WO2023159845A1 - 一种海上风电机组检修全过程优化方法及系统 - Google Patents

一种海上风电机组检修全过程优化方法及系统 Download PDF

Info

Publication number
WO2023159845A1
WO2023159845A1 PCT/CN2022/103075 CN2022103075W WO2023159845A1 WO 2023159845 A1 WO2023159845 A1 WO 2023159845A1 CN 2022103075 W CN2022103075 W CN 2022103075W WO 2023159845 A1 WO2023159845 A1 WO 2023159845A1
Authority
WO
WIPO (PCT)
Prior art keywords
maintenance
offshore wind
average
function
objective
Prior art date
Application number
PCT/CN2022/103075
Other languages
English (en)
French (fr)
Inventor
高晨
童博
赵勇
谢小军
韩毅
宋子琛
张宝锋
Original Assignee
西安热工研究院有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 西安热工研究院有限公司 filed Critical 西安热工研究院有限公司
Publication of WO2023159845A1 publication Critical patent/WO2023159845A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06313—Resource planning in a project environment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Definitions

  • This application belongs to the field of wind power generation, and specifically relates to a method and system for optimizing the whole process of maintenance of offshore wind turbines.
  • Offshore wind turbines have large single-unit capacity, poor accessibility, harsh operating environment, high maintenance costs, and large economic losses caused by downtime.
  • the fault maintenance mode of offshore wind turbines mainly draws on the experience of onshore wind power, and a process control mechanism suitable for the maintenance of offshore wind turbines has not yet been formed; at the same time, after the failure of offshore wind turbine equipment, the maintenance mode adopted is often a single defect elimination , did not optimize the overall process, leading to problems such as increased downtime, increased personnel costs and transportation costs, and low maintenance efficiency.
  • the purpose of this application is to provide a method and system for optimizing the whole process of maintenance of offshore wind turbines, which solves the above-mentioned deficiencies in the prior art.
  • the application provides a method for optimizing the whole process of offshore wind turbine overhaul, including the following steps:
  • Step 1 Statistics of the fault handling information of the target offshore wind farm.
  • the fault handling information includes the average total downtime, average maintenance implementation time, average maintenance personnel, and daily average work volume and average time spent at sea;
  • Step 2 according to the fault handling information obtained in step 1, respectively set the economic index objective function, equipment failure rate index objective function and workload balance index objective function with economy, equipment failure rate and workload balance as the optimization goals;
  • Step 3 constructing and obtaining the multi-objective optimization algorithm function
  • Step 4 setting constraint conditions for the multi-objective optimization algorithm function obtained in step 3;
  • Step 5 combined with the constraints obtained in step 4, perform multi-objective optimization calculation on the multi-objective optimization algorithm function obtained in step 3, and obtain a variety of offshore wind turbine maintenance schemes with the shortest downtime, the lowest maintenance cost, and the lowest equipment failure rate as indicators .
  • step 2 the calculation method of the economic index objective function is as follows:
  • F is the cost caused by the overall maintenance
  • C p is the electricity price
  • S ti is the average total downtime after the failure of item i
  • P is the average theoretical power generation during the downtime
  • C O is the daily cost of going to sea
  • O ti is the average sea time after the i-th failure occurs
  • C fi is the loss of the i-th failure repair.
  • step 2 the calculation method of the objective function of the equipment failure rate index is as follows:
  • F ri is the failure rate of the corresponding equipment after the i-th failure occurs;
  • MTBF i is the average time between failures of the i-th failure;
  • ⁇ f ci is the total number of failures of the i-th failure within the statistical time period;
  • C ti is The number of hours in the statistical time period;
  • WT i is the number of units;
  • ⁇ S ti is the total downtime of the i-th fault.
  • step 2 the calculation method of the workload balance indicator objective function is as follows:
  • W b is the work balance index
  • M pi is the average maintenance personnel for the i-th failure
  • M ti is the average maintenance time for the i-th failure
  • w i is the actual working hours of item i failure per day.
  • step 3 the calculation method of the multi-objective optimization algorithm function obtained by constructing is as follows:
  • S is a set of solutions that satisfy economy, failure rate, and balance
  • O is a multi-objective optimization algorithm function
  • F is the cost caused by overall maintenance
  • F ri is the failure rate of the corresponding equipment after the i-th fault occurs
  • W b is an indicator of job balance.
  • step 4 constraint conditions are set for the multi-objective optimization algorithm function obtained in step 3, wherein the constraint conditions include maintenance resource constraints and equipment importance constraints.
  • overhaul resource constraints are:
  • Z i (t) is the maintenance resources required for the maintenance of the i-th fault within the t time period; m is the number of faults, and Z max is the upper limit of the maintenance resources within the t time period.
  • the equipment importance constraints are:
  • step 5 the multi-objective optimization algorithm function obtained in step 3 is combined with the constraints obtained in step 4, and the improved monarch butterfly optimization algorithm is used to perform multi-objective optimization calculations to obtain the shortest downtime, the lowest maintenance cost, and equipment failure A variety of offshore wind turbine maintenance programs with the lowest rate as the index.
  • the present application provides an optimization system for the whole process of maintenance of offshore wind turbines, the system can run the method, including:
  • the data statistics unit is used to count the fault handling information of the target offshore wind farm.
  • the fault handling information includes the average total downtime corresponding to various types of faults during the long-term operation of the target offshore wind farm, the average maintenance implementation time, the average maintenance personnel, and Average daily workload and average sea time;
  • the objective function unit is used to respectively set the economic index objective function, the equipment failure rate index objective function and the workload balance index objective function with economy, equipment failure rate and workload balance as optimization targets according to the obtained fault processing information;
  • a function construction unit for constructing and obtaining a multi-objective optimization algorithm function
  • a condition setting unit is used to set constraint conditions for the obtained multi-objective optimization algorithm function
