Title: Investigation on the influence of augmented rail geometries on rail gun design parameters using MSNN-PFOA approach

Authors: Jeyakumar Lydia; Ramasamy Karpagam; Ramakrishnan Murugan; Stephen Leones Sherwin Vimalraj

Addresses: Department of Electrical and Electronics Engineering, Easwari Engineering College, Chennai, 600089, India ' Department of Electrical and Electronics Engineering, Easwari Engineering College, Chennai, 600089, India ' Department of Electrical and Electronics Engineering, Bharath Institute of Higher Education and Research, Chennai, 600073, India ' Department of Electronics and Communication Engineering, Panimalar Engineering College, Chennai, 600123, India

Abstract: This paper proposes augmented rail geometries on rail gun design. The proposed method is the combined execution of multiresolution sinusoidal neural networks (MSNN) and Piranha Foraging Optimisation Algorithm (PFOA). Hence it is named the MSNN-PFOA approach. Heat minimisation in electromagnetic rail guns is the main goal of the hybrid MSNN-PFOA technique. The proposed MSNN algorithm is utilised to predict the extrapolation of electromagnetic force. Consequently, the PFOA is proposed to optimise the MSNN weight parameters. The proposed approach is evaluated in MATLAB and compared with existing methods like artificial neural network (ANN), particle swarm optimisation (PSO) and deep belief network-deep neural network (DBN-DNN). The basis error value of the proposed approach is 10% less than that of the existing methods. The ANN error value of the proposed method is more than that of the current one, which is 20%. The findings show that the efficiency of the proposed strategy is less than that of the existing approaches.

Keywords: armature velocity; electromagnetic force; energy; heat reduction; inductance gradient; rail gun and temperature.

DOI: 10.1504/IJHVS.2025.150216

International Journal of Heavy Vehicle Systems, 2025 Vol.32 No.6, pp.758 - 775

Received: 24 Jul 2024
Accepted: 25 Jan 2025
Published online: 03 Dec 2025 *

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