Wind power gear box assembly task scheduling system and method

Abstract

The invention discloses a wind power gear box assembly task scheduling system and method. The system comprises a data input module, an automatic modeling module, a simulation module and a scheduling scheme output module. A key station assembly task data table and a crown block personnel resource data table are imported into the system, an automatic modeling module is utilized, a resource pool is automatically configured, all assembly task objects are created, resource constraints, time constraints and pre-and-post process constraints are added, simulation or optimization scheduling after simulation is carried out according to whether the resource constraints exist or not, and the assembly task objects can be obtained. And an optimal scheduling scheme is obtained, and a task Gantt chart, a resource Gantt chart and a time data table are generated to guide assembly work. According to the method, the dynamism, randomness and multi-factor constraints in the assembly process can be visually, accurately and visually described, a scenarized intelligent simulation optimization algorithm is combined, task scheduling and crown block personnel resource scheduling schemes are automatically optimized, and the assembly efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of assembly operation scheduling, and particularly to a wind power gearbox assembly task scheduling system and method. Background Art

[0002] The wind power gearbox is one of the key components in a wind turbine generator set, mainly used to transmit the power generated by the wind turbine under the action of wind to the generator, and appropriately increase the rotational speed to meet the working range requirements of the generator. Its assembly involves multiple components and complex assembly relationships. During the assembly process, gantry cranes such as semi-gantry cranes, overhead cranes, and gantry cranes are frequently used, and interference and collision between the three need to be avoided. At the same time, limited overhead crane resources and personnel resources need to cooperate to complete the assembly operation. Therefore, reasonable task scheduling and overhead crane and personnel resource scheduling are required to ensure the smooth progress of the assembly process. Assembly task scheduling not only needs to consider factors such as the skill level, workload, working hours, auxiliary devices, and assembly sequence and priority of workers, but also needs to consider factors such as the location, working duration, and priority of overhead crane resources to ensure the efficient completion of assembly tasks.

[0003] Traditional assembly task scheduling methods rely too much on manual experience and subjective judgment, resulting in inaccurate and inefficient scheduling results. Manual scheduling may not fully consider the complex relationships between various factors, leading to problems such as resource waste and overhead crane collisions during the assembly process. At the same time, there are a large number of uncertain abnormal factors in the actual site, and general mathematical programming scheduling methods are not applicable. Therefore, it is necessary to develop a new task scheduling system and method to adapt to the complex assembly tasks of wind power gearboxes. Summary of the Invention

[0004] The purpose of the present invention is to provide a wind power gearbox assembly task scheduling system and method for the deficiencies of the prior art. By comprehensively considering the requirements of various cranes and personnel resources, as well as the characteristics and processes of assembly tasks, it provides guidance for the actual assembly operation execution and improves the assembly efficiency.

[0005] The technical solution for achieving the purpose of the present invention is as follows:

[0006] A wind power gearbox assembly task scheduling system, comprising:

[0007] A data input module, including a task input module for supporting a user to input an assembly task data table of each subtask on the wind power gearbox assembly station and a resource input module for inputting a resource data table corresponding to the subtask;

[0008] An automatic modeling module, which is used to automatically create each assembly task object according to the sub-task data table respectively, define the front and rear constraint relationships of the task objects, create a resource pool according to the resource data table and manage the resources, and build an assembly task simulation network model based on the assembly tasks and resources;

[0009] A simulation module, which is used for simulation deduction to obtain the completion cycle of the assembly operation and the critical path;

[0010] A scheduling plan output module, which is used to display the task Gantt chart and the resource Gantt chart according to the simulation execution process, and output a time data table for guiding the assembly operation.

[0011] Furthermore, the assembly task data table includes a task serial number, a task description, a preceding task, an assembly time, a resource type, and a resource quantity; the resource data table includes all resource types and the total quantity required during the sub-task assembly operation.

[0012] Furthermore, the simulation module includes a simulation calculation module and a simulation algorithm optimization module; the simulation calculation module is based on discrete event simulation software and is applicable to simulation deduction without resource constraints; the simulation algorithm optimization module is based on simulation software combined with a genetic algorithm and is applicable to simulation deduction with resource constraints.

