Papers by Keyword: Dispatching Rule

Abstract: This paper considers two stage hybrid flow shop with identical parallel machine and evaluate performance of common dispatching rules; shortage processing time (SPT) longest processing time (LPT) earliness due date (EDD) and first in first out (FIFO). The objectives are to determine makespan and total tardiness have been minimized. To evaluated performance of dispatching rules, the results have been compared on each criterion. The experimental results show that SPT outperform than other rules with minimizes makespan as an objective function for all problems. On the other hand, for minimize total tardiness as an objective. The EDD rule outperform than other rules.

Abstract: In this paper, we researched a one-of-a-kind assembly production system where every product is unique (i.e. each product has its unique tree-like process route) and arrives one by one randomly with the exponentially distributed inter arrival times. We proposed a new effective combined dispatching rule (LFD/RPS/CP rule) that is constructed by considering three factors: the latest finishing date (LFD), the remaining path size (RPS) and whether an operation is on the critical path (CP). We did many numerical experiments to compare the efficiency between the proposed rule and other rules that were reported in existing studies such as LFD rule and EDD rule. The performance analysis shows that the proposed dispatching rule is more effective in reducing the number of tardy products and total tardiness time.

Abstract: This paper proposes a non-cooperative game approach based on neural network (GMBNN) to solve the job shop scheduling problem. Machines in manufacturing task are defined as players and strategies consist of all the feasible programs which are selected by dispatching rules for minimizing the mean flowtime. Strategies for the game model are generated from a backpropagation neural network, which selects combination of the rules for the machines. Case study shows that the GMBNN can be an effective approach to solve the job shop scheduling problem.

Abstract: The problem of resource allocation and scheduling is considered for a flexible job shop composed of several work centers with multiple identical machines. Each machine has its own setup time that depends on the current and the arriving batch types. The optimal number of machines at each center and the optimal batch size for each job type is to be determined for several dispatching rule. The objective of the study is to assist the scheduler in selecting the best dispatching rule with respect to a desired performance measure along with its corresponding batch size and optimum number of machines in each center. Several measures are considered including the average flow time, sum of earliness and tardiness, and the number of tardy jobs. The simulation package ProModel is used to build the model and its optimization tool called SimRunner is used for optimization.

Abstract: In the paper, the problem of dynamic scheduling with random disturbance is taken into consideration. Through analyzing the workshop disturbance, the processing strategy and simulation procedure is proposed. On this basis, the supervisory control expert system is developed on the platform of G2. The simulation results given at last illustrate the main function of the system, including manufacturing process monitoring, abnormal event warning, and rescheduling.

Abstract: Photolithography area is usually a bottleneck area in a semiconductor wafer manufacturing system (SWMS). It is difficult to schedule photolithography area on real-time optimally. Here, an Elman neural network (ENN)-based dynamic scheduling method is proposed. An ENN-based sample learning algorithm is proposed for selecting best combination of scheduling rules. To illustrate the feasibility and practicality of the presented method, the simulation experiment is developed. A numerical example is use to evaluate the proposed method. Results of simulation experiments show that the proposed method is effective to schedule a complex wafer photolithography process.

Abstract: Photolithography is usually the bottleneck process with the most expensive equipment in a semiconductor wafer fabrication system. To improve the performances of the photolithography area with dynamic combination rules, a method of Kohonen neural network (KNN)–based performance improvements is proposed. First, a dynamic scheduling framework based on a KNN model and scheduling rules is proposed. A KNN-based sample learning algorithm for improving the performances is presented. Finally, to demonstrate the validity and feasibility of the proposed method, data from a real wafer fabrication system are used to simulate the proposed method. Results of simulation experiments indicate that the proposed method can be used to improve a complex wafer photolithography performance.

Abstract: The scheduling problem of LED chip sorting workstation is a multiprocessor open shop scheduling problem. In practice, this problem is usually solved with finding a dispatching rule to achieve certain performance indexes. Experimental design was applied to find a proper rule, and dispatching rule, wafer quantity, wafer mix type, and bottleneck location were chosen as independent variables. Maximum make-span and average queuing time were selected as dependent variables. Five dispatching rules were considered in the dispatching rule factor. Experimental results showed that all independent variables are significant on all dependent variables. While make-span as the performance index, three dispatching rules common in applying LPT in bottleneck machines obtained better results. A dispatching rule with applying SPT in non-bottleneck machines has least average queuing time among those three, and this rule is recommended for practical application.