Research On Bottleneck Management And Scheduling Optimization Of Semiconductor Wafer Fabrication System

With the rapid development of electronic information technology,the semiconductor chip industry in China has been developing rapidly.The most important in semiconductor chip production process and manufacturing process is the most complex semiconductor wafer manufacturing system,it has obvious characteristics of long production cycle,the production process is complicated,the production environment uncertainty and the mode of production in repeated processing,and is a bright model,multiple large scale,multi product and process complex manufacturing system.The most complex manufacturing system is also the world now exist.Therefore,the semiconductor chip manufacturer,how to effectively carry out the bottleneck management and scheduling of semiconductor wafer fabrication system to meet the rapidly changing market demand is the key to achieve the industry competitive advantage.The bottleneck management and scheduling optimization problem of semiconductor wafer fabrication system is related to the realization of the goal of shortening the processing cycle,improving the equipment productivity and increasing the output of wafer.Bottleneck management can be divided into two aspects: Bottleneck Identification and bottleneck prediction,which is one of the urgent problems to be solved.Also,scheduling optimization problem is the rational allocation and arrangement according to the limited resources of semiconductor wafer fabrication system,is the enterprise to meet the needs of customers,so that their market share,develop and grow.In this paper,based on the idea of controlling the production process,the bottleneck management and scheduling optimization problem of semiconductor wafer fabrication system is studied.First of all,the bottleneck problem of bottleneck management is to explore the Bottleneck Identification method.The bottleneck of the concept of non uniform,so that the bottleneck identification method of research showing a variety of features.In this paper,the method of judging the comprehensive bottleneck from the point of view of equipment and production system is put forward.From the angle of equipment,this paper gives an analysis of the method to identify the inherent bottleneck of the equipment.From the point of view of production system,the knowledge of complex network theory is used to abstract the semiconductor wafer fabrication system.The comprehensive bottleneck degree is a bottleneck identification method which is based on a certain transformation.Secondly,the bottleneck prediction of bottleneck management is mainly about the establishment and analysis of the model.By using the data collected by the semiconductor wafer fabrication system,the bottleneck of the system is predicted based on the support vector machine(SVM).At the same time,in order to solve the arbitrariness of some parameters in support vector machine,a particle swarm optimization(PSO)algorithm is proposed.Finally,the scheduling optimization problem in semiconductor wafer fabrication system is mainly to make full use of the system bottleneck equipment based on the idea,put forward feed control strategy and hierarchical scheduling strategy,so as to ensure the number of wafer products and the performance of the system in the production process to achieve the optimal.