Intelligent system for health monitoring and predictive maintenance of physical machines
With the rapid advancements of computing power, data storage and processing capacity, health monitoring and fault diagnosis of physical machines in real-time are becoming more practical everyday. In this research project, we are developing a comprehensive pipeline of topics to measure physical plants, identify them, and propose solutions based on the system identifications. Our research interests and topics include but are not limited to:
1) Technologies to miniaturize conventional sensors
2) Distributed sensor system development and wireless data streaming
3) Hardware and software development of automated and self-preceptive physical plants
4) Development of novel sensors across various engineering domains
5) Data mining and system identification from high-dimensional time-series data
6) Real-time fault diagnosis algorithms
7) Construction of time-series anomalous data archive
8) Active maintenance of anomalous machines with robot intervention
2) Distributed sensor system development and wireless data streaming
3) Hardware and software development of automated and self-preceptive physical plants
4) Development of novel sensors across various engineering domains
5) Data mining and system identification from high-dimensional time-series data
6) Real-time fault diagnosis algorithms
7) Construction of time-series anomalous data archive
8) Active maintenance of anomalous machines with robot intervention
Publications
2019 |
||
| 1. |  | Design of Versatile and Low-Cost Shaft Sensor for Health Monitoring Inproceedings pp. 1926-1932, IEEE IEEE, 2019, ISBN: 978-1-5386-6027-0. |