Xili Chen

Rule driven multi objective dynamic scheduling by data envelopment analysis and reinforcement learning

This paper presents a rule driven method of developing composite dispatching rule for multi objective dynamic scheduling. Data envelopment analysis is adopted to select elementary dispatching rules, where each rule is justified as efficient for optimizing specific operational objectives of interest. The selected rules are subsequently combined into a single composite rule using the weighted aggregation manner. An intelligent agent is trained using reinforcement learning to acquire the scheduling knowledge of assigning the appropriate weighting values for building the composite rule to cope with the WIP fluctuation of a machine. Implementation of the proposed method in a two objective dynamic job shop scheduling problem is demonstrated and the results are satisfactory.

Cooperative Bayesian Optimization Algorithm: A Novel Approach to Simultaneous Multiple Resources Scheduling Problem

During the past several years, there has been a significant amount of research conducted simultaneous multiple resources scheduling problem (SMRSP) Intelligence manufacturing based on meta-heuristics, such as genetic algorithms (GAs), simulated annealing (SA) particle swarm optimization(PSO), has become a common tool to find satisfactory solutions within reasonable computational times in real settings. However, there are few researches considering interdependent relation during the decision activities, moreover for complex and large problems, local constraints and objectives from each managerial entity cannot be effectively represented in a single model for complex and large problems. In this paper, we propose a novel cooperative Bayesian optimization algorithm (COBOA) undertaking divide-and-conquer strategy and co-evolutionary framework. Considerable experiments are conducted and the results confirmed that COBOA outperforms recent researches for the scheduling problem in FMS.

Optimization method of short life cycle product supply chain network with recycle flow and dispersed markets

Under the context of globalization of Supply Chain and the diversity of product with the shortening product life cycle, the supply chain network design method with recycling reusable resources is being advocated. Hence this paper intent to qualify the impact of recycle strategy on the performance of global supply chain for short life cycle product, and propose an optimization method to provide an integrated planning for incorporating supply chain partners activities during the entire life cycle period of products in order to minimize supply chain operating cost. A Mixed Integer Programming model is proposed to formulate the supply chain network for short life cycle product demanded in multiple markets with recycle material flows. The experiment result shows that proper recycle operation policy will effectively down the total cost of entire supply chain.

Dispatching rule composition method for single machine multi objective dynamic scheduling

This paper presents a novel dispatching rule composition method based on Analytic Hierarchy Process for multi objective dynamic scheduling of single machines. By combining different elementary dispatching rules, the proposed method is capable of solving hetero-objective dynamic scheduling problems. Computer simulations were conducted to demonstrate the performance of the proposed method. Dynamic scheduling problems of various multi objective combinations were tested and the results were satisfactory. The features of the proposed method are discussed.

Multiple Objective Scheduling for Discrete Production System based on Compositional Dispatching Rules

The multiple objective scheduling problem (MOSP) becomes focus in recent years in actual manufacturing system. The most practical way to solve MOSP is using dispatching rule combination based on simulation evaluation. It mostly combines particular dispatching rules with linear manner corresponding to multiple scheduling objectives, however it is difficult to determine what combination of dispatching rules is effective to achieve multiple scheduling objectives and also to adapt compositional dispatching rules to change of scheduling objective. This paper presents a new heuristic method to deal MOSP based on unified ranking measure of the job priority with multiple dispatching rules. The priority of jobs regarding to respective dispatching rules are calculated and the unified priority of the job priority is decided by using analytic hierarchical process with adjusted weights corresponding to scheduling objectives. The simulation result demonstrates that the proposed method is feasible and flexible to solve MOSP.