Game theory-based offshore wind power plant target unit screening, fault repairing and generating capacity optimizing method

Abstract

The invention discloses a game theory-based offshore wind power plant target unit screening, fault repairing and generating capacity optimization method. The method comprises the following steps of: sorting generating capacity of units and selecting problematic units; performing power generation capacity ranking once every half a year, comparing the two rankings, and performing half-year power generation capacity ranking and analysis of the unit; constructing a multi-party participant game model, and optimizing a repair strategy in combination with a non-cooperative game and a cooperative game; based on a game model output result, dynamically allocating resources and formulating a repair scheme, including fault diagnosis, a brief decision model, resource scheduling and an emergency response mechanism, so as to maximize the generating capacity and reduce the repair cost; according to the method, multiple stakeholders such as an operation and maintenance team, an equipment supplier, a contractor and a wind power plant operator are brought into a decision framework through an optimization model of the game theory, resources of all parties are coordinated through strategy optimization of the game theory, an optimal fault processing scheme is formulated, the generating capacity of the wind power plant is maximized, and the repair cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of offshore wind turbine fault analysis, and in particular relates to a method for selecting target turbines in offshore wind farms, repairing faults, and optimizing power generation based on game theory. Background Art

[0002] Offshore wind farm operations are challenging to manage, requiring a large workforce and operating in a complex environment. As a key component of renewable energy, offshore wind power is becoming a key force in the global energy transition. However, offshore wind farm operations and maintenance (O&M) face numerous challenges, particularly when turbine failures occur. How to quickly and effectively repair faults, minimize downtime, and maximize power generation remains a pressing issue in the O&M field.

[0003] In existing technologies, the wind farm fault repair process typically relies on empirical judgment and intuitive decision-making, lacking a systematic, scientific optimization method. This repair approach not only makes it difficult to ensure the optimal repair time, but can also lead to high maintenance costs and fails to fully consider the interests and cooperation potential of multiple parties involved. For example, conflicts of interest often exist between equipment suppliers, contractors, operation and maintenance teams, and wind farm operators regarding repair time, costs, and equipment selection, leading to coordination difficulties, wasted resources, and time delays. This is especially true for offshore wind farms, where remote locations, severe weather, and complex sea conditions make fault handling even more complex and costly.

[0004] Therefore, it is necessary to design a game theory-based offshore wind farm target unit screening, fault repair and power generation optimization method to solve the above problems. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory. Through the optimization model of game theory, multiple stakeholders such as the operation and maintenance team, equipment suppliers, contractors and wind farm operators are incorporated into the decision-making framework. Through the strategy optimization of game theory, the resources of all parties are coordinated to formulate the optimal fault handling plan, thereby maximizing the power generation of the wind farm and reducing the repair cost.

[0006] In order to achieve the above technical objectives, the technical solution adopted by the present invention is: A method for selecting target units, repairing faults, and optimizing power generation in an offshore wind farm based on game theory includes the following steps: S1, sort the power generation of the units and select the problematic units; S2: Power generation ranking is conducted every six months, and the two rankings are compared to sort and analyze the power generation of the units in six months; S3, build a multi-player game model and optimize the repair strategy by combining non-cooperative and cooperative games; S4, based on the output of the game model, dynamically allocates resources and formulates repair plans, including fault diagnosis, simplified decision-making model, resource scheduling and emergency response mechanism, to maximize power generation and reduce repair costs.

[0007] Preferably, in step S1, sorting the power generation of the units includes: Data collection and analysis: Collect the quarterly power generation data of each wind turbine, assuming P i (t) Indicates the i Typhoon in the quarter t Power generation; Execute the power generation sorting algorithm: Calculate the power generation of each wind turbine and sort them. Assuming that there are N The power generation of all wind turbines is expressed as: P(t)={P 1( t),P 2( t),…,P N (t)} ; The units are grouped and sorted based on brand, model and single unit capacity; for fans i , let its brand, model and single unit capacity be {b i ,m i ,s i } , the sorting formula is: R i( t)=Rank(P i (t)|b i ,m i ,s i ) ; in, R i( t) It is a fan i The power generation ranking for the quarter controlled for variables such as brand, model, and unit capacity to ensure a reasonable comparison of different types of wind turbines.

[0008] Preferably, in step S1, isolated factors are eliminated after executing the power generation ranking algorithm, specifically: By calculating the historical power generation mean μi and standard deviation σi of the wind turbine, the impact of long-term shutdown or abnormal weather on power generation is eliminated and the z-score standardization method is used to eliminate it: ; cull| z i (t) |>3 outlier data.

[0009] Preferably, in step S1, the problem unit is selected as: Each quarter, the last k wind turbines ranked by power generation are selected as problem wind turbines for further analysis: ; in, k is the number of fans selected.