[0013] A method for scheduling the assembly tasks of a wind power gearbox, using the above-mentioned assembly task scheduling system, includes the following steps:

[0014] Step S1: Basic data definition: For a certain assembly station of a wind power gearbox, define the assembly task data table and the resource data table for each sub-task at this station;

[0015] Step S2: Assembly task modeling: Based on discrete event simulation software, automatically create a resource pool for resource management according to the resource data table, automatically create each assembly task object according to the assembly task data table, set the required assembly time, resource requirement type and quantity of the task object, and define the front and rear constraint relationships of the task object to complete the construction of an assembly task simulation network model with complex requirements;

[0016] Step S3: Manually judge whether there are resource constraints for the current assembly task according to production experience, the quantity of resources and their usage methods, and perform simulation deduction respectively according to the judgment results to solve the critical path:

[0017] If there are no resource constraints for the assembly task, run the assembly task simulation network model N times to obtain the completion cycle of the assembly operation and the critical path;

[0018] If there are resource constraints in the assembly task, based on the assembly task simulation network model and combined with the genetic algorithm, a simulation optimization algorithm is obtained to schedule and optimize the resources shared by the assembly tasks, and an optimal resource scheduling plan is obtained. The optimal resource scheduling plan is simulated and run to obtain the completion cycle of the assembly operation and the critical path.

[0019] Step S4: Output of the assembly task scheduling plan: According to the detailed process record of the simulation run, a Gantt chart of the assembly tasks and a Gantt chart of the resources are obtained, and a time data table is output to guide on-site assembly operations.

[0020] Furthermore, the construction of the assembly task simulation network model specifically includes the following steps:

[0021] Step S21, create material inlet and outlet objects, and set the material inlet object to generate 1 material arrival signal at the zero moment of the simulation.

[0022] Step S22, create and enable a resource pool object. According to the resource data table through the script function of the simulation software, automatically add the resource type and the configured quantity to the resource pool, and set the resource pool task scheduling rule to the high-priority first service policy.

[0023] Step S23, automatically create each assembly task object according to the assembly task data table through the script function of the simulation software, and set the corresponding task number, task description, and assembly time of the task object. The assembly time is set to a fixed value or a distribution function that follows a normal distribution or a triangular distribution according to the uncertainty of time.

[0024] Step S24, add resource constraints: Through the script function of the simulation software, according to the resource data in the assembly task data table, automatically add resource constraints to each assembly subtask object, that is, each assembly subtask needs to submit a resource application of the corresponding resource type and quantity to the resource pool, and the resource pool processes the resource requests according to the task scheduling rule. The assembly task object can start the operation only when the resources are satisfied.

[0025] Step S25, add precedence constraints: Through the script function of the simulation software, according to the precedence task data in the assembly task data table, automatically create connection lines to connect each task object with all its precedence tasks, and automatically add a control method for checking before arranging tasks to each assembly task, that is, it can start the operation only when all the completion signals of the precedence tasks arrive. Add a control method before the material leaves, that is, create a completion signal in the subsequent task object after this assembly task is completed. The last created completion signal records all the historical critical paths and the latest task object to form a new critical path, and complete the construction of the complex assembly task simulation network model.

[0026] Furthermore, the simulation software is FactorySimulation.

[0027] Further, when there are resource constraints in the assembly task, the specific method for scheduling and optimizing the resources includes the following steps:

[0028] Step S41, design genetic coding: Adopt the chromosome sequential coding method, and use the sub-task number of each assembly task as a gene for coding. The total number of sub-tasks of this assembly task is the chromosome length;

[0029] Step S42, select genetic parameters: Select an appropriate population size according to the actual problem scale. The population size refers to the number of initial individuals, which is usually determined by comprehensively considering aspects such as the complexity of the problem, computing resources, convergence speed, and algorithm performance. The common value of the genetic algorithm is between 20 and 100. Select the parental chromosomes according to the probability determined by the fitness value. The crossover operator is the order crossover OX, the initial value of the crossover probability is 0.8, the mutation operator is the exchange of gene element positions, the initial value of the mutation probability is 0.4, set the number of genetic iterations as the genetic termination condition, set the reciprocal of the simulation duration as the fitness of the chromosome, and the optimization goal is to maximize the chromosome fitness;

[0030] Step S43, judge the genetic termination condition: If the condition is met, the algorithm stops; otherwise, execute Step S44;

[0031] Step S44, genetic decoding method: Set the gene numbers of the chromosome as the resource scheduling priorities of the assembly task objects in the simulation model represented by the gene positions, and perform resource scheduling during the simulation process;

[0032] Step S45, fitness value simulation calculation: After setting the resource scheduling priorities of the complex assembly task simulation network model according to the decoded resource scheduling priority scheme, perform multiple predictive simulation runs and output the individual fitness;

[0033] Step S46: Execute the selection operator, crossover operator, and mutation operator to generate a new population, and then execute Step S43.

