基于FLANN的传感器动态特性研究方法  

FLANN Based Dynamic Characteristic Investigations of Sensor

作　　者：殷铭[1] 徐科军[2] 

机构地区：[1]东南大学自动控制系 [2]合肥工业大学自动化研究所

出　　处：《东南大学学报（自然科学版）》1999年第4期103-108,共6页Journal of Southeast University：Natural Science Edition

基　　金：国家自然科学基金

摘　　要：将函数联接型神经网络引入传感器动态特性的研究，利用神经元网络良好的逼近能力，建立腕力传感器的动态数学模型，该方法所建模型阶次低，精度 数据个数和采样频率无特殊要求。The functional link artificial neural network (FLANN) is introduced in investigations of sensor’s dynamic characteristic. Its excellent approach ability is used to establish the wrist sensor’s dynamic mathematical models. The built model’s order is lower and the precision is higher. This method has no special demand for data number and sampling frequency in the process of modeling. According to the idea of inverse model, a sensor’s dynamic compensation method based on FLANN is proposed. Dynamic compensation device designed by this method is easy and good in real time. It is independent of the sensor’s model and has strong robust.

关 键 词：传感器 动态建模 FLANN 动态补偿 神经网络 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]