  • the function calculation unit is used to perform multi-objective optimization calculation on the obtained multi-objective optimization algorithm function in combination with the obtained constraints, and obtain various offshore wind turbine maintenance schemes with the shortest downtime, the lowest maintenance cost, and the lowest equipment failure rate as indicators.
  • the present application provides an electronic device, including:
  • the processor When the computer-executable instructions are executed by the processor, the processor is caused to implement the method according to any embodiment of the first aspect.
  • the present application provides a non-volatile computer storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the method according to any embodiment of the first aspect is implemented.
  • the present application provides a computer program.
  • the program is executed by a processor, the method according to any embodiment of the first aspect is implemented.
  • This application provides an optimization method for the whole process of maintenance of offshore wind turbines.
  • the concept of "virtual maintenance” is used at the first time when a fault occurs, that is, the average total downtime after each type of fault occurs during the long-term operation of the target offshore wind farm is collected.
  • the multi-objective optimization method is used to calculate the time, manpower and cost, and equipment failure rate required by various schemes, and a variety of conditions that meet the conditions can be given.
  • the maintenance plan is for the operation and maintenance personnel to choose.
  • the monarch butterfly optimization algorithm is used for multi-objective optimization, the calculation process is simple, the required calculation parameters are less, and it is easy to implement the program; it has good convergence performance and certain search ability, and can quickly realize multi-objective optimization.
  • the program can formulate the weight of each parameter according to the actual situation, realize the customization of the program, solve the above-mentioned shortcomings in the existing technology, and minimize the loss of power generation caused by shutdown and the cost of maintenance.
  • Fig. 1 is a schematic flow diagram of a method for optimizing the whole process of maintenance of offshore wind turbines according to an embodiment of the present application
  • Figure 2 is a three-dimensional scatter diagram of the frontier matrix
  • Figure 3 is the frontier xoy projection
  • Figure 4 is the frontier xoz projection
  • Figure 5 is the frontier yoz projection
  • Fig. 6 is a schematic diagram of the hardware structure of the electronic equipment implementing the method for optimizing the whole process of offshore wind turbine overhaul provided by the embodiment of the present application.
  • An embodiment of the present application provides a method for optimizing the whole process of offshore wind turbine overhaul based on the improved Monarch Butterfly algorithm, as shown in Figure 1, and the specific steps are as follows:
  • Step 1 Calculate the average total downtime of various types of failures during the long-term operation of the target offshore wind farm, the average maintenance implementation time, the average maintenance personnel (rounded up), the average daily workload, and the average time to go to sea to form a matrix A, then A for:
  • S t , M t , M p , w, O t are respectively the average total downtime, average maintenance implementation time, average maintenance personnel (rounded up), and the average vector of working hours in the maintenance planning period after each type of failure occurs and the average sea-going time vector;
  • S ti , M ti , M pi , w i , O ti represent the average total shutdown time, average maintenance implementation time, average maintenance personnel (rounded up), and maintenance plan after the failure of item i respectively. Average hours worked and average sea time during the period. used in subsequent calculations.
  • Step 2 according to the fault handling information of the target wind farm collected in step 1, the economic efficiency, equipment failure rate and workload balance are respectively used as the objective functions, and the economic calculation method is as follows:
  • F is the cost caused by the overall maintenance
  • C p is the electricity price
  • S ti is the average total downtime after the failure of item i
  • P is the average theoretical power generation during the downtime
  • C O is the daily cost of going to sea
  • O ti is the average time to go to sea after the i-th failure occurs
  • C fi is the loss of the i-th failure maintenance, including equipment failure loss and maintenance costs.
  • the failure rate is calculated as follows:
  • F ri is the failure rate of the corresponding equipment after the i-th failure occurs;
  • MTBF i is the average time between failures of the i-th failure;
  • ⁇ f ci is the total number of failures of the i-th failure within the statistical time period;
  • C ti is The number of hours in the statistical time period;
  • WT i is the number of units;
  • ⁇ S ti is the total downtime of the i-th fault.
  • the workload balance calculation method is as follows:
  • W b is the work balance index
  • M pi is the average maintenance personnel of the i-th failure
  • M ti is the average maintenance time of the i-th failure
  • w i is the actual working hours of item i failure per day.
  • Step 3 carry out the multi-objective optimization algorithm for the economic index, failure rate index, and work balance, and introduce the parameter S, then:
  • S is the set of solutions satisfying economy, failure rate, and balance
  • O is the multi-objective optimization algorithm function
  • F, F ri , W b are economic index, failure rate index, and work balance index, respectively.
  • Step 4 set constraints for the multi-objective optimization algorithm obtained in step 3, including:
  • Maintenance resource constraints refer to the number of maintenance personnel, technical ability, equipment transportation capacity, etc. Due to limited resources, the number of equipment that can be repaired at the same time is limited.
  • Z i (t) is the maintenance resources required for the maintenance of the i-th fault within the t time period; m is the number of faults, and Z max is the upper limit of the maintenance resources within the t time period.
  • Step 5 Taking economy, equipment failure rate, and workload balance as optimization objectives, comprehensively considering maintenance resource constraints and equipment importance constraints, the improved monarch butterfly optimization algorithm is used for multi-objective optimization calculations, specifically:
  • Pareto optimal the solution s is called Pareto optimal
  • Pareto solution set is the set S opt of Pareto optimal solutions, namely:
  • Pareto front A set containing the value of the Pareto solution set objective function is called the Pareto front, expressed as:
  • g is the Pareto front function.
  • Step 7 save the non-dominated solutions found in the search process into the transit matrix TR.
