• Journal of the Semiconductor & Display Technology
• /
• v.23 no.2
• /
• pp.107-113
• /
• 2024

Scheduling of semiconductor test facilities has been crucial since effective scheduling contributes to the profits of semiconductor enterprises and enhances the quality of semiconductor products. This study aims to solve the scheduling problems for the wafer burn-in test facilities of the semiconductor back-end process by utilizing simulation and deep reinforcement learning-based methods. To solve the scheduling problem considered in this study. we propose novel state, action, and reward designs based on the Markov decision process. Furthermore, a neural network is trained by employing the recent RL-based method, named proximal policy optimization. Experimental results showed that the proposed method outperformed traditional heuristic-based scheduling techniques, achieving a higher due date compliance rate of jobs in terms of total job completion time.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.27 no.2
• /
• pp.97-109
• /
• 2002

Manufacturing environments in the real world are subject to many sources of change and uncertainty, such as new job releases, job cancellations, a chance in the processing time or start time of some operation. Thus, the realistic scheduling method should Properly reflect these dynamic environment. Based on the release times of jobs, JSSP (Job Shoe Scheduling Problem) can be classified as static and dynamic scheduling problem. In this research, we mainly consider the dynamic JSSP with continually arriving jobs. The goal of this research is to develop an efficient scheduling method based on GA (Genetic Algorithm) to address dynamic JSSP. we designed scheduling method based on SGA (Sing1e Genetic Algorithm) and PGA (Parallel Genetic Algorithm) The scheduling method based on GA is extended to address dynamic JSSP. Then, This algorithms are tested for scheduling and rescheduling in dynamic JSSP. The results is compared with dispatching rule. In comparison to dispatching rule, the GA approach produces better scheduling performance.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.11a
• /
• pp.85-88
• /
• 2003

In case that any jobs in a Job Shop can be scheduled on more than one machine and may have flexible operation sequences, with considering such case it is very difficult and complex to make the optimal process plans and scheduling. But they should be considered for an integrated model to perform more effective process planning and scheduling in this job shop problem. In this paper, we propose GA-based scheduling method to integrate effectively the problem of alternative machines, alternative operation sequences and scheduling. The performance of proposed GA is evaluated through comparing integrated scheduling with not integrated scheduling in molding company with alternative machines and operation sequences. Also, we use benchmark problems to evaluate performance. The scheduling method in this research will apply usefully to real world scheduling problems.

• Korean Management Science Review
• /
• v.20 no.1
• /
• pp.51-64
• /
• 2003

The JSSP (Job Shop Scheduling Problem) Is one of the most general and difficult of all traditional scheduling problems. The goal of this research is to develop an efficient scheduling method based on genetic algorithm to address JSSP. we design scheduling method based on SGA (Single Genetic Algorithm) and PGA (Parallel Genetic Algorithm). In the scheduling method, the representation, which encodes the job number, is made to be always feasible, initial population is generated through integrating representation and G&T algorithm, the new genetic operators and selection method are designed to better transmit the temporal relationships in the chromosome, and island model PGA are proposed. The scheduling method based on genetic algorithm are tested on five standard benchmark JSSPs. The results were compared with other proposed approaches. Compared to traditional genetic algorithm, the proposed approach yields significant improvement at a solution. The superior results indicate the successful Incorporation of generating method of initial population into the genetic operators.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.26 no.2
• /
• pp.59-68
• /
• 2001

The job shop scheduling problem is not only NP-hard, but is one of the well known hardest combinatorial optimization problems. The goal of this research is to develop an efficient scheduling method based on hybrid genetic algorithm to address job shop scheduling problem. In this scheduling method, generating method of initial population, new genetic operator, selection method are developed. The scheduling method based on genetic algorithm are tested on standard benchmark job shop scheduling problem. The results were compared with another genetic algorithm0-based scheduling method. Compared to traditional genetic, algorithm, the proposed approach yields significant improvement at a solution.

• Korean Management Science Review
• /
• v.21 no.2
• /
• pp.79-91
• /
• 2004

In industrial production settings, scheduling problems for detailed day-to-day operations are often ordeals to production practitioners. For those who have scheduling experiences with the Gantt Chart, the job oriented heuristic scheduling has illustrated its merits in solving practically large scale scheduling problems. It schedules all operations of a job within a finite capacity before considering the next job. In this paper, we Introduce the LSB (load smoothing backward) scheduling algorithm for the job oriented heuristic scheduling. Through a computer experiment in a hypothetical setting, we make a performance comparison of LSB scheduling algorithm with existing algorithms and also suggest a guideline for selecting the suitable algorithm for certain industrial settings.

• Korean Management Science Review
• /
• v.9 no.1
• /
• pp.119-137
• /
• 1992

A two phase heuristic algorithm has been developed for the resolution of resource conflicts in a single project scheduling problem. Phase 1 of the algorithm generates a feasible schedule by repairing resource conflicts. Phase 2 finds local improvements in the schedule found in phase 1. Then, the algorithm has been applied to multi project and job shop scheduling. Computational results are compared with those of dispatching procedures. Index Terms-disjunctive constraints, heuristic algorithm, project scheduling, job-shop scheduling.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2000.10a
• /
• pp.149-152
• /
• 2000

The chartered bus scheduling is to determine the allocation of buses to customer service requests. For the scheduling, we first represent the scheduling problem using a graph and develop a mathematical model. Second, we develop an algorithm for the scheduling problem including heuristic methods. We tested the performance of the algorithm on instances with real data. As a result, the total empty load driving time is reduced over 10% comparing with that of current practice at the company

• Journal of the Korean Operations Research and Management Science Society
• /
• v.22 no.1
• /
• pp.25-49
• /
• 1997

Printed circuit board (PCB) assembly line configuration is characterized by very long set-up times and high work in process (WIP) inventory level. The scheduling method can significantly reduce the set-up times and WIP inventory level. Greedy sequence dependent scheduling (GSDS) method is proposed based on the current methods. The proposed method is compared with the current method in terms of three performance measures: line throughput, average WIP inventory level, and implementation complexity.

• Journal of Korean Society for Quality Management
• /
• v.15 no.2
• /
• pp.74-81
• /
• 1987

The purpose of this paper is to find out the relative priority among the queueing products for next operation. Critical ratio scheduling is a technique for use in production scheduling to establish and maintain relative priority among the jobs. The relative priority is based on a ratio of when the completed job is required and how much time is required to complete it. A numerical example of "D" company is solved. Jobs are classified into 3 categories; the behind scheduling jobs, the on time jobs and the ahead scheduling jobs.