Title: A machine learning algorithm for scheduling a burn-in oven problem

Authors: M. Mathirajan; Reddy Sujan; M. Vimala Rani; Pujara Dhaval

Addresses: Department of Management Studies, Indian Institute of Science, Bangalore, India ' Department of Information Technology, National Institute of Technology Suratkal, Karnataka, India ' Vinod Gupta School of Management, Indian Institute of Technology-Kharagpur, India ' Department of Management Studies, Indian Institute of Science, Bangalore, India

Abstract: This study applies artificial neural network (ANN) to achieve more accurate parameter estimations in calculating job-priority-data of jobs and the same is applied in a proposed dispatching rule-based greedy heuristic algorithm (DR-GHA) for efficiently scheduling a burn-in oven (BO) problem. The integration of ANN and DR-GHA is called as a hybrid neural network (HNN) algorithm. Accordingly, this study proposed eight variants of HNN algorithms by proposing eight variants of DR-GHA for scheduling a BO. The series of computational analyses (empirical and statistical) indicated that each of the variants of proposed HNN is significantly enhancing the performance of the respective proposed variants of DR-GHA for scheduling a BO. That is, more accurate parameter estimations in calculating job-priority-data for DR-GHA via back-propagation ANN leads to high-quality schedules w.r.t. total weighted tardiness. Further, proposed HNN variant: HNN-ODD is outperforming relatively with other HNN variants and provides very near optimal/estimated solution.

Keywords: dispatching rules; semiconductor manufacturing; greedy heuristic algorithm; GHA; artificial neural network; ANN; optimal solution; estimated optimal solution; dispatching rule-based greedy heuristic algorithm; DR-GHA; hybrid neural network; HNN.

DOI: 10.1504/IJISE.2023.128403

International Journal of Industrial and Systems Engineering, 2023 Vol.43 No.1, pp.20 - 58

Received: 21 Apr 2020
Accepted: 28 Feb 2021
Published online: 20 Jan 2023 *