  • the transit matrix TR is empty, it is directly judged whether the solution is a non-dominated solution. If the solution is a non-dominated solution, it will be added to the transit matrix TR. If the transfer matrix TR is not empty, first judge whether the solution is a non-dominated solution, if it is a non-dominated solution, then judge whether the solution is not dominated by the solutions in the transfer matrix TR, if so, add the solution to the transfer matrix TR , and then delete other solutions that are dominated by this solution.
  • the judgment method of non-dominated solution is as follows:
  • Step 8 set the migration algorithm, the migration operation refers to updating the position of the monarch butterfly between the destinations Land1 and Land2. Assuming that the total number of butterflies is NP and the mobility of butterflies is M R , the number of butterflies at Land1 is:
  • Subset1 represents the number of butterflies located at Land1
  • Ceil(M R ⁇ NP) represents the rounding of (M R ⁇ NP).
  • the migration operation of the butterfly can be expressed as:
  • rand is a random number in [0, 1]
  • R is a random number between -1 and 1.
  • Step 9 set the crossover algorithm, after the migration operation and adjustment operation, the populations are merged, the merged populations are sorted non-dominated, and the individual crowding degree is calculated at the same time. Then select the parental individuals according to the degree of crowding, and update the solution through the crossover operator. After two individuals x 1 and x 2 perform the arithmetic crossover operation, the calculation method of new individuals x′ 1 and x′ 2 is as follows:
  • x′ 1 w ⁇ x 2 +(1-w) ⁇ x 1
  • x′ 2 w ⁇ x 1 +(1-w) ⁇ x 2
  • w is a random number between [-0.5, 1.5]. Performing the above operations can better maintain the diversity of the population.
  • Step 10 on the basis of steps 6 to 9, perform the monarch butterfly optimization algorithm to generate the next generation population, and repeat the above process until the stop condition is met.
  • Step 11 according to the calculation result of step 10, a set containing the Pareto solution set objective function value is obtained, which is called the Pareto frontier S f .
  • S f is three-dimensional, corresponding to the conditions of economy, equipment failure rate and workload balance respectively. solution, there are:
  • S f is the Pareto frontier
  • F f , F ri,f , W b,f represent the solution vector that satisfies the conditions of economy, equipment failure rate and workload balance
  • the vector is l-dimensional
  • F f1 , F ri,f1 , W b, f1 represent the first element in F f , F ri,f , W b, f vectors respectively
  • F fl , F ri,fl , W b, fl represent F f , F ri,f , W b , The lth element in the f vector.
  • Step 12 according to the Pareto frontier S f matrix obtained in step 11, let the column vectors F f , F ri,f , W b, f of the matrix correspond to the three-dimensional x, y, z axis data respectively, then a set of three-dimensional scattered
  • the dot diagram, as shown in Figure 2 the three-dimensional scatter diagram is projected on the xoy plane, xoz plane and yoz plane, as shown in Figure 3-5.
  • Step 13 using the AHP to set the weight, the weight ⁇ can be expressed as:
  • Step 14 calculate the final measurement index Val of each solution in Sf , and the calculation method of the measurement index of the uth solution is:
  • val u ⁇ 1 ⁇ F fu + ⁇ 2 ⁇ F ri,fu + ⁇ 3 ⁇ M pi ⁇ (W b,f ) 2
  • Val best min[Val 1 ,Val 2 ,...,Val u ,...Val l ]
  • Val best represents the best solution, that is, the minimum value among Val 1 , Val 2 ,...,Val u ,...Val l .
  • Fig. 6 is a schematic diagram of the hardware structure of an electronic device for implementing the whole-process optimization method for offshore wind turbine overhaul provided by the embodiment of the present application.
  • the device includes: one or more processors 610 and memory 620, in Fig. Take a processor 610 as an example; the device for implementing the method for optimizing the whole process of offshore wind turbine maintenance may also include: an input device 630 and an output device 640 .
  • the processor 610, the memory 620, the input device 630, and the output device 640 may be connected through a bus or in other ways, and connection through a bus is taken as an example in FIG. 6 .
  • the memory 620 can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as the optimization of the whole process of offshore wind turbine maintenance in the embodiment of this application
  • the program instruction/module to which the method corresponds The processor 610 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 620, that is, realizes the whole-process optimization method for offshore wind turbine maintenance in the above method embodiment.
  • the memory 620 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and at least one application required by the function; data etc.
  • the memory 620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage devices.
  • the storage 620 may optionally include storages that are set remotely relative to the processor 610, and these remote storages may be connected to the overall process optimization system for offshore wind turbine maintenance through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the input device 630 can receive input digital or character information, and generate key signal input related to user settings and function control of the whole process optimization system for offshore wind turbine maintenance.
  • the output device 640 may include a display device such as a display screen.
  • the one or more modules are stored in the memory 620, and when executed by the one or more processors 610, the method for optimizing the whole process of offshore wind turbine overhaul in any method embodiment above is executed.
  • the electronic equipment of the embodiment of the present application exists in various forms, including but not limited to:
  • Mobile communication equipment This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communication.
  • Such terminals include: smart phones (such as iPhone), multimedia phones, feature phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has the characteristics of mobile Internet access.
  • Such terminals include: PDA, MID and UMPC equipment, such as iPad.
  • Portable entertainment equipment This type of equipment can display and play multimedia content.
  • Such devices include: audio and video players (such as iPod), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.
  • Server A device that provides computing services.
  • the composition of a server includes a processor, hard disk, memory, system bus, etc.
  • the server is similar to a general-purpose computer architecture, but due to the need to provide high-reliability services, it is important in terms of processing power and stability. , Reliability, security, scalability, manageability and other aspects have high requirements.
  • the device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each embodiment can be implemented by means of software plus a general hardware platform, and of course also by hardware.
  • the essence of the above technical solutions or the part that contributes to related technologies can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, disk , CD, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

