期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于遗传算法的小波神经网络研究及应用 被引量：9

Research and application of wavelet neural network based on genetic algorithm
在线阅读 下载PDF
导出
摘要 目的为改进小波神经网络算法的缺陷。方法当网络的输出层节点的输出值与1之差或输出层节点输出值小于等于设定的阈值,使用变系数法调整输出层的误差,然后再利用遗传算法优化小波网络的参数。结果在齿轮箱故障诊断中,变系数法有效地防止了误差无法逆向传播下去,使网络失去学习能力。然而,通过遗传算法的全局优化搜索能力得到网络的最优参数,从而避免了网络陷入局部最小。结论提出的基于遗传算法的小波神经网络即提高网络的诊断精度,又加快了其收敛速度。 Aim To improve the flaw of WNN. Methods Variable-coefficient method is used to adjust the output layer＇s error of WNN, when the values of output layer nodes are less than or equal to threshold, and genetic algorithm is adopted to get the best parameters of WNN. Results In the process of gearbox fault diagnosis, the variable-coefficient method effectively prevents the influence that output layer＇s error can not be transmitted back to the hidden layers and the WNN loses the ability of learning. By the performance of global optimum searching of the genetic algorithm, the network can avoid falling into the local minimums in studying. Conclusion The novel algorithm of WNN not only improves its fault diagnosis precision, but also accelerates rate of convergence.
作者 胡新辉 陈莉
机构地区 西北大学信息科学与技术学院
出处 《西北大学学报（自然科学版）》 CAS CSCD 北大核心 2009年第2期203-207,共5页 Journal of Northwest University（Natural Science Edition）
基金 陕西省自然科学基金资助项目(98X11) 陕西省教育厅重点科研计划基金资助项目(00JK015)
关键词 小波分析 小波神经网络(WNN) 变系数法 WNNGA 遗传算法 故障分析 wavelet analysis wavelet neural networks variable-coefficient WNNGA GA fault diagnosis
分类号 TP183 [自动化与计算机技术—控制理论与控制工程]
作者简介 胡新辉，男，陕西西安人，从事数据挖掘及小波神经网络研究。
  • 相关文献

参考文献10

  • 1BASHIR Z, El-HAWARY M E. Short term load forecasting by using wavelet neural networks [ C ]//Proc of the IEEE Conference on Electrical and Computer Engineering. Piscataway : IEEE, 2000 : 163-166.
  • 2LI Sheng-tun, CHEN Shu-ching. Function approximation using robust wavelet neural networks [ C ]//Proc of the 14th IEEE International Conference on Tools with Artificial Intelligence. Los Alamitos: IEEE Comput Soc, 2002 : 483-488.
  • 3ZHANG Q, BENVENISE A. Wavelet networks [ J ]. Proc IEEE Trans on Neural Network, 1992, 3(6) :889-898.
  • 4DELYON B, JUDILSKY A, BENVENISIE A. Accuracy analysis for wavelet approximations [J]. IEEE Trans on Neural Network,1995,6(2) :332-348.
  • 5CHEN Z, FENG T J, MENG Q C. The application of wavelet neural network in time series prediction and system modeling based on mutiresolution learning [ J ]. IEEE Conference on Systems Man and Cybernetics, 1999, ( 1 ) : 425-430.
  • 6SRINIVAS M, PATNAIK L M. Adaptive probabilities of crossover and mutation in genetic algorithms [ J ]. IEEE Trans on Systems, Man, & Cybernetics, 1994, 24(4) : 656-665.
  • 7TABARAKI R, KHAYAMIAN T, ENSAFI A A. Wavelet neural network modeling in QSPR for prediction of solubility of 25 anthraquinone dyes at different temperatures and pressures in supercritical carbon dioxide [ J ]. Journal of Molecular Graphics and Modelling,2006,25:46-54.
  • 8Yin Shirong Chen Guangju Xie Yongle.Wavelet neural network based fault diagnosis in nonlinear analog circuits[J].Journal of Systems Engineering and Electronics,2006,17(3):521-526. 被引量：16
  • 9吴新根,葛家理.关于BP算法的初步研究[J].小型微型计算机系统,1994,15(1):42-45. 被引量：5
  • 10HA1 Ning-meng, YONG Qi, DI Hou, et al. Liang Liu Software Aging Forecasting Model of Service-oriented Application Server Based on Wavelet Network with Adaptive Genetic Algorithm [ C ]//Proc of third International Conference on Natural Computation. Haikou: IEEE Comput Soc ,2007:353-357.

二级参考文献8

  • 1Burdiek B.The qualitative form of optimum transient test signals for analog circuits derived from control theory methods.Proc of IEEE International Symposium on Circuits and Systems,2002,1:157 ～160.
  • 2Taylor D,Platts A.Transient response testing of nonlinear analogue circuits using optimized fault sets.IEE Proceedings on Circuits Device System,2003,150(2):101～112.
  • 3Cesare Alippi,Marcantonio Catelani,Ada Fort,et al.SBT soft fault diagnosis in analog electronic circuits:a sensitivity-based approach by randomized algorithms.IEEE Trans on Instrumentation and Measurement,2002,51(5):1116～1125.
  • 4Martin Hagan T.Backpropagation.Neural network design.Beijing:China Machinary Press,2002.
  • 5Stopjakova V,Micusik D,L' Benuskova,et al.Neural networks-based parametric testing of analog IC.Proc.of IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems,2002:408～416.
  • 6Zhang Xuegong.Select and extract signature.Bian Zhaoqi:Pattern identification.Beijing:Tsinghua Press,2000:176～198.
  • 7Leopoldo Angrisani,Pasquale Daponte,Massimo D'Apuzzo.Wavelet network-based detection and classification of transients.IEEE Trans.on Instrumentation and Measurement,2001,50(5):1425～1435.
  • 8Kondagunturi R,Bradley E,Maggard K,et al.Benchmark circuits for analog and mixed-signal testing.Southeastcon Proceedings,IEEE,1999:217～220.

共引文献19

同被引文献74

引证文献9

二级引证文献56

西北大学学报（自然科学版）
2009年 第2期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
关于我们 | 版权声明 | 联系我们 | 帮助中心| 意见反馈
主办单位：上海市教育委员会
技术支持：重庆维普资讯有限公司
渝公网安备 50019002500403号
使用帮助 返回顶部