矢功率谱与概率神经网络结合在旋转机械故障诊断中的应用研究

Vector power spectrum and probabilistic neural networks applied to rotating equipment fault diagnosis

与传统功率谱相比,矢功率谱融合了多通道的能量信息,反映的信息更全面,而概率神经网络学习速度快、收敛性好,基于此,结合矢功率谱和概率神经网络,提出一种故障诊断的新方法,该方法是以矢功率谱作为特征输入到概率神经网络分类器进行故障识别,并应用到旋转机械故障诊断中。实验结果表明,该方法是有效的。

Compared with the traditional power spectrum, the vector power spectrum can fuse the power information from different channels,and reflect more comprehensive information. The Probabilistic Neural Networks（PNN） has high studying rate and good convergence and so on. Here, combining vector power spectrum and PNN, a new fault diagnosis approach is proposed, this approach is that the vector power spectrum is used as eigenvectors, PNN as a elassifier. The proposed approach has been successfully applied to the fault diagnosis of rotating machinery. The experiment result shows that the proposed approach is very effective.