[1]潘继财.大数据样本与半监督环境下基于生成对抗网络的故障诊断[J].机械与电子,2021,(05):20-25.
　PAN Jicai.Large Data Samples and Fault Diagnosis Based on Generation Countermeasure Network in Semi-supervised Environment[J].Machinery & Electronics,2021,(05):20-25.
点击复制

大数据样本与半监督环境下基于生成对抗网络的故障诊断()
分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2021年05期
页码:
20-25
栏目:
设计与研究
出版日期:
2021-05-24

文章信息/Info

Title:
Large Data Samples and Fault Diagnosis Based on Generation Countermeasure Network in Semi-supervised Environment
文章编号:
１００１-２２５７ ( ２０２１ ) ０５-００２０-０６
作者:
潘继财
中国科学技术信息研究所,北京 １０００３８
Author(s):
PAN Jicai
(Institute of Scientific and Technical Information of China, Beijing １０００３８,China)
关键词:
大数据样本; 半监督; 生成对抗网络; 梯度函数; 分类诊断
Keywords:
big data sample; semi-supervision ;  generation countermeasure network; gradient function; classification diagnosis
分类号:
TH１７; TP１８１
文献标志码:
A
摘要:
在大故障样本条件下,提出一种基于生成对抗网络模型的故障诊断方法研究.构建生成对抗网络模型,保证模型判别器输出数据的总体分布与原始故障集趋同,并基于空间测量工具对梯度函数进行优化,降低损失;采用故障集图像转换方式实现对原始信号的降维处理,利用判别器的神经网络结构训练输入数据,并提取出机械故障数据集中的故障特征点.实验结果表明,提出方法具有良好的分类诊断性能,故障诊断精度能够达到９９．４５％.
Abstract:
Under the condition of large fault samples,a fault diagnosis method based on the generation countermeasure network model is proposed．The model of generating countermeasure network is constructed to ensure that the overall distribution of output data of model discriminator is similar to the original fault set, and the gradient function is lost based on the spatial measurement tool; the method of fault set image conversion is used to realize the dimensionality reduction of the original signal,and the neural network structure of discriminator is used to train the input data and extract the fault features of the mechanical fault data set．The experimental results show that the proposed method has good performance of classification and diagnosis, and the accuracy of fault diagnosis can reach ９９．４５％．

参考文献/References:

[１] 么子云,汪成文,车煜全,等．往复机械连杆轴承磨损故障仿真与实验研究[J]．机械强度,２０１８,４０(２):２５５-２６０．

[２] 郭煜敬,陈士刚,李少华,等．基于经验模态分解及支持向量机的高压隔离开关机械故障诊断方法[J]．高压电器,２０１８,５４(９):１２-１８．
[３] 汪崔洋,江全元,唐雅洁,等．基于告警信号文本挖掘的电力调度故障诊断[J]．电力自动化设备,２０１９,３９(４):１２６-１３２．
[４] 林江刚,胡正新,李晶,等．低转速下基于AE信号与LMD的滚动轴承故障诊断[J]．动力工程学报,２０１９,３９(４):２９３-２９８．
[５] 胡轲珽,刘志刚,胡冉冉,等．一种新型基于模型的动车组牵引逆变器开路故障诊断方法[J]．铁道学报,２０１８,４０(２):３１-３８．
[６] 陈奇,姚志刚,陈无畏,等．基于模型的液力变矩器故障诊断系统的设计与校验[J]．汽车工程,２０１８,４０(１０):１２４６-１２５３．
[７] ZHANG H D,AHMED F,DOU Z．Fault diagnosis and life prediction of mechanical equipment based on artificial intelligence[J]． Journal of intelligent and fuzzy systems,２０１ ,３７(１２):３５３５-３５４４．
[８] 李梦诗,余达,陈子明,等．基于深度置信网络的风力发电机故障诊断方法[J]．电机与控制学报,２０１９,２３(２):１１４-１２２．
[９] 侯荣涛,周子贤,赵晓平,等．基于堆叠稀疏自编码的滚动轴承故障诊断[J]．轴承,２０１８(３):４９-５４,６０．
[１０] 王珂,吕勇,易灿灿．压缩感知框架下的共振解调故障诊断方法[J]．中国机械工程,２０１８,２９(１ ):１９０７-１９１１．
[１１] 李宗民,徐希云,刘玉杰,等．条件随机场像素建模与深度特征融合的目标区域分割算法[J]．计算机辅助设计与图形学学报,２０１８,３０(６):１０００-１００７．
[１２] 邓芳明,温开云,何怡刚,等．基于RFID传感标签及QPSO-RVM的变压器绕组故障在线诊断技术[J].中国电机工程学报,２０１８,３８(２４):７１８３-７１９３．
[１３] 王昆,周骅．深度学习中的卷积神经网络系统设计及硬件实现[J]．电子技术应用,２０１８,４４(５):５６-５９．
[１４] SINGARAVEL S,SUYKENS J,GEYER P．Deep learning neural network architectures and methods:Using component-based models inbuilding-design energy prediction[J]．Advanced engineering informatics,２０１８,３８:８１-９０．
[１５] GATOS I,TSANTIS S,SPILIOPOULOS S,et al．Temporal stability assessment in shear wave elasticity images validated by deep learning neural network for chronic liver disease fibrosis stage assessment[J]．Medical physics,２０１９,４６(５):２２９８-２３０９．

备注/Memo

备注/Memo:
收稿日期:２０２０-１２-２９
基金项目:国家重点研发计划(２０１８YFB１４０３５０２)
作者简介:潘继财(１９６３－),男,吉林扶余人,高级工程师,研究方向为数字资源管理、科技咨询和数字出版等.
更新日期/Last Update: 2021-05-26