本申请提供的一种海上风电机组检修全过程优化方法包括以下步骤：步骤1，统计目标海上风电场的故障处理信息，步骤2，根据得到的故障处理信息，分别设置以经济性、设备失效率以及工作量均衡为优化目标的经济性指标目标函数、设备失效率指标目标函数以及工作量均衡指标目标函数；步骤3，构建得到多目标优化算法函数；步骤4，针对得到的多目标优化算法函数设置约束条件；步骤5，结合得到的约束条件对步骤3得到的多目标优化算法函数进行多目标优化计算，得到以停机时间最短、检修成本最低、设备失效率最低为指标的多种海上风电机组检修方案；本申请解决了现有技术中存在的上述不足，最大限度降低因停机造成的发电量损失及维修所需费用。

Description

一种海上风电机组检修全过程优化方法及系统
本申请要求在2022年02月28日提交中国专利局、申请号为202210190120.7、发明名称为“一种海上风电机组检修全过程优化方法及系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请属于风力发电领域，具体涉及一种海上风电机组检修全过程优化方法及系统。
背景技术
海上风电机组单机容量大，可达性差，运行环境恶劣，维修成本高，停机带来的经济损失大。目前，海上风电机组故障维修模式主要借鉴陆上风电经验，还未形成适合于海上风电机组检修的过程管控机制；同时，在海上风电机组设备发生故障后，采取的维修模式往往是单一的消缺，并未对整体流程进行优化，导致停机时间增长、人员成本与交通成本增大、维修效率较低等问题。
发明内容
本申请的目的在于提供一种海上风电机组检修全过程优化方法及系统，解决了现有技术中存在的上述不足。
为了达到上述目的，本申请采用的技术方案是：
第一方面，本申请提供的一种海上风电机组检修全过程优化方法，包括以下步骤：
步骤1，统计目标海上风电场的故障处理信息，该故障处理信息包括目标海上风电场长期运行期间各类型故障发生后对应的平均总停机时间、平均检修实施时间、平均检修人员、每日平均工作量和平均出海时间；
步骤2，根据步骤1得到的故障处理信息，分别设置以经济性、设备失效率以及工作量均衡为优化目标的经济性指标目标函数、设备失效率指标目标函数以及工作量均衡指标目标函数；
步骤3，构建得到多目标优化算法函数；
步骤4，针对步骤3得到的多目标优化算法函数设置约束条件；
步骤5，结合步骤4得到的约束条件对步骤3得到的多目标优化算法函数进行多目标优化计算，得到以停机时间最短、检修成本最低、设备失效率最低为指标的多种海上风电机组检修方案。
可选地，步骤2中，经济性指标目标函数的计算方式如下：
Figure PCTCN2022103075-appb-000001
其中，F为整体检修造成的费用；C p为电价；S ti为第i项故障发生后平均总停机时间；P为停机时间内平均理论发电功率；C O为出海每日所需费用；O ti为第i项故障发生后平均出海时间；C fi为第i项故障检修的损失。
可选地，步骤2中，设备失效率指标目标函数的计算方式如下：
Figure PCTCN2022103075-appb-000002
其中，F ri第i项故障发生后对应设备的失效率；MTBF i第i项故障的平均故障间隔时间；∑f ci为统计时间段内的第i项故障发生的故障总次数；C ti为统计时间段内的小时数；WT i为机组数量；∑S ti为第i项故障发生的总停机时间。
可选地，步骤2中，工作量均衡指标目标函数的计算方式如下：
Figure PCTCN2022103075-appb-000003
其中，W b为工作均衡性指标；M pi为第i项故障的平均检修人员；M ti为第i项故障的平均检修时间；
Figure PCTCN2022103075-appb-000004
为第i项故障检修计划周期内工时的平均值；w i为第i项故障每天实际工时数。
可选地，步骤3中，构建得到的多目标优化算法函数计算方式如下：
S＝O(F,F ri,W b)
其中，S为满足经济性、失效率、均衡性的解的集合；O为多目标优化算法函数；F为整体检修造成的费用；F ri第i项故障发生后对应设备的失效率；W b为工作均衡性指标。
可选地，步骤4中，针对步骤3得到的多目标优化算法函数设置约束条件，其中，约束条件包括检修资源约束和设备重要度约束。
可选地，检修资源约束条件是：
Figure PCTCN2022103075-appb-000005
式中，Z i(t)为t时间段内第i项故障检修所需要的检修资源；m为故障数量，Z max为t时间段内检修资源上限。
可选地，设备重要度约束条件是：
Figure PCTCN2022103075-appb-000006
上式中，
Figure PCTCN2022103075-appb-000007
表示t时间段内第i项故障的检修初始检修状态，为1表明建议立即执行检修，为0表示不建议立即执行检修；Im i表示第i项故障对应的设备的重要度；max(Im 1,Im 2…Im i-1,Im i+1…Im m)表示其他故障对应的设备的重要度的最大值；m为t时间段内的故障数量。
可选地，步骤5中，结合步骤4得到的约束条件对步骤3得到的多目标优化算法函数，采用改进帝王蝶优化算法进行多目标优化计算，得到以停机时间最短、检修成本最低、设备失效率最低为指标的多种海上风电机组检修方案。
第二方面，本申请提供一种海上风电机组检修全过程优化系统，该系统能够运行所述的方法，包括：
数据统计单元，用于统计目标海上风电场的故障处理信息，该故障处理信息包括目标海上风电场长期运行期间各类型故障发生后对应的平均总停机时间、平均检修实施时间、平均检修人员、每日平均工作量和平均出海时间；
目标函数单元，用于根据得到的故障处理信息，分别设置以经济性、设备失效率以及工作量均衡为优化目标的经济性指标目标函数、设备失效率指标目标函数以及工作量均衡指标目标函数；
函数构建单元，用于构建得到多目标优化算法函数；
条件设置单元，用于针对得到的多目标优化算法函数设置约束条件；
函数计算单元，用于结合得到的约束条件对得到的多目标优化算法函数进行多目标优化计算，得到以停机时间最短、检修成本最低、设备失效率最低为指标的多种海上风电机组检修方案。
第三方面，本申请提供一种电子设备，包括：
处理器；以及
计算机可读存储装置，其上存储有计算机可执行指令，
当所述计算机可执行指令被所述处理器执行时，使所述处理器实现根据所述第一方面的任一实施例的方法。
第四方面，本申请提供一种非易失性计算机存储介质，其上存储有计算机程序，其中，该程序被处理器执行时实现根据所述第一方面的任一实施例的方法。
第五方面，本申请提供一种计算机程序，所述程序被处理器执行时，实现根据所述第一方面的任一实施例的方法。
