1 September 2019 in Journal of Petroleum Science and Engineering
24 September 2016 in Journal of Intelligent Systems
Manufacturing resources are shared and centrally managed on the cloud platform in cloud manufacturing, which is a new model of modern manufacturing. The production data are collected, which can be used to predict the manufacturing events. Based on those, disruption problems of scheduling should be researched from a new point of view. In this paper, new job arrivals were considered as the disruption event. The time of the occurrence of disruption was predictable in contrast to uncertainty. Alternative subcontractors chosen from the cloud platform were available for outsourcing with different processing prices and transporting distances. The objective of the original scheduling, the deviation between the new schedule and the old one, and the outsourcing cost were all considered. To express the problem, mathematical models and a three-field notation model were constructed. To solve the problem, a hybrid quantum-inspired chaotic group leader optimization algorithm was proposed, in which a hybrid encoding way was applied. To verify the algorithm, experiments were carried out. The results showed that the proposed algorithm performs well.
15 September 2016 in Journal of Intelligent Systems
A large number of changeovers exist in multi-item and small lot size production mode, which lead to a long setup time and significantly influence productivity. However, setup time has received significantly less attention in previous studies regarding the single machine scheduling (SMS) problem. This paper investigates the SMS problem with sequence-dependent setup time (SDST). First, a model of SMS-SDST is developed to minimise the makespan. An earliest due date (EDD), SDST, and ant colony optimisation (ACO) heuristic algorithm is presented. In order to evaluate the performance of the proposed algorithm, Taguchi’s robust design method is employed to define the best parameter values. Related results are analysed by statistical tools. The computational experiments are compared with an ACO algorithm and a genetic algorithm. The experimental results and statistical analyses show that the proposed EDD-SDST-ACO is effective for the problem.