Machine learning in industrial measurement technology for detection of known and unknown faults of equipment and sensors

Abstract This paper focuses on the application of novelty detection in combination with supervised fault classification for industrial condition monitoring. Its goal is to provide a guideline for engineers on how to apply novelty detection for outlier detection, monitoring of supervised classification and detection of unknown faults without the need of a data scientist. All guidelines are demonstrated by means of a publicly available condition monitoring dataset. In each application case the results achieved with different common novelty detection algorithms are compared, advantages and disadvantages of the respective algorithms are shown. To increase applicability of the suggested approach visualization of results is emphasized and all algorithms have been included in a publicly available data analysis software toolbox with graphical user interface.

[1]  Klaus Backhaus,et al.  Multivariate Analysemethoden - Eine anwendungsorientierte Einführung , 2018 .

[2]  Andreas Schütze,et al.  D8.1 - Detecting and Compensating Sensor Faults in a Hydraulic Condition Monitoring System , 2015 .

[3]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[4]  Sameer Singh,et al.  Novelty detection: a review - part 1: statistical approaches , 2003, Signal Process..

[5]  Eamonn J. Keogh.  Nearest Neighbor , 2010, Encyclopedia of Machine Learning.

[6]  Nikolai Helwig,et al.  Condition monitoring of a complex hydraulic system using multivariate statistics , 2015, 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings.

[7]  Gian Antonio Susto,et al.  A One-Class SVM Based Tool for Machine Learning Novelty Detection in HVAC Chiller Systems , 2014 .

[8]  Anirban DasGupta,et al.  Probability for Statistics and Machine Learning , 2011 .

[9]  Venkatesh Saligrama,et al.  Anomaly Detection with Score functions based on Nearest Neighbor Graphs , 2009, NIPS.

[10]  Andreas Schütze,et al.  Industrial condition monitoring with smart sensors using automated feature extraction and selection , 2018, Measurement Science and Technology.

[11]  Miguel Angel Ferrer-Ballester,et al.  Review of Automatic Fault Diagnosis Systems Using Audio and Vibration Signals , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[12]  Eamonn J. Keogh,et al.  Experimental comparison of representation methods and distance measures for time series data , 2010, Data Mining and Knowledge Discovery.

[13]  M. Bastuck,et al.  DAV3E – a MATLAB toolbox for multivariate sensor data evaluation , 2018, Journal of Sensors and Sensor Systems.

[14]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[15]  Dubravko Miljkovic,et al.  Review of novelty detection methods , 2010, The 33rd International Convention MIPRO.

[16]  Eamonn J. Keogh,et al.  On the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration , 2002, Data Mining and Knowledge Discovery.

[17]  E. Kuntsche,et al.  Multivariate Analysemethoden: Eine anwendungsorientierte Einführung. , 2001 .

[18]  A. Asuncion,et al.  UCI Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences , 2007 .

[19]  Jonathan Goldstein,et al.  When Is ''Nearest Neighbor'' Meaningful? , 1999, ICDT.

[20]  C. K. Chow,et al.  On optimum recognition error and reject tradeoff , 1970, IEEE Trans. Inf. Theory.