An adaptive neuro fuzzy inference system for makespan estimation in multiprocessor no-wait two stage flow shop

This article may be used for research, teaching and private study purposes. Any substantial or systematic reproduction, redistribution , reselling , loan, sub-licensing, systematic supply or distribution in any form to anyone is expressly forbidden. The publisher does not give any warranty express or implied or make any representation that the contents will be complete or accurate or up to date. The accuracy of any instructions, formulae and drug doses should be independently verified with primary sources. The publisher shall not be liable for any loss, actions, claims, proceedings, demand or costs or damages whatsoever or howsoever caused arising directly or indirectly in connection with or arising out of the use of this material. In a flow shop scheduling problem, no-wait processing is becoming an important subject where the subsequent operations are performed with no-waiting time in between. In addition, it is important to estimate the schedule performance in terms of given criteria. This enables managers to conduct a reliable logistic planning while estimating robust job completion times. In this study, six heuristic algorithms are used to solve a no-wait two stage flexible flow shop with minimising makespan. Furthermore, an adaptive neuro fuzzy inference system (ANFIS) with neural network and fuzzy theory is applied for estimating the makespan. The robustness of the proposed ANFIS using the six heuristic scheduling algorithms is testified by comparing its performance with that of the actual schedule performance. This is followed by concluding remarks and potential area for further researches. 1. Introduction Production scheduling plays a crucial role in both manufacturing systems and service industry as it leads to efficient utilisation of resources while meeting customer needs (Wang 2003, Stadtler 2005). Among the scheduling problems, flow shop scheduling problem (FSSP) has been widely studied by researchers. This has been considered as a difficult class of In practice, one of the most applicable flow shop problems is a flexible flow shop, also known as a hybrid flow shop or FSSP with parallel machines, i.e. flexible flow line. This has been studied by many researchers; among them include those investigated by Zandieh et al. In the flexible FSSP, there are a set of n jobs j ¼ {1,2. .. n} that need to be processed at k working stages (i ¼ {1,2. .. k}). Each stage might have a number of identical machines performing in parallel (m i). When there is more than one parallel machine at …