's expectations, the comprehensive expected realization level of the associated local maintenance goals under the coupled decision-making with quantitative definition is used here. U i Take measurements.

[0070] A game subject P under coupled decision-making p The overall expected level of achievement of all associated local maintenance objectives for each sub-maintenance requirement undertaken The calculation formula for measuring is:

[0071] (2)

[0072] Among them, dg p is the total number of associated local maintenance objectives. is the relative weight of the associated local maintenance objective j. is the expected achievement level of the associated local maintenance objective j. To divide P p The content of the operation scheduling plan for the maintenance and repair requirements undertaken by other game entities other than the game entity P p The impact of the expected level of achievement of local maintenance target j associated with the undertaken maintenance needs.

[0073] for , the calculation formula is:

[0074] (3)

[0075] Among them, dv p For the game subject P p The number of maintenance and repair requirements undertaken. To define the game subject P p The degree of influence of the optional operation scheduling scheme k of the sub-maintenance demand i in the sub-maintenance demand undertaken on the expected level of achievement of the associated local maintenance target j is The value of is obtained by using a finite The evaluation language term set H for odd-numbered labels is (extremely negative impact, strong negative impact, moderate negative impact, weak negative impact, no impact, weak positive impact, moderate positive impact, strong positive impact, extremely strong positive impact) and the cloud model is used for quantitative analysis and calculation. When the optional operation scheduling scheme k of the maintenance demand i negatively affects the expected level of realization of the associated local maintenance target j, When , the optional job scheduling scheme k for the maintenance demand i positively affects the expected achievement level of the associated local maintenance target j.

[0076] for , considering the conflicts and dependencies between coupled maintenance objectives, when there is a positive correlation between the objectives, the more consistent the expected level of realization is, the more positive correction should be made, while when there is a negative correlation, the more consistent the expected level of realization is, the more negative correction should be made. Therefore, the entropy method can be combined for measurement. Here we define The calculation formula for measuring is:

[0077] (4)

[0078] Where m is the total number of tasks. i,j It quantifies the positive and negative correlations between local maintenance objectives and characterizes the dependency or conflict relationship between them.

[0079] For Cc i,j By introducing covariance and correlation coefficient to measure the positive and negative correlation Cc between local maintenance targets i and j i,j The measurement calculation formula is:

[0080] (5)

[0081] (6)

[0082] (7)

[0083] (8)

[0084] Among them, RO i is the correlation vector between local target i and all global targets, RO i =(ro i,1 ,ro i,2 ,…,ro i,k ),ro i,q Represents the correlation between the local target i and the global target q; Cov(.) is the covariance; E[.] is the expectation; RO i Standard deviation; is the mean of the correlation between local target i and all global targets.

[0085] Based on the filtered and reduced feasible global job scheduling solution set, and relying on the previously proposed game negotiation transformation model and utility value quantitative measurement calculation method, the process of obtaining the candidate solution set for the second-stage cooperative game through non-cooperative game negotiation analysis in the first stage is as follows:

[0086] 1) Select each feasible strategy combination of each game subject in turn, calculate the utility value of each game subject under the strategy, and use formula (9) to calculate the utility value of the corresponding combination.

[0087] (9)

[0088] Non-cooperative game utility matrix of feasible job scheduling strategy combinations

[0089]

[0090] *a is the product of the number of strategy items in the strategy space of each of the n game players

[0091] 2) Relying on the combination comparison procedure, according to formula (10), we determine whether the selected strategy combination satisfies Nash equilibrium. When Nash equilibrium is satisfied, any individual change to the strategy combination by each player will reduce its own benefits.

[0092] (10)

[0093] in, and They are the game subjects P at Nash equilibrium i strategies and the strategies of other game players.

[0094] 3) Obtain all strategy combinations that satisfy Nash equilibrium, using a predefined combination utility threshold To select the candidate solution set for the two-stage cooperative game (the threshold processing here is used to improve the tolerance of game negotiation decision-making to the ambiguity of cognitive evaluation information).

[0095] (11)

[0096] in, and are the maximum and minimum combined utilities respectively, and α=0.8 is taken as the empirical value.

[0097] Furthermore, the specific scheme for the two-stage global job scheduling scheme combination solution negotiation optimization decision based on cooperative game is as follows:

[0098] In the second stage, the candidate solutions obtained in the first stage are selected through negotiation and optimization, and the global expected quality and efficiency of the selected global job scheduling solution combination is improved as much as possible through cooperative game.

