Dynamic modeling of magnetic suspension isolator using artificial neural network: a modified genetic approach

Active vibration isolation technology has been widely used to reduce vibration transmission in many different engineering systems. Magnetic suspension isolator (MSI), as an active isolation actuator, has shown advantages including non‐contact, high response frequency, high reliability and long life‐span. However, its potential has not been fully explored due to the nonlinear and hysteretic behavior in a dynamic environment, and there is limited research work in the area. This paper proposes a new artificial neural network (ANN)‐based approach to model the dynamics of MSI. A modified genetic algorithm (MGA) is developed to train the ANN to improve the model accuracy. Results clearly show that the ANN model with the MGA approach outperforms the back propagation (BP) approach and the analytic method based on the least squares fitting method.

[1]  Zhou Zude.  Semi-active fuzzy control for a floating raft isolation system with magnetic suspension supporting , 2009 .

[2]  Yangmin Li,et al.  A general dynamics and control model of a class of multi-DOF manipulators for active vibration control , 2011 .

[3]  Mooyoung Jung,et al.  a Hybrid-Type Active Vibration Isolation System Using Neural Networks , 1996 .

[4]  Wang Yong.  Experiment and Modeling about the Dynamic Electromagnetic Force of a Magnetic Suspension Isolator , 2009 .

[5]  Shahid Hussain,et al.  Dynamic modeling of pneumatic muscles using modified fuzzy inference mechanism , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[6]  Hiroshi Matsuhisa,et al.  Semi-active vibration isolation system with variable stiffness and damping control , 2008 .

[7]  Zude Zhou,et al.  Semi-Active Mode Fuzzy Control for Multi-Dof Floating Raft Isolation System with Magnetic Suspension Isolators , 2009, 2009 Asia-Pacific Power and Energy Engineering Conference.

[8]  Ming-Chang Shih,et al.  Active control of electro-rheological fluid embedded pneumatic vibration isolator , 2008, Integr. Comput. Aided Eng..

[9]  P. Couzon,et al.  Neuro-fuzzy Active Control of Rotor Suspended on Active Magnetic Bearing , 2007 .

[10]  M. Takasaki,et al.  An Active Micro Vibration Isolator with Zero-Power Controlled Magnetic Suspension Technology , 2006 .

[11]  M. F. Golnaraghi,et al.  A Novel Semi-active Magnetorheological Bushing Design for Variable Displacement Engines , 2008 .

[12]  S. E. Semercigil,et al.  A VARIABLE DAMPING TUNED ABSORBER WITH ELECTRO-RHEOLOGICAL FLUID FOR TRANSIENT RESONANCE OF LIGHT STRUCTURES , 2001 .

[13]  Xiaoping Liu,et al.  Active Vibration Control of a Modular Robot Combining a Back-Propagation Neural Network with a Genetic Algorithm , 2005 .

[14]  D. Owens,et al.  ACTIVE VIBRATION ISOLATION IN A “SMART SPRING” MOUNT USING A REPETITIVE CONTROL APPROACH , 2005 .

[15]  F. A. Johnson,et al.  Active vibration control for marine applications , 2004 .

[16]  Sergio E. Diaz,et al.  A Neural Network-Based Closed Loop Identification of a Magnetic Bearings System , 2004 .

[17]  Søren Nielsen,et al.  Semi-active control of shallow cables with magnetorheological dampers under harmonic axial support motion , 2008 .

[18]  Md.E. Hoque,et al.  Development of a three-axis active vibration isolator using zero-power control , 2006, IEEE/ASME Transactions on Mechatronics.

[19]  S. Narayanan,et al.  Optimal semi-active preview control response of a half car vehicle model with magnetorheological damper , 2009 .

[20]  A. K. Mallik,et al.  PERFORMANCE CHARACTERISTICS OF A VIBRATION ISOLATOR WITH ELECTRO-RHEOLOGICAL FLUIDS , 1999 .

[21]  Emile Fiesler,et al.  Neural Networks with Adaptive Learning Rate and Momentum Terms , 1995 .