University of Oulu

I. S. Khan, U. Ghafoor and T. Zahid, "Meta-Heuristic Approach for the Development of Alternative Process Plans in a Reconfigurable Production Environment," in IEEE Access, vol. 9, pp. 113508-113520, 2021, doi: 10.1109/ACCESS.2021.3104116

Meta-heuristic approach for the development of alternative process plans in a reconfigurable production environment

Saved in:
Author: Khan, Iqra Sadaf1; Ghafoor, Usman2; Zahid, Taiba3
Organizations: 1Industrial Engineering and Management, Faculty of Technology, University of Oulu, 90570 Oulu, Finland
2Department of Mechanical Engineering, Institute of Space Technology, Islamabad 44000, Pakistan
3National University of Science and Technology, Islamabad 44000, Pakistan
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 7.4 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2021-10-28


The need for automated production plans has evolved over the years due to internal and external drivers like developed products, new enhanced processes and machinery. Reconfigurable manufacturing systems focus on such needs at both production and process planning level. The age of Industry 4.0 focused on mass customization requires computer aided planning techniques that are able to cope with custom changes in products and explores intelligent algorithms for efficient scheduling solutions to reduce lead time. This problem has been categorized as NP-Hard in literature and is addressed by providing intelligent heuristics that focus on reducing machining time of the products at hand. However, as 70% of the lead time is consumed in non-value added tasks, it is fundamental to provide modular solutions that can reduce this time and handle part variety. To address the subject, this paper focuses on the generation of automated process plans for a single machine problem while focusing on reducing time lead time. Two evolutionary algorithms (EAs) have been proposed and compared to answer complex problem of process planning. A modified genetic algorithm (GA) has been proposed in addition to cuckoo search (CS) heuristic for this discrete problem. On testing with selected benchmark part ANC101, significant improvement was seen in terms of convergence with proposed EAs. Moreover, a novel Precedence Group Algorithm (PGA) is proposed to generate quality input for heuristics. The algorithm produces a set of initial population which significantly effects the performance of proposed heuristics. For the discrete constrained process planning problem, GA outperforms CS providing 10% more feasible scheduling options and three times lesser run time as compared to CS. The proposed technique is flexible and responsive in order to accommodate part variety, a necessary requirement for reconfigurable systems.

see all

Series: IEEE access
ISSN: 2169-3536
ISSN-E: 2169-3536
ISSN-L: 2169-3536
Volume: 9
Pages: 113508 - 113520
DOI: 10.1109/ACCESS.2021.3104116
Type of Publication: A1 Journal article – refereed
Field of Science: 222 Other engineering and technologies
Copyright information: © 2021 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see