基于信息融合的集成小波神经网络故障诊断

Integrated Wavelet Neural Networks in Fault Diagnosis Based on Information Fusion

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 ,建立了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了各种特征信息 ,可以有效提高确诊率·

The tight wavelet neural network was constituted taking the nonlinear Morlet wavelet radices 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 information fusion technology and actual fault diagnosis. The system takes the sub-wavelet neural network as primary diagnosis from different sides, and then gains the conclusions through decision-making fusion. The realizable policy of the diagnosis system and established principle of the sub-wavelet neural networks were given. The system takes full advantage of diversified characteristic information, and improves diagnosis rate.