与现有技术相比，本申请的有益效果是：
本申请提供的一种海上风电机组检修全过程优化方法，在故障发生的第一时间，利用“虚拟检修”的概念，即利用收集所得目标海上风电场长期运行期间各类型故障发生后平均总停机时间，平均检修实施时间，平均检修人员，每日平均工作量等历史记录，以经济性指标、失效率指标、工作量均衡性为目标建立计算模型；经济性指标、失效率指标、工作量均衡性之间往往无法同时满足最优，不利于运维人员制定检修计划，采用多目标优化的方式计算各种方案所需的时间、人力与成本、设备失效率，可以给出多种满足条件的维修方案供运维人员选择。在采用帝王蝶优化算法进行多目标优化，计算过程简单，所需计算参数较少，易于程序实现；具有较好的收敛性能和一定的搜索能力，可以快速实现多目标优化。同时，该方案可以根据实际情况制定各参数权重，实现方案的定制化，解决了现有技术中存在的上述不足，最大限度降低因停机造成的发电量损失及维修所需费用。
附图说明
图1为根据本申请一实施例的一种海上风电机组检修全过程优化方法的流程示意图；
图2为前沿矩阵三维散点图；
图3为前沿xoy投影图；
图4为前沿xoz投影图；
[根据细则91更正 24.08.2022]
图5为前沿yoz投影图;
图6为本申请实施例提供的执行海上风电机组检修全过程优化方法的电子设备的硬件结构示意图。
具体实施方式
下面结合附图，对本申请进一步详细说明。
本申请一实施例提供的一种基于改进帝王蝶算法的海上风电机组检修全过程优化方法，如图1所示，具体步骤如下：
步骤1，统计目标海上风电场长期运行期间各类型故障发生后平均总停机时间，平均检修实施时间，平均检修人员(向上取整)，每日平均工作量，平均出海时间构成矩阵A，则A为：
Figure PCTCN2022103075-appb-000008
其中，S t、M t、M p、w、O t分别为各类型故障发生后平均总停机时间、平均检修实施时间、平均检修人员(向上取整)、检修计划周期内工时的平均值向量和平均出海时间向量；S ti、M ti、M pi、w i、O ti分别表示第i项故障发生后的平均总停机时间、平均检修实施时间、平均检修人员(向上取整)、检修计划周期内工时的平均值和平均出海时间。用于后续步骤的计算。
步骤2，根据步骤1中收集目标风电场的故障处理信息，分别以经济性、设备失效率以及工作量均衡为目标函数，经济性计算方式如下所示：
Figure PCTCN2022103075-appb-000009
其中，F为整体检修造成的费用；C p为电价；S ti为第i项故障发生后平均总停机时间；P为停机时间内平均理论发电功率；C O为出海每日所需费用；O ti为第i项故障发生后平均出海时间；C fi为第i项故障检修的损失，包括设备故障损失和检修费用。
失效率计算方式如下所示：
Figure PCTCN2022103075-appb-000010
其中，F ri第i项故障发生后对应设备的失效率；MTBF i第i项故障的平均故障间隔时间；∑f ci为统计时间段内的第i项故障发生的故障总次数；C ti为统计时间段内的小时数；WT i为机组数量；∑S ti为第i项故障发生的总停机时间。
工作量均衡性计算方式如下：
Figure PCTCN2022103075-appb-000011
其中，W b为工作均衡性指标；M pi为第i项故障的平均检修人员；M ti为第i项故障的平均检修时间；
Figure PCTCN2022103075-appb-000012
为第i项故障检修计划周期内工时的平均值；w i为第i项故障每天实际工时数。
步骤3，对经济性指标、失效率指标、工作均衡性开展多目标优化算法，引入参量S，则有：
S＝O(F,F ri,W b)
其中，S为满足经济性、失效率、均衡性的解的集合；O为多目标优化算法函数；F、F ri、W b分别为经济性指标、失效率指标、工作均衡性指标。
步骤4，针对步骤3中得到的多目标优化算法设置约束条件，包括：
(1)检修资源约束
检修资源约束是指检修人员数量及技术能力、设备交通能力等，由于资源有限使得能同时进行检修的设备数量有限。
Figure PCTCN2022103075-appb-000013
式中，Z i(t)为t时间段内第i项故障检修所需要的检修资源；m为故障数量，Z max为t时 间段内检修资源上限。
(2)设备重要度约束
若t时间段内同时存在多项故障需要检修且所需检修资源大于资源上限，则首先应该处理设备重要度高的检修内容。
Figure PCTCN2022103075-appb-000014
上式中，
Figure PCTCN2022103075-appb-000015
表示t时间段内第i项故障的检修初始检修状态，为1表明建议立即执行检修，为0表示不建议立即执行检修；Im i表示第i项故障对应的设备的重要度；max(Im 1,Im 2…Im i-1,Im i+1…Im m)表示其他故障对应的设备的重要度的最大值；m为t时间段内的故障数量。
步骤5，以经济性、设备失效率以及工作量均衡作为优化目标，综合考虑检修资源约束与设备重要度约束，采用改进帝王蝶优化算法进行多目标优化计算，具体地：
首先，确定解空间为3维，即最终计算所得Pareto前沿为三维，Pareto前沿具体定义如下：
对于解空间内的一个解s∈S，当且仅当
Figure PCTCN2022103075-appb-000016
则称该解s为Pareto最优，而Pareto解集即为Pareto最优解的集合S opt，即：
Figure PCTCN2022103075-appb-000017
一个包含Pareto解集目标函数值的集合称为Pareto前沿，表示为：
S f＝{g(s p),s p∈S opt}
其中，g为Pareto前沿函数。
步骤6，开始多目标帝王蝶算法，初始化算法参数，令t＝0，随机生成父代种群T 0，计算种群T 0中各个解的目标函数值，将值赋给对应的解。
步骤7，将搜索过程中找到的非支配解保存到中转矩阵TR中。此时保存非支配解存在两种情况：若中转矩阵TR为空，则直接判断该解是否为非支配解。若该解是非支配解，则将其加入到中转矩阵TR中。若中转矩阵TR不为空，先判断该解是否为非支配解，如果是非支配解，再判断该解是否不被中转矩阵TR中的解支配，如果满足，则将该解加入到中转矩阵TR中，然后将被该解支配的其他解删除。其中，非支配解判断方式如下：
对于两个b维向量x和y，当且仅当
Figure PCTCN2022103075-appb-000018
Figure PCTCN2022103075-appb-000019
称之为x支配y，用
Figure PCTCN2022103075-appb-000020
表示，f表示目标函数，否则，这称这两个向量互不支配。
