摘要
针对轴承故障诊断时振动信号呈现复杂性和混沌特性,故障特征分量容易淹没在噪声之中。引用自适应线性神经网络(Adaptive Linear Neuron,ADALINE)降噪和小波包Shannon熵(Wavelet Packet Analysis Shannon Entropy,WPASE)相结合的方法诊断轴承故障。首先利用ADALINE对不同故障模式的振动信号进行降噪处理,引用小波包理论对降噪后的信号进行小波包分解,计算各层细节信号的Shannon熵值,以此作为不同故障模式的故障特征量。仿真实验表明ADALINE降噪效果明显,Shannon熵能够清楚区别不同的故障模式。该方法简单可靠,为轴承故障诊断提供了新的思路和方法。
Based on many deficiencies that exist in bearing fault of synchronous generator diagnosis ,the signals are easily influenced by the variation of the noise and the signal after fault is nonlinear and chaos. The method via ADALINE and wave- let packet Shannon entropy were introduced. The method of ADLINE was used to wipe out the noise. The different fault mode signals of Shannon entropy were calculated after wavelet packet analysis, and the Shannon entropy was used to distinguish the different bearing fault mode. Experiment results shows this method is useful ,efficient ,and easy to be used in engineering.
出处
《微特电机》
北大核心
2013年第8期36-39,共4页
Small & Special Electrical Machines