[0010] Preferably, in step S2, the semi-annual ranking analysis includes: The power generation ranking is conducted every six months, and the two rankings are compared to calculate the ranking change rate. ΔR i (t) To identify wind turbines whose ranking has dropped significantly; the formula for the ranking change rate is: ; if ΔR i (t) If the absolute value is greater than the set threshold, it is considered that the fan has a fault or other abnormal condition and needs to be inspected.

[0011] Preferably, the analysis of the half-year power generation of the units after sorting is as follows: An analysis of the causes of wind turbines with significant ranking drops was conducted, including one or more of equipment failure, maintenance issues, and wind speed changes. Game theory was used to optimize repair decisions to ensure the rational allocation of resources and time.

[0012] Preferably, the game model construction in step S3 includes: Identify the players involved, including operations and maintenance teams, equipment suppliers, contractors, and wind farm operators; Establish the game theory type: Use a combination of non-cooperative and cooperative games to simulate the decision-making behavior of each party in troubleshooting.

[0013] Preferably, the non-cooperative game is: The operation and maintenance team, equipment suppliers, and contractors engage in a game of negotiation over repair costs and time, with each party making decisions based on their own interests. The cooperative game is: all parties reach a long-term cooperation agreement through negotiation and reach a consensus to optimize resource allocation and improve restoration efficiency.

[0014] Preferably, the optimized game strategy is: Use game theories such as Nash equilibrium and optimal strategy to analyze the decisions of all parties and find the optimal repair solution: Assume that each participant j The strategy is S j , whose income is U j (S j ) , the game equation is: U j (S j )=f(P j ,C j ,T j ) ; in, P j For the repair effect, C j For cost, T j For time.

[0015] Preferably, in step S4, based on the output of the game model, resources are dynamically allocated and a repair plan is formulated, including fault diagnosis, a simplified decision model, resource scheduling, and an emergency response mechanism, to maximize power generation and reduce repair costs, including: Troubleshooting: First, the operation and maintenance team diagnoses the wind turbine faults, collecting information such as the fault type and severity. Based on the specific equipment fault, they select different repair strategies. Decision model establishment: Based on the diagnosis results, the game theory model is used to optimize the repair strategy: Evaluate repair time, cost, and downtime loss factors; Based on the behavioral predictions of all parties, a game theory model is constructed to analyze the optimal decisions of all parties, including maintenance planning, supplier selection, and contractor scheduling.

[0016] Resource allocation and scheduling: Through the calculation of game models, optimize the allocation of resources among all parties, coordinate the use of equipment, spare parts and maintenance personnel resources, and schedule them according to actual conditions; Emergency response mechanism: In the event of an emergency failure, the system automatically calls the emergency response strategy in game theory to quickly allocate resources and ensure timely repairs.

[0017] The beneficial effects of the present invention are as follows: 1. Improve fault handling efficiency: Optimize decision-making by all parties through game theory, reduce decision-making conflicts and coordination difficulties, ensure that wind turbines resume operation in the shortest possible time, and reduce downtime.

[0018] 2. Reduce repair costs: Avoid resource waste and reduce maintenance costs by rationally allocating resources and optimizing repair strategies.

[0019] 3. Improve collaboration efficiency: Promote effective cooperation between operation and maintenance teams, equipment suppliers, contractors and operators, enhance information sharing and resource integration capabilities, and improve overall operation and maintenance efficiency.

[0020] 4. Strong emergency response capability: In the event of sudden failures, the system can quickly respond and dispatch resources from all parties, reducing additional losses caused by slow emergency response.

[0021] 5. Optimize long-term operation and maintenance management: Through cooperative game, encourage all parties to establish a long-term trust and cooperation mechanism to improve the operation and maintenance management efficiency of the entire wind farm.

[0022] 6. Improve overall power generation: By focusing specifically on wind turbines with low power generation, conducting in-depth analysis of the causes and taking targeted measures, the power generation capacity of the problem units can be effectively improved, thereby increasing the power generation of the entire wind farm.

[0023] 7. Dynamic tracking and trend analysis: By comparing and analyzing ranking changes over six months, we can promptly identify wind turbines with fluctuating operating conditions, quickly take measures to optimize and repair them, and prevent potential problems from worsening. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic diagram of a flow chart of the present invention. DETAILED DESCRIPTION

[0025] Example 1: like Figure 1 As shown, a method for selecting target units, repairing faults, and optimizing power generation in an offshore wind farm based on game theory includes the following steps: S1, sort the power generation of the units and select the problematic units; S2: Power generation ranking is conducted every six months, and the two rankings are compared to sort and analyze the power generation of the units in six months; S3, build a multi-player game model and optimize the repair strategy by combining non-cooperative and cooperative games; S4, based on the output of the game model, dynamically allocates resources and formulates repair plans, including fault diagnosis, simplified decision-making model, resource scheduling and emergency response mechanism, to maximize power generation and reduce repair costs.

