An approach of Eddy current sensor calibration in state estimation for maglev system
Hesheng Zhang, Xun-kai Cao, Bin Guo, Qiang Wang, Yue-hui Fu · 2007
Eddy current sensors are used in state estimation of the maglev system. However, the input output characteristic of the eddy current sensor is nonlinear and cannot be fit for the precision and time limit of the control system. So the radial basis function (RBF) neural network is used to construct the inverse model of the eddy current sensor. The simplified adaptive algorithm for hidden layer structure and center value can quickly and accurately compute the structure and parameter of RBF network. And the eddy current sensor is calibrated. In the practical measurement, the method can satisfy the requirement of the control system. The calibration error is less than 0.7% and the linear range is extended.