Skip to main content

Heterogeneous sensors-based feature optimisation and deep learning for tool wear prediction.

Zhang, X., Wang, S., Li, W. and Lu, X., 2021. Heterogeneous sensors-based feature optimisation and deep learning for tool wear prediction. The International Journal of Advanced Manufacturing Technology, 114, 2651-2675.

Full text available as:

Heterogeneous sensors-based feature optimisation and deep learning for tool wear prediction.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.


DOI: 10.1007/s00170-021-07021-6


During machining processes, accurate prediction of cutting tool wear is prominent to prevent ineffective tool utilisation and significant resource waste. Tool wear conditions and progression involve complex physical mechanisms, and a promising approach is to deploy heterogeneous sensors and design a deep learning algorithm to conduct real-time tool wear monitoring and precious prediction. To tackle the challenge of deep learning algorithms in processing complex signals from heterogeneous sensors, in this paper, a systematic methodology is designed to combine signal de-noising, feature extraction, feature optimisation and deep learning-based prediction. In more details, the methodology is comprised of the following three steps: (i) signal de-noising is carried out by a designed Hampel filter-based method to eradicate random spikes and outliers in the signals for raw data quality enhancement; (ii) features extracted from heterogeneous sensors in the time and frequency domains are optimised using designed recursive feature elimination and cross-validation (RFECV)-based and Isomap-based methods; (iii) a convolutional neural networks (CNN) algorithm is devised to process the optimised features to implement tool wear prediction. In this paper, a case study showed that 80% features were reduced from the originally extracted features and 86% prediction accuracy was achieved based on the developed methodology. The presented methodology was benchmarked with several main-stream methodologies, and the superior performance of the methodology over those comparative methodologies in terms of prediction accuracy was exhibited.

Item Type:Article
Additional Information:Funding: This research was partially sponsored by the SABOT project funded by the IUK funder (UK). The research was also sponsored by the National Natural Science Foundation of China (Project No. 51975444).
Uncontrolled Keywords:Tool wear prediction; feature optimisation; convolutional neural networks (CNN); heterogeneous sensors
Group:Faculty of Science & Technology
ID Code:35395
Deposited By: Symplectic RT2
Deposited On:15 Apr 2021 09:46
Last Modified:12 Apr 2022 01:08


Downloads per month over past year

More statistics for this item...
Repository Staff Only -