An Anomaly Detection Approach to Detect Unexpected Faults in Recordings from Test Drives

Authors: Andreas Theissler, Ian Dear

Abstract:

In the automotive industry test drives are being conducted during the development of new vehicle models or as a part of quality assurance of series-production vehicles. The communication on the in-vehicle network, data from external sensors, or internal data from the electronic control units is recorded by automotive data loggers during the test drives. The recordings are used for fault analysis. Since the resulting data volume is tremendous, manually analysing each recording in great detail is not feasible. This paper proposes to use machine learning to support domainexperts by preventing them from contemplating irrelevant data and rather pointing them to the relevant parts in the recordings. The underlying idea is to learn the normal behaviour from available recordings, i.e. a training set, and then to autonomously detect unexpected deviations and report them as anomalies. The one-class support vector machine “support vector data description” is utilised to calculate distances of feature vectors. SVDDSUBSEQ is proposed as a novel approach, allowing to classify subsequences in multivariate time series data. The approach allows to detect unexpected faults without modelling effort as is shown with experimental results on recordings from test drives.

Keywords: Anomaly detection, fault detection, test drive analysis, machine learning.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1087119

References:

[1] K. Lamberg, “Model-based testing of automotive electronics,” Design, Automation and Test in Europe Conference and Exhibition, vol. 1, p. 28, 2006.
[2] M. Kr¨amer, A. R¨ohringer, W. Kirchner, T. Vogel, and J. Rochlitzer, “Programme Management and Project Control,” ATZ extra. The New E-Class by Mercedes-Benz, 2009.
[3] C. Marscholik and P. Subke, Road vehicles – Diagnostic communication. H¨uthig GmbH und Co. KG, 2008.
[4] “ISO 26262: Road vehicles – Functional safety – Part 1: Vocabulary. Final Draft.” 2011.
[5] I. Sommerville, Software Engineering (6th Edition). Redwood City, CA, USA: Addison Wesley Longman Publishing Co., Inc., 2001.
[6] R. Isermann, Fault-Diagnosis Systems – An Introduction from Fault Detection to Fault Tolerance, 1st ed. Springer, 2006.
[7] B. Stein, O. Niggemann, and H. Balzer, “Diagnosis in Automotive Applications: A Case Study with the Model Compilation Approach,” in Third Monet Workshop on Model-Based Systems at the ECAI, 2006, pp. 34–40.
[8] V. Venkatasubramanian, R. Rengaswamy, K. Yin, and S. N. Kavuri, “A review of process fault detection and diagnosis: Part I: Quantitative model-based methods,” Computers and Chemical Engineering, vol. 27, no. 3, pp. 293–311, 2003.
[9] V. Chandola, “Anomaly detection for symbolic sequences and time series data,” Ph.D. dissertation, Computer Science Department, University of Minnesota, 2009.
[10] V. J. Hodge and J. Austin, “A survey of outlier detection methodologies,” Artificial Intelligence Review, vol. 22, p. 2004, 2004.
[11] S. Theodoridis and K. Koutroumbas, Pattern Recognition, Fourth Edition, 4th ed. Academic Press, 2009. REFERENCES
[12] S. Abe, Support Vector Machines for Pattern Classification (Advances in Pattern Recognition), 2nd ed. Springer-Verlag London Ltd., 2010.
[13] D. M. Tax and R. P. Duin, “Data domain description using support vectors,” in Proceedings of the European Symposium on Artificial Neural Networks, 1999, pp. 251–256.
[14] A. Theissler and I. Dear, “Detecting anomalies in recordings from test drives based on a training set of normal instances,” in Proceedings of the IADIS International Conference Intelligent Systems and Agents 2012 and European Conference Data Mining 2012. IADIS Press, Lisbon., 2012, pp. 124–132.
[15] D. M. Tax, “One-class classification. concept-learning in the absence of counter-examples,” Ph.D. dissertation, Delft University of Technology, 2001.
[16] C. A. Jones, “Lecture notes: Math2640 introduction to optimisation 4,” University of Leeds, School of Mathematics, Tech. Rep., 2005.
[17] D. Tax and R. Duin, “Support vector data description,” Machine Learning, vol. 54, no. 1, pp. 45–66, Jan. 2004.
[18] A. Theissler and I. Dear, “Autonomously determining the parameters for SVDD with RBF kernel from a one-class training set,” in Proceedings of the WASET International Conference on Machine Intelligence 2013, Stockholm (to be published)., 2013.
[19] T. Mitsa, Temporal Data Mining. Chapman & Hall/CRC, 2010.
[20] T. Raykov and G. Marcoulides, Basic Statistics: An Introduction with R. Rowman & Littlefield Publishers, 2012.
[21] J. Laurikkala, M. Juhola, and E. Kentala, “Informal identification of outliers in medical data,” in 14th European Conference on Artificial Intelligence ECAI-2000. Berlin, 2000.
[22] R. Etzold, So wird’s gemacht. Pflegen - warten - reparieren: Renault Twingo von 6/93 bis 12/06, 8th ed. Delius Klasing, 2011.
[23] A. Theissler, D. Ulmer, and I. Dear, “Interactive knowledge discovery in recordings from vehicle tests,” in 33rd FISITA World Automotive Congress. FISITA, 2010.