Abstract
With large amount of machine log data at our disposal, predictive maintenance has come into play in many avenues. A key component in predictive modelling is to identify and track error patterns that are indicative of underlying component failure. Subject matter experts (SME) or system experts who know internals of the said component and its interaction with overall system usually define the error patterns. However, this opinion is biased and prone to human error. Subjectivity in defining error patterns can result in omission of certain error patterns. Here, we introduce an approach to identify probable error patterns in an unsupervised manner on MR machine log data, which allows us to automate this task with high efficiency and without need of subject matter expert and bias. This automation also reduces the time taken to analyse large volumes of log data and create meaningful machine learning models for predicting possible failure of components.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Simoncicova, V., Hrcka, L., Spendla, L., Tanuska, P., Vazan, P.: Pattern recognition for predictive analysis in automotive industry. In: Silhavy, R., Senkerik, R., Kominkova Oplatkova, Z., Prokopova, Z., Silhavy, P. (eds.) CSOC 2017. AISC, vol. 574, pp. 311–318. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-57264-2_32
Sipos, R., Fradkin, D., Moerchen, F., Wang, Z.: Log-based predictive maintenance. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1867–1876. ACM (2014)
Fan, X., Wang, F., Liu, J.: Boosting service availability for base stations of cellular networks by event-driven battery profiling. ACM SIGMETRICS Perform. Eval. Rev. 44(2), 88–93 (2016)
Rabin-Karp Algorithm: Brilliant.org. https://brilliant.org/wiki/rabin-karp-algorithm/. Accessed 12:17, 22 Aug 2017
Aharon, M., Barash, G., Cohen, I., Mordechai, E.: One graph is worth a thousand logs: uncovering hidden structures in massive system event logs. In: Buntine, W., Grobelnik, M., Mladenić, D., Shawe-Taylor, J. (eds.) ECML PKDD 2009. LNCS, vol. 5781, pp. 227–243. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-04180-8_32
Patil, R.B., Patil, M.A., Ravi, V., Naik, S.: Predictive modeling for corrective maintenance of imaging devices from machine logs. In: 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, Jeju, Korea (2017)
Zheng, Z., Lan, Z., Park, B.H., Geist, A.: System log pre-processing to improve failure prediction. In: 2009 IEEE/IFIP International Conference on Dependable Systems & Networks, Lisbon, pp. 572–577 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ravi, V., Patil, R. (2018). Unsupervised Time Series Data Analysis for Error Pattern Extraction for Predictive Maintenance. In: Singh, M., Gupta, P., Tyagi, V., Flusser, J., Ören, T. (eds) Advances in Computing and Data Sciences. ICACDS 2018. Communications in Computer and Information Science, vol 906. Springer, Singapore. https://doi.org/10.1007/978-981-13-1813-9_1
Download citation
DOI: https://doi.org/10.1007/978-981-13-1813-9_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-1812-2
Online ISBN: 978-981-13-1813-9
eBook Packages: Computer ScienceComputer Science (R0)