Industry 4.0
Vol. 9 (2024), Issue 4, pg(s) 130-133

TECHNOLOGICAL BASIS OF “INDUSTRY 4.0”

Unified Framework for PdM Algorithm Development: The pdm-tools Architecture

  • 1 AGH University of Krakow, Poland

Abstract

This paper proposes a novel architecture for pdm-tools, a dedicated library designed to streamline the development process of predictive maintenance (PdM) algorithms within the Industry 4.0 paradigm. pdm-tools tackles the time-consuming nature of PdM algorithm development by encompassing five key components within a unified framework. pdm-tools tackles the time challenge by offering a unified workflow: generate synthetic vibration data (gearboxes, bearings, shafts) for rapid prototyping, eliminating initial real-world data collection. Data preparation and feature extraction ensure readiness through scaling, filtering, and extracting diverse condition indicators, empowering robust algorithms. Finally, user-defined model development and evaluation allow training, optimization, and selection of optimal PdM algorithms (machine learning/deep learning). By integrating these functionalities within a single architecture, pdm-tools empowers rapid development and evaluation of PdM algorithms, ultimately leading to a more efficient and effective implementation of predictive maintenance strategies within the Industry 4.0 landscape.

Keywords

References

  1. Hu, Yang, et al. "Prognostics and health management: A review from the perspectives of design, development and decision." Reliability Engineering & System Safety 217 (2022): 108063.M.
  2. Ran, Yongyi, et al. "A survey of predictive maintenance: Systems, purposes and approaches." arXiv preprint arXiv:1912.07383 (2019).
  3. Krupitzer, Christian, et al. "A survey on predictive maintenance for industry 4.0." arXiv preprint arXiv:2002.08224 (2020).
  4. Tiddens, Wieger, Jan Braaksma, and Tiedo Tinga. "Decision framework for predictive maintenance method selection." Applied Sciences 13.3 (2023): 2021.
  5. Namuduri, Srikanth, et al. "Deep learning methods for sensor based predictive maintenance and future perspectives for electrochemical sensors." Journal of The Electrochemical Society 167.3 (2020): 037552.
  6. Lalik, Krzysztof, et al. "Simulation Modeling for Mass Customization Furniture Production: Investigating Production Volume and Machine Load in scope of Industry 4.0 standard." Industry 4.0 8.4 (2023): 116-122.
  7. Lalik, Krzysztof, et al. "The steam pressure impacts reducing system for a biomass cogenerator based on monitoring of the frequency characteristics of the steam actuator." Vibrations in Physical Systems 30.2 (2019).
  8. Lalik, Krzysztof, et al. "Self-powered wireless sensor matrix for air pollution detection with a neural predictor." Energies 15.6 (2022): 1962
  9. Balazy, P., Paweł Gut, and Paweł Knap. "Neural classifying system for predictive maintenance of rotating devices." IOP Conference Series: Materials Science and Engineering. Vol. 1239. No. 1. IOP Publishing, 2022.
  10. Knap, Paweł, Krzysztof Lalik, and Patryk Bałazy. "Boosted Convolutional Neural Network Algorithm for the Classification of the Bearing Fault Form 1-D Raw Sensor Data." Sensors 23.9 (2023): 4295.
  11. Jablonski, Adam. Condition monitoring algorithms in Matlab. Springer Nature, 2021.
  12. Oppenheim, Alan V. Discrete-time signal processing. Pearson Education India, 1999.
  13. Aurélien Géron. „Hands-on Machine Learning with Scikit Learn, Keras, and TensorFlow, Concepts, Tools, and Techniques to Build Intelligent Systems (second edition)”. Sebastopol, CA: O’Reilly Media, Inc., 2019.

Article full text

Download PDF