[0099] The two-stage negotiation game is modeled using the coalition game model as G=(N,v), where N is the set of game entities and v is the utility function of all possible game coalitions (subsets of N) that satisfy And for all and Both Here, each global maintenance objective is selected as the game subject, and the candidate solution set output in the first stage is used as the feasible strategy combination.

[0100] First, calculate the utility vector U(X i ), each subject's utility uses the expected level of realization of the corresponding global maintenance goal ST i To characterize, it is measured and calculated by formula (12).

[0101] (12)

[0102] Among them, Ncv i is the number of lower-level targets associated with the upper-level target i, .

[0103] Then, calculate the alliance benefit function v. When calculating, when the alliance consists of only a single player, use the "min-max criterion" to first calculate the maximum utility value of each player under different strategy combinations, and then take the minimum value as the measurement value of v. When the alliance consists of multiple players, take the minimum value of the sum of the utility values ​​of each player under different strategy combinations as the measurement value of v.

[0104] Then, the utility distribution of the alliance is carried out. The utility distribution method in the alliance is determined by the Shapley value method. The components in the Shapley value vector are Calculation refers to formula (13):

[0105] (13)

[0106] Among them, alliance S is any subset of the set of game entities N; |S| represents the number of game entities contained in S, and v(S\{i}) represents the utility of the alliance composed of other game entities in alliance S except game entity i.

[0107] Finally, according to the solution of Shapley value Φ and the corresponding strategy combination X i The utility vector U(X i ), we can calculate the strategy combination X i The corresponding global expected return evaluation value β i :

[0108] (14)

[0109] Among the candidate strategy combinations obtained in one stage, the maximum β i The strategy combination corresponding to the value is the global optimal maintenance operation scheduling solution combination solution selected by the decision node through negotiation.

[0110] The following examples are provided in this embodiment:

[0111] This article uses the operation and maintenance scheduling decision-making of wind turbines in complex mountainous environments as the background. The negotiation decision-making at the operation plan level of the coupled and associated operation tasks T1 (functional maintenance of the wind turbine generator subsystem) and T2 (functional maintenance of the wind turbine variable speed drive subsystem) of two maintenance operation participants P1 and P2 (the corresponding maintenance service providers of the two wind turbine subsystems) is selected as an example to illustrate the use of the technical method:

[0112] Due to the close coupling between the subsystems of wind turbines and the limitations of terrain, location and space for wind turbine maintenance operations, the two operation tasks T1 and T2 will inevitably have coupled interference in the operation arrangements in terms of the scheduling of technical personnel and special equipment arrival time, maintenance operation sequence, operation time, operation space occupancy, and maintenance equipment resource occupancy. Different operation scheduling arrangements will result in different operation resource occupancy, operation cycle and operation cost for each maintenance service provider, and will also affect the quality and efficiency level of the entire maintenance operation cycle. Therefore, negotiated decision-making is required.

[0113] The subject P1 negotiates and customizes the operation scheduling plan around the main maintenance requirements of T1, Ts1 (pitch jam maintenance), Ts2 (blade pitch deviation maintenance), Ts3 (internal circulation air cooling inlet overtemperature maintenance), and Ts4 (yaw brake pressure instability maintenance). The subject P2 negotiates and customizes the operation scheduling plan around the maintenance requirements of T2, Ts5 (wheel box oil temperature abnormality maintenance) and Ts6 (axle damage and abrasion maintenance). The corresponding acceptable operation plan solutions customized by each subject for different maintenance requirements (involving professional resource allocation, approach time, waiting time, operation sequence, operation location, operation cycle, etc., which are not related to the technical method of the present invention and are not listed in detail here) are compared with Table 1 below.

[0114] Table 1 Acceptable solutions for coupled maintenance content

[0115]

[0116] Based on the method steps proposed above (1. Consistency filtering and reduction of combined solutions for maintenance operation scheduling schemes), the experts first evaluated the relative weights of the six maintenance requirements Ts1, Ts2, Ts3, Ts4, Ts5, and Ts6 under the two operation tasks T1 and T2. The relative weights were 0.1926, 0.2143, 0.1571, 0.1729, 0.1254, and 0.1377, respectively. They were arranged in descending order of weight to be Ts2, Ts1, Ts4, Ts3, Ts6, and Ts5. The operational coupling relationship between each maintenance requirement is shown in Table 2. According to the consistency reduction steps, the experts filtered and deleted the 864 pairs of combined solutions corresponding to Table 1 without removing feasible solutions, and finally obtained a total of 20 feasible combined solutions, as shown in Table 3.

