Neural identification and indirect control of a nonlinear mechanical oscilatory plant

A new Modular Recurrent Trainable Neural Network (MRTNN) has been used for system identification of nonlinear oscillatory mechanical plant. The first MRTNN module identified the exponential part of the unknown plant and the second one - the oscillatory part of the plant. The plant has been controlled by an adaptive sliding mode control system with integral term. The RTNN controller used the estimated parameters and states to suppress the plant oscillations and the static plant output control error is reduced by an I-term added to the control.

[1]  Kyo-Beum Lee,et al.  Vibration control of 2-mass system using a neural network torsional torque estimator , 1998, IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200).

[2]  Gaetan Libert,et al.  Nonlinear dynamic system identification with dynamic recurrent neural networks , 1996, Proceedings of International Workshop on Neural Networks for Identification, Control, Robotics and Signal/Image Processing.

[3]  A. Kazemy,et al.  Second Order Diagonal Recurrent Neural Network , 2007, 2007 IEEE International Symposium on Industrial Electronics.

[4]  Gustavo Luiz C. M. de Abreu,et al.  A neural network-based direct inverse control for active control of vibrations of mechanical systems , 2000, Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks.

[5]  Martin Bouchard,et al.  New recursive-least-squares algorithms for nonlinear active control of sound and vibration using neural networks , 2001, IEEE Trans. Neural Networks.

[6]  Mark W. Spong,et al.  Robot dynamics and control , 1989 .

[7]  Heikki Handroos,et al.  Application of neural network in suppressing mechanical vibration of a permanent magnet linear motor , 2008 .

[8]  Ieroham S. Baruch,et al.  A levenberg–marquardt learning applied for recurrent neural identification and control of a wastewater treatment bioprocess , 2009, HIS 2009.

[9]  이광원,et al.  Vibration control of 2-mass system using a neural network torsional torque estimator , 1998 .

[10]  Mark W. Spong,et al.  On the force control problem for flexible joint manipulators , 1989 .

[11]  George W. Irwin,et al.  Second-order training of adaptive critics for online process control , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[12]  Hicham Chaoui,et al.  ANN-Based Adaptive Control of Robotic Manipulators With Friction and Joint Elasticity , 2009, IEEE Transactions on Industrial Electronics.