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...

EMD遗传神经网络方法

DOI: 10.13190/jbupt.201205.68.254, PP. 68-72

Keywords: 经验模态,本征模函数,神经网络,遗传算法

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对BP(backpropagation)神经网络搜索速度慢、容易陷入局部最小的缺陷,提出了经验模态分解(EMD)遗传神经网络方法,首先用对带噪的信号进行分解,得到信号的各阶本征模函数分量,每个本征模函数分量对应着一个能量不同的频段,即一种故障特征,将各频段能量的特征向量作为优化神经网络的输入样本;其次用遗传算法对神经网络的初始权值和阈值进行优化.利用EMD遗传神经网络方法对滚动轴承多类故障信号进行分析,可提高故障识别能力.

References

[1]  Zhou N, Zhu X, Huang Y, et al. Low Complexity Cross-Layer Design with Packet Dependent Scheduling for Heterogeneous Traffic in Multi-user OFDM Systems[J]. Wireless Com IEEE, 2010, 9(6):1912-1923.
[2]  Shen Z K, Andrews J G and Evans L B. Adaptive Resource Allocation in Multi-user OFDM Systems With Proportional Rate Constraints[J]. IEEE Transactions on Wireless Communications, 2005,4(6): 2726-2737.
[3]  Wang J B, Chen H M, Chen M, et al. Cross-layer packet scheduling for downlink multi-user OFDM systems[J].Science in China Series F: Information Sciences,2009, 12(52):2369-2377.
[4]  Li Jian, Wang Cheng. A modified self-adaptive particle swarm optimization[J]. Journal of Huazhong University of Science and Technology: Natural Science Edition, 2008,36(3):118-121.
[5]  Cheng Yongming, Jiang Mingyan. Adaptive resource allocation in multiuser OFDM system based on improved artificial fish swarm algorithm[J]. Application Research of Computers, 2009,26(6): 2092-2094.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133