Sensor selection and tool wear prediction with data‐driven models for precision machining

Han, Seulki; Yang, Qian; Pattipati, Krishna R.; Bollas, George M.

doi:10.1002/amp2.10143

Sensor selection and tool wear prediction with data‐driven models for precision machining

Journal Article · Wed Aug 31 00:00:00 EDT 2022 · Journal of Advanced Manufacturing and Processing

DOI:https://doi.org/10.1002/amp2.10143· OSTI ID:1893230

Han, Seulki ^[1]; Yang, Qian ^[2]; Pattipati, Krishna R. ^[2]; ^[1]

Department of Chemical &, Biomolecular Engineering University of Connecticut Storrs Connecticut USA
Department of Electrical &, Computer Engineering University of Connecticut Storrs Connecticut USA

Abstract

Estimation of tool wear in precision machining is vital in the traditional subtractive machining industry to reduce processing cost, improve manufacturing efficiency and product quality. In this vein, fusion of time and frequency‐domain features of commonly sensed signals can provide an early indication of tool wear and improve its prediction accuracy for prognostics and health management. This paper presents a data‐driven methodology and a complete tool chain for the inference of precision machining tool wear from fused machine measurements, such as cutting force, power, audio and vibration signals, and quantify the usefulness of each measurement. Indicators of tool wear are extracted from time‐domain signal statistics, frequency‐domain analysis, and time‐frequency domain analysis. Correlation coefficients between the extracted features (indicators) and the tool wear are used to select the most informative features. Principal Component Analysis and Partial Least‐Squares are used to reduce the dimensionality of the feature space. Regression models, including linear regression, support vector regression, Decision tree regression, neural network regression and Gaussian process regression, are used to predict the tool wear using data from a Haas milling machine performing spiral boss face milling. The performance of the regression models based on subsets of sensors validates the preliminary estimates about the saliency of the sensors. The experimental results show that the proposed methods can predict the machine tool wear precisely, with readily available sensor measurements. Neural network and Gaussian process regression were able to achieve good estimates of tool wear at different machine operating conditions. The most informative signal in predicting tool wear was shown to be the vibration signal. Time‐frequency domain features were the most informative features among the combination of features of three domains. In addition, using partial least squares components extracted from the original features of signals led to higher prediction accuracy.

View Accepted Manuscript (Publisher)

Sponsoring Organization:: USDOE

Grant/Contract Number:: EE0007613

OSTI ID:: 1893230

Journal Information:: Journal of Advanced Manufacturing and Processing, Journal Name: Journal of Advanced Manufacturing and Processing Journal Issue: 4 Vol. 4; ISSN 2637-403X

Publisher:: Wiley Blackwell (John Wiley & Sons)Copyright Statement

Country of Publication:: United States

Language:: English

References (25)

