QQ客服 官方微博 反馈留言

	Research on improved FLANN for sensor dynamic modeling
	Wu Dehui ; Zhao Wei ; Huang Songling ; Hao Kuansheng
	2010-10-12 ; 2010-10-12
关键词	Practical Experimental/ difference equations electric sensing devices learning (artificial intelligence) neural nets/ FLANN functional link artificial neural network sensor dynamic modeling single-input single-output sensor dynamic difference equation model partial derivative iterative training/ B7230 Sensing devices and transducers B0290P Differential equations (numerical analysis) C5290 Neural computing techniques C4170 Differential equations (numerical analysis)
中文摘要	An improved functional link artificial neural networks (FLANN) is presented and applied to dynamic modeling for sensor. Firstly, the single-input single-output (SISO) sensor is expressed as a dynamic difference equation model. Secondly, the partial derivatives of the dynamic model output w. r. t its parameter are re-derived and the dependences of the past dynamic model output on the parameters are also considered. Therefore more accurate evaluations of partial derivative of the weight parameters are obtained. Lastly, through iterative training using the novel model gradient, the improved FLANN effectively accelerates the convergence rate and enhances the stability of the network. Experimental results show that the improved FLANN has higher convergence rate and stronger robustness, which is more suitable for sensor dynamic modeling.
语种	中文
出版者	China Publications Center ; China
内容类型	期刊论文
源URL	[http://hdl.handle.net/123456789/82431]
专题	清华大学
推荐引用方式 GB/T 7714	Wu Dehui,Zhao Wei,Huang Songling,et al. Research on improved FLANN for sensor dynamic modeling[J],2010, 2010.
APA	Wu Dehui,Zhao Wei,Huang Songling,&Hao Kuansheng.(2010).Research on improved FLANN for sensor dynamic modeling..
MLA	Wu Dehui,et al."Research on improved FLANN for sensor dynamic modeling".(2010).

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。