Heterogeneous sensors-based feature optimisation and deep learning for tool wear prediction
Authors: Zhang, X., Wang, S., Li, W. and Lu, X.
Journal: International Journal of Advanced Manufacturing Technology
Volume: 114
Issue: 9-10
Pages: 2651-2675
eISSN: 1433-3015
ISSN: 0268-3768
DOI: 10.1007/s00170-021-07021-6
Abstract: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.
https://eprints.bournemouth.ac.uk/35395/
Source: Scopus
Heterogeneous sensors-based feature optimisation and deep learning for tool wear prediction
Authors: Zhang, X., Wang, S., Li, W. and Lu, X.
Journal: INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
Volume: 114
Issue: 9-10
Pages: 2651-2675
eISSN: 1433-3015
ISSN: 0268-3768
DOI: 10.1007/s00170-021-07021-6
https://eprints.bournemouth.ac.uk/35395/
Source: Web of Science (Lite)
Heterogeneous sensors-based feature optimisation and deep learning for tool wear prediction
Authors: Zhang, X., Wang, S., Li, W. and Lu, X.
Journal: The International Journal of Advanced Manufacturing Technology
Publisher: Springer Nature
ISSN: 0178-0026
DOI: 10.1007/s00170-021-07021-6
Abstract: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.
https://eprints.bournemouth.ac.uk/35395/
Source: Manual
Heterogeneous sensors-based feature optimisation and deep learning for tool wear prediction
Authors: Zhang, X., Wang, S., Li, W. and Lu, X.
Journal: The International Journal of Advanced Manufacturing Technology
Volume: 114
Pages: 2651-2675
ISSN: 0268-3768
Abstract: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.
https://eprints.bournemouth.ac.uk/35395/
Source: BURO EPrints