A Fine-grained Semi-supervised Anomaly Detection Framework for Predictive Maintenance of Industrial Assets

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Oct 26, 2023
Xiaorui Tong Wee Quan Jung Jeremy Frimpong Banning

Abstract

Reliable operation of industrial assets is of high priority for businesses where productivity determines the ability to deliver safety-critical products of high quality in a timely manner. The aerospace industry leads the demand for predictive maintenance (PdM). In the manufacturing space, unscheduled down time causes production delay and increases operational costs while introducing potential risks in product quality and on-time delivery. In field application of these products, unexpected breakdown of critical components can result in safety-critical events. Failure events are, therefore, extremely rare in industrial settings. Diverse operating conditions in the manufacturing environment and field applications contribute to the heterogeneous nature of data collected from these assets. This work presents an anomaly detection framework for PdM of industrial assets to address the practical challenges of scarce failure data sources and heterogeneous data across assets. We introduce a fine-grained modeling approach that efficiently accounts for individual asset differences in a semi-supervised fashion which requires only normal operation data for model training. The framework is demonstrated with an industrial 4.0 use case. Vibration sensor data from pumps in one of our manufacturing facilities is ingested to enable PdM with 2 weeks lead time using the proposed framework. This transforms unexpected breakdown time to scheduled maintenance, thereby reducing cost of delays and operation interruptions. The systematic implementation of the framework in the case study covers the practical production aspects including data quality evaluation, model training, optimization and daily serving of predictions. Furthermore, implementation challenges and recommendations are discussed based on the end-to-end solution implementation experiences.

How to Cite

Tong, X., Jung, W. Q. ., & Banning, J. F. (2023). A Fine-grained Semi-supervised Anomaly Detection Framework for Predictive Maintenance of Industrial Assets. Annual Conference of the PHM Society, 15(1). https://doi.org/10.36001/phmconf.2023.v15i1.3547
Abstract 186 | PDF Downloads 129

##plugins.themes.bootstrap3.article.details##

Keywords

Industry 4.0, Predictive Maintenance, Aerospace, Anomaly Detection, Fine-grained

References
Ahmad S., Lavin A., Purdy S., Agha Z. (2017). Unsupervised real-time anomaly detection for streaming data. Neurocomputing, 262 , pp. 134-147. doi: doi.org/10.1016/j.neucom.2017.04.070
Bergstra, J., Yamins, D., Cox, D. D. (2013) Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures. Proceedings of the 30th International Conference on Machine Learning. PMLR vol. 28(1), pp. 115-123
Cavalieri S, Salafia MG. (2020). A Model for Predictive Maintenance Based on Asset Administration Shell. Sensors 20, no. 21: 6028. doi: https://doi.org/10.3390/s20216028
Cho, S., May G., Tourkogiorgis I., Perez R., Lazaro O., Maza B.D.L., Kiritsis D. (2018). A Hybrid Machine Learning Approach for Predictive Maintenance in Smart Factories of the Future. Advances in Production Management Systems. Smart Manufacturing for Industry 4.0. APMS 2018. vol 536. Springer, Cham. https://doi.org/10.1007/978-3-319-99707-0_39
Foorthuis, R. (2021). On the nature and types of anomalies: a review of deviations in data. International Journal of
Data Science and Analytics, vol. 12, pp. 297–331. doi: https://doi.org/10.1007/s41060-021-00265-1
Jiang, J., Kao, J. & Li ,Y. (2021). Semi-Supervised Time Series Anomaly Detection Based on Statistics and Deep Learning. Applied Sciences. vol. 11, no. 15, pp. 6698. https://doi.org/10.3390/app11156698
Audibert, J., Michiardi, P., Guyard, F., MartiS., and Zuluaga, M., A. (2020). USAD: UnSupervised Anomaly
Detection on Multivariate Time Series. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD '20). Association for Computing Machinery, New York, NY,
USA, pp. 3395–3404. https://doi.org/10.1145/3394486.3403392
Sgueglia A., Sorbo A. D., Visaggio C. A., Canfora G. (2022). A systematic literature review of IoT time series anomaly detection solutions. Future Generation Computer Systems. vol. 134, pp.170-186, ISSN 0167- 739X, doi: https://doi.org/10.1016/j.future.2022.04.005.
Shaukat,K., Alam, T. M., Luo, S., Shabbir, S., Hameed, I. A., Li, J., Abbas, S. K., & Javed. U. (2021). A Review of Time-Series Anomaly Detection Techniques: A Step to Future Perspectives. Advances in Information and Communication. FICC 2021. Advances in Intelligent Systems and Computing, vol 1363. Springer, Cham. https://doi.org/10.1007/978-3-030-73100-7_60
Tong, X., Bakhshi, R., & Prabhu, C. (2022). Industry 4.0 for Aerospace Manufacturing: Condition Based Maintenance Methodology, Implementation and Challenges. Annual Conference of the PHM Society, 14(1). https://doi.org/10.36001/phmconf.2022.v14i1.3189
Teng, X., Lin,Y., & Wen, X. (2017). Anomaly Detection in Dynamic Networks using Multi-view Time-Series Hypersphere Learning. Proceedings of the 2017 ACM on Conference on Information and Knowledge
Management (CIKM '17). Association for Computing Machinery, New York, NY, USA, pp 827–836. https://doi.org/10.1145/3132847.3132964
Section
Poster Presentations