[0026] Example 2: This embodiment specifically expands the process of the above optimization method, including: In step S1, sorting the power generation of the units includes: Data collection and analysis: Collect the quarterly power generation data of each wind turbine, assuming P i (t) Indicates the i Typhoon in the quarter t Power generation; Execute the power generation sorting algorithm: Calculate the power generation of each wind turbine and sort them. Assuming that there are N The power generation of all wind turbines is expressed as: P(t)={P 1( t),P 2( t),…,P N (t)} ; The units are grouped and sorted based on brand, model and single unit capacity; for fans i , let its brand, model and single unit capacity be {b i ,m i ,s i } , the sorting formula is: R i( t)=Rank(P i (t)|b i ,m i ,s i ) ; in, R i( t) It is a fan i The power generation ranking for the quarter controlled for variables such as brand, model, and unit capacity to ensure a reasonable comparison of different types of wind turbines.

[0027] Preferably, in step S1, isolated factors are eliminated after executing the power generation ranking algorithm, specifically: By calculating the historical power generation mean μi and standard deviation σi of the wind turbine, the impact of long-term shutdown or abnormal weather on power generation is eliminated and the z-score standardization method is used to eliminate it: ; cull| z i (t) |>3 outlier data.

[0028] Preferably, in step S1, the problem unit is selected as: Each quarter, the last k wind turbines ranked by power generation are selected as problem wind turbines for further analysis: ; in, k is the number of fans selected.

[0029] Preferably, in step S2, the semi-annual ranking analysis includes: The power generation ranking is conducted every six months, and the two rankings are compared to calculate the ranking change rate. ΔR i (t) To identify wind turbines whose ranking has dropped significantly; the formula for the ranking change rate is: ; if ΔR i (t) If the absolute value is greater than the set threshold, it is considered that the fan has a fault or other abnormal condition and needs to be inspected.

[0030] Preferably, the analysis of the half-year power generation of the units after sorting is as follows: An analysis of the causes of wind turbines with significant ranking drops was conducted, including one or more of equipment failure, maintenance issues, and wind speed changes. Game theory was used to optimize repair decisions to ensure the rational allocation of resources and time.

[0031] Preferably, the game model construction in step S3 includes: Identify the players involved, including operations and maintenance teams, equipment suppliers, contractors, and wind farm operators; Establish the game theory type: Use a combination of non-cooperative and cooperative games to simulate the decision-making behavior of each party in troubleshooting.

[0032] Preferably, the non-cooperative game is: The operation and maintenance team, equipment suppliers, and contractors engage in a game of negotiation over repair costs and time, with each party making decisions based on their own interests. The cooperative game is: all parties reach a long-term cooperation agreement through negotiation and reach a consensus to optimize resource allocation and improve restoration efficiency.

[0033] Preferably, the optimized game strategy is: Use game theories such as Nash equilibrium and optimal strategy to analyze the decisions of all parties and find the optimal repair solution: Assume that each participant j The strategy is S j , whose income is U j (S j ) , the game equation is: U j (S j )=f(P j ,C j ,T j ) ; in, P j For the repair effect, C j For cost, T j For time.

[0034] Preferably, in step S4, based on the output of the game model, resources are dynamically allocated and a repair plan is formulated, including fault diagnosis, a simplified decision model, resource scheduling, and an emergency response mechanism, to maximize power generation and reduce repair costs, including: Troubleshooting: First, the operation and maintenance team diagnoses the wind turbine faults, collecting information such as the fault type and severity. Based on the specific equipment fault, they select different repair strategies. Decision model establishment: Based on the diagnosis results, the game theory model is used to optimize the repair strategy: Evaluate repair time, cost, and downtime loss factors; Based on the behavioral predictions of all parties, a game theory model is constructed to analyze the optimal decisions of all parties, including maintenance planning, supplier selection, and contractor scheduling.

[0035] Resource allocation and scheduling: Through the calculation of game models, optimize the allocation of resources among all parties, coordinate the use of equipment, spare parts and maintenance personnel resources, and schedule them according to actual conditions; Emergency response mechanism: In the event of an emergency failure, the system automatically calls the emergency response strategy in game theory to quickly allocate resources and ensure timely repairs.

Claims

1. A method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory, characterized in that: The following steps are involved: S1, sort the power generation of the units and select the problematic units; S2: Power generation ranking is conducted every six months, and the two rankings are compared to sort and analyze the power generation of the units in six months; S3, build a multi-player game model and optimize the repair strategy by combining non-cooperative and cooperative games; S4, based on the output of the game model, dynamically allocates resources and formulates repair plans, including fault diagnosis, simplified decision-making model, resource scheduling and emergency response mechanism, to maximize power generation and reduce repair costs.

