Welcome to the InfoSci Platform
Reference Hub5
Optimization of Correlated and Conflicting Responses of ECM Process Using Flower Pollination Algorithm

Optimization of Correlated and Conflicting Responses of ECM Process Using Flower Pollination Algorithm

Bappa Acherjee, Debanjan Maity, Arunanshu S. Kuar
Copyright: © 2020 |Volume: 11 |Issue: 4 |Pages: 15
ISSN: 1947-8283|EISSN: 1947-8291|EISBN13: 9781799802877|DOI: 10.4018/IJAMC.2020100101
Cite Article Cite Article

MLA

Acherjee, Bappa, et al. "Optimization of Correlated and Conflicting Responses of ECM Process Using Flower Pollination Algorithm." IJAMC vol.11, no.4 2020: pp.1-15. http://doi.org/10.4018/IJAMC.2020100101

APA

Acherjee, B., Maity, D., & Kuar, A. S. (2020). Optimization of Correlated and Conflicting Responses of ECM Process Using Flower Pollination Algorithm. International Journal of Applied Metaheuristic Computing (IJAMC), 11(4), 1-15. http://doi.org/10.4018/IJAMC.2020100101

Chicago

Acherjee, Bappa, Debanjan Maity, and Arunanshu S. Kuar. "Optimization of Correlated and Conflicting Responses of ECM Process Using Flower Pollination Algorithm," International Journal of Applied Metaheuristic Computing (IJAMC) 11, no.4: 1-15. http://doi.org/10.4018/IJAMC.2020100101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The electrochemical machining (ECM) process has been investigated in this article to achieve the desired process performances by optimizing the machining parameters using the flower pollination algorithm (FPA). Two major process performances namely: material removal rate (MRR) and surface roughness (Ra), which are correlated and conflicting in nature, are optimized with respect to the key process parameters. The regression equations developed by using experimental data are used as objective functions in the flower pollination algorithm. Objectives are set to find the optimal set of process parameters to fulfil a single objective as well as multiple objectives. The performance of the algorithm is checked in terms of accuracy, convergence speed, number of optimized populations, and computational time. The mean values of functional evaluations for MRR and Ra obtained are close to their respective optimal results, which ensures the quality of the convergence. It is further seen that FPA can predict the true overall parametric trends as it does not require keeping any parameter as constant during the analysis.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.