Universal cyber physical system, a prototype for predictive maintenance

Keh-Kim Kee, Simon Lau Boung Yew, Yun Seng Lim, Yip Ping Ting, Ramli Rashidi

Abstract


Industrial 4.0 technology of cyber-physical system enables real-time monitoring, sensing and actuating of physical machinery for predictive maintenance that replaces the conventional labor-intensive approach. This paper presents the design and development of a universal, cost-effective and internet of thing (IoT)-based proof-of-concept prototype universal cyber-physical system (UniCPS) with a cloud platform with an open and modular-based design of three-tier system architecture. The prototype demonstrates promising precision and accuracy for predictive maintenance on a pilot use case with MAPE of 3.77%, and average RMSE of 0.50. Besides, real-time visualization and detection of anomaly were also demonstrated with a cloud-based solution. The maintenance alert sent out by the actuator serves to notify the authorized personnel immediately for corrective action. As an extension to this work, a wireless sensor network can be incorporated in future work to acquire various data from diverse locations to overcome the limitations of sensor data.

Keywords


Cloud computing; Cyber physical system; Industrial 4.0; Internet of things; Predictive maintenance

Full Text:

PDF


DOI: https://doi.org/10.11591/eei.v11i1.3216

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Stats