Compensation of gap sensor for high-speed maglev train with RBF neural network

The gap sensor plays an important role for a electro-magnetic levitation system, which is a critical component of high-speed maglev trains. An artificial neural network is a promising area in the development of intelligent sensors. In this paper, a radial basis function (RBF) neural network modelling approach is introduced for the compensation of the non-contact inductive gap sensor of the high-speed maglev train. As an inverse model compensator, the designed RBF-based model is connected in series to the output terminal of the gap sensor. The network is trained by using a gradient descent learning algorithm with momentum. This scheme could estimate accurately the correct air-gap distance in a wide range of temperatures. The simulation studies of this model show that it can provide a compensated gap value with an error of less than ±0.4 mm at any temperature from 20° to 80°C. In particulr, the maximum estimation error can be reduced to ±0.1 mm when the working gap varies from 8 to 12 mm. The experimental results indicate that the compensated gap signal could meet the requirements of the levitation control system.

[1]  S. E. Khaikin,et al.  Theory of Oscillators , 1966 .

[2]  Bimal K. Bose,et al.  Neural Network Applications in Power Electronics and Motor Drives—An Introduction and Perspective , 2007, IEEE Transactions on Industrial Electronics.

[3]  Minglu Zhang,et al.  Application of RBF Neural Network to Temperature Compensation of Gas Sensor , 2008, 2008 International Conference on Computer Science and Software Engineering.

[4]  U. Hollenbach,et al.  Combdrive Configuration for an Electromagnetic Reluctance Actuator , 2008, Journal of Microelectromechanical Systems.

[5]  Ganapati Panda,et al.  An intelligent pressure sensor using neural networks , 2000, IEEE Trans. Instrum. Meas..

[6]  B.M. Wilamowski,et al.  Neural network architectures and learning algorithms , 2009, IEEE Industrial Electronics Magazine.

[7]  S. Fericean,et al.  New Noncontacting Inductive Analog Proximity and Inductive Linear Displacement Sensors for Industrial Automation , 2007, IEEE Sensors Journal.

[8]  Li Lu.  Research on Levitation Gap Sensor for High Speed Maglev Train , 2009 .

[9]  Xiao Jian,et al.  Modeling of gap sensor for high-speed maglev train based on RBF network , 2011, 2011 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems.

[10]  Zhang Chao,et al.  The application of RBF neural network in the compensation for temperature drift of the silicon pressure sensor , 2010, 2010 International Conference On Computer Design and Applications.

[11]  Sadasivan Puthusserypady,et al.  Estimation of the Hemodynamic Response of fMRI Data Using RBF Neural Network , 2007, IEEE Transactions on Biomedical Engineering.

[12]  Zhang Kunlun.  Design of gap determination system for high-speed maglev train , 2005 .

[13]  Mahnaz Hashemi,et al.  Modeling and compensation for capacitive pressure sensor by RBF neural networks , 2010, IEEE ICCA 2010.

[14]  M. Jagiella,et al.  Miniaturized inductive sensors for industrial applications , 2002, Proceedings of IEEE Sensors.

[15]  Shuzhi Sam Ge,et al.  Adaptive neural control of uncertain MIMO nonlinear systems , 2004, IEEE Transactions on Neural Networks.

[16]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[17]  Hou Liqun,et al.  A Vitual Instrument for Sensors Nonlinear Errors Calibration , 2005, 2005 IEEE Instrumentationand Measurement Technology Conference Proceedings.

[18]  Bogdan M. Wilamowski,et al.  Compensation of Nonlinearities Using Neural Networks Implemented on Inexpensive Microcontrollers , 2011, IEEE Transactions on Industrial Electronics.