节点文献

集成小波神经网络在故障诊断中的应用研究

Study on Application of Integrated Wavelet Neural Networks in Fault Diagnosis

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 张松鹤罗跃纲闻邦椿

【Author】 ZHANG Song-he~1 LUO Yue-gang~(1,2) WEN Bang-chun~2 (1.Dalian Nationalities University,Dalian Liaoning 116600,China; 2.Northeastern University,Shenyang 110004,China)

【机构】 大连民族学院力学基础实验中心东北大学 辽宁大连116600辽宁大连116600东北大学沈阳110004

【摘要】 以非线性Morlet小波基作为激励函数,形成神经元,结合小波变换与神经网络各自的优点,建立集小波分析与神经网络于一体的紧致型小波神经网络,并给出了具体的算法。基于信息融合技术的思想,从设备故障诊断的实际出发,建立了基于信息融合技术的集成小波神经网络故障诊断系统,即通过故障特征信息的有效组合,用各种子小波神经网络从不同侧面对设备故障进行初步诊断,然后对诊断结果进行决策融合。给出了系统的实现策略和子网络的组建原则。从诊断实例中可以看出,此诊断系统充分利用各种特征信息,可以有效的提高确诊率。

【Abstract】 The tight wavelet neural network was constituted taking the nonlinear Morlet wavelet radi- ces as the stimulant function.The idiographic algorithm was presented.It can combine the advantages of wavelet analysis and neural networks.The integrated wavelet neural network fault diagnosis system was set up based on both the information fusion technology and actual fault diagnosis,which taking the sub- wavelet neural network as primary diagnosis from different sides,then gained the conclusions through de- cision-making fusion.The realizable policy of the diagnosis system and established principle of the sub- wavelet neural networks were given in the paper.It can be educed from the examples that it takes full ad- vantage of diversified characteristic information,and improves the diagnosis rate.

【基金】 国家自然科学基金(50275024)
  • 【文献出处】 噪声与振动控制 ,Noise and Vibration Control , 编辑部邮箱 ,2007年06期
  • 【分类号】TP183
  • 【被引频次】12
  • 【下载频次】202
节点文献中: 

本文链接的文献网络图示:

本文的引文网络