[1]俞阿龙,黄惟一.基于改进遗传神经网络的微硅加速度传感器动态补偿研究[J].东南大学学报(自然科学版),2004,34(4):455-458.[doi:10.3969/j.issn.1001-0505.2004.04.008]
 Yu Along,Huang Weiyi.Study on dynamic compensation method based on improved genetic neural network for micro-silicon accelerometer[J].Journal of Southeast University (Natural Science Edition),2004,34(4):455-458.[doi:10.3969/j.issn.1001-0505.2004.04.008]
点击复制

基于改进遗传神经网络的微硅加速度传感器动态补偿研究()
分享到:

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

卷:
34
期数:
2004年第4期
页码:
455-458
栏目:
自动化
出版日期:
2004-07-20

文章信息/Info

Title:
Study on dynamic compensation method based on improved genetic neural network for micro-silicon accelerometer
作者:
俞阿龙 黄惟一
东南大学仪器科学与工程系, 南京 210096
Author(s):
Yu Along Huang Weiyi
Department of Instrument Science and Technology, Southeast University, Nanjing 210096, China
关键词:
微硅加速度传感器 函数连接型神经网络 动态补偿 遗传算法
Keywords:
micro-silicon accelerometer functional link neural network dynamic compensation genetic algorithm
分类号:
TP212.6
DOI:
10.3969/j.issn.1001-0505.2004.04.008
摘要:
比较遗传算法与神经网络的特点, 并对将遗传算法用于函数连接型神经网络(FLNN)的优点进行了研究.对遗传算法的编码方法、交换和变异操作做了改进,提出了一种融合改进遗传算法的FLNN用于微硅加速度传感器动态性能补偿的新方法.该方法不依赖于传感器的动态模型, 可根据传感器的动态响应数据, 建立补偿模型,采用改进遗传神经网络搜索和优化补偿模型参数,既保留了遗传算法的全局搜索能力,又具有神经网络的鲁棒性和自学习能力.介绍补偿原理及算法, 给出动态补偿网络的数学模型.结果表明, 该补偿方法能克服FLNN收敛速度慢、容易陷入局部极小的缺陷,具有网络训练速度快、实时性好、良好的全局搜索能力、精度高、鲁棒性好及动态补偿器实现简单等优点.
Abstract:
The characteristics of neural networks(NN)and genetic algorithm(GA)are described. The advantages of the application of genetic algorithm to the functional link neural networks(FLNN)are discussed. The coding method and the operator of crossover and mutation for GA is improved. A kind of neural networks compensation method is proposed in which genetic algorithm and neural networks are mixed for micro-silicon accelerometer. In this method, a dynamic compensation model can be set up according to measurement data of dynamic response of micro-silicon accelerometer without knowing its dynamic model. The dynamic compensation model parameters are trained by improved genetic neural network. So the method remains both the global searching ability of GA and the robustness and self-learning ability of NN. The compensation principle and algorithms are introduced and the mathematical model is founded. The results show that the proposed new dynamic compensation method can overcome the shortcomings of FLNN, such as the slow speed in training and easy convergence to the local minimum points, and has the advantages of fast training process, good real time, good global searching ability, high precision, strong robustness and easy realization of dynamic compensation device.

参考文献/References:

[1] 才海男,周兆英,李勇,等.加速度传感器的动态特性软件补偿方法研究 [J].仪器仪表学报,1998,19(3):263-267.
  Cai Hainan,Zhou Zhaoying,Li Yong,et al.A study on software compensation method of accelerometer’s dynamic characteristics [J].Chinese Journal of Scientific Instrument,1998,19(3):263-267.(in Chinese)
[2] 陈俊杰,卢俊,黄惟一.基于遗传神经网络的传感器系统的非线性校正[J].仪器仪表学报,2003,24(2):201-204.
  Chen Junjie,Lu Jun,Huang Weiyi.Non-linearity rectification of sensor systems based on genetic neural network [J].Chinese Journal of Scientific Instrument, 2003,24(2):201-204.(in Chinese)
[3] Brignell J B. Software techniques for sensor compensation [J]. Sensors & Actuators, 1991,A25(27):37-41.
[4] 徐科军,殷铭.基于FLANN的腕力传感器动态补偿方法[J].仪器仪表学报,1999,20(5):511-514.
  Xu Kejun,Yin Ming.A dynamic compensating method based on FLANN for wrist force sensor [J]. Chinese Journal of Scientific Instrument, 1999,20(5):511-514.(in Chinese)
[5] Prtra J C, Pal R N.A functional link artificial neural network for adaptive channel equalization [J].Signal Processing, 1995,43(2):181-195.
[6] Prtra J C. An artificial neural network based smart capacitive pressure sensor [J]. Measurement,1997,22(3,4):113-121.
[7] Prtra J C, Panda G,Baliarsingh R.Artificial neural network based non-linearity estimation of pressure sensors[J].IEEE Trans Instru Meas,1994,63(6):874-881.
[8] 钟颖,汪秉文.基于遗传算法的BP神经网络时间序列预测模型[J].系统工程与电子技术,2002,24(4):9-11.
  Zhong Ying,Wang Bingwen.BP network sequence prediction based on genetic algorithm [J].Systems Engineering and Electronics, 2002,24(4):9-11.(in Chinese)
[9] 刘清. 神经网络和遗传算法相结合实现非线性传感特性的线性化 [J].南京师范大学学报.2002,2(3):11-15.
  Liu Qing.Linearization of sensor’s non-linearity by using genetic algorithm and neural network [J].Journal of Nanjing Normal University,2002,2(3):11-15.(in Chinese)
[10] 禹东川.压力传感器动态性能分析与动态补偿[J].中国仪器仪表,2003(7):9-11.
  Yu Dongchuan.Analysis and calibration for dynamic characteristic of the pressure sensor [J].China Instrumentation, 2003(7):9-11.(in Chinese)

备注/Memo

备注/Memo:
作者简介: 俞阿龙(1964—),男,博士生,副教授; 黄惟一(联系人),男,教授,博士生导师,hhwy@seu.edu.cn.
更新日期/Last Update: 2004-07-20