Cyber-physical microgrid components fault prognosis using electromagnetic sensors
Open Access
- 1 June 2019
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Cyber-Physical Systems: Theory & Applications
- Vol. 4 (2), 173-178
- https://doi.org/10.1049/iet-cps.2018.5043
Abstract
Higher operational requirements in cyber-physical microgrid system stress the electrical system and may push it to the edge of stability. Therefore, prognosis of the imminent failures is vital. Accessing stray electromagnetic waves of power components helps in power system protection and non-intrusive prognosis of electric components faults in a cyber-physical microgrid environment. This study implements a cyber-physical approach associated between the electromagnetic waves radiated by components in the microgrid and the communication structure. To verify the same, the entire system is implemented on a real-time lab-based microgrid environment. The major problem with the stray electromagnetic waves is receiving appropriate fields. This is resolved by placing magnetic coil antennas at optimal distances and monitoring the radiated electromagnetic waves and their harmonics. Quick response code recognition technique is used to recognise the source and its corresponding healthy mode while harmonic analysis through artificial neural network helps to find the type and origin of faults. This would be an artificial intelligence-enabled system which self-optimises and acts according to the patterns. The proposed monitoring system can be utilised in any cyber-physical microgrid system especially those located in extreme/remote areas.Keywords
This publication has 16 references indexed in Scilit:
- Real-Time Energy Management in MicrogridsIEEE Transactions on Smart Grid, 2015
- Fault detection and classification in electrical power transmission system using artificial neural networkSpringerPlus, 2015
- Condition monitoring of electrical machines for extreme environments using electromagnetic stray fieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Trends in Microgrid ControlIEEE Transactions on Smart Grid, 2014
- Distributed charge/discharge control of energy storages in a renewable‐energy‐based DC micro‐gridIET Renewable Power Generation, 2014
- Multi-task hidden Markov modeling of spectrogram feature from radar high-resolution range profilesEURASIP Journal on Advances in Signal Processing, 2012
- An equivalent source model for the study of radiated electromagnetic fields in multi-machine electric drive systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Recent developments of induction motor drives fault diagnosis using AI techniquesIEEE Transactions on Industrial Electronics, 2000
- An unsupervised, on-line system for induction motor fault detection using stator current monitoringIEEE Transactions on Industry Applications, 1995
- Feasibility of using unsupervised learning, artificial neural networks for the condition monitoring of electrical machinesIEE Proceedings - Electric Power Applications, 1994