Abstract
Recently, the concept of smart manufacturing systems urges for intelligent optimization of process parameters to eliminate wastage of resources, especially materials and energy. In this context, the current study deals with optimization of hard-turning parameters using evolutionary algorithms. Though the complex programming, parameters selection, and ability to obtain the global optimal solution are major concerns of evolutionary based algorithms, in the present paper, the optimization was performed by using efficient algorithms i.e., teaching–learning-based optimization and bacterial foraging optimization. Furthermore, the weighted sum method was used to transform the diverse responses into a single response, and then multi-objective optimization was performed using the teaching–learning-based optimization method and the standard bacterial foraging optimization method. Finally, the optimum results reported by these methods are compared to choose the best method. In fact, owing to better convergence within shortest time, the teaching–learning-based optimization approach is recommended. It is expected that the outcome of this research would help to efficiently and intelligently perform the hard-turning process under automatic and optimized environment.
Funder
Regional Operational Programme for the Opole Voivodeship financed by the Structural Funds of the European Union and the State budget of Poland
Subject
General Materials Science
Reference18 articles.
1. An intelligent system for core-competence identification for industry 4.0 based on research results from german and polish manufacturing companies;Patalas-Maliszewska,2017
2. Intelligent Manufacturing in the Context of Industry 4.0: A Review
3. Smart manufacturing, manufacturing intelligence and demand-dynamic performance
4. Soft modelling-based methodology of raw material waste estimation;Kujawińska,2017
5. Development of an Intelligent and Automated System for Lean Industrial Production, Adding Maximum Productivity and Efficiency in the Production Process;Araújo,2018
Cited by
63 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献