纸浆浓度传感器非线性估计和动态标定的一种新方法

本文提出了一种基于人工神经网络的纸浆浓度传感器非线性估计和动态标定新方法。该方法用４次幂级数多项式拟合浓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。当环境条件发生变化时，只要给出几组测量数据对，该方法可自动重新训练网络，获得新的多项式系数，实现传感器的在线动态标定

A New Method for Nonlinear Estimation and Dynamic Calibration of Pulp Consistency Sensors

Anew method to pulp consistency sensor nonlinear estimation and dynamic calibration based on artificial neural networks is proposed.The response of the 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 environmental 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 the on line dynamic calibration was realized.