基于神经网络的温度测量方法研究

The Research of Thermometry Based on Neural Networks

介绍基于神经网络的温度测量方法,给出系统原理图及温度测量误差自动校正方法;采用错位累加计算法(LEA判别法)以实现梯度迭代法和牛顿迭代法的有效结合,使神经网络学习步数明显减少而收敛率提高;采用DSP技术实现温度实时快速测量,并给出实验结果。

In this article, thermometry based on neural networks is thoroughly introduced the system principle diagram, and the automation error calibration method in thermometry are given. The LEA's decision method is given so that grads methods and Newton methods can be effectively combined in neural networks learning. DSP technology is used to realize live, fast temperature measuring. The experiment result is also given .