Authors: Ravindrakumar M. Nagarale; B.M. Patre
Addresses: Department of Instrumentation Engineering, MBE Society's, College of Engineering, Ambajogai-431517, India ' SGGS Institute of Engineering and Technology, Vishnupuri, Nanded-431606, India
Abstract: In this paper, neural-fuzzy sliding mode control is proposed for robust asymptotic stabilisation of a non-linear system. The sliding mode control has two terms as continuous mode and discontinuous mode are approximated using direct neural network control method based on neural sliding mode control and fuzzy sliding mode control method respectively. The combined control is termed as neural-fuzzy sliding mode control. The weights of the neural network are updated online to minimise the cost function. The cost function is the difference between reference value and plant output. The performance of the proposed controller is tested using an example of non-linear inverted pendulum and results are compared with conventional SMC and FSMC methods to demonstrate its superiority in terms of parameter variations and disturbance rejection.
Keywords: sliding mode control; fuzzy SMC; fuzzy control; FSMC; neural SMC; NSMC; mechatronic systems; fuzzy logic; neural networks; nonlinear systems; inverted pendulum; parameter variation; disturbance rejection.
International Journal of Advanced Mechatronic Systems, 2013 Vol.5 No.3, pp.209 - 219
Received: 08 May 2021
Accepted: 12 May 2021
Published online: 31 Oct 2013 *