基于小波和神经网络的风机故障诊断系统设计

本文在LabVIEW平台下,设计了一种基于小波和神经网络的风机故障在线诊断系统。以风机产生的噪声为诊断依据,用噪声信号的功率谱重心、A声级、小波分解后相关频段的能量构成故障诊断的特征向量,以BP网络作为故障的智能分类器,建立起智能诊断系统。实验结果表明,采用小波和神经网络相融合的诊断与识别技术,是提取风机故障特征,进行状态识别的一种有效方法。所设计系统有较强的学习能力和容错能力。诊断结果比较可靠、准确。

Design of a fan fault diagnosis system based on wavelet and neural network

An online fan fault diagnosis system is proposed based on wavelet and neural network,and developed on the LabVIEW platform.Relying on the noise sig- nal from the fan,the recognition system utilizes power spectrum gravity center, sound level,wavelet frequency segment power of the signal as feature vectors,and a BP network as classifier for fault diagnosis.The experimental results show that it is effective to extract fault information by the combination of wavelet and neural net- work.The entire system has adaptability and fault-tolerant capability.