[0117] Table 2 Coupling relationship c ij

[0118]

[0119] Table 3. Combination solution set of feasible global job scheduling schemes

[0120]

[0121] For the two work tasks T1 and T2 that the entities P1 and P2 are responsible for respectively and the six sub-maintenance requirements Ts1, Ts2, Ts3, Ts4, Ts5, and Ts6, the overall maintenance objectives associated with T1 and T2 are cycle control dtt1, cost control dtt2, and maintenance satisfaction dtt3. The local maintenance objectives associated with the sub-maintenance requirements Ts1, Ts2, Ts3, and Ts4 under T1 include water cooling cycle detection and troubleshooting dst1, circuit false connection detection and troubleshooting dst2, sensor feedback detection and troubleshooting dst3, hydraulic circuit detection and troubleshooting dst4, and component deformation detection and troubleshooting dst5. The local maintenance objectives associated with the sub-maintenance requirements Ts5 and Ts6 under T2 include oil level and oil temperature detection and troubleshooting dst6, transmission link detection and troubleshooting dst7, and corrosion and wear detection and troubleshooting dst8. The cloud-based language terminology set evaluation calculations obtained the positive and negative correlations between local maintenance targets (see Table 4) and the correlations between local maintenance targets and global maintenance targets (see Table 5).

[0122] Table 4 Positive and negative correlations Cc between local targets i,j

[0123]

[0124] Table 5 Correlation between local and global targets ro i,q

[0125]

[0126] In the first stage of the sequential game negotiation decision-making of the maintenance operation scheduling plan, that is, the stage of obtaining the Nash equilibrium candidate solution set based on the non-cooperative game, according to the model definition of this stage, the game subjects P1 and P2 are selected. According to Table 3, the strategy space of the game subject P1 is {(A1,B1,C2,D1)、(A1,B1,C1,D1)、(A1,B1,C1,D2)、(A1,B1,C3,D1)、(A1,B1,C3,D2)、(A1,B1,C2,D2)、(A2,B1,C2,D2)、 The strategy space of the two players is {(E2,F3), (E2,F2), (E2,F1), (E1,F2), (E3,F2), (E1,F3), (E3,F1), (E3,F3)}. Since filtering and reduction have been performed in the first stage, the feasible strategy combinations of the two players here are only the 20 listed in Table 3.

[0127] For each feasible strategy combination, the expected level of achievement of the local maintenance target under the independent decision-making of the two negotiating subjects P1 and P2 is first evaluated based on formula (3), and then its correction value under the coupled decision-making is calculated according to formula (4), as shown in Table 6.

[0128] Table 6 Examples of partial evaluation results of the expected level of achievement of local maintenance objectives for each feasible strategy combination

[0129]

[0130] The utility of the two game subjects P1 and P2 is measured by the comprehensive expected realization level of the associated local maintenance goals under the coupled decision. According to the data in Table 6 and formula (2), the subject utility values ​​corresponding to each feasible strategy combination are obtained, as shown in Table 7. Based on the data in Table 7 and formula (11), the screening threshold is calculated as =1.1246, the candidate feasible strategy combinations for the next stage of cooperative game are: s3, s4, s6, s9, s 11 、s 16 、s 18 .

[0131] Table 7 Non-cooperative game utility matrix of each feasible strategy combination

[0132]

[0133] In the second stage of the sequential game negotiation decision of the maintenance operation scheduling plan, that is, the negotiation and optimization decision stage of the global operation scheduling plan combination solution based on the cooperative game, the pursuit of the maximization of the overall expected quality and efficiency level of the maintenance combination plan is carried out. According to the definition of the model in this stage, the three global maintenance goals dtt1, dtt2 and dtt3 are selected as the game subjects. The candidate solutions s3, s4, s6, s9, s10, s20, s30, s40, s60, s70, s80, s90, s100, s101, s102, s103, s104, s105, s106, s107, s108, s109, s110, s111, s112, s113, s114, s 11 、s 16 、s 18 As a feasible strategy combination, the utility of each game subject under different strategy combinations is measured and calculated by formula (12), and the alliance utility benefits of different alliance combinations are calculated at the same time. In combination with formula (13), the Shapley value method is used to determine the utility distribution. This distribution represents the optimal contribution distribution of each game subject to the overall game alliance utility. Then, according to formula (14), the feasible combination strategies s3, s4, s6, s9, s 11 、s 16 、s 18 The global expected return evaluation value β i The results are β3=1.5194, β4=1.7483, β6=2.6748, β9=3.1243, β 11 =2.1842, β 16=1.2164, β 18 =2.1132, and for the maximum value β9=3.1243, the corresponding strategy combination s9={A2,B1,C2,D2,E3,F2} is the optimal job scheduling solution selected by the current decision node negotiation.

