摘要
针对最小二乘法和分段线性化等传统方法的不足 ,提出了解决传感器输出特性拟合和在线标定问题的遗传神经网络算法 ,实验验证了其有效性 .本文的论述不但可以用于传感器 。
Genetic neural network algorithm of solving the problems on the fitting of sensor output character and its on line scaling were put forward for the shortcoming of conventional methods, such as least square and segmentation linearization and so on. The effectiveness of method is verified by experiments. The discuss of this paper can be used for not only sensors but also other similar systems.
出处
《传感技术学报》
CAS
CSCD
2001年第4期323-327,共5页
Chinese Journal of Sensors and Actuators
基金
国家教委博士点基金项目 (980 2 861 9)
关键词
传感器
遗传神经网络
输出特性
sensor, genetic neural network
output character, fitting
on line scaling
