A Flywheel Energy Storage System Suspended by Active Magnetic Bearings Using an Online Trained Adaptive Neural Network Controller

Abstract:

A flywheel energy storage system (FESS) is an effective energy-saving device. It works by accelerating a rotor flywheel disc at a very high speed and maintaining the energy in the system as rotational energy. Active magnetic bearings (AMB) are ideally suited for use at high-speed and are so used in FESSs. This work develops a mathematical model of the levitation force and rotational torque of a flywheel. The systems for controlling the position and velocity of the flywheel are designed based on the emergent approaches of fuzzy logic controller (FLC) and an online trained adaptive neural network controller (NNC). In the proposed controller system, an FLC was first designed to identify the parameters of the FESS. This allowed the initial training data with two inputs, the error and derivate of the error, and one output signal from the FLC to be obtained. Finally, an NNC with online training features was designed using an S-function in Matlab software to achieve improved performance. The results obtained concerning the FESS indicate that the system exhibited satisfactory control performance including transient and steady-state responses under various operating conditions.

• Periodical: Applied Mechanics and Materials (Volumes 602-605)
• Pages: 1411-1416
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.602-605.1411
• Online since: August 2014
• Authors: Seng Chi Chen*, Van Sum Nguyen, Dinh Kha Le, Nguyen Thi Hoai-Nam
• Keywords: Active Magnetic Bearing, Energy Storage System, FCL, Flywheel, Neural Network (NN)

References

[1] Hai Chang Liu and Jihai Jiang. Flywheel energy storage-an upswing technology for energy sustainability. [J]. Energy and Buildings, 2007 (39) 599–604.

DOI: 10.1016/j.enbuild.2006.10.001

[2] Seng Chi Chen, Van-Sum Nguyen, Dinh-Kha Le and Ming Mao Hsu. ANFIS controller for an active magnetic bearing system [C]. IEEE, International Conference on Fuzzy Systems, (2013).

DOI: 10.1109/fuzz-ieee.2013.6622360

[3] Gupta Nitin and S P Dubey. Neural Network Based Shunt Active Filter for Harmonic and Reactive Power Compensation under Non-ideal Mains Voltage [C]. IEEE, (ICIEA), 2010 370–375.

DOI: 10.1109/iciea.2010.5516896

[4] Seng Chi Chen, Lin Ying Jyh, Van-Sum Nguyen and Ming Mao Hsu. A novel fuzzy neural network controller for maglev system with controlled-PM electromagnets. [J]. Springer, Lecture Notes in Electrical Engineering, 2013 (234) 551-561.

DOI: 10.1007/978-1-4614-6747-2_65

[5] Gerhard Schweitzer and Eric. Maslen. Magnetic bearings–theory, design and application to rotating machinery, Springer-Verlag, (2009).

DOI: 10.1007/978-3-642-00497-1

[6] Faa Jeng Lin and Rong Jong Wai. Hybrid control using recurrent fuzzy neural network for linear induction motor servo drive. [J]. IEEE Trans on Fuzzy systems, 2001 (9) 102-115.

DOI: 10.1109/91.917118

[7] Negnevitsky Michael, artificial intelligence. A guide to intelligent systems, Pearson Education, Second edition, (2005).