Classifying machinery condition using oil samples and binary logistic regression

Abstract The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically “black box” approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.

[1]  Dhananjay S. Phatak,et al.  Connectivity and performance tradeoffs in the cascade correlation learning architecture , 1994, IEEE Trans. Neural Networks.

[2]  David G. Stork,et al.  Pattern Classification , 1973 .

[3]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[4]  Zhou,et al.  Application of a Novel Method for Machine Performance Degradation Assessment Based on Gaussian Mixture Model and Logistic Regression , 2011 .

[5]  D. Thukaram,et al.  Artificial neural network and support vector Machine approach for locating faults in radial distribution systems , 2005, IEEE Transactions on Power Delivery.

[6]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[7]  David J. Hand,et al.  ROC Curves for Continuous Data , 2009 .

[8]  Lin Ma,et al.  Prognostic modelling options for remaining useful life estimation by industry , 2011 .

[9]  J A Swets,et al.  Measuring the accuracy of diagnostic systems. , 1988, Science.

[10]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[11]  Wei Li,et al.  Fault diagnosis of rotating machinery with a novel statistical feature extraction and evaluation method , 2015 .

[12]  Yuhua Li,et al.  A review of condition monitoring and fault diagnosis for diesel engines , 2000 .

[13]  Robert X. Gao,et al.  PCA-based feature selection scheme for machine defect classification , 2004, IEEE Transactions on Instrumentation and Measurement.

[14]  Asoke K. Nandi,et al.  FAULT DETECTION USING SUPPORT VECTOR MACHINES AND ARTIFICIAL NEURAL NETWORKS, AUGMENTED BY GENETIC ALGORITHMS , 2002 .

[15]  Daniel Westreich,et al.  Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression. , 2010, Journal of clinical epidemiology.

[16]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[17]  Kyung S. Park.  Condition-based predictive maintenance by multiple logistic function , 1993 .

[18]  Bo-Suk Yang,et al.  Application of relevance vector machine and logistic regression for machine degradation assessment , 2010 .

[19]  Pingyu Jiang,et al.  Facility health maintenance through SVR-driven degradation prediction , 2008 .

[20]  Markus Höhfeld,et al.  Learning with limited numerical precision using the cascade-correlation algorithm , 1992, IEEE Trans. Neural Networks.

[21]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[22]  Jong-Myon Kim,et al.  Singular value decomposition based feature extraction approaches for classifying faults of induction motors , 2013 .

[23]  Lexin Li,et al.  Evaluation of distribution fault diagnosis algorithms using ROC curves , 2010, IEEE PES General Meeting.

[24]  Ignacio Requena,et al.  Are artificial neural networks black boxes? , 1997, IEEE Trans. Neural Networks.

[25]  Soteris A. Kalogirou,et al.  Artificial intelligence for the modeling and control of combustion processes: a review , 2003 .

[26]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[27]  C. Metz.  Basic principles of ROC analysis. , 1978, Seminars in nuclear medicine.

[28]  Jay Lee,et al.  Degradation Assessment and Fault Modes Classification Using Logistic Regression , 2005 .

[29]  Jian-Da Wu,et al.  Investigation of engine fault diagnosis using discrete wavelet transform and neural network , 2008, Expert Syst. Appl..

[30]  B. Samanta,et al.  Gear fault detection using artificial neural networks and support vector machines with genetic algorithms , 2004 .

[31]  J. Hilden.  The Area under the ROC Curve and Its Competitors , 1991, Medical decision making : an international journal of the Society for Medical Decision Making.

[32]  S.A.V. Satya Murty,et al.  Roller element bearing fault diagnosis using singular spectrum analysis , 2013 .

[33]  Julie Zhang,et al.  EXPERIMENTAL STUDY AND LOGISTIC REGRESSION MODELING FOR MACHINE CONDITION MONITORING THROUGH MICROCONTROLLER-BASED DATA ACQUISITION SYSTEM , 2009 .

[34]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[35]  Ibrahim Esat,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROTATING MACHINERY USING WAVELET TRANSFORMS AS A PREPROCESSOR , 1997 .

[36]  D. Xu,et al.  Reliability prediction using multivariate degradation data , 2005, Annual Reliability and Maintainability Symposium, 2005. Proceedings..

[37]  Ji Zhu,et al.  Kernel Logistic Regression and the Import Vector Machine , 2001, NIPS.

[38]  S. H. Upadhyay,et al.  Fault diagnosis of rolling element bearing by using multinomial logistic regression and wavelet packet transform , 2013, Soft Computing.

[39]  J. Míguez,et al.  Diesel engine condition monitoring using a multi-net neural network system with nonintrusive sensors , 2011 .

[40]  Jay Lee,et al.  A comparative study of maintenance data classification based on neural networks, logistic regression and support vector machines , 2010 .

[41]  A C McCormick,et al.  Classification of the rotating machine condition using artificial neural networks , 1997 .

[42]  Chun-Chieh Wang,et al.  Construction of Wind Turbine Bearing Vibration Monitoring and Performance Assessment System , 2013 .

[43]  Qinghua Hu,et al.  Mechanical fault diagnosis based on redundant second generation wavelet packet transform, neighborhood rough set and support vector machine , 2012 .

[44]  J. K. Spoerre.  Application of the cascade correlation algorithms (CCA) to bearing fault classification problems , 1997 .

[45]  V. Sugumaran,et al.  Fault diagnosis of automobile hydraulic brake system using statistical features and support vector machines , 2015 .

[46]  Xiaoyuan Zhang,et al.  Multi-fault diagnosis for rolling element bearings based on ensemble empirical mode decomposition and optimized support vector machines , 2013 .

[47]  Mukta Paliwal,et al.  Neural networks and statistical techniques: A review of applications , 2009, Expert Syst. Appl..

[48]  Gaigai Cai,et al.  Reliability estimation for cutting tools based on logistic regression model using vibration signals , 2011 .

[49]  K. E. Spezzaferro.  Applying logistic regression to maintenance data to establish inspection intervals , 1996, Proceedings of 1996 Annual Reliability and Maintainability Symposium.

[50]  Bo-Suk Yang,et al.  Condition classification of small reciprocating compressor for refrigeration using artificial neural networks and support vector machines , 2005 .

[51]  Bharatendra Rai.  A Study of Classification Models to Predict Drill-Bit Breakage Using Degradation Signals , 2014 .