Multi-objective optimization and innovization-based knowledge discovery of sustainable machining process. (July 2022)

• Record Type: Journal Article
• Authors: Salem, Amr; Hegab, Hussien; Rahnamayan, Shahryar; Kishawy, Hossam A.
• Is Part Of: Journal of manufacturing systems. Volume 64(2022)
• Page Start: 636
• Page End: 647
• Publication Date: 2022-07
• Subjects: Sustainable machining -- Multi-objective optimization -- Clustering -- Knowledge discovery -- Machine learning; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2022.04.013
• Languages: English
• ISSNs: 0278-6125

Abstract

Abstract: Nowadays, establishing sustainable machining processes is getting a widespread interest in many industries. Moreover, the last decade has seen a rapid rise in using knowledge-embedded optimization techniques to optimal determining of cutting conditions, and accordingly achieving the required sustainability targets. However, there is still a need to establish an approach which can fully analyse the optimized results, offering recommended settings to accommodate any desired levels of the sustainable machining responses. Such approach should be also flexible to switch between different desired objectives with extremely minimum efforts to accommodate the various requirements of the sustainable machining system. In this context, the current study offers a novel knowledge discovery approach to optimize the sustainable machining processes. In addition, a case study is conducted in order to validate the proposed approach. Genetic Programming (GP) and Non-dominated Sorting Genetic Algorithm (NSGA-II) were utilized for modelling and optimization purposes, respectively. In addition, the optimal cutting conditions were clustered into seven clusters, offering five different desirability levels to minimize the surface roughness, specific energy, and unit volume machining time. These obtained results showed that the decision maker can easily use any of the discovered knowledge based on the optimal solutions in their determined clusters. The proposed approach is promisingly applicable on similar engineering applications as a novel direction resulted by collaboration between machine learning (ML) and multi-objective optimization (MOO).