步骤8，设置迁移算法，迁移操作是指更新帝王蝶在目的地Land1和Land2之间的位置。设蝴蝶的总数为NP，蝴蝶的迁移率为M R，则位于Land1位置的蝴蝶数为：
Subset1＝Ceil(M R×NP)
其中，Subset1表示位于Land1位置的蝴蝶数，Ceil(M R×NP)表示将(M R×NP)取整。
同理，位于Land2位置的蝴蝶数为：
Subset2＝NP-Ceil(M R×NP)
蝴蝶的迁移操作可表示为:
Figure PCTCN2022103075-appb-000021
其中，
Figure PCTCN2022103075-appb-000022
是第t+1次迭代时x j的第k维，
Figure PCTCN2022103075-appb-000023
是第t次迭代时x j的个体极值的第k 维，
Figure PCTCN2022103075-appb-000024
与
Figure PCTCN2022103075-appb-000025
分别为Subset2中随机选出的第t次迭代的两个不同个体；R表示查封向量的权值，计算方式为：
R＝(rand-0.5)×2
其中rand为[0，1]的随机数，则R是-1到1之间的随机数。
步骤9，设置交叉算法，在进行完迁移操作和调整操作后，将种群进行合并，将合并后的种群进行非支配排序，同时计算个体拥挤度。然后根据拥挤度选择亲代个体，通过交叉算子进行更新解。x 1和x 2两个个体进行算数交叉操作后新个体x′ 1和x′ 2的计算方式如下所示：
x′ 1＝w×x 2+(1-w)×x 1
x′ 2＝w×x 1+(1-w)×x 2
其中，w是[-0.5，1.5]之间的随机数。进行上面操作可以更好保持种群的多样性。
步骤10，在步骤6至步骤9的基础之上进行帝王蝶优化算法生成下一代种群,重复以上过程直到满足停止条件。
步骤11，根据步骤10计算结果得到一个包含Pareto解集目标函数值的集合称为Pareto前沿S f,根据定义可知,S f为三维,分别对应满足经济性、设备失效率以及工作量均衡条件的解,则有:
Figure PCTCN2022103075-appb-000026
其中,S f为Pareto前沿,F f,F ri,f,W b,f表示满足经济性、设备失效率以及工作量均衡条件的解向量,向量为l维,F f1,F ri,f1,W b,f1分别表示F f,F ri,f,W b,f向量中第一个元素,F fl,F ri,fl,W b,fl分别表示F f,F ri,f,W b,f向量中第l个元素。
步骤12,根据步骤11中得到Pareto前沿S f矩阵,令矩阵各列向量F f,F ri,f,W b,f分别对应为三维x,y,z轴数据,则可以得到一组三维散点图,如图2所示,三维散点图在xoy平面,xoz平面与yoz平面投影,如图3-5所示。
步骤13,利用层次分析法设置权重,权重ω可表示为:
ω＝[ω 1,ω 2,ω 3]
步骤14,计算S f中每一个解最终的衡量指标Val,第u个解的衡量指标计算方法为:
val u＝ω 1×F fu+ω 2×F ri,fu+ω 3×∑M pi×(W b,f) 2
则有:
Val best＝min[Val 1,Val 2,…,Val u,…Val l]
其中,Val best表示最佳方案,即Val 1,Val 2,…,Val u,…Val l中最小值。
图6是本申请实施例提供的执行海上风电机组检修全过程优化方法的电子设备的硬件结构示意图，如图6所示，该设备包括：一个或多个处理器610以及存储器620，图6中以一个处理器610为例；执行海上风电机组检修全过程优化方法的设备还可以包括：输入装置630和输出装置640。
处理器610、存储器620、输入装置630和输出装置640可以通过总线或者其他方式连接，图6中以通过总线连接为例。
存储器620作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本申请实施例中的海上风电机组检修全过程优化方法 对应的程序指令/模块。处理器610通过运行存储在存储器620中的非易失性软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现上述方法实施例海上风电机组检修全过程优化方法。
存储器620可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据海上风电机组检修全过程优化系统的使用所创建的数据等。此外，存储器620可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器620可选包括相对于处理器610远程设置的存储器，这些远程存储器可以通过网络连接至海上风电机组检修全过程优化系统。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置630可接收输入的数字或字符信息，以及产生与海上风电机组检修全过程优化系统的用户设置以及功能控制有关的键信号输入。输出装置640可包括显示屏等显示设备。
所述一个或者多个模块存储在所述存储器620中，当被所述一个或者多个处理器610执行时，执行上述任意方法实施例中的海上风电机组检修全过程优化方法。
上述产品可执行本申请实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本申请实施例所提供的方法。
本申请实施例的电子设备以多种形式存在，包括但不限于:
(1)移动通信设备:这类设备的特点是具备移动通信功能，并且以提供话音、数据通信为主要目标。这类终端包括:智能手机(例如iPhone)、多媒体手机、功能性手机，以及低端手机等。
(2)超移动个人计算机设备:这类设备属于个人计算机的范畴，有计算和处理功能，一般也具备移动上网特性。这类终端包括:PDA、MID和UMPC设备等，例如iPad。
(3)便携式娱乐设备:这类设备可以显示和播放多媒体内容。该类设备包括:音频、视频播放器(例如iPod)，掌上游戏机，电子书，以及智能玩具和便携式车载导航设备。
(4)服务器:提供计算服务的设备，服务器的构成包括处理器、硬盘、内存、系统总线等，服务器和通用的计算机架构类似，但是由于需要提供高可靠的服务，因此在处理能力、稳定性、可靠性、安全性、可扩展性、可管理性等方面要求较高。
(5)其他具有数据交互功能的电子装置。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修 改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (13)

