The Neural Network Method for Non-linear Correction of the Thermal Resistance Transducer

For the purpose of better application, the nonlinear correction of the transducer is very important. The soft computing methods which include the neural network linearization correction method and linear interpolation method are put forward to realize the nonlinear correction for the transducer. The principles, algorithms and realization of these methods are discussed, and nonlinear correction experiments by means of the two kinds of soft computing methods were done. Through the experiments, it is proved that the soft computing methods are able to realize the nonlinear correction, and the neural networks method is more effective and accurate than the linear interpolation method