Affiliation of Author(s):计算机科学与技术学院/人工智能学院/软件学院

Journal:ENGINEERING OPTIMIZATION

Key Words:Flow-shop scheduling with blocking estimation of distribution algorithm path relinking makespan

Abstract:This article presents an effective estimation of distribution algorithm, named P-EDA, to solve the blocking flow-shop scheduling problem (BFSP) with the makespan criterion. In the P-EDA, a Nawaz-Enscore-Ham (NEH)-based heuristic and the random method are combined to generate the initial population. Based on several superior individuals provided by a modified linear rank selection, a probabilistic model is constructed to describe the probabilistic distribution of the promising solution space. The path relinking technique is incorporated into EDA to avoid blindness of the search and improve the convergence property. A modified referenced local search is designed to enhance the local exploitation. Moreover, a diversity-maintaining scheme is introduced into EDA to avoid deterioration of the population. Finally, the parameters of the proposed P-EDA are calibrated using a design of experiments approach. Simulation results and comparisons with some well-performing algorithms demonstrate the effectiveness of the P-EDA for solving BFSP.

ISSN No.:0305-215X

Translation or Not:no

Date of Publication:2018-01-01

Co-author:邵仲世,邵炜世

Correspondence Author:Pi Dechang