A rule-based robot scheduling system for flexible manufacturing cells

Biological computation of optimal task arrangement for a flexible machining cell

“…Furthermore, in producing algorithms or generating optimal schedules for FMS, a lot of constraints such as time, material resources, and so on should be considered. Most researchers try to solve this by employing artificial intelligent or/and soft computing techniques such as the rule-based method [6], genetic algorithms [8,9], fuzzy logic [10,11,35], machine learning [36], neural networks [4,13,37], as well as hybrid methods [2,3,12].…”

“…Chen and Guerrero [6] propose a rule-based approach to assist the cell supervisor in selecting an appropriate robot in scheduling strategies dynamically. They employed an algorithmic method based on Petri nets and a heuristic method to assist the cell supervisor in making long-term and shortterm decisions, respectively.…”

“…They employed an algorithmic method based on Petri nets and a heuristic method to assist the cell supervisor in making long-term and shortterm decisions, respectively. In reference [6] two elements are proposed in the rule-based system: dynamic decision rules (DDRs) and cycle switching rules (CSRs). The DDR method is based on single strategies on which an appropriate dispatching rule is selected from a rule pool to schedule a robot as the system environment changes.…”

“…Many researchers have proposed various techniques and algorithms to accelerate the production of manufacturing and to enhance its efficiency using available sources. For example, Chen and Guerrero [6] propose a rule-based algorithm of flexible production systems; He et al [7] and Kumar and Shanker [8] present genetic scheduling; Yang and Wu [9] apply adaptive genetic algorithms in dynamic rescheduling; Kamel and Biles [10] and Kong et al [11] describe fuzzy logic control methods; Low et al [12] deal with the multiple objective problem; and Paulli [13] presents a hierarchical approach.…”