Nonlinear errors correcting method of sensors based on RBF neural network

The principles for correcting the nonlinear errors of the sensors with a neural network are introduced. The method of radial basis function neural network (RBFNN) is given to correct the nonlinear errors of the sensors. A BP neural network has been developed to solve the same problem for comparison. The experimental results show that network learning speed can be sped up markedly and nonlinear errors of the sensors can be greatly reduced by using RBFNN. RBFNN is quite effective and superior to BPNN in correcting nonlinear errors of the sensors.