The focus of this paper is the design and implementation of adaptive network based fuzzy inference (ANFIS) controller by using the training data obtained from a system controlled by Linear Quadratic Regulator (LQR). This work is motivated by the need to remove stochastic observer required for LQR in noisy environments while at the same time to have optimal performance. This theory is validated by taking the well investigated case of Active Suspension System of a Quarter Vehicle. The performance of the obtained ANFIS controller is tested using Quanser© Active Suspension Plant. It is observed that the ANFIS controller gives good close loop performance, while removing the requirement of a stochastic observer.
CITATION STYLE
Rashid, U., Jamil, M., Gilani, S. O., & Niazi, I. K. (2016). LQR based training of adaptive neuro-fuzzy controller. In Smart Innovation, Systems and Technologies (Vol. 54, pp. 311–322). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-33747-0_31
Mendeley helps you to discover research relevant for your work.