[0134] To sum up, the multi-party coupled maintenance operation negotiation scheduling method for mountain wind turbines in this embodiment, compared with the methods in the prior art, can use the method proposed in this embodiment to assist in decision-making at each decision node based on the current actual task environment, which can help promote the expected results of maintenance operations to converge to a better expected quality and efficiency level.

[0135] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A multi-party coupled maintenance and repair negotiation scheduling method for mountain wind turbines, characterized by: The steps include: Step 1: At a negotiation decision node, based on the current job scheduling environment and their respective demands for cost and cycle time, each maintenance operation participant in the negotiation, combined with their own understanding, develops multiple acceptable local job scheduling solutions for their respective maintenance needs. These solutions are then combined and integrated to form an initial solution set for the global maintenance operation scheduling solution combination. Step 2: Use consistency filtering and reduction to preprocess the initial solution set formed in step 1, delete the local conflict interference invalid redundant solutions that do not meet the job scheduling constraints or cannot form a feasible global job scheduling solution combination, and obtain the feasible global job scheduling solution combination solution set; Step 3: Establish a sequential serial game negotiation model to characterize and analyze the negotiation process among multiple agents in the space of multiple feasible job scheduling solutions, and obtain a relatively optimal decision result that takes both local and global considerations into account. The consistency filtering and reduction steps used in step 2 are as follows: Step 21: Analyze the correlation between the sub-maintenance requirements, evaluate and calculate the relative importance of each sub-maintenance requirement, and arrange them in descending order of importance to obtain a new sub-maintenance requirement sequence TS, where the requirement Ts i The relative importance is greater than or equal to Ts i +1; Establish the demand coupling correlation matrix C n×n , c ij Represents the demand Ts ranked by relative importance i i and the demand Ts ranked as j i The coupling relationship between them: ； Step 22: Select each item Ts in the maintenance requirement sequence TS obtained in step 21 in turn i , search matrix C n×n And judge c ij The value of c ij =1, j∈i+1,i+2,…,n, then for each solution combination in the initial solution set of the global maintenance operation scheduling solution obtained in step 1, Ts i The corresponding local job scheduling scheme is the current filter reduction comparison reference item, where Ts j The corresponding local operation scheduling schemes are compared and judged for conflicts and interferences. If there is a conflict, the scheme combination solution is deleted from the initial solution set of the global maintenance operation scheduling scheme combination; Step 2 and 3: After the filtering and reduction process is completed, the consistency filtering and reduction results of the initial solution set of the global maintenance operation scheduling scheme combination are output to obtain the feasible global operation scheduling scheme combination solution set; A sequential serial game negotiation model established in the step three includes two serial game negotiation stages, specifically a first-stage non-cooperative game-based Nash equilibrium candidate solution set acquisition stage and a second-stage cooperative game-based global job scheduling solution combination negotiation and optimization decision-making stage. In the first-stage non-cooperative game, the comprehensive expected realization level of the local maintenance goals associated with the sub-maintenance demands undertaken by each negotiating subject is used as a measure to coordinate the demands conflicts among the subjects. At the same time, considering the fault tolerance of fuzzy cognitive evaluation data, the feasible combination solution set with utility value exceeding a specific threshold is retained as the candidate solution set of the second-stage cooperative game; in the second-stage cooperative game, the alliance game model of the cooperative game is used to negotiate and optimize a maintenance job scheduling solution with the optimal compromise of the comprehensive expected realization level of the global maintenance goal from the candidate solution set output in the first stage.

2. The multi-party coupled maintenance and repair negotiation scheduling method for mountain wind turbines according to claim 1 is characterized by: The negotiation game in the first stage of step 3 is modeled using a non-cooperative game model and represented as G=(P i ;S i ;U i ), i∈1,2,3,…,n; where the game subject P i Corresponding to the negotiation subjects who undertake the coupling-related maintenance requirements; the game subject strategy S i The combined solution of the feasible operation scheduling scheme after filtering and reduction corresponding to the subset of maintenance requirements undertaken by each negotiating subject; the utility of the game subject Ui corresponds to the satisfaction degree of the maintenance operation scheduling expectations of each subject, by measuring the satisfaction and expected realization level of their respective local maintenance goals Carry out characterization of it.

