一种改进型BP网络算法在凝汽器故障诊断中的应用  

Application of An Improved BP Net Calculation to the Fault Diagnosis of Condensers

作　　者：石永恒[1] 陈荣生[2] 杨亚平[1] 

机构地区：[1]东南大学热能工程研究所,江苏南京210096 [2]福建泉州电力学校,福建泉州362000

出　　处：《电站辅机》2006年第1期15-19,共5页Power Station Auxiliary Equipment

摘　　要：针对BP网络学习收敛速度慢和易陷入局部最小点的不足,提出了一种自适应学习速率动量梯度下降反向传播算法对BP神经网络进行训练。该算法使BP神经网络在学习速率和稳定性上有了进一步的提高。并将这种改进的BP网络算法应用于凝汽设备故障诊断实例中取得了实效。A reverse transmission calculation of self adapting learning rate with momentum gradient reduction is described in the paper against the problems of slow convergence and easy trapping into smallest spot. The calculation has made the BP net upgrade the rate and stability of learning, which has made an effective fault diagnosis of condensers.

关 键 词：凝汽器 故障诊断 BP神经网络 

分 类 号：TM621[电气工程—电力系统及自动化]