Title: Cost-effective reconfigurable manufacturing system using multi-objective hybrid optimisation for vehicle routing problem

Authors: Pushpa Manoj Bangare; Ratnaprabha Ravindra Borhade; Ravindra Sadashivrao Apare; Nitin S. More; Manoj Limchand Bangare

Addresses: Department of Electronics and Telecommunication, Smt. Kashibai Navale College Engineering, Pune-411041, Maharashtra, India ' Department of Electronics and Telecommunication, Cummins College of Engineering for Women, Pune 411052, Maharashtra, India ' Department of Artificial Intelligence and Data Science, Pune Vidyarthi Griha's College of Engineering, Technology and Management, Pune, India ' Department of Computer Science and Engineering, MIT Art, Design and Technology University, Pune – 412201, Maharashtra, India ' Department of Information Technology, Smt. Kashibai Navale College Engineering, Pune, Maharashtra, India

Abstract: A reconfigurable manufacturing system (RMS) offers flexibility to produce single product through multiple routes. However, optimising manufacturing configuration and vehicle routing remains complex. To address this gap, this research proposes an intelligent RMS framework for multi-objective decision-making. In the first phase, a customised convolutional neural network (cus-CNN) model is employed to optimise parameters, including product, cost, completion time, quality, and quantity for accurately identifies machine numbers in product's manufacturing. While cus-CNN effectively configures machines under normal conditions, and machine failure scenarios are mitigated through proposed butterfly-assisted chimp optimisation algorithm (BACOA), which combines butterfly optimisation and chimp optimisation algorithms. This hybrid algorithm optimising parameters including total cost, production time, scalability, and modularity. In second phase, BACOA method optimising vehicle routing, considering distance. Performance comparisons demonstrate that proposed model achieved lowest cost (0.516595) and reduced RMSE (0.20756), outperforming all benchmarks and ensures scalable solution for manufacturing and delivery in dynamic production environments.

Keywords: reconfigurable manufacturing system; RMS; convolutional neural network; cus-CNN; BACOA; vehicle routing; modularity.

DOI: 10.1504/IJAMECHS.2026.155369

International Journal of Advanced Mechatronic Systems, 2026 Vol.13 No.3, pp.156 - 177

Received: 19 Oct 2024
Accepted: 26 Nov 2025
Published online: 30 Jul 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article