No abstract

No abstract

The complexity of printed circuit boards (PCBs), as an important sector of the electronics manufacturing industry, has increased over the last three decades. This paper focuses on a practical application observed at a PCB assembly line of electronics manufacturing facility. It is shown that this problem is equivalent to a flowshop scheduling with multiple heterogeneous batch processors where processors can perform multiple tasks as long as the sizes of jobs in a batch do not violate the processors' capacity. The equivalent problem is mathematically formulated as a mixed integer programming model. Then, a Monte Carlo simulation is incorporated into high-level genetic algorithm-based intelligent optimization techniques to assess the performance of makespan-oriented system under uncertain processing times. At each iteration of algorithm, the output of simulator is used by optimizers to provide online feedbacks on the progress of the search and direct the search toward a promising solution zone. Furthermore, various parameters and operators of the algorithm are discussed and calibrated by means of Taguchi statistical technique. The result of extensive computational experiments shows that the solution approach gives high-quality solutions in reasonable computational time.

The flow shop is a well-known class of manufacturing system for production process planning. The need for scheduling approaches arises from the requirement of most systems to implement more than one process at a moment. Batch processing is usually carried out to load balance and share system resources effectively and gain a desired quality of service level. A flow shop manufacturing problem with batch processors (BP) is discussed in current paper so as to minimize total penalty of earliness and tardiness. To address the problem, two improved discrete particle swarm optimization (PSO) algorithms are designed where most important properties of basic PSO on velocity of particles are enhanced. We also employ the attractive properties of logistic chaotic map within PSO so as to investigate the influence of chaos on search performance of BP flow shop problem. In order to investigate the suggested algorithms, a comprehensive computational study is carried out and performance of algorithms is compared with (1) a commercial optimization solver, (2) a well-known algorithm from PSO's literature and (3) three algorithms from BP's literature. The experimental results demonstrate the superiority of our algorithm against others.

No abstract