基于非线性主元分析和概率神经网络的凝汽器故障诊断方法研究

该文提出了一种基于两个神经网络的凝汽器故障诊断方法.首先使用非线性主元分析神经网络进行特征提取,降低数据维数,既简化了诊断过程,又确保故障诊断精度.随后使用概率神经网络获取最终的故障诊断结果,该神经网络训练速度快,而且容易添加新的训练样本.最后将提出的方法用于某汽轮机组凝汽器故障诊断中,测试结果表明该方法行之有效,且易于工程实现.

RESEARCH ON FAULT DIAGNOSIS OF CONDENSER VIA NONLINEAR PRINCIPAL COMPONENT ANALYSIS AND PROBABILISTIC NEURAL NETWORKS

An approach to diagnosing the faults in a condenser via two neural networks is presented in this paper.At first,the nonlinear principal component analysis neural networks(PCANN) is employed to extract main features from high dimension patterns.Not only is the diagnosing process simplified but also the diagnosing accuracy is ensured.Consequently,the probabilistic neural networks(PNN) is utilized to obtain the final diagnosed results.PNN can be trained quickly;moreover,the new trained samples can be added to PNN easily.Finally,the proposed scheme is applied to diagnose the faults in a condenser of a turbine unit,the diagnosis results show that it is effective and easy to be put into practice.