一种基于函数型神经网络的传感器静态模型辨识方法

An Approach to Identification of Transducer Model Based on Artificial Neural Networks

本文提出一种基于函数型神经网络的传感器静态模型辨识方法．该神经网络连接系数直接反映了传感器静态模型中的被辨识参数，网络结构简单，具有良好的收敛性．文章将这一方法实际应用到铂热电阻静态模型辨识．仿真结果表明，本方法是可行的．

In this paper, an approach to identification of transducer model based on artificial neural networks is proposed. The connection coofficicnt of this neural networks directly reflects parameters of model to be identified. The method was applied to building the model of Pt100 thermal resistance and the results showed that the accuracy of model is very satisfactory.