ABSTRACT
We present an automated Machine Learning (ML) tool designed as a continual learning pipeline to adapt to evolving data streams in the Industrial Internet of Things (IIoT). This tool creates ML experiences, starting with training a neural network model. It then iteratively refines this model using fresh data while judiciously replaying pertinent historical data segments. When applied to IIoT sensor data, our tool ensures sustained ML performance amid evolving data dynamics while preventing the undue accumulation of obsolete sensor data. We have successfully assessed our tool across three industrial datasets and affirm its efficacy in dynamic knowledge retention and adaptation.
- Paolo Bellavista, Roberto Della Penna, Luca Foschini, and Domenico Scotece. 2020. Machine learning for predictive diagnostics at the edge: An IIoT practical example. In ICC’20. 1–7.Google Scholar
- Arda Goknil, Phu Nguyen, Sagar Sen, Dimitra Politaki, Harris Niavis, Karl John Pedersen, Abdillah Suyuthi, Abhilash Anand, and Amina Ziegenbein. 2023. A Systematic Review of Data Quality in CPS and IoT for Industry 4.0. Comput. Surveys 55, 14s, Article 327 (2023), 38 pages.Google Scholar
- Erik Johannes Husom, Simeon Tverdal, Arda Goknil, and Sagar Sen. 2022. UDAVA: an unsupervised learning pipeline for sensor data validation in manufacturing. In CAIN’22. 159–169.Google Scholar
- Mauro Isaja, Phu Nguyen, Arda Goknil, Sagar Sen, Erik Johannes Husom, Simeon Tverdal, Abhilash Anand, Yunman Jiang, Karl John Pedersen, Per Myrseth, 2023. A blockchain-based framework for trusted quality data sharing towards zero-defect manufacturing. Computers in Industry 146 (2023), 103853.Google ScholarDigital Library
- iterative.ai. Visited in 2022. Open-source Version Control System for Machine Learning Projects. https://dvc.org/.Google Scholar
- Benjamin Maschler, Thi Thu Huong Pham, and Michael Weyrich. 2021. Regularization-based Continual Learning for Anomaly Detection in Discrete Manufacturing. Procedia CIRP 104 (2021), 452–457.Google ScholarCross Ref
- Benjamin Maschler, Hannes Vietz, Nasser Jazdi, and Michael Weyrich. 2020. Continual learning of fault prediction for turbofan engines using deep learning with elastic weight consolidation. In ETFA’20, Vol. 1. 959–966.Google Scholar
- Sagar Sen, Erik Johannes Husom, Arda Goknil, Dimitra Politaki, Simeon Tverdal, Phu Nguyen, and Nicolas Jourdan. 2023. Virtual sensors for erroneous data repair in manufacturing a machine learning pipeline. Computers in Industry 149 (2023), 103917.Google ScholarDigital Library
- Sagar Sen, Erik Johannes Husom, Arda Goknil, Simeon Tverdal, and Phu Nguyen. 2023. Uncertainty-aware Virtual Sensors for Cyber-Physical Systems. IEEE Software (2023).Google Scholar
- Sagar Sen, Erik Johannes Husom, Arda Goknil, Simeon Tverdal, Phu Hong Nguyen, and Iker Mancisidor. 2022. Taming Data Quality in AI-Enabled Industrial Internet of Things. IEEE Software 39, 6 (2022), 35–42.Google ScholarDigital Library
- Sagar Sen, Simon Myklebust Nielsen, Erik Johannes Husom, Arda Goknil, Simeon Tverdal, and Leonardo Sastoque Pinilla. 2023. Replay-driven continual learning for the industrial internet of things. In CAIN’23. IEEE, 43–55.Google Scholar
- Wen Sun, Jiajia Liu, and Yanlin Yue. 2019. AI-enhanced offloading in edge computing: When machine learning meets industrial IoT. IEEE Network 33, 5 (2019), 68–74.Google ScholarDigital Library
- Hasan Tercan, Philipp Deibert, and Tobias Meisen. 2022. Continual learning of neural networks for quality prediction in production using memory aware synapses and weight transfer. Journal of Intelligent Manufacturing 33, 1 (2022), 283–292.Google ScholarDigital Library
- Simeon Tverdal, Arda Goknil, Phu Nguyen, Erik Johannes Husom, Sagar Sen, Jan Ruh, and Francesca Flamigni. 2023. Edge-based Data Profiling and Repair as a Service for IoT. In IoT’23. https://doi.org/10.1145/3627050.3627065Google ScholarDigital Library
Recommendations
Role of machine learning and deep learning in securing 5G-driven industrial IoT applications
AbstractThe Internet of Things (IoT) connects millions of computing devices and has set a stage for future technology where industrial use cases like smart cities and smart houses will operate with minimal human intervention. IoT’s cross-...
IIOT Within The Architecture Of The Manufacturing Company
DTMIS '20: Proceedings of the International Scientific Conference - Digital Transformation on Manufacturing, Infrastructure and ServiceThe introduction of the Internet of Things (IoT) in industry can increase the level of production management, increase the speed of managerial decision-making, and provide higher quality products. The article discusses the use of the Industrial Internet ...
A MEC-IIoT intelligent threat detector based on machine learning boosted tree algorithms
AbstractIn recent years, new management methods have appeared that mark the beginning of a new industrial revolution called Industry 4.0 or the Industrial Internet of Things (IIoT). IIoT brings together new emerging technologies, such as the Internet of ...
Comments