Pertanika J. Sci. & Technol. 28 (4): 1469 - 1486 (2020) ISSN: 0128-7680 e-ISSN: 2231-8526 SCIENCE & TECHNOLOGY Journal homepage: http://www.pertanika.upm.edu.my/ Article history: Received: 5 April 2020 Accepted: 2 June 2020 Published: 21 October 2020 ARTICLE INFO E-mail addresses: achandra@amity.edu (Anil Chandra) sgupta11@amity.edu (Surbhi Gupta) ckjaggi@yahoo.com (Chandra Kant Jaggi) *Corresponding author © Universiti Putra Malaysia Press DOI: https://doi.org/10.47836/pjst.28.4.18 A Multi-State Model for Reliability Analysis of Metal Sheet Manufacturing Process using Artificial Neural Network Technique Anil Chandra 1 , Surbhi Gupta 1 * and Chandra Kant Jaggi 2 1 Amity Institute of Applied Sciences, Amity University Uttar Pradesh, 201313 Noida, India 2 Department of Operational Research, University of Delhi, 110007 Delhi, India ABSTRACT A manufacturing system is governed by its various processes upon which its efciency is dependent. Since, failure results in considerable losses, many manufacturing systems have certain redundancies for some processes. These redundancies cause the system to work under diferent efciency states called multi-state elements. In this paper various processes of metal sheet manufacturing unit have been categorized as subsystems to determine the multi-state probabilities of its diferent efciency states. Artifcial Neural Network Technique (ANN) has been used to estimate the change in these multi-state probabilities over time. The ANN has also been used to estimate variation in upstate and downstate probabilities of the system for a particular-time period. The results have been used to determine variation in proft over time for the system. Keywords: Artifcial neural network, downstate, metal sheet manufacturing, reliability, state transition, upstate INTRODUCTION A well-established industrial process is designed to provide the best quality product within optimum cost. However, these processes are susceptible to failures due to various reasons. Most of the industrial processes are designed to accommodate parallel redundancy with reduced functionality of plant so as to minimize the losses during corrective maintenance of the process. This leads to the whole system