[0034] Adopting the above technical solution, the present invention has the following beneficial effects:

[0035] (1) By constructing a simulation network model of the assembly task with complex resource requirements, the present invention can visually, accurately, and visually describe the dynamics, randomness, and multi-factor constraints of the assembly process, overcome the problems of low flexibility and accuracy of traditional assembly task planning and scheduling methods, analyze the critical path more efficiently and reliably, and combine with the scenario-based intelligent optimization algorithm to automatically optimize the task scheduling and resource scheduling schemes, providing data support for actual production and guiding the execution of actual assembly operations.

[0036] (2) The assembly task modeling of the present invention is based on discrete event simulation software. By combining specific assembly task process data and resource data, an assembly task simulation network model for resource requirements in the complex assembly process of key workstations for wind turbine gearboxes is established. Compared with traditional mathematical models, it can more intuitively reflect the complexity of the assembly operation process, overcome the difficulties of traditional methods in describing complex assembly processes, can comprehensively and accurately simulate and model the assembly process, deeply consider various factors such as the characteristics and processes of wind turbine gearbox assembly tasks, and the utilization of complex resources, and combine intelligent optimization algorithms to discover potential problems and optimize scheduling strategies, thereby improving assembly efficiency.

[0037] (3) The present invention uses parametric modeling methods to quickly obtain optimized scheduling plans after new product planning or process changes, and adopts an intelligent simulation optimization method integrating genetic algorithms to quickly determine the critical path of assembly operations. The plan verified through virtualization can directly guide on-site actual assembly operations, and this optimization design method is simple and easy to implement, and is also convenient for expansion and development for more complex scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to make the content of the present invention easier to be clearly understood, the following further details the present invention according to specific embodiments in conjunction with the accompanying drawings, where:

[0039] Figure 1 is the structural block diagram of the scheduling system of the present invention;

[0040] Figure 2 is the assembly task data table for the secondary general assembly workstation in Embodiment 1;

[0041] Figure 3 is the resource data table for the general assembly workstation in Embodiment 1;

[0042] Figure 4 is the assembly task simulation network model for the secondary general assembly workstation in Embodiment 1;

[0043] Figure 5 is the genetic algorithm parameter definition and decoding method in Embodiment 1;

[0044] Figure 6 is the comparison chart before and after optimization of the intelligent simulation optimization algorithm in Embodiment 1;

[0045] Figure 7 is the Gantt chart of the assembly task and the resource Gantt chart in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] In order to better understand the above technical solutions, the following will detail the above technical solutions in conjunction with the accompanying drawings of the specification and specific embodiments.

[0047] (Embodiment 1)

[0048] In view of the defects of the existing assembly task scheduling methods, this embodiment provides a wind power gearbox assembly task scheduling system and method considering the requirements of multiple overhead cranes and personnel resources, which is applied to the assembly task scheduling of the wind power gearbox assembly station and the arrangement and guidance of overhead crane resources and personnel resources.

[0049] As Figure 1 The wind power gearbox assembly task scheduling system shown includes a data input module, an automatic modeling module, a simulation module, and a scheduling scheme output module. Among them, the data input module includes a task input module and a resource input module, which are respectively used to support the user to input the basic data including assembly tasks and resources. The automatic modeling module is used to automatically configure the resource pool according to the basic data, create each assembly task object, and add overhead crane resource constraints, personnel resource constraints, time constraints, and front and back process constraints. The simulation module includes a simulation calculation module and a simulation algorithm optimization module. Through the simulation calculation module, the completion cycle of the assembly operation without resource constraints and the critical path are obtained through simulation deduction. Through the algorithm iteration of the simulation algorithm optimization module, the optimal resource scheduling scheme under resource constraints, as well as the corresponding assembly operation completion cycle and critical path, are obtained. The scheduling scheme output module is used to display the task Gantt chart and the resource Gantt chart according to the simulation execution process, and output the time data table for guiding the assembly operation.

