摘要
深度学习具有强大的学习能力和特征分类能力,能够在海量、多源和高维测量数据中进行特征提取,具有不依赖人工干预而进行模型诊断和泛化的能力,广泛应用于设备故障诊断领域。阐述了深度学习的典型模型:深度置信网络(DBN)、卷积神经网络(CNN)和自编码器(AE),重点论述了深度学习在轴承故障诊断领域的应用进展。最后讨论了深度学习在轴承故障诊断领域所存在的问题及发展趋势。
With strong learning ability,feature classification ability,and generalization capabilities,deep learning could be used in the feature extraction and model diagnosis based on massive,multi-source and high-dimensional measurement data,with no reliance on human intervention,and it can be widely used in the field of equipment fault diagnosis.The typical models of deep learning:deep belief network(DBN),convolutional neural network(CNN)and automatic encoders(AE)were described,and the application progress of deep learning in bearing fault diagnosis was emphasized.Finally,the problems and development trends of deep learning in the field of bearing fault diagnosis were discussed.
作者
洪腾蛟
丁凤娟
王鹏
冯定
凃忆柳
HONG Teng-jiao;DING Feng-juan;WANG Peng;FENG Ding;TU Yi-liu(School of Mechanical Engineering, Yangtze University, Jingzhou 434023, China;Hubei Engineering Research Center for Oil & Gas Drilling and Completion Tools, Jingzhou 434023, China;College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China)
出处
《科学技术与工程》
北大核心
2021年第22期9203-9211,共9页
Science Technology and Engineering
基金
国家科技重大专项(2016ZX05038-002-LH001)
湖北省中央引导地方科技发展专项(2017ZYYD006)
湖北省技术创新专项(2019AAA010)
中海石油(中国)有限公司湛江分公司项目(CCL2017ZJFN2272)。
关键词
深度学习
故障诊断
神经网络
发展趋势
轴承
deep learning
fault diagnosis
neural network
development trend
bearing