摘要
为了克服BP算法中存在的网络学习速度慢,以及容易陷入极小的问题,在运用改进遗传算法的基础上,探讨了一种自适应遗传神经网络算法结合模型,并将其应用于汽轮发电机组故障识别。实验数据表明:该算法收敛速度快,能有效地识别故障,具有一定的参考价值。
In order to overcome the problems of slow rate of convergence and falling easily into local minimum in BP algorithm, In this paper the adaptive genetic neural algorithm and combining model are discussed on the using genetic algorithm, The paper applies it to steam turbine - generators fault recognition. The experiment data shows that the algorithm converges quickly and recognize faults efficiently, It has a reference value for faults recognition.
出处
《汽轮机技术》
北大核心
2007年第4期288-291,258,共5页
Turbine Technology
基金
山东省自然科学基金资助(编号:Y2004F15)
关键词
遗传算法
神经网络
故障诊断
汽轮发电机
genetic algorithm
neural network
faults diagnosis
steam turbine generator
