摘要
研究了一种基于深度置信网络的故障诊断方法,主要应用于针对航空发电机旋转整流器所进行的故障诊断中,对方法进行了仿真及实际实验验证。采集主励磁机励磁电流作为故障诊断所使用的有效信号,对所采集到的励磁电流信号进行快速傅里叶变换以获取其频域信息,将所得到的频域数据分为训练样本和测试样本输入至深度置信网络中进行故障分类,计算诊断正确率并做出分析。实验证明,所提出的方法具有良好的故障分类效果。
This paper studied on a fault diagnosis method of rotating rectifier of aircraft generator based on deep belief network,the results of the simulation and physical experiments were shown. First,filed current of the main exciter was collected. Second,the acquired excitation current signal is subjected to fast Fourier transform to obtain its frequency domain information. Then the obtained data is divided into train samples and test samples to be the input of a deep belief network for fault classification,and calculate diagnostic accuracy. The experiments show that the method proposed in this paper has good fault classification effect.
作者
孟飒飒
孔德明
崔江
师鸽
MENG Sa-sa;KONG De-ruing;CUI Jiang;SHI Ge(College of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China)
出处
《航空计算技术》
2018年第4期105-108,111,共5页
Aeronautical Computing Technique
基金
中央高校基本科研业务费项目资助(NS2017019)
关键词
无刷同步发电机
旋转整流器
深度置信网络
故障诊断
深度学习
brushless synchronous generator
rotating rectifier
deep belief network
fault detection
deeplearning
