MLOps for PHM Systems



Published Sep 4, 2023
Mikael Yemane


Advances in machine learning (ML) techniques allow practitioners to generate substantial predictive value from historical data. Modern sensors generate vast amounts of data which inform prognostic health management (PHM) systems. As ML techniques continue to grow in importance for PHM, the system that manages and deploys ML models becomes critical for successful production software. Machine Learning Operations (MLOps) is centered around implementing continuous integration and deployment (CI/CD) practices in the context of ML applications. We will present MLOps designs for deploying machine learning based PHM software and discuss ML pipelines that automate data ingestion, model training, testing, deployment, and monitoring. The principles we will examine ensure model quality, performance, and software stability. We will call attention to important design considerations and demonstrate solutions for the full model lifecycle when building MLOps pipelines for PHM systems.

Abstract 121 | PDF Downloads 134



Machine Learning, Artificial Intelligence, PHM, MLOps, Big Data

Mojtaba Shahin, Muhammad Babar, and Liming Zhu (2017). Continuous Integration, Delivery and Deployment: A Systematic Review on Approaches, Tools, Challenges and Practices. IEEE Access vol. 5, pp. 3909-3943. doi:10.1109/ACCESS.2017.2685629

Georgios Symeonidis, Evangelos Nerantzis, Apostolos Kazakis, and George Papakostas (2022). MLOps Definitions, Tools, and Challenges. IEEE 12th Annual Computing and Communication Workshop and Conference. Las Vegas, NV, USA doi:10.1109/CCWC54503.2022.9720902

Eric Breck, Neoklis Polyzotis, Sudip Roy, Steven Euijong Whang, and Martin Zinkevich (2019). Data Validation for Machine Learning. Proceedings of the 2nd SysML Conference, Palo Alto, CA, USA

Rakshith Subramanya, Seppo Sierla, and Valeriy Vyatkin (2022). From DevOps to MLOps: Overview and Application to Electricity Market Forecasting. Applied Sciences 2022 vol. 12. doi:10.3390/app12199851

Naeem Seliya, Taghi M. Khoshgoftaar, and Jason Hulse (2009). A Study on the Relationships of Classifier Performance Metrics. 2009 21st IEEE International Conference on Tools with Artificial Intelligence. doi:10.1109/ICTAI.2009.25

Alexei Botchkarev (2019). A New Typology Design of Performance Metrics to Measure Errors in Machine Learning Regression Algorithms. Interdisciplinary Journal of Information, Knowledge, and Management, vol. 14, pp. 45-79. doi:10.28945/4184

Odd Gundersen, Saeid Shamsaliei, and Richard Juul Isdah (2022). Do machine learning platforms provide out-ofthe-box reproducibility? Future Generation Computer Systems. vol. 126, pp. 34-47

Nicolas Ferry, Alessandro Rossini, Franck Chauvel, Brice Morin, Arnor Solberg (2013). Towards model-driven provisioning, deployment, monitoring, and adaptation of multi-cloud systems. 2013 IEEE Sixth International Conference on Cloud Computing. Santa Clara, CA, USA

Laura Savu (2011). Cloud Computing, Deployment models, Delivery Models, Risks and Research Challenges. 2011 International Conference on Computer and Management (CAMAN) doi:10.1109/CAMAN.2011.5778816
Special Session Papers