Applications of Active Learning in Predictive Maintenance
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Nowadays, the common choice in maintenance strategies is predictive maintenance (PdM), deprecating the corrective and preventive kinds. Even with various machine learning techniques to get advanced predictive models to achieve PdM, difficulties remain in the data acquisition process. While there is a plethora of unlabeled data from sensors, most of those available techniques can only process labeled data, i.e, supervised learning. To combat the fact that the availability of the labeled
data is limited, this paper proposes the use of Active Learning to label and annotate the informative instances while minimizing overall processing time. This approach maintains high performance and decreases the number of labeled instances, with support from experimental results and a discussion of the applicability of this method.
##plugins.themes.bootstrap3.article.details##
active learning, predictive maintenance, mission critical, machine learning
Aydin, G., Hallac, R., I., & Karakus, B. (2015). Architec- ture and implementation of a scalable sensor data stor- age and analysis system using cloud computing and big data technologies. Hindawi, Journal of Sensors.
Balcan, M., Broder, A., & Zhang, T. (2007). Margin based active learning. In Learning theory (Vol. 4539). doi: https://doi.org/10.1007/978-3-540-72927-35
Bentejac, C., Csorgo, A., & Martınez-Munoz, G. (2021). A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review, 54, 1937–1967. doi: https://doi.org/10.1007/s10462-020-09896-5
Chen, T., & Guestrin, C. (2016). Xgboost: A scal- able tree boosting system. In (p. 785–794). doi: 10.1145/2939672.2939785
L’Heureux, A., Grolinger, K., Higashino, W. A., & Capretz, M. A. (2017). A gamification framework for sensor data analytics. In 2017 ieee international congress on internet of things (iciot) (p. 74-81). doi: 10.1109/IEEE.ICIOT.2017.18
Roan, M., Erling, J., & Sibul, L. (2002). A new, non- linear, adaptive, blind source separation approach to gear tooth failure detection and analysis. Mechanical Systems and Signal Processing, 16(5), 719-740. doi: https://doi.org/10.1006/mssp.2002.1504
Rosenthal, S., & Dey, A. K. (2010). Towards maximizing the accuracy of human-labeled sensor data. In Conference: Proceedings of the 2010 international conference on intelligent user interfaces.
Settles, B. (2009). In Active learning literature survey.
Teh, H., Kempa-Liehr, A., & Wang, K. (2020). Sensor data quality: a systematic review. In J big data 7. doi: 10.1186/s40537-020-0285-1
Wen, C., B., Xiao, Q., M., Wang, Q., X., Zhao, X., Li, F., J., & Chen, X. (2021). Data-driven remaining useful life prediction based on domain adaptation. In Peerj. computer science, 7. doi: 10.7717/peerj-cs.690
Woodward, K., & Kanjo, A. e. a., E.and Oikonomou. (2020). Labelsens: enabling real-time sensor data labelling at the point of collection using an artificial intelligence- based approach. In Pers ubiquit comput 24,. doi: 10.1007/s00779-020-01427-x
This work is licensed under a Creative Commons Attribution 3.0 Unported License.