Classification and regression trees: Classification and regression trees Loh, Wei-Yin Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, Vol. 1, Issue 1 https://doi.org/10.1002/widm.8	journal	January 2011
Quality Engineering through Design Optimization Taguchi, G.; Phadke, M. S. Quality Control, Robust Design, and the Taguchi Method https://doi.org/10.1007/978-1-4684-1472-1_5	book	January 1989
Pearson Correlation Coefficient Benesty, Jacob; Chen, Jingdong; Huang, Yiteng Noise Reduction in Speech Processing https://doi.org/10.1007/978-3-642-00296-0_5	book	January 2009
Support-vector networks Cortes, Corinna; Vapnik, Vladimir Machine Learning, Vol. 20, Issue 3 https://doi.org/10.1007/BF00994018	journal	September 1995
CHMM for tool condition monitoring and remaining useful life prediction Wang, Mei; Wang, Jie The International Journal of Advanced Manufacturing Technology, Vol. 59, Issue 5-8 https://doi.org/10.1007/s00170-011-3536-7	journal	August 2011
Hidden semi-Markov model-based method for tool wear estimation in milling process Kong, Dongdong; Chen, Yongjie; Li, Ning The International Journal of Advanced Manufacturing Technology, Vol. 92, Issue 9-12 https://doi.org/10.1007/s00170-017-0404-0	journal	May 2017
Tool wear condition monitoring based on continuous wavelet transform and blind source separation Benkedjouh, Tarak; Zerhouni, N.; Rechak, S. The International Journal of Advanced Manufacturing Technology, Vol. 97, Issue 9-12 https://doi.org/10.1007/s00170-018-2018-6	journal	May 2018
Advanced monitoring of machining operations Teti, R.; Jemielniak, K.; O’Donnell, G. CIRP Annals, Vol. 59, Issue 2 https://doi.org/10.1016/j.cirp.2010.05.010	journal	January 2010
Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks Tso, Geoffrey K. F.; Yau, Kelvin K. W. Energy, Vol. 32, Issue 9 https://doi.org/10.1016/j.energy.2006.11.010	journal	September 2007
State of health monitoring in machining: Extended Kalman filter for tool wear assessment in turning of IN718 hard-to-machine alloy Akhavan Niaki, Farbod; Michel, Martin; Mears, Laine Journal of Manufacturing Processes, Vol. 24 https://doi.org/10.1016/j.jmapro.2016.06.015	journal	October 2016
Data-driven smart manufacturing: Tool wear monitoring with audio signals and machine learning Li, Zhixiong; Liu, Rui; Wu, Dazhong Journal of Manufacturing Processes, Vol. 48 https://doi.org/10.1016/j.jmapro.2019.10.020	journal	December 2019
Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems Han, Seulki; Mannan, Nasir; Stein, Daryl C. Journal of Manufacturing Systems, Vol. 61 https://doi.org/10.1016/j.jmsy.2021.08.004	journal	October 2021
Tool wear monitoring of a retrofitted CNC milling machine using artificial neural networks Hesser, Daniel Frank; Markert, Bernd Manufacturing Letters, Vol. 19 https://doi.org/10.1016/j.mfglet.2018.11.001	journal	January 2019
Application of deep visualization in CNN-based tool condition monitoring for end milling Kothuru, Achyuth; Nooka, Sai Prasad; Liu, Rui Procedia Manufacturing, Vol. 34 https://doi.org/10.1016/j.promfg.2019.06.096	journal	January 2019
Wavelets for fault diagnosis of rotary machines: A review with applications Yan, Ruqiang; Gao, Robert X.; Chen, Xuefeng Signal Processing, Vol. 96 https://doi.org/10.1016/j.sigpro.2013.04.015	journal	March 2014
Cutting tool wear classification and detection using multi-sensor signals and Mahalanobis-Taguchi System Rizal, M.; Ghani, J. A.; Nuawi, M. Z. Wear, Vol. 376-377 https://doi.org/10.1016/j.wear.2017.02.017	journal	April 2017
Multi-sensor data fusion framework for CNC machining monitoring Duro, João A.; Padget, Julian A.; Bowen, Chris R. Mechanical Systems and Signal Processing, Vol. 66-67 https://doi.org/10.1016/j.ymssp.2015.04.019	journal	January 2016
A tutorial on support vector regression Smola, Alex J.; Schölkopf, Bernhard Statistics and Computing, Vol. 14, Issue 3 https://doi.org/10.1023/B:STCO.0000035301.49549.88	journal	August 2004
Prediction of cutting tool wear during milling process using artificial intelligence techniques Shankar, S.; Mohanraj, T.; Rajasekar, R. International Journal of Computer Integrated Manufacturing, Vol. 32, Issue 2 https://doi.org/10.1080/0951192X.2018.1550681	journal	November 2018
LIII. On lines and planes of closest fit to systems of points in space Pearson, Karl The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, Vol. 2, Issue 11 https://doi.org/10.1080/14786440109462720	journal	November 1901
Tool Wear Condition Monitoring in Milling Process Based on Current Sensors Zhou, Yuqing; Sun, Weifang IEEE Access, Vol. 8 https://doi.org/10.1109/ACCESS.2020.2995586	journal	January 2020
Real-time predictive maintenance for wind turbines using Big Data frameworks Canizo, Mikel; Onieva, Enrique; Conde, Angel 2017 IEEE International Conference on Prognostics and Health Management (ICPHM) https://doi.org/10.1109/ICPHM.2017.7998308	conference	June 2017
A multi-sensor fusion model based on artificial neural network to predict tool wear during hard turning Paul, P. Sam; Varadarajan, As Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, Vol. 226, Issue 5 https://doi.org/10.1177/0954405411432381	journal	January 2012
Measuring Skewness and Kurtosis Groeneveld, Richard A.; Meeden, Glen The Statistician, Vol. 33, Issue 4 https://doi.org/10.2307/2987742	journal	December 1984
Tool Condition Monitoring for High-Performance Machining Systems—A Review Mohamed, Ayman; Hassan, Mahmoud; M’Saoubi, Rachid Sensors, Vol. 22, Issue 6 https://doi.org/10.3390/s22062206	journal	March 2022

Similar Records

Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems

Journal Article · Sun Aug 22 20:00:00 EDT 2021 · Journal of Manufacturing Systems · OSTI ID:1977353

Hybrid data-driven and model-informed online tool wear detection in milling machines

Journal Article · Sun Apr 17 20:00:00 EDT 2022 · Journal of Manufacturing Systems · OSTI ID:1977356

Physics-based modeling and information-theoretic sensor and settings selection for tool wear detection in precision machining

Journal Article · Thu Jul 07 20:00:00 EDT 2022 · Journal of Manufacturing Processes · OSTI ID:1977318

Sensor selection and tool wear prediction with data‐driven models for precision machining

Citation Formats

References (25)

Similar Records

Related Subjects