基于概率神经网络的水泵故障诊断研究  

Fault Diagnosis of Water Pump Based on Probabilistic Neural Network

作　　者：李铁军[1] 朱成实[1] 吕营[1] 王丹[1] 王学平[1] 

机构地区：[1]沈阳化工学院机械工程学院,沈阳110142

出　　处：《农机化研究》2008年第3期53-55,共3页Journal of Agricultural Mechanization Research

摘　　要：介绍了概率神经网络(PNN)的基本原理,并将其应用于水泵的故障诊断,以征兆诊断法为理论基础,以信号频谱中各阶倍频和分频作为智能诊断的特征因子,提取故障样本,进行PNN网络训练。结果表明,PNN可以克服反向传播神经网络(BPNN)学习收敛速度慢、易陷入局部极小值等缺点,对传感器测量噪声具有较强的诊断鲁棒性,能够满足故障诊断快速和准确的要求,适用于在线检测,具有实际应用价值。The basic principle of probabilistic neural network （PNN） is introduced; the theory of the neural network is used in the way of the fault diagnosis of it in this paper. The multiple and separated frequency in the spectrum are taken as the characteristic factor, and the sample of the fault is established and the probabilistic neural network neural network is trained based on the symptom diagnosis. The result shows that probabilistic neural network can overcome the local optimization of rate and high diagnosis precision during fault diagnosis the real time diagnosis, and the fault diagnosis based on BPNN and can meet the requirement for fast diagnosis process, so probabilistic neural network can be used in probabilistic neural network is useful.

关 键 词：机械设计 概率神经网络 理论研究 水泵 故障诊断 

分 类 号：TH17[机械工程—机械制造及自动化]