[0050] The wind power gearbox assembly task scheduling method of this embodiment adopts the above system, and takes the second-level general assembly station of an assembly factory in a wind power gearbox base as an example for specific elaboration. This general assembly station includes 33 assembly operation tasks from incoming material inspection to transfer to the first-level general assembly. There are 3 workers in the second-level general assembly station, and the number of workers required for each assembly subtask is different. A large number of subtasks require the cooperation of overhead crane resources to complete. The overhead crane resource is a semi-gantry crane, and there is only 1 unit. The specific steps are as follows:

[0051] Step S1: Definition of basic data: For a certain assembly station of the wind power gearbox, define the assembly task data table and the resource data table for each subtask on this station; among them, the assembly task data table includes task number, task description, preceding task, assembly time, resource type, and resource quantity, as Figure 2 shown; the resource data table includes all resource types and the total quantity required during the assembly operation of the subtask, as Figure 3 shown. Import the assembly task data table and the resource data table into the system through the task input module and the resource input module respectively.

[0052] Step S2: Assembly task modeling: Based on discrete event simulation software, automatically create a resource pool for resource management according to the resource data sheet, automatically create each assembly task object according to the assembly task data sheet, set the required assembly time, resource requirement type and quantity of the task object, define the precedence and successor constraints of the task object, and complete the construction of the assembly task simulation network model with complex requirements, which specifically includes the following steps;

[0053] Step S21, create material inlet and outlet objects, and set the material inlet object to generate 1 material arrival signal at the zero moment of the simulation;

[0054] Step S22, create and enable the resource pool object. According to the resource data sheet through the script function of the simulation software, automatically add the resource type and configured quantity to the resource pool, and set the resource pool task scheduling rule to the high-priority first-served policy;

[0055] Step S23, automatically create each assembly task object according to the assembly task data sheet through the script function of the simulation software, and set the corresponding task number, task description, and assembly time of the task object. The assembly time is set to a fixed value or a distribution function that follows a normal distribution or a triangular distribution according to the uncertainty of time;

[0056] Step S24, add resource constraints: Through the script function of the simulation software, according to the resource data in the assembly task data sheet, automatically add resource constraints to each assembly subtask object, that is, each assembly subtask needs to submit a resource application of the corresponding resource type and quantity to the resource pool, and the resource pool processes the resource requests according to the task scheduling rule. The assembly task object can start working only when the resources are satisfied;

[0057] Step S25, add precedence constraints: Through the script function of the simulation software, according to the precedence task data in the assembly task data sheet, automatically create connection lines to connect each task object with all its precedence tasks, and automatically add a pre-task check control method to each assembly task, that is, it can start working only when all the precedence task completion signals arrive. Add a control method before the material leaves, that is, create a completion signal in the successor task object after this assembly task is completed. Record all historical critical paths and the latest task object in the finally created completion signal to form a new critical path, and complete the construction of the complex assembly task simulation network model.

[0058] In this embodiment, the simulation software uses the domestic independent and controllable production system FactorySimulation. By using the automatic modeling module therein, the automatic modeling for generating the assembly task simulation network model is run. The resource types and configured quantities of the resource pool objects are automatically configured, and the resource pool task scheduling rule is set to the high-priority first service strategy; each assembly task object is automatically generated, and the corresponding task serial number, task description, and task time parameters of the task object are configured. The crane and personnel resource constraints and the front and back process constraints are added to each assembly task object, and a three-dimensional simulation model as shown in Figure 4 is generated. By integrating the Petri net theory, the improvement of the assembly process constraints and efficient modeling are realized.

[0059] Step S3: Manually judge whether there are resource constraints for the current assembly task according to production experience, the quantity of resources, and their usage methods, and perform simulation deductions respectively according to the judgment results to solve the critical path:

[0060] If there are no resource constraints for the assembly task, the assembly task simulation network model is directly run N times to obtain the assembly operation completion cycle and the critical path;

[0061] If there are resource constraints for the assembly task, based on the assembly task simulation network model and combined with the genetic algorithm, a simulation optimization algorithm is obtained to optimize the scheduling of the resources shared by the assembly tasks, and an optimal resource scheduling scheme is obtained. The optimal resource scheduling scheme is simulated and run to obtain the assembly operation completion cycle and the critical path, which specifically includes the following steps:

[0062] Step S41, design genetic coding: Adopt the chromosome sequential coding method, and use the sub-task serial number of each assembly task as a gene for coding. The total number of sub-tasks of this assembly task is the chromosome length;

