[1]殷铭,徐科军,戴先中.基于FLANN的传感器动态特性研究方法[J].东南大学学报(自然科学版),1999,29(4):103-108.[doi:10.3969/j.issn.1001-0505.1999.04.022]
 Yin Ming,Xu Kejun,Dai Xianzhong.FLANN-Based Dynamic Characteristic Investigations of Sensor[J].Journal of Southeast University (Natural Science Edition),1999,29(4):103-108.[doi:10.3969/j.issn.1001-0505.1999.04.022]
点击复制

基于FLANN的传感器动态特性研究方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
29
期数:
1999年第4期
页码:
103-108
栏目:
自动化
出版日期:
1999-07-20

文章信息/Info

Title:
FLANN-Based Dynamic Characteristic Investigations of Sensor
作者:
殷铭1 徐科军2 戴先中1
1 东南大学自动控制系, 南京 210096; 2 合肥工业大学自动化研究所, 合肥 230009
Author(s):
Yin Ming1 Xu Kejun2 Dai Xianzhong1
1 Department of Automatic Control, Southeast University, Nanjing 210096
2 Institute of Automation, Hefei University of Technology, Hefei 230009
关键词:
传感器 动态建模 逆模型 动态补偿 函数联接型神经网络
Keywords:
sensor dynamic modeling inverse model dynamic compensation functional link artificial neural network
分类号:
TP212
DOI:
10.3969/j.issn.1001-0505.1999.04.022
摘要:
将函数联接型神经网络(FLANN)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、 精度高, 对数据个数和采样频率无特殊要求.根据“逆模型”的思想, 提出了基于函数联接型神经网络的传感器动态补偿方法.此方法设计出的动态补偿器简单、 实时性好; 不依赖于传感器的模型, 鲁棒性强.
Abstract:
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. 

参考文献/References:

[1] 徐科军.多维腕力传感器时域动态建模.科学通报,1993,38(20):1893~1996
[2] 徐科军,张 颖,江敦明,等.腕力传感器动态特性中关键问题的研究.计量学报,1997,18(4):263~269
[3] 徐科军,张 颖,张崇巍.腕力传感器动态补偿研究.计量学报,1997,18(2):116~121
[4] 殷勤业,杨宗凯.模式识别与神经网络.北京:机械工业出版社,1995.1~50
[5] 黄德双.神经网络模式识别系统理论.北京:电子工业出版社,1996.31~39
[6] Prtra J C,Panda G,Baliarsingh R.Artificial neural network-based nonlinearity estimation of pressure sensors,In:Proceeding of IEEE,1994,63(6):874~881
[7] Prtra J C,Pal R N.A functional link artificial network for adaptive channel equalization.Signal Processing,1995,43:181~195
[8] 沈毅,张建秋,王世忠,等.纸浆浓度传感器非线性估计和动态标定的一种新方法.仪器仪表学报,1997,18(1):1~6

相似文献/References:

[1]黄金彪,童勤义,唐国洪,等.脉宽调制输出的集成真空度传感器[J].东南大学学报(自然科学版),1992,22(3):89.[doi:10.3969/j.issn.1001-0505.1992.03.012]
 Huang Jinbiao,Tong Qinyi,Tang Guohong,et al.An Integrated Vacuum Sensor with Pulse-Width-Modulated Output[J].Journal of Southeast University (Natural Science Edition),1992,22(4):89.[doi:10.3969/j.issn.1001-0505.1992.03.012]
[2]袁红星,贺安之,李振华,等.PSD位置特性与光斑及背景的关系研究[J].东南大学学报(自然科学版),1999,29(2):145.[doi:10.3969/j.issn.1001-0505.1999.02.028]
 Yuan Hongxing,He Anzhi,Li Zhenghua,et al.Relation Study of Position Characteristic of PSD with Lightspot and Background[J].Journal of Southeast University (Natural Science Edition),1999,29(4):145.[doi:10.3969/j.issn.1001-0505.1999.02.028]
[3]沈克强.集成CMOS流量传感器[J].东南大学学报(自然科学版),1995,25(6):62.[doi:10.3969/j.issn.1001-0505.1995.06.012]
 Shen Keqiang.An Integrated CMOS Flow Sensor[J].Journal of Southeast University (Natural Science Edition),1995,25(4):62.[doi:10.3969/j.issn.1001-0505.1995.06.012]
[4]刘国海,苏勇,杨铭,等.基于多准则和高斯过程回归的动态软测量建模方法[J].东南大学学报(自然科学版),2015,45(6):1086.[doi:10.3969/j.issn.1001-0505.2015.06.011]
 Liu Guohai,Su Yong,Yang Ming,et al.Dynamic soft sensor modeling based on multi-criterion method and Gaussian process regression[J].Journal of Southeast University (Natural Science Edition),2015,45(4):1086.[doi:10.3969/j.issn.1001-0505.2015.06.011]

备注/Memo

备注/Memo:
基金项目:国家自然科学基金资助项目(59675085).
第一作者:男,1974年生,博士研究生.
更新日期/Last Update: 1999-07-20