基于BP算法的电站燃气轮机故障诊断

针对传统故障诊断方法在燃气轮机系统中应用的局限性,研究了基于ＢＰ算法的神经网络方法在电站燃气轮机故障诊断中的应用,通过选择足够的故障样本来训练神经网络,将代表故障的信息输入训练的神经网络后,由输出结果,就可以判断发生的故障种类,这样不仅减小了用于诊断的知识库,而且加快了计算速度,满足了实时在线诊断的要求。

GAS TURBINE FAULT DIAGNOSIS BASE ON THE BP ALGORITHM

In this paper, a new effective method of intelligence fault diagnosis was proposed. The fault diagnosis model of gas turbine system was established. The simulation results show that the artificial neural network fault diagnosis is very effective.When symptoms that represents fault is inputted to the trained neural network, the type of fault can be obtained in the output of the neural network. The fault diagnosis model based on this new approach makes fully use of the advantage of artificial neural network, which makes the fault diagnosis rapidly and accurately.