摘要
深度学习算法具有强大的时间序列预测能力以及可实时处理大数据海量样本的优势。针对水轮机系统振动故障诊断存在精度低、漏诊及难预测等问题,提出了一种基于深度学习长短时记忆(long short time memory,简称LSTM)网络结合深度置信网络(deep belief networks,简称DBN)的水轮机系统故障预测方法。将小波包能量带与时频域指标信息相结合,提取高维故障统计特征,利用DBN深层网络的自适应特征提取能力对原始故障数据进行高维特征表示,准确地判断故障种类,并凭借LSTM对时序信号强大的预测能力,预测出未来系统可能发生的振动故障。工程实验验证了该算法的有效性。
Deep learning algorithms have attracted attention due to their powerful time series forecasting capabili⁃ties and the advantages of being able to process massive samples of massive data in real time.Aiming at the prob⁃lems of low accuracy,missing diagnosis,and difficult prediction in the vibration fault diagnosis of hydraulic tur⁃bine systems,a hydraulic turbine system fault prediction method based on deep learning long short time memory(LSTM)networks combined with deep belief networks(DBN)is proposed.This method combines wavelet packet energy bands with time-frequency domain index information to extract high-dimensional fault statistical features,and uses the adaptive feature extraction capabilities of the DBN deep network to perform high-dimen⁃sional feature representations on the original fault data,to more accurately determine the types of faults,and to predict the possible vibration faults of the system in the future with the powerful predictive ability of LSTM on time series signals.The effectiveness of the algorithm is verified by engineering experiments.
作者
罗毅
武博翔
LUO Yi;WU Boxiang(School of Control and Computer Engineering,North China Electric Power University Beijing,102206,China)
出处
《振动．测试与诊断》
EI
CSCD
北大核心
2022年第6期1233-1238,1251,共7页
Journal of Vibration,Measurement & Diagnosis
基金
国家自然科学基金资助项目(52277216)。
关键词
水轮机
深度学习
故障预测
长短期记忆网络
深度置信网络
小波包分解
hydraulic turbine
deep learning
fault prediction
long short time memory networks
deep belief net⁃works
wavelet packet transform