[0063] Step S42, select genetic parameters: Select an appropriate population size according to the scale of the actual problem. The population size refers to the number of initial individuals, which is usually determined by comprehensively considering aspects such as the complexity of the problem, computing resources, convergence speed, and algorithm performance. The commonly used values of the genetic algorithm are between 20 and 100, and the specific value needs to be continuously adjusted during the application process until an appropriate one is finally selected. Select the parental chromosomes according to the probability determined by the fitness value. The crossover operator is the order crossover OX, the initial value of the crossover probability is 0.8, the mutation operator is the exchange of gene element positions, the initial value of the mutation probability is 0.4, set the genetic iteration algebra as the genetic termination condition, set the reciprocal of the simulation duration as the fitness of the chromosome, and the optimization goal is to maximize the chromosome fitness;

[0064] Step S43, judge the genetic termination condition: If the condition is met, the algorithm stops; otherwise, execute Step S44;

[0065] Step S44, genetic decoding method: Set each gene number of the chromosome as the resource scheduling priority of the assembly task object in the simulation model represented by the gene position, and perform resource scheduling during the simulation process;

[0066] Step S45, fitness value simulation calculation: After setting the resource scheduling priority of the complex assembly task simulation network model according to the decoded resource scheduling priority scheme, perform multiple predictive simulation runs and output the individual fitness;

[0067] Step S46: Execute the selection operator, crossover operator, and mutation operator to generate a new population, and execute step S43.

[0068] In this embodiment, there are resource constraints in the assembly task, and the simulation algorithm optimization module is used for simulation and deduction. As Figure 5 shown, the chromosome length is set to the total number of subtasks of the assembly task, which is 33. According to experience, the population size is set to 50, the chromosome decoding method is to set the resource scheduling priority of the assembly task object represented by each gene position in the simulation model as each gene number, the crossover operator is order crossover OX, the initial value of the crossover probability is 0.8, the mutation operator is gene element position exchange, the initial value of the mutation probability is 0.4, the genetic iteration is set to 10 generations as the genetic termination condition, and the shortest simulation duration is set as the optimization goal.

[0069] Run the simulation optimization algorithm to obtain the assembly operation completion cycle of 4 hours and 54 minutes, and the operation critical path AO178 - AO179 - AO183 - AO189 - AO190 - AO191 - AO193 - AO195. Compared with the result of 5 hours and 2 minutes without resource scheduling optimization, the completion time is saved by 8 minutes. As Figure 6 shown.

[0070] Step S4: Output of the assembly task scheduling plan: According to the detailed process record of the simulation run, obtain the Gantt chart of the assembly task and the resource Gantt chart, as Figure 7 shown, and output the time data table to guide the on-site assembly operation, which is beneficial to reducing the collision of overhead crane - type resources in actual production.

[0071] The wind power gearbox assembly task scheduling system and method implemented according to the present invention can visually and accurately describe the dynamics, randomness, and multi-factor constraints of the assembly process by constructing a complex assembly task simulation network model with multi-crane and personnel resource requirements. It overcomes the problems of low flexibility and accuracy in traditional assembly task planning and scheduling methods, analyzes the critical path more efficiently and reliably, and combines with a scenario-based intelligent optimization algorithm to automatically optimize the task scheduling and crane and personnel resource scheduling schemes, providing data support for collision avoidance of each crane operation in actual production and guiding the execution of actual assembly operations. This method and system are applicable to the task arrangement and scheduling of assembly operation workstations with complex multi-crane and personnel resource requirements, and are also of reference significance for the operation optimization of similar assembly operations.

[0072] In the specific embodiments described above, the purpose, technical solutions, and beneficial effects of the present invention have been further described in detail. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A wind turbine gearbox assembly task scheduling system, characterized in that: include: The data input module includes a task input module for supporting a user to input an assembly task data table of each subtask on a wind power gearbox assembly station and a resource input module for inputting a resource data table of a corresponding subtask; An automatic modeling module is used to automatically create each assembly task object according to the subtask data table and define the before and after constraint relationship of the task object, and to create a resource pool according to the resource data table and perform resource management, and to build an assembly task simulation network model based on assembly tasks and resources; The simulation module is used for simulation and deduction to obtain the assembly operation completion cycle and critical path; The scheduling scheme output module is used to display the task Gantt chart and resource Gantt chart according to the simulation execution process, and output the time data table for guiding the assembly operation.

2. A wind turbine gearbox assembly task scheduling system according to claim 1, characterized in that: The assembly task data table includes task serial number, task description, predecessor task, assembly time, resource type and resource quantity; the resource data table includes all resource types and total quantities required in the subtask assembly operation process.

