Title: An intelligent hybrid model approach for predictive maintenance of tool wear using machine learning techniques

Authors: Soorya Prabha Mohan; S. Jaya Nirmala

Addresses: Department of Computer Science and Engineering, National Institute of Technology, Trichy, Tamil Nadu, India ' Department of Computer Science and Engineering, National Institute of Technology, Trichy, Tamil Nadu, India

Abstract: Machine uptime is highly important as the repairing time takes longer which affects the production and the manufacturing industry focus on new ways of being competitive. Manufacturing and assembly parts of the machine are the key component for ensuring machine uptime. Maintenance of these components plays a major role in ensuring the key component health and is an ongoing process. For this, predictive maintenance is the commonly used approach, based on machine running conditions and tool information in production environment. For the proposed methodology, data has been collected from a well-reputed machinery manufacturer. This paper presents the hybrid model, which predicts the machine failure based on multiple ensembling techniques followed by the stacking approach, which performs the k-fold cross-validation and leads to results that provide good accuracy and less false alarms.

Keywords: tool wear; heat dispatch failure; stacking; ensembling.

DOI: 10.1504/IJVICS.2023.135103

International Journal of Vehicle Information and Communication Systems, 2023 Vol.8 No.4, pp.398 - 412

Received: 26 Oct 2022
Accepted: 31 Jan 2023
Published online: 30 Nov 2023 *

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