基于混合遗传算法的浓度传感器的非线性估计和动态标定  

Nonlinear Estimation and Dynamic Calibration of Density Sensors Based on Hybrid Genetic Algorithm

作　　者：钱光耀[1] 赵光兴[1] 韩华明[1] 

机构地区：[1]安徽工业大学电气信息学院,安徽马鞍山243002

出　　处：《中国仪器仪表》2006年第9期44-47,共4页China Instrumentation

基　　金：安徽省自然科学基金项目资助(03042309)

摘　　要：本文针对最小二乘法、分段线性化、神经网络等拟合方法的不足,提出解决浓度传感器输出特性拟合和在线标定问题的混合遗传算法,实验验证了其有效性。当环境条件发生变化时,只要测量几组数据对,该方法可自动重新训练网络,获得新的多项式系数,实现浓度传感器的在线动态标定。Hybrid genetic algorithm of solving the problems on the fitting of sensor output character and its on-line scaling were put forward for the shortcoming of least square and segmentation linearization and neutral network and so on. The effect of method is verified by experiments. 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. The discussing of this method can be used for not only sensors but also other similar systems.

关 键 词：浓度传感器 混合遗传算法 非线性估计 动态标定 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]