全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于回归神经网络的大跨度结构风压场预测

DOI: 10.13197/j.eeev.2014.05.180.sunfj.023, PP. 180-187

Keywords: 回归神经网络,在线学习,递归预报误差法,大跨度结构,风压场

Full-Text   Cite this paper   Add to My Lib

Abstract:

为提高计算效率并降低存储耗时,提出一种局部回归神经网络方法用来预测大跨度结构风压场。将原有整体优化问题分解为神经元层的子问题进行处理,基于在线学习方法中的递归预报误差法对局部回归神经网络进行训练。首先给出了整体递归预报误差算法,对所有可调权进行同步处理,然后将整体优化问题分解为子问题推导出局部回归神经网络,在更新递归过程中使用二阶信息。将该方法应用于大跨度屋盖的风压预测中,并将计算结果与传统神经网络计算结果进行了比较。结果表明,本文方法的计算误差小,收敛速度快,达到了提高计算效率和降低存储耗时的目的。提出的局部回归神经网络方法为大跨度结构风压场的预测提供了准确高效的方法。

References

[1]  GB 50009-2001建筑结构荷载规范[S].北京:中国标准出版社. GB 50009-2001 Codes of Loads on Building Structures[S]. Beijing: Standard Press of China.(in Chinese)
[2]  顾 明,周?毅.神经网络方法在大跨度屋面风压研究中的应用[J].工程力学, 2003, 20(4): 99-103. GU Ming, ZHOU Xuanyi. Application of neural networks in the prediction of wind load on long-span roofs[J]. Engineering Mechanics, 2003, 20(4): 99-103.(in Chinese)
[3]  傅继阳,谢壮宁,倪振华.大跨度屋盖结构风压分布特性的模糊神经网络预测[J].建筑结构学报,2002, 23(1): 62-67. FU Jiyang, XIE Zhuangning, NI Zhenhua. Prediction of wind load on large span roof using fuzzy neural networks[J]. Journal of Building Structures,2002, 23(1): 62-67.(in Chinese)
[4]  傅继阳,甘 泉.大跨平屋盖结构风压分布特性的神经网络模型[J].华南理工大学学报, 2003, 31(8): 62-66. FU Jiyang, GAN Quan. Nerual network model for wind pressure distribution characteristics of large-span flat roofs[J]. Journal of South China University of Technology, 2003, 31(8): 62-66.(in Chinese)
[5]  丁幼亮,李爱群,杜东升,等.基于神经网络的大跨度空间结构脉动风荷载的随机模拟[J].特种结构, 2006, 23(2): 1-3. DING Youliang, LI Aiqun, DU Dongsheng, et al. Random simulation of fluctuating wind load of large-span roofs based on neural networks[J]. Special Structures, 2006, 23(2): 1-3.(in Chinese)
[6]  Williams RJ, Peng J. An efficient gradient-based algorithm for on-line training of recurrent network trajectories[J]. Neural Computer, 1990,2(4):490-501.
[7]  Parlos AG, Chong KT, Atiya AF. Application of the recurrent multilayer perceptron in modeling complex process dynamics[J]. IEEE Trans. Neural Networks, 1994,5(2): 255-266.
[8]  Puskorius GV, Feldkamp LA. Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks[J].IEEE Trans. Neural Networks,1994,5(2):279-297.
[9]  Zhang Yi. Foundations of implementing the competitive layer model by Lotka-Volterra recurrent neural networks[J]. IEEE Transactions on Neural Networks, 2010,21(3): 494-507.
[10]  Zhou Wei, Zurada J M. Competitive layer model of discrete time recurrent neural networks with LT neurons[J]. Neural Computation, 2010,22:2137-2160.
[11]  Feng DZ, Zheng WX, Jia Y, Neural network learning algorithm for tracking minor subspace in high-dimensional data stream[J]. IEEE Transactions on Neural Networks,2005,16(3):513-521.
[12]  Kirk David B, Hwu, Wen mei W. Applications of GPU computing series, Programming massively parallel processors: a hands-on approach[M]. Morgan Kaufmann, 2010.
[13]  Campolucci P, Uncini A, Piazza F, et al. On-line learning algorithms for locally recurrent neural networks[J]. IEEE Trans. Neural Networks, 1999(10):253-271.
[14]  Puskorius GV, Feldkamp LA.Recurrent network training with the decoupled Extended Kalman Filter Algorithm[C]// in Proceedings of the 1992 SPIE Conference on the Science of Artificial Neural Networks, Orlando 1992(1710):461-473.
[15]  Puskorius GV, Feldkamp LA. Model reference adaptive control with recurrent networks trained by the dynamic DEKF algorithm[C]// in International Joint Conference on Neural Networks, Baltimore II, 1992, 106-113.
[16]  Puskorius GV, Feldkamp LA, Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks[J]. IEEE Trans. Neural Networks,1994,5(2):279-297.
[17]  Abdelbaki Djouambi, Alina Voda, Abdelfatah Charef, Recursive prediction error identification of fractional order models[J].Communications in Nonlinear Science and Numerical Simulation, 2012,17(6): 2517-2524.
[18]  Frasconi P, Gori M, Soda G. Local feedback multilayered networks[J]. Neural Computation, 1992, 4(1): 120-130.
[19]  王吉民. 薄膜结构的风振响应分析和风洞试验研究[D]. 杭州:浙江大学, 2001. WANG Jimin. Wind-induced response analysis and study on wind tunnel exprement of membrane structures[D].Hangzhou:zhejiang University,2001.(in Chinese)

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133