基于人工神经网络铂电阻非线性估计方法的研究

The Study of a New Method for Nonlinear Estimation of Pt Resistors based on Artificial Neural Networks

本文提出了一种基于人工神经网络的铂电阻传感器非线性估计方法．该方法用二次幂级数多项式拟合温度传感器的非线性模型，多项式的系数可由神经网络学习算法得到．当条件发生变化时，只要给出几组测量数据对，通过该方法可自动重新训练网络，获得新的多项式系数，实现传感器的非线性估计．

A new method to Pt resistors sensor nonlinear estimation based artificial neural networks is proposed. The response of sensor is expressed in terms of its output by a power series. The coefficients of the power series can be trained by a simple neural algorithm. When the change of conditions so long as several sets of measure data are given, the neural network can be retrained and a new set of coefficients can be obtained. So nonlinear estimation of Pt resistor was realized.