首页 | 本学科首页   官方微博 | 高级检索  
     

基于WDCNN-SVM深度迁移学习的燃气轮机转子故障诊断方法
引用本文:唐竞鹏,王红军,钟建琳,刘淑聪,张翔,徐伍峰.基于WDCNN-SVM深度迁移学习的燃气轮机转子故障诊断方法[J].电子测量与仪器学报,2021,35(11):115-123.
作者姓名:唐竞鹏  王红军  钟建琳  刘淑聪  张翔  徐伍峰
作者单位:北京信息科技大学机电工程学院 北京 100192;高端装备制造智能感知与控制北京市国际科技合作基地 北京 100192;南京航空航天大学航空学院 南京 210016
基金项目:国家自然科学基金(51975058)项目资助
摘    要:针对在使用深度学习对燃气轮机转子故障诊断过程中,因振动信号样本中正常运行数据多、故障数据少而使得模型故障诊断准确率低的问题,提出了一种采用深度迁移学习对燃气轮机转子进行故障诊断的方法。首先,使用典型行业样本数据集预训练第一层宽卷积核深度卷积神经网络(WDCNN)模型,给予模型初始的权重。其次,在源域中,使用某型燃气轮机试车获得的大量正常运行样本更新WDCNN模型的权重;在目标域中,利用源域训练的卷积层提取燃气轮机的正常和故障数据样本特征,然后使用支持向量机(support vector machines, SVM)进行分类识别,从而达到燃气轮机故障识别的目的。试车数据实验结果表明,该方法能够实现96%的识别准确率,验证了将轴承数据集预训练的深度学习模型迁移到燃气轮机转子领域进行故障诊断的可行性。

关 键 词:燃气轮机转子  振动分析  迁移学习  故障诊断

Gas turbine rotor fault diagnosis method based on WDCNN SVM deep transfer learning
Tang Jingpeng,Wang Hongjun,Zhong Jianlin,Liu Shucong,Zhang Xiang,Xu Wufeng.Gas turbine rotor fault diagnosis method based on WDCNN SVM deep transfer learning[J].Journal of Electronic Measurement and Instrument,2021,35(11):115-123.
Authors:Tang Jingpeng  Wang Hongjun  Zhong Jianlin  Liu Shucong  Zhang Xiang  Xu Wufeng
Affiliation:1.School of Mechanical and Electrical Engineering, Beijing Information Science & Technology University,Beijing 100192, China; 2.Intelligent Perception and Control of High end Equipment Beijing International Science and Technology Cooperation Base, Beijing 100192, China; College of Aerospace Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China
Abstract:In industries for gas turbine rotor, there are a large number of normal operation vibration signal sample data and few fault data,which caused fault diagnosis accuracy lower. A gas turbine rotor deep transfer learning fault diagnosis method is proposed. First, a first layer wide convolutional kernel deep convolutional neural network (WDCNN) model is pre trained with a typical industry sample dataset, obtained the model initial weights. Second, in the source domain, the weights of the WDCNN model are updated using a large number of normal operation samples obtained from the test drive of a certain type of gas turbine; In the target domain, the normal and fault data sample characteristics of the gas turbine are extracted by using the convolutional layer trained in the source domain, and then the support vector machines (SVM) are used for classification identification, so as to achieve the gas turbine fault identification. The experimental results of the test data show that the method identification accuracy is 96%, which verifies the feasibility of migrating the pre trained deep learning model of the bearing dataset to the field of gas turbine rotor for fault diagnosis.
Keywords:gas turbine rotor system  vibration analysis  transfer learning  fault diagnosis
本文献已被 万方数据 等数据库收录!
点击此处可从《电子测量与仪器学报》浏览原始摘要信息
点击此处可从《电子测量与仪器学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号