RBF网络在发电机状态监测中的应用研究

Application of RBF Network in Monitoring the Condition of Generator

为提高发电机状态异常判别和故障诊断的能力,研究一种状态监测的智能判别方法。设计了一种基于径向基函数神经网络的模型,阐述其网络结构、训练算法及综合决策方法。该模型不仅能利用故障样本及专家经验知识进行状态判别,而且可以不断学习新的样本获取新的知识。经过训练的网络能很好地判别电机状态,仿真结果表明,该网络及决策方法有效,并具有良好的实用价值。

In order to improve the ability of monitoring the condition of generator, an intelligent diagnostic method, which is based on the radial basis function network, is proposed. The network structure, training algorithm and synthetic decision are elucidated. The model not only makes use of fault samples and original expert experience and knowledge, but also acquires new knowledge through continuous learning. After the training of neural network, the generator抯 conditions are diagnosed. Simulation results show that the method is compact, effective and of practical value.