  1. 一种海上风电机组检修全过程优化方法，其特征在于，包括以下步骤：
    步骤1，统计目标海上风电场的故障处理信息，该故障处理信息包括目标海上风电场长期运行期间各类型故障发生后对应的平均总停机时间、平均检修实施时间、平均检修人员、每日平均工作量和平均出海时间；
    步骤2，根据步骤1得到的故障处理信息，分别设置以经济性、设备失效率以及工作量均衡为优化目标的经济性指标目标函数、设备失效率指标目标函数以及工作量均衡指标目标函数；
    步骤3，构建得到多目标优化算法函数；
    步骤4，针对步骤3得到的多目标优化算法函数设置约束条件；
    步骤5，结合步骤4得到的约束条件对步骤3得到的多目标优化算法函数进行多目标优化计算，得到以停机时间最短、检修成本最低、设备失效率最低为指标的多种海上风电机组检修方案。
  2. 根据权利要求1所述的一种海上风电机组检修全过程优化方法，其特征在于，步骤2中，经济性指标目标函数的计算方式如下：
    Figure PCTCN2022103075-appb-100001
    其中，F为整体检修造成的费用；C p为电价；S ti为第i项故障发生后平均总停机时间；P为停机时间内平均理论发电功率；C O为出海每日所需费用；O ti为第i项故障发生后平均出海时间；C fi为第i项故障检修的损失。
  3. 根据权利要求1所述的一种海上风电机组检修全过程优化方法，其特征在于，步骤2中，设备失效率指标目标函数的计算方式如下：
    Figure PCTCN2022103075-appb-100002
    其中，F ri第i项故障发生后对应设备的失效率；MTBF i第i项故障的平均故障间隔时间；∑f ci为统计时间段内的第i项故障发生的故障总次数；C ti为统计时间段内的小时数；WT i为机组数量；∑S ti为第i项故障发生的总停机时间。
  4. 根据权利要求1所述的一种海上风电机组检修全过程优化方法，其特征在于，步骤2中，工作量均衡指标目标函数的计算方式如下：
    Figure PCTCN2022103075-appb-100003
    其中，W b为工作均衡性指标；M pi为第i项故障的平均检修人员；M ti为第i项故障的平均检修时间；
    Figure PCTCN2022103075-appb-100004
    为第i项故障检修计划周期内工时的平均值；w i为第i项故障每天实际工时数。
  5. 根据权利要求1所述的一种海上风电机组检修全过程优化方法，其特征在于，步骤3中，构建得到的多目标优化算法函数计算方式如下：
    S＝O(F,F ri,W b)
    其中，S为满足经济性、失效率、均衡性的解的集合；O为多目标优化算法函数；F为整体检修造成的费用；F ri第i项故障发生后对应设备的失效率；W b为工作均衡性指标。
  6. 根据权利要求1所述的一种海上风电机组检修全过程优化方法，其特征在于，步骤4中，针对步骤3得到的多目标优化算法函数设置约束条件，其中，约束条件包括检修资源约 束和设备重要度约束。
  7. 根据权利要求6所述的一种海上风电机组检修全过程优化方法，其特征在于，检修资源约束条件是：
    Figure PCTCN2022103075-appb-100005
    式中，Z i(t)为t时间段内第i项故障检修所需要的检修资源；m为故障数量，Z max为t时间段内检修资源上限。
  8. 根据权利要求6所述的一种海上风电机组检修全过程优化方法，其特征在于，设备重要度约束条件是：
    Figure PCTCN2022103075-appb-100006
    上式中，
    Figure PCTCN2022103075-appb-100007
    表示t时间段内第i项故障的检修初始检修状态，为1表明建议立即执行检修，为0表示不建议立即执行检修；Im i表示第i项故障对应的设备的重要度；max(Im 1,Im 2…Im i-1,Im i+1…Im m)表示其他故障对应的设备的重要度的最大值；m为t时间段内的故障数量。
  9. 根据权利要求1所述的一种海上风电机组检修全过程优化方法，其特征在于，步骤5中，结合步骤4得到的约束条件对步骤3得到的多目标优化算法函数，采用改进帝王蝶优化算法进行多目标优化计算，得到以停机时间最短、检修成本最低、设备失效率最低为指标的多种海上风电机组检修方案。
  10. 一种海上风电机组检修全过程优化系统，其特征在于，该系统能够运行权利要求1-9中任一项所述的方法，包括：
    数据统计单元，用于统计目标海上风电场的故障处理信息，该故障处理信息包括目标海上风电场长期运行期间各类型故障发生后对应的平均总停机时间、平均检修实施时间、平均检修人员、每日平均工作量和平均出海时间；
    目标函数单元，用于根据得到的故障处理信息，分别设置以经济性、设备失效率以及工作量均衡为优化目标的经济性指标目标函数、设备失效率指标目标函数以及工作量均衡指标目标函数；
    函数构建单元，用于构建得到多目标优化算法函数；
    条件设置单元，用于针对得到的多目标优化算法函数设置约束条件；
    函数计算单元，用于结合得到的约束条件对得到的多目标优化算法函数进行多目标优化计算，得到以停机时间最短、检修成本最低、设备失效率最低为指标的多种海上风电机组检修方案。
  11. 一种电子设备，包括：
    处理器；
    计算机可读存储装置，其上存储有计算机可执行指令，
    其特征在于，当所述计算机可执行指令被所述处理器执行时，使所述处理器实现如权利要求1-9中任一所述的方法。
  12. 一种非易失性计算机存储介质，其上存储有计算机程序，其特征在于，该程序被处理器执行时实现如权利要求1-9中任一所述的方法。
  13. 一种计算机程序，其特征在于，所述程序被处理器执行时，实现如权利要求1-9中 任一所述的方法。
PCT/CN2022/103075 2022-02-28 2022-06-30 一种海上风电机组检修全过程优化方法及系统 WO2023159845A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210190120.7 2022-02-28
CN202210190120.7A CN114548444A (zh) 2022-02-28 2022-02-28 一种海上风电机组检修全过程优化方法及系统