3. A wind turbine gearbox assembly task scheduling system according to claim 1, characterized in that: The simulation module includes a simulation calculation module and a simulation algorithm optimization module; the simulation calculation module is based on discrete event simulation software and is suitable for simulation deduction without resource constraints; the simulation algorithm optimization module is based on simulation software combined with genetic algorithm and is suitable for simulation deduction with resource constraints.

4. A method for scheduling wind turbine gearbox assembly tasks, characterized in that: The assembly task scheduling system according to any one of claims 1 to 3 comprises the following steps: Step S1: Basic data definition: for a certain assembly station of a wind turbine gearbox, define the assembly task data table and resource data table of each subtask on the station; Step S2: Assembly task modeling: Based on discrete event simulation software, a resource pool is automatically created according to the resource data table for resource management, each assembly task object is automatically created according to the assembly task data table, the assembly time, resource requirement type and quantity required for the task object are set, and the before and after constraint relationships of the task object are defined to complete the construction of an assembly task simulation network model with complex requirements; Step S3: Determine whether the current assembly task has resource constraints, and perform simulations and deductions based on the determination results to solve the critical path: If there is no resource constraint for the assembly task, run the assembly task simulation network model N times to obtain the assembly task completion cycle and critical path; If there are resource constraints in the assembly task, a simulation optimization algorithm is obtained based on the assembly task simulation network model and combined with a genetic algorithm to optimize the scheduling of resources shared by the assembly task and obtain the optimal resource scheduling solution. The optimal resource scheduling solution is simulated and run to obtain the assembly task completion cycle and critical path. Step S4: Output of assembly task scheduling plan: According to the detailed process record of the simulation operation, the assembly task Gantt chart and resource Gantt chart are obtained, and a time data table is output to guide the on-site assembly operation.

5. A method for scheduling wind turbine gearbox assembly tasks according to claim 4, characterized in that: The construction of the assembly task simulation network model specifically includes the following steps: Step S21, creating material inlet and outlet objects, setting the material inlet object to generate a material arrival signal at simulation time zero; Step S22, creating and enabling a resource pool object, automatically adding resource types and configured quantities to the resource pool according to the resource data table through the simulation software script function, and setting the resource pool task scheduling rule to a high priority first service strategy; Step S23, automatically creating each assembly task object according to the assembly task data table through the simulation software script function, setting the task sequence number, task description, and assembly time corresponding to the task object, and setting the assembly time to a fixed value or to a distribution function that obeys a normal distribution or a triangular distribution according to the uncertainty of the time; Step S24, adding resource constraints: using the simulation software script function, automatically adding resource constraints to each assembly subtask object according to the resource data in the assembly task data table; Step S25, adding predecessor constraints: through the simulation software script function, according to the predecessor task data in the assembly task data table, automatically create connecting lines to connect each task object with all its predecessor tasks, automatically add a pre-task inspection control method for each assembly task, add a pre-material departure control method, and record all historical critical paths and the latest task objects to form a new critical path, thereby completing the construction of a complex assembly task simulation network model.

6. A method for scheduling wind turbine gearbox assembly tasks according to claim 4, characterized in that: The simulation software is FactorySimulation.

7. A method for scheduling wind turbine gearbox assembly tasks according to claim 4, characterized in that: When there are resource constraints on the assembly task, the specific method for scheduling and optimizing the resources includes the following steps: Step S41, designing genetic coding: using chromosome sequence coding, encoding the subtask number of each assembly task as a gene, and the total number of subtasks of the assembly task is the chromosome length; Step S42, select genetic parameters: select the appropriate population size according to the actual problem scale, select the parent chromosome according to the probability determined by the fitness value, the crossover operator is the sequential crossover OX, the initial value of the crossover probability is 0.8, the mutation operator is the gene element position exchange, the initial value of the mutation probability is 0.4, set the genetic iteration generation as the genetic termination condition, set the inverse of the simulation time as the chromosome fitness, and the optimization goal is to maximize the chromosome fitness; Step S43, genetic termination condition judgment: if the condition is met, the algorithm stops, otherwise execute step S44; Step S44, genetic decoding method: setting each gene number of the chromosome as the resource scheduling priority of the assembly task object in the simulation model represented by the gene position, and performing resource scheduling during the simulation process; Step S45, fitness value simulation calculation: after setting the resource scheduling priority of the complex assembly task simulation network model according to the resource scheduling priority scheme obtained by decoding, multiple predictive simulation runs are performed to output individual fitness; Step S46: Execute the selection operator, crossover operator, and mutation operator to generate a new population, and execute step S43.

Images