A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests

Manufacturers have faced an increasing need for the development of predictive models that predict mechanical failures and the remaining useful life (RUL) of manufacturing systems or components. Classical model-based or physics-based prognostics often require an in-depth physical understanding of the system of interest to develop closedform mathematical models. However, prior knowledge of system behavior is not always available, especially for complex manufacturing systems and processes. To complement model-based prognostics, data-driven methods have been increasingly applied to machinery prognostics and maintenance management, transforming legacy manufacturing systems into smart manufacturing systems with artificial intelligence. While previous research has demonstrated the effectiveness of data-driven methods, most of these prognostic methods are based on classical machine learning techniques, such as artificial neural networks (ANNs) and support vector regression (SVR). With the rapid advancement in artificial intelligence, various machine learning algorithms have been developed and widely applied in many engineering fields. The objective of this research is to introduce a random forests (RFs)-based prognostic method for tool wear prediction as well as compare the performance of RFs with feed-forward back propagation (FFBP) ANNs and SVR. Specifically, the performance of FFBP ANNs, SVR, and RFs are compared using an experimental data collected from 315 milling tests. Experimental results have shown that RFs can generate more accurate predictions than FFBP ANNs with a single hidden layer and SVR. [DOI: 10.1115/1.4036350]

[1]  Tuğrul Özel,et al.  Machine Learning Based Predictive Modeling of Machining Induced Microhardness and Grain Size in Ti–6Al–4V Alloy , 2015 .

[2]  Taejin Kim,et al.  Semi-supervised learning with co-training for data-driven prognostics , 2012, 2012 IEEE Conference on Prognostics and Health Management.

[3]  Durmus Karayel,et al.  Prediction and control of surface roughness in CNC lathe using artificial neural network , 2009 .

[4]  Robert X. Gao,et al.  Stochastic Tool Wear Prediction for Sustainable Manufacturing , 2016 .

[5]  A. S. Varadarajan,et al.  A multi-sensor fusion model based on artificial neural network to predict tool wear during hard turning , 2012 .

[6]  Soundarr T. Kumara,et al.  Flank Wear Estimation in Turning Through Wavelet Representation of Acoustic Emission Signals , 2000 .

[7]  Kai Goebel,et al.  Model-Based Prognostics With Concurrent Damage Progression Processes , 2013, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[8]  Steven Y. Liang,et al.  Modeling of CBN Tool Flank Wear Progression in Finish Hard Turning , 2004 .

[9]  Jay Lee,et al.  Machine performance monitoring and proactive maintenance in computer-integrated manufacturing: review and perspective , 1995 .

[10]  Donghua Zhou,et al.  A Wiener-process-based degradation model with a recursive filter algorithm for remaining useful life estimation , 2013 .

[11]  Krzysztof Jemielniak,et al.  Advanced monitoring of machining operations , 2010 .

[12]  Noureddine Zerhouni,et al.  Health assessment and life prediction of cutting tools based on support vector regression , 2015, J. Intell. Manuf..

[13]  Antanas Verikas,et al.  Mining data with random forests: A survey and results of new tests , 2011, Pattern Recognit..

[14]  Gérard Biau,et al.  Analysis of a Random Forests Model , 2010, J. Mach. Learn. Res..

[15]  David Dornfeld,et al.  Tool Wear Detection Using Time Series Analysis of Acoustic Emission , 1989 .

[16]  Satish T. S. Bukkapatnam,et al.  Fractal Estimation of Flank Wear in Turning , 2000 .

[17]  George J. Vachtsevanos,et al.  A particle-filtering approach for on-line fault diagnosis and failure prognosis , 2009 .

[18]  Ichiro Inasaki,et al.  Tool Condition Monitoring (TCM) — The Status of Research and Industrial Application , 1995 .

[19]  Chatchapol Chungchoo,et al.  On-line tool wear estimation in CNC turning operations , 2001 .

[20]  Tuğrul Özel,et al.  Predictive modeling of surface roughness and tool wear in hard turning using regression and neural networks , 2005 .

[21]  Frederick Winslow Taylor,et al.  On The Art Of Cutting Metals.pdf , 2017 .

[22]  S. Shanmugasundaram,et al.  Prediction of tool wear using regression and ANN models in end-milling operation , 2008 .

[23]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[24]  Robert X. Gao,et al.  Cloud-enabled prognosis for manufacturing , 2015 .

[25]  David Dornfeld,et al.  A self-organizing approach to the prediction and detection of tool wear , 1998 .

[26]  M. J. Er,et al.  Fuzzy Neural Network Modelling for Tool Wear Estimation in Dry Milling Operation , 2009 .

[27]  Durul Ulutan,et al.  Stochastic tool wear assessment in milling difficult to machine alloys , 2015 .

[28]  C. Sanjay,et al.  Modeling of tool wear in drilling by statistical analysis and artificial neural network , 2005 .

[29]  N. R. Sakthivel,et al.  Evaluation of expert system for condition monitoring of a single point cutting tool using principle component analysis and decision tree algorithm , 2011, Expert Syst. Appl..

[30]  Joseph C. Chen,et al.  An artificial-neural-networks-based in-process tool wear prediction system in milling operations , 2005 .

[31]  Dongfeng Shi,et al.  Tool wear predictive model based on least squares support vector machines , 2007 .

[32]  Satish T. S. Bukkapatnam,et al.  Analysis of acoustic emission signals in machining , 1999 .

[33]  Sohyung Cho,et al.  Tool breakage detection using support vector machine learning in a milling process , 2005 .

[34]  Soundar Kumara,et al.  Machinery Fault Diagnosis and Prognosis: Application of Advanced Signal Processing Techniques , 1999 .

[35]  L. Swanson.  Linking maintenance strategies to performance , 2001 .

[36]  Mark Schwabacher,et al.  A Survey of Data -Driven Prognostics , 2005 .

[37]  Marcello Braglia,et al.  The analytic hierarchy process applied to maintenance strategy selection , 2000, Reliab. Eng. Syst. Saf..

[38]  David He,et al.  Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis , 2007, Eur. J. Oper. Res..

[39]  Lakhtakia,et al.  Analysis of sensor signals shows turning on a lathe exhibits low-dimensional chaos. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[40]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[41]  Dazhong Wu,et al.  Fog-Enabled Architecture for Data-Driven Cyber-Manufacturing Systems , 2016 .

[42]  Richard M. Feldman,et al.  A survey of preventive maintenance models for stochastically deteriorating single-unit systems , 1989 .

[43]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[44]  Kai Goebel,et al.  Comparison of prognostic algorithms for estimating remaining useful life of batteries , 2009 .

[45]  Kai Goebel,et al.  A Survey of Artificial Intelligence for Prognostics , 2007, AAAI Fall Symposium: Artificial Intelligence for Prognostics.

[46]  Robert X. Gao,et al.  Adaptive resampling-based particle filtering for tool life prediction , 2015 .

[47]  Bernhard Sick,et al.  ON-LINE AND INDIRECT TOOL WEAR MONITORING IN TURNING WITH ARTIFICIAL NEURAL NETWORKS: A REVIEW OF MORE THAN A DECADE OF RESEARCH , 2002 .

[48]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[49]  Farbod Akhavan Niaki,et al.  State of health monitoring in machining: Extended Kalman filter for tool wear assessment in turning of IN718 hard-to-machine alloy , 2016 .