Publications (1)

Publication Number Publication Date
WO2023159845A1 true WO2023159845A1 (zh) 2023-08-31

Family

ID=81660975

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/103075 WO2023159845A1 (zh) 2022-02-28 2022-06-30 一种海上风电机组检修全过程优化方法及系统

Country Status (2)

Country Link
CN (1) CN114548444A (zh)
WO (1) WO2023159845A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117057256A (zh) * 2023-10-11 2023-11-14 中交公路长大桥建设国家工程研究中心有限公司 桥梁结构维护策略优化方法、装置、设备及可读存储介质
CN117764515A (zh) * 2023-12-13 2024-03-26 国网冀北电力有限公司经济技术研究院 一种变电站设备的故障检修成本核算方法及系统

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114548444A (zh) * 2022-02-28 2022-05-27 西安热工研究院有限公司 一种海上风电机组检修全过程优化方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105740977A (zh) * 2016-01-28 2016-07-06 福州大学 一种基于多目标粒子群的停电管理优化方法
EP3438448A1 (fr) * 2017-07-31 2019-02-06 Electricité de France Pilotage d'un parc éolien
CN113469379A (zh) * 2021-06-24 2021-10-01 中国能源建设集团广东省电力设计研究院有限公司 一种基于大数据中心的海上风电场运维管理方法及装置
CN114548444A (zh) * 2022-02-28 2022-05-27 西安热工研究院有限公司 一种海上风电机组检修全过程优化方法及系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105740977A (zh) * 2016-01-28 2016-07-06 福州大学 一种基于多目标粒子群的停电管理优化方法
EP3438448A1 (fr) * 2017-07-31 2019-02-06 Electricité de France Pilotage d'un parc éolien
CN113469379A (zh) * 2021-06-24 2021-10-01 中国能源建设集团广东省电力设计研究院有限公司 一种基于大数据中心的海上风电场运维管理方法及装置
CN114548444A (zh) * 2022-02-28 2022-05-27 西安热工研究院有限公司 一种海上风电机组检修全过程优化方法及系统

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
GUO HUIDONG, WANG WEI, XIA MINGCHAO: "On-line Multi-objective Decision Model for the Maintenance Scheduling of Offshore Wind Turbine Group", PROCEEDINGS OF THE CSEE, ZHONGGUO DIANJI GONGCHENG XUEHUI, CN, vol. 37, no. 7, 5 April 2017 (2017-04-05), CN , pages 1993, XP093088596, ISSN: 0258-8013, DOI: 10.13334/j.0258-8013.pcsee.160542 *
HUA, DINGJIAN: "Management of Power Grid Comprehensive Blackout Plan Based on Multi-objective Decision Analysis", ENTERPRISE REFORM AND MANAGEMENT, no. 3, 15 February 2017 (2017-02-15), pages 216, XP009549398, ISSN: 1007-1210, DOI: 10.13768/j.cnki.cn11-3793/f.2017.1090 *
HUAN JIAJIA, GANG WANG, LI HAIFENG, WANG LONGJUN, : "A Comprehensive Outage Management Model Based on Multi-Objective Decision Analysis", POWER SYSTEM TECHNOLOGY, SHUILI-DIANLIBU DIANLI KEXUE YANJIUYUAN, BEIJING, CN, vol. 37, no. 10, 5 October 2013 (2013-10-05), CN , pages 2802 - 2807, XP093088598, ISSN: 1000-3673, DOI: 10.13335/j.1000-3673.pst.2013.10.046 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117057256A (zh) * 2023-10-11 2023-11-14 中交公路长大桥建设国家工程研究中心有限公司 桥梁结构维护策略优化方法、装置、设备及可读存储介质
CN117057256B (zh) * 2023-10-11 2024-03-15 中交公路长大桥建设国家工程研究中心有限公司 桥梁结构维护策略优化方法、装置、设备及可读存储介质
CN117764515A (zh) * 2023-12-13 2024-03-26 国网冀北电力有限公司经济技术研究院 一种变电站设备的故障检修成本核算方法及系统

Also Published As

Publication number Publication date
CN114548444A (zh) 2022-05-27

Similar Documents

Publication Publication Date Title
WO2023159845A1 (zh) 一种海上风电机组检修全过程优化方法及系统
WO2016165392A1 (zh) 一种基于遗传算法的云计算资源调度方法
CN111966677A (zh) 数据报表的处理方法、装置、电子设备及存储介质
CN108810109B (zh) 一种基于能耗优化的虚拟数据中心放置方法
Liao et al. Energy consumption optimization scheme of cloud data center based on SDN
CN114781763A (zh) 一种多情景下港口碳排放预测方法、系统、计算设备和存储介质
Yang et al. An energy-efficient storage strategy for cloud datacenters based on variable K-coverage of a hypergraph
CN115629576A (zh) 非侵入式柔性负荷聚合特性辨识与优化方法、装置及设备
CN110059840B (zh) 一种受端电网中电池储能系统选址方法及系统
CN202261410U (zh) 渲染农场高性能集群系统
CN107257356B (zh) 一种基于超图分割的社交用户数据优化放置方法
CN102880832A (zh) 一种集群下的数据海量管理的系统的实现方法
CN108829230B (zh) 基于排队论的数据中心节能模型的设计方法
Huang et al. Multi objective scheduling in cloud computing using MOSSO
CN115528750B (zh) 一种面向电网安全稳定的数据模型混合驱动机组组合方法
CN109829591A (zh) 一种风电并网的调度方法、装置、设备及存储介质
CN116431281A (zh) 一种基于鲸鱼优化算法的虚拟机迁移方法
CN113034343B (zh) 参数自适应的高光谱图像分类gpu并行方法
CN115994612A (zh) 基于业扩规划的配电网运行优化方法、装置及存储介质
Yan et al. Dueling-DDQN Based Virtual Machine Placement Algorithm for Cloud Computing Systems
CN115776138A (zh) 一种考虑多维不确定性和能量管理策略的微电网容量规划方法及装置
CN115001978A (zh) 一种基于强化学习模型的云租户虚拟网络智能映射方法
Qian et al. A Cost-driven multi-objective optimization algorithm for SaaS applications placement
Yinghua et al. The multi-join query optimization for smart grid data
Jinjuan Research on enterprise credit risk assessment method based on improved genetic algorithm

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22928115

Country of ref document: EP

Kind code of ref document: A1