2. A method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory according to claim 1, characterized in that: In step S1, sorting the power generation of the units includes: Data collection and analysis: Collect the quarterly power generation data of each wind turbine, assuming P i (t) Indicates the i Typhoon in the quarter t Power generation; Execute the power generation sorting algorithm: Calculate the power generation of each wind turbine and sort them. Assuming that there are N The power generation of all wind turbines is expressed as: P(t)={P 1( t),P 2( t),…,P N (t)} ； The units are grouped and sorted based on brand, model and single unit capacity; for fans i , let its brand, model and single unit capacity be {b i ,m i ,s i } , the sorting formula is: R i( t)=Rank(P i (t)|b i ,m i ,s i ) ； in, R i( t) It is a fan i The power generation ranking for the quarter controlled for variables such as brand, model, and unit capacity to ensure a reasonable comparison of different types of wind turbines.

3. The method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory according to claim 2, characterized in that: In step S1, the power generation ranking algorithm is executed to eliminate isolated factors, specifically: By calculating the historical power generation mean μi and standard deviation σi of the wind turbine, the impact of long-term shutdown or abnormal weather on power generation is eliminated and the z-score standardization method is used to eliminate it: ； cull| z i (t) | > 3 outlier data.

4. A method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory according to claim 3, characterized in that: In step S1, the problem unit is selected as: Each quarter, the last k wind turbines ranked by power generation are selected as problem wind turbines for further analysis: ； in, k is the number of fans selected.

5. The method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory according to claim 1, characterized in that: In step S2, the semi-annual ranking analysis includes: The power generation ranking is conducted every six months, and the two rankings are compared to calculate the ranking change rate. ΔR i (t) To identify wind turbines whose ranking has dropped significantly; the formula for the ranking change rate is: ； if ΔR i (t) If the absolute value is greater than the set threshold, it is considered that the fan has a fault or other abnormal condition and needs to be inspected.

6. A method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory according to claim 5, characterized in that: The analysis of the half-year power generation of the units after sorting is as follows: An analysis of the causes of wind turbines with significant ranking drops was conducted, including one or more of equipment failure, maintenance issues, and wind speed changes. Game theory was used to optimize repair decisions to ensure the rational allocation of resources and time.

7. The method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory according to claim 1, characterized in that: The game model construction in step S3 includes: Identify the players involved, including operations and maintenance teams, equipment suppliers, contractors, and wind farm operators; Establish the game theory type: Use a combination of non-cooperative and cooperative games to simulate the decision-making behavior of each party in troubleshooting.

8. The method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory according to claim 7, characterized in that: The non-cooperative game is: The operation and maintenance team, equipment suppliers, and contractors engage in a game of negotiation over repair costs and time, with each party making decisions based on their own interests. The cooperative game is: all parties reach a long-term cooperation agreement through negotiation and reach a consensus to optimize resource allocation and improve restoration efficiency.

9. The method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory according to claim 8, characterized in that: The optimized game strategy is: Use game theories such as Nash equilibrium and optimal strategy to analyze the decisions of all parties and find the optimal repair solution: Assume that each participant j The strategy is S j , whose income is U j (S j ) , the game equation is: U j (S j )=f(P j ,C j ,T j ) ； in, P j For the repair effect, C j For cost, T j For time.

10. The method for selecting target units, repairing faults and optimizing power generation in offshore wind farms based on game theory according to claim 1, characterized in that: In step S4, based on the output of the game model, resources are dynamically allocated and a repair plan is formulated, including fault diagnosis, a simplified decision model, resource scheduling, and an emergency response mechanism, to maximize power generation and reduce repair costs. The following are included: Troubleshooting: First, the operation and maintenance team diagnoses the wind turbine faults, collecting information such as the fault type and severity. Based on the specific equipment fault, they select different repair strategies. Decision model establishment: Based on the diagnosis results, the game theory model is used to optimize the repair strategy: Evaluate repair time, cost, and downtime loss factors; Based on the prediction of each party's behavior, a game theory model is constructed to analyze the optimal decision-making of each party, including maintenance planning, supplier selection and contractor scheduling; Resource allocation and scheduling: Through the calculation of game models, optimize the allocation of resources among all parties, coordinate the use of equipment, spare parts and maintenance personnel resources, and schedule them according to actual conditions; Emergency response mechanism: In the event of an emergency failure, the system automatically calls the emergency response strategy in game theory to quickly allocate resources and ensure timely repairs.

Images