TY - GEN
T1 - Intelligent integral backstepping sliding mode control using recurrent neural network for magnetic levitation system
AU - Lin, Faa Jeng
AU - Chen, Syuan Yi
PY - 2010
Y1 - 2010
N2 - An intelligent integral backstepping sliding mode control (IIBSMC) system using a multi-input multi-output (MIMO) recurrent neural network (RNN) is proposed to control the position of a levitated object of a magnetic levitation system considering the uncertainties in this study. First, the dynamic model of the magnetic levitation system is derived. Then, an integral backstepping sliding mode control (IBSMC) system with an integral action is proposed for the tracking of the reference trajectory. Moreover, to relax the requirements of the needed bounds and discard the switching function in IBSMC, an IIBSMC system using a MIMO RNN estimator is proposed to improve the control performance and further increase the robustness of the magnetic levitation system. The adaptive learning algorithms are derived using Lyapunov stability theorem to train the parameters of the RNN online. Finally, some experimental results of the tracking of periodic sinusoidal trajectory demonstrate the validity of the proposed IIBSMC system for practical applications.
AB - An intelligent integral backstepping sliding mode control (IIBSMC) system using a multi-input multi-output (MIMO) recurrent neural network (RNN) is proposed to control the position of a levitated object of a magnetic levitation system considering the uncertainties in this study. First, the dynamic model of the magnetic levitation system is derived. Then, an integral backstepping sliding mode control (IBSMC) system with an integral action is proposed for the tracking of the reference trajectory. Moreover, to relax the requirements of the needed bounds and discard the switching function in IBSMC, an IIBSMC system using a MIMO RNN estimator is proposed to improve the control performance and further increase the robustness of the magnetic levitation system. The adaptive learning algorithms are derived using Lyapunov stability theorem to train the parameters of the RNN online. Finally, some experimental results of the tracking of periodic sinusoidal trajectory demonstrate the validity of the proposed IIBSMC system for practical applications.
UR - http://www.scopus.com/inward/record.url?scp=79959428801&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79959428801&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2010.5596898
DO - 10.1109/IJCNN.2010.5596898
M3 - Conference contribution
AN - SCOPUS:79959428801
SN - 9781424469178
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010
Y2 - 18 July 2010 through 23 July 2010
ER -