摘要
为进一步提高PSD传感器线性度,提出了一种基于改进型神经网络(小生境遗传算法和BP算法的混合算法)的PSD传感器的非线性调校方法,该方法利用神经网络良好的非线性映射能力逼近反非线性函数,从而完成非线性校正。仿真结果表明:与BP算法相比,改进型BP神经网络收敛速度快,而且该方法能有效地消除由于制作工艺及技术等因素对传感器非线性的影响。
In order to further enhance the PSD sensor linearity, the nonlinear correction method of PSD sensor based on improved neural network that NGA and BP was combined together was introduced, which approached inverse nonlinear function to finish the nonlinear correction by use of nonlinear mapping ability of neural network. The experimental results showed that the improved neural network has quick convergence rate compared with BP algorithm. This method could eliminate effectively the effect of some factors, such as production technology and technical factors, on the sensor nonlinear fluctuation.
出处
《中国测试》
CAS
2009年第2期37-39,共3页
China Measurement & Test
