基于贝叶斯网络的水电机组振动故障诊断研究

水电站的状态监测系统积累了大量的监测数据，但由于现场专家缺乏，目前这些数据没有得到很好的利用，如何挖掘这些数据并结合专家经验对水电机组进行故障诊断是本文研究的重点。本文提出了一种基于贝叶斯网络的水电机组振动故障诊断模型。根据专家经验获得贝叶斯网络结构和部分节点参数，通过SOM神经网络对数据信号进行离散化处理，利用EM算法参数学习获得其他节点的概率分布，搭建基于贝叶斯网络的子系统模型，并将子系统模型整合成完整的系统模型。文章最后通过设计试验，验证了所建模型诊断结果的正确性和合理性。

Vibration fault diagnosis for hydro-power units based on Bayesian network

A huge mass of on-site monitor data of hydropower stations has accumulated, but its practical use is quite limited due to lack of on-site experts. How to mine these data and combine with expert experiences in fault diagnosis is our focus. This paper describes a vibration fault diagnosis model for hydropower units based on a Bayesian network that integrates subsystem models constructed through formulating the network structure and certain node parameters using expert experiences, discretizing data signals with a self-organizing map (SOM) neural network, and determining the probability distribution of the rest of the nodes via learning parameters of the expectation-maximization (EM) algorithm. This model is verified by examining the effect and rationality of its diagnosis results in design tests.