A CPPS based on GBDT for predicting failure events in milling

Cyber-physical production systems (CPPS) are mechatronic systems monitored and controlled by software brains and digital information. Despite its fast development along with the advancement of Industry 4.0 paradigms, an adaptive monitoring system remains challenging when considering integration with traditional manufacturing factories. In this paper, a failure predictive tool is developed and implemented. The predictive mechanism, underpinned by a hybrid model of the dynamic principal component analysis and the gradient boosting decision trees, is capable of anticipating the production stop before one occurs. The proposed methodology is implemented and experimented on a repetitive milling process hosted in a real-world CPPS hub. The online testing results have shown the accuracy of the predicted production failures using the proposed predictive tool is as high as 73% measured by the AUC score.

[1]  Kati Pöllänen,et al.  Dynamic PCA-based MSPC charts for nucleation prediction in batch cooling crystallization processes , 2006 .

[2]  Barry M. Wise,et al.  The process chemometrics approach to process monitoring and fault detection , 1995 .

[3]  Roman Rosipal,et al.  Kernel Partial Least Squares Regression in Reproducing Kernel Hilbert Space , 2002, J. Mach. Learn. Res..

[4]  Chuanhou Gao,et al.  Modeling of the Thermal State Change of Blast Furnace Hearth With Support Vector Machines , 2012, IEEE Transactions on Industrial Electronics.

[5]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[6]  Kok Kiong Tan,et al.  Fault Diagnosis and Fault-Tolerant Control in Linear Drives Using the Kalman Filter , 2012, IEEE Transactions on Industrial Electronics.

[7]  Jhareswar Maiti,et al.  Process monitoring and fault detection strategies: a review , 2012 .

[8]  Giovanna Martínez-Arellano,et al.  Tool wear classification using time series imaging and deep learning , 2019, The International Journal of Advanced Manufacturing Technology.

[9]  Amiya R Mohanty,et al.  Bayesian-inference-based neural networks for tool wear estimation , 2006 .

[10]  Oleg Troyansky,et al.  QlikView Your Business: An Expert Guide to Business Discovery with QlikView and Qlik Sense , 2015 .

[11]  Alessandra Caggiano,et al.  Cloud-based manufacturing process monitoring for smart diagnosis services , 2018, Int. J. Comput. Integr. Manuf..

[12]  Michel Kinnaert,et al.  Diagnosis and Fault-tolerant Control, 2nd edition , 2006 .

[13]  Inderjit S. Dhillon,et al.  Gradient Boosted Decision Trees for High Dimensional Sparse Output , 2017, ICML.

[14]  Mickaël Hilairet,et al.  Design of a Fault-Tolerant Controller Based on Observers for a PMSM Drive , 2011, IEEE Transactions on Industrial Electronics.

[15]  T. McAvoy,et al.  Nonlinear principal component analysis—Based on principal curves and neural networks , 1996 .

[16]  Rui Liu,et al.  Application of audible sound signals for tool wear monitoring using machine learning techniques in end milling , 2017, The International Journal of Advanced Manufacturing Technology.

[17]  Janos Gertler,et al.  Fault detection and diagnosis in engineering systems , 1998 .

[18]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[19]  Pedro J. Arrazola,et al.  The capacity of statistical features extracted from multiple signals to predict tool wear in the drilling process , 2019, The International Journal of Advanced Manufacturing Technology.

[20]  Riccardo Muradore,et al.  A PLS-Based Statistical Approach for Fault Detection and Isolation of Robotic Manipulators , 2012, IEEE Transactions on Industrial Electronics.

[21]  Zhiwei Gao,et al.  Novel Parameter Identification by Using a High-Gain Observer With Application to a Gas Turbine Engine , 2008, IEEE Transactions on Industrial Informatics.

[22]  Steven X. Ding,et al.  A Review on Basic Data-Driven Approaches for Industrial Process Monitoring , 2014, IEEE Transactions on Industrial Electronics.

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

[24]  Germano Veiga,et al.  Online inspection system based on machine learning techniques: real case study of fabric textures classification for the automotive industry , 2019, J. Intell. Manuf..

[25]  R. Rosipal,et al.  Kernel Partial Least Squares for Nonlinear Regression and Discrimination , 2002 .

[26]  Michel Kinnaert,et al.  Introduction to Diagnosis and Fault-Tolerant Control , 2016 .

[27]  Ruey-Shiang Guh,et al.  An effective application of decision tree learning for on-line detection of mean shifts in multivariate control charts , 2008, Comput. Ind. Eng..

[28]  Richard D. Braatz,et al.  Perspectives on process monitoring of industrial systems , 2016, Annu. Rev. Control..

[29]  Daniel U. Campos-Delgado,et al.  An Observer-Based Diagnosis Scheme for Single and Simultaneous Open-Switch Faults in Induction Motor Drives , 2011, IEEE Transactions on Industrial Electronics.

[30]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[31]  Christos Georgakis,et al.  Disturbance detection and isolation by dynamic principal component analysis , 1995 .

[32]  Leo Guelman,et al.  Gradient boosting trees for auto insurance loss cost modeling and prediction , 2012, Expert Syst. Appl..

[33]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

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

[35]  Etienne Chové,et al.  Continuous improvement of HSM process by data mining , 2019, J. Intell. Manuf..

[36]  Birgit Vogel-Heuser,et al.  Correction to: Cyber-physical production systems architecture based on multi-agent’s design pattern—comparison of selected approaches mapping four agent patterns , 2019, The International Journal of Advanced Manufacturing Technology.

[37]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[38]  In-Beum Lee,et al.  Nonlinear dynamic process monitoring based on dynamic kernel PCA , 2004 .

[39]  George Chryssolouris,et al.  Monitoring and Control of Manufacturing Processes: A Review☆ , 2013 .

[40]  Steven X. Ding,et al.  Model-based Fault Diagnosis Techniques: Design Schemes, Algorithms, and Tools , 2008 .

[41]  Yang Liu,et al.  Least-Squares Fault Detection and Diagnosis for Networked Sensing Systems Using A Direct State Estimation Approach , 2013, IEEE Transactions on Industrial Informatics.

[42]  Jin Hyun Park,et al.  Fault detection and identification of nonlinear processes based on kernel PCA , 2005 .

[43]  J Elith,et al.  A working guide to boosted regression trees. , 2008, The Journal of animal ecology.

[44]  M. Hallin,et al.  Dynamic functional principal components , 2015 .

[45]  Junhong Li,et al.  Improved kernel principal component analysis for fault detection , 2008, Expert Syst. Appl..

[46]  Yi Zhu,et al.  Nonlinear process monitoring using wavelet kernel principal component analysis , 2012, 2012 International Conference on Systems and Informatics (ICSAI2012).