3. The multi-party coupled maintenance and repair negotiation scheduling method for mountain wind turbines according to claim 2 is characterized by: The game subject P p The overall expected level of achievement of all associated local maintenance objectives for each sub-maintenance requirement undertaken The calculation formula for measuring is: Among them, dg p is the total number of associated local maintenance objectives, is the relative weight of the associated local maintenance objective j, is the expected level of achievement of the associated local maintenance target j, To divide P p The content of the operation scheduling plan for the maintenance and repair requirements undertaken by other game entities other than the game entity P p The impact of the expected level of achievement of local maintenance target j associated with the undertaken maintenance needs.

4. The multi-party coupled maintenance and repair negotiation scheduling method for mountain wind turbines according to claim 3 is characterized by: described The calculation formula for measuring is: Among them, dv p For the game subject P p The number of maintenance requirements undertaken, To define the game subject P p The degree of influence of the optional operation scheduling scheme k of the sub-maintenance demand i in the sub-maintenance demand undertaken on the expected level of achievement of the associated local maintenance target j is The value of is obtained by using a finite The evaluation language term set H for odd-numbered labels is (extremely negative impact, strong negative impact, moderate negative impact, weak negative impact, no impact, weak positive impact, moderate positive impact, strong positive impact, extremely strong positive impact), and the cloud model is used for quantitative analysis and calculation. When the optional operation scheduling scheme k of the maintenance demand i negatively affects the expected level of realization of the associated local maintenance target j, When , the optional job scheduling scheme k for the maintenance demand i positively affects the expected achievement level of the associated local maintenance target j.

5. The multi-party coupled maintenance and repair negotiation scheduling method for mountain wind turbines according to claim 4 is characterized in that: described The calculation formula for measuring is: Among them, m is the total number of tasks, Cc i,j It quantifies the positive and negative correlations between local maintenance objectives and characterizes the dependency or conflict relationship between them.

6. The multi-party coupled maintenance and repair negotiation scheduling method for mountain wind turbines according to claim 5 is characterized by: The Cc i,j By introducing covariance and correlation coefficient to measure the positive and negative correlation Cc between local maintenance targets i and j i,j The measurement calculation formula is: Among them, RO i is the correlation vector between local target i and all global targets, RO i =(ro i,1 ,ro i,2 ,…,ro i,k ),ro i,q Represents the correlation between the local target i and the global target q; Cov(.) is the covariance; E[.] is the expectation; RO i Standard deviation; is the mean of the correlation between local target i and all global targets.

7. The multi-party coupled maintenance and repair negotiation scheduling method for mountain wind turbines according to claim 1 is characterized by: The process of obtaining the candidate solution set for the second-stage cooperative game through non-cooperative game negotiation analysis in the first stage is: Step 3.1: Select each feasible strategy combination of each game player in turn, calculate the utility value of each game player under the strategy, and use the following formula to calculate the utility value of the corresponding combination: ； In step 32, we rely on the combination comparison procedure to determine whether the selected strategy combination satisfies the Nash equilibrium according to the following formula: in, and They are the strategy of the game subject Pi and the strategies of other game subjects at the Nash equilibrium; Step 33: Obtain all strategy combinations that satisfy the Nash equilibrium, using the predefined combination utility threshold To select a set of candidate solutions for the two-stage cooperative game; in, and are the maximum and minimum combined utilities respectively, and α takes the empirical value of 0.

8.

8. The multi-party coupled maintenance and repair negotiation scheduling method for mountain wind turbines according to claim 1 is characterized by: The second stage of the cooperative game-based global job scheduling solution combination solution negotiation optimization decision phase in step 3 is modeled using the coalition game model and represented as G=(N,v), where N is the set of game entities and v is the utility function of all possible game coalitions, satisfying And for all and Both , the negotiation and optimization process of the best combination solution is as follows: Steps 3 and 4: Calculate the utility vector U(Xi) of each game subject under different feasible strategy combinations. The utility of each subject uses the expected realization level ST corresponding to the global maintenance goal. i To characterize, the measurement calculation formula is: Among them, Ncvi is the number of lower-level targets associated with the upper-level target i, and there are ; Step 35: Calculate the alliance benefit function v; Step 36: Allocate utility to the alliance. The utility allocation method in the alliance is determined using the Shapley value method. The components in the Shapley value vector are The calculation is as follows: Where alliance S is any subset of the set of game players N; |S| represents the number of game players contained in S, and v(S\{i}) represents the utility of the alliance composed of other game players in alliance S except game player i. Step 37: Based on the solution of the Shapley value Φ and the utility vector U(Xi) of each player corresponding to the strategy combination Xi, the global expected return evaluation value βi corresponding to the strategy combination Xi can be calculated: Step 38: Select the strategy combination corresponding to the maximum βi value as the optimal combination solution for the global maintenance operation scheduling plan of the current negotiation decision node.

Images