基于人工势场的制造系统车间自适应调度研究

发布时间：2018-05-08 17:13

本文选题：人工势场算法 + 车间作业调度　；参考：《南京航空航天大学》2012年硕士论文

【摘要】：近年来随着以动态化、全球化和用户驱动为显著特征的市场竞争的加剧，制造系统正朝着“小批量、多品种”的方向发展，使得制造系统的复杂性与动态性不断增加。如何快速处理制造环境中出现的各种不确定因素以及各种动态变化，已成为提高企业自身的竞争力要的一环。为了对制造车间中复杂多变的生产活动进行高效的调度，本文将人工势场算法(ArtificialPotential Field)引入到车间作业调度问题的研究中，探索新的作业调度方法，以提高制造系统对动态扰动事件的响应能力以及调度的质量。全文的主要研究内容如下：首先，本文分析了车间调度的基本问题，以及国内外研究现状。同时阐述了遗传算法、模拟退火算法、禁忌搜索算法等经典算法在车间作业调度中的运用及其优缺点。基于此作者认为随着制造系统的发展，新型的调度优化算法必然进一步与生产实践相结合，并向着集成化、动态化、智能化、实用化的方向发展。其次，阐述了人工势场的基本理论并给出自己的理解，结合车间作业调度问题的基本特征，提出了基于人工势场算法的车间调度框架模型，着重介绍了人工势场算法中引力场在制造系统中的应用，通过实例结果表明，该算法能有效地克服经典调度算法在解决作业生产调度问题时存在的搜索数度低与收敛性难以控制的问题。通过对经典的车间作业调度问题进行仿真验证，本文提出算法的调度结果优于一些其它调度算法，体现了该算法的优越性与可行性。同时针对制造系统中存在的随机事件如任务的增加、设备故障等，提出了基于人工势场的动态调度策略。同时在C#平台上，开发了基于人工势场的车间作业调度软件系统。该系统实现了资源设备以及生产任务的信息管理、基于人工势场算法的车间作业调度、针对设备故障和紧急任务的动态调度的产生、以及设计并开发硬件仿真平台中的机床控制板，实现上位机与硬件仿真平台的实时互联。最后，，在与同课题组成员共同设计的硬件仿真平台上进行了物理仿真，进一步研究了车间制造系统中各项参数对作业调度的影响，以及生产自动化的关键技术。对实验结果进行分析，表明了该算法具有计算简便、易实现、通信量少、鲁棒性好等特点。
[Abstract]:In recent years, with the aggravation of market competition characterized by dynamic, globalization and user driving, manufacturing system is developing towards the direction of "small batch, multi-variety", which makes the complexity and dynamic of manufacturing system increasing. How to deal with all kinds of uncertain factors and dynamic changes in manufacturing environment quickly has become an important part to improve the competitiveness of enterprises. In order to efficiently schedule the complex and changeable production activities in the manufacturing shop, this paper introduces the artificial potential field algorithm (Artificial potential Field) into the study of the job shop scheduling problem, and explores a new job scheduling method. In order to improve the response ability of manufacturing system to dynamic disturbance events and the quality of scheduling. The main contents of this thesis are as follows: First of all, this paper analyzes the basic problems of job shop scheduling, as well as domestic and foreign research status. At the same time, the application of genetic algorithm, simulated annealing algorithm, Tabu search algorithm in job shop scheduling and its advantages and disadvantages are discussed. The author thinks that with the development of manufacturing system, the new scheduling optimization algorithm must be further combined with production practice, and develop towards integration, dynamic, intelligent and practical. Secondly, the basic theory of artificial potential field is expounded and its own understanding is given. Combined with the basic characteristics of job shop scheduling problem, a job shop scheduling framework model based on artificial potential field algorithm is proposed. The application of gravitational field in manufacturing system in artificial potential field algorithm is emphatically introduced. This algorithm can effectively overcome the problems of low search number and uncontrollable convergence of classical scheduling algorithms in solving job production scheduling problems. Through the simulation of the classical job shop scheduling problem, the scheduling results of the proposed algorithm are superior to those of some other scheduling algorithms, which reflect the superiority and feasibility of the algorithm. At the same time, a dynamic scheduling strategy based on artificial potential field is proposed for the random events in manufacturing system, such as the increase of tasks and the failure of equipment. At the same time, a job shop scheduling software system based on artificial potential field is developed on C # platform. The system realizes the information management of resource equipment and production tasks, the workshop job scheduling based on artificial potential field algorithm, and the generation of dynamic scheduling for equipment failures and urgent tasks. The machine tool control board in hardware simulation platform is designed and developed to realize the real-time interconnection between upper computer and hardware simulation platform. Finally, the physical simulation is carried out on the hardware simulation platform designed with the members of the same research group. The influence of the parameters in the workshop manufacturing system on job scheduling and the key technologies of production automation are further studied. The experimental results show that the algorithm is simple, easy to realize, less communication and good robustness.
【学位授予单位】：南京航空航天大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：TH186

【相似文献】