云制造环境下车间生产加工能力云服务化研究

发布时间：2018-09-14 08:32

【摘要】：云制造是一种通过虚拟化和服务化技术将各类制造资源封装,为用户提供按需服务的制造新模式,它融合了现有的云计算、高性能计算、智能科学和现有的信息制造技术。云制造技术为加强企业间的相互协作,提高制造资源利用率,提升整体竞争力提供了新的思路和方法。为了促进车间之间的资源共享,加强彼此之间的协作能力,本文针对车间生产加工能力的云服务化进行研究。1.针对车间生产加工能力的服务化封装问题,通过对车间生产加工过程的研究,对车间生产加工资源进行了分类,分析了车间生产加工能力云的特点,构造了车间生产加工能力云服务平台的体系结构,并给出了基于本体的车间生产加工能力云服务描述。2.为了缩短用户选择最佳服务的时间,针对云制造服务的特点,综合考虑服务属性、制造属性和网络属性三个方面,从线上协定和线下生产两个角度出发,构建了云制造服务综合评估指标体系。在此基础上提出了一种基于模块神经网络的量化评估模型。首先,该模型基于模块化的思想对任务进行聚类分解;然后,用BP网络对子任务进行处理;最后,用自适应遗传算法优化各个子任务处理模块的集成权重。结合云制造评价指标体系和模块神经网络模型,可以对云制造服务进行有效的评估,为用户快速选择云制造服务提供支持。3.针对制造执行系统间调度算法资源共享度不高,并且难以高效地从候选调度算法资源中选择合适的求解算法进行调度排产的问题,研究了云制造环境下的作业车间调度算法资源云服务化方法。首先基于OWL-S(Ontology Web Language for Services)建立调度算法资源的本体数据模型以及发布规范,然后为了提高算法服务请求者满意度和算法资源提供者经济收益,提出了基于加权多维特征融合的量化匹配与推荐方法。最后,通过搭建原型系统,并利用哈电机的历史数据进行仿真实验,结果表明所提出的数据模型和推荐算法能够有效的提升调度算法资源的共享程度和选择速度。
[Abstract]:Cloud manufacturing is a new manufacturing model which encapsulates all kinds of manufacturing resources and provides on-demand services to users through virtualization and service technology. It combines the existing cloud computing, high-performance computing, intelligent science and existing information manufacturing technology. Cloud manufacturing technology provides new ideas and methods for strengthening the cooperation among enterprises, improving the utilization of manufacturing resources and enhancing the overall competitiveness. In order to promote the sharing of resources between workshops and enhance the ability of cooperation between each other, this paper studies the cloud service of workshop production and processing capacity. In view of the service packaging problem of workshop production and processing ability, through the research of workshop production and processing process, this paper classifies the workshop production and processing resources, and analyzes the characteristics of workshop production and processing ability cloud. The architecture of workshop manufacturing capability cloud service platform is constructed, and the description of workshop manufacturing capacity cloud service based on ontology is given. In order to shorten the time for users to choose the best service, according to the characteristics of cloud manufacturing service, considering three aspects: service attribute, manufacturing attribute and network attribute, this paper sets out from the two angles of online protocol and offline production. A comprehensive evaluation index system of cloud manufacturing service is constructed. On this basis, a quantitative evaluation model based on modular neural network is proposed. Firstly, the task is clustered and decomposed based on modularization; then, the sub-task is processed by BP network; finally, the integration weight of each sub-task processing module is optimized by adaptive genetic algorithm. Combined with cloud manufacturing evaluation index system and modular neural network model, cloud manufacturing services can be effectively evaluated, providing support for users to quickly select cloud manufacturing services. In order to solve the problem that the resource sharing degree of scheduling algorithm among manufacturing execution systems is not high and it is difficult to select the appropriate solution algorithm from the candidate scheduling algorithm resource to schedule and schedule production efficiently. In this paper, the resource cloud service method of job shop scheduling algorithm in cloud manufacturing environment is studied. In order to improve the satisfaction of algorithm service requester and the economic benefit of algorithm resource provider, the ontology data model and publication specification of scheduling algorithm resource are established based on OWL-S (Ontology Web Language for Services). A quantization matching and recommendation method based on weighted multidimensional feature fusion is proposed. Finally, the prototype system is built, and the simulation results show that the proposed data model and the recommended algorithm can effectively improve the resource sharing and selection speed of the scheduling algorithm.
【学位授予单位】：哈尔滨理工大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TB49;TP393.09

【相似文献】