Title: Drilling automation in mining industry

Authors: Marzieh Zare; Hesam Jafarian; Ari Visa

Addresses: Department of Computing Sciences, Tampere University, Tampere, Finland ' Department of Engineering and Natural Sciences, Tampere University, Tampere, Finland ' Department of Computing Sciences, Tampere Univesity, Tampere, Finland

Abstract: In response to the critical need for enhanced monitoring in the mining industry, our research focuses on early fault detection in drilling. We explored how strategic sensor placement, determined through statistical feature extraction, influences fault detection accuracy. This approach aimed to gather crucial data for assessing the machinery's internal state. We developed a hybrid method, which is capable with triaxial accelerometers, to recognise different drilling operations. This method significantly enhances fault detection and provides deep insights into the machine's internal state, marking a major step in automation science and leading to safer, eco-friendly, and cost-efficient drilling operations.

Keywords: machine learning; sensor placement; data fusion; multi-class classification; mining industry; health monitoring.

DOI: 10.1504/IJISE.2026.156482

International Journal of Industrial and Systems Engineering, 2026 Vol.54 No.1, pp.85 - 102

Received: 27 Jan 2024
Accepted: 25 Sep 2024
Published online: 21 Sep 2026 *

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