QSCGAN: An Un-Supervised Quick Self-Attention Convolutional GAN for LRE Bearing Fault Diagnosis Under Limited Label-Lacked Data

鉴别器 计算机科学 规范化(社会学) 模式识别(心理学) 断层(地质) 人工智能 分类器(UML) 预言 数据挖掘 探测器 人类学 电信 地质学 社会学 地震学
作者
Wenqing Wan,Shuilong He,Jinglong Chen,Aimin Li,Yong Feng
出处
期刊:IEEE Transactions on Instrumentation and Measurement [Institute of Electrical and Electronics Engineers]
卷期号:70: 1-16 被引量:49
标识
DOI:10.1109/tim.2021.3125973
摘要

For the fault diagnosis of rolling bearings in the liquid rocket engine(LRE), the fault data is scarce due to the high cost of doing experiments, and lacks labels due to the unsure occurrence time of faults. Aiming at the above problem, in this paper, an unsupervised fault diagnosis method based on quick self-attention convolutional generative adversarial network(QSCGAN) is proposed. QSCGAN consists of three convolutional sub-networks: a generator(G), a discriminator(D), and a classifier(C). G-D pair can map the noise distribution to the actual data distribution and then generate raw mechanical signals to enhance the training dataset of C. Finally, well-trained C finishes the task of fault diagnosis. By adding a self-attention layer to D and G, the network acquires a solid ability to mine features of the sample deeply. The spectral normalization (SN) to each layer parameter of G and D improves the stability and the convergence rate of the model. The experimental results on three cases of bearing fault diagnosis(CWRU, SQ, and the data of bearings in liquid rocket engines) evaluate the effectiveness of the proposed method for fault diagnosis under small sample: get average accuracy of 99.73% and 98.74%, 95.47%, respectively. The superiority of the proposed method is showed and discussed via comparing with related researches.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
刚刚
1秒前
斯文败类应助kkkkk采纳,获得10
2秒前
3秒前
hlf完成签到,获得积分10
3秒前
3秒前
洁净灭男完成签到,获得积分10
3秒前
CD56应助黄黄采纳,获得20
5秒前
fx发布了新的文献求助20
5秒前
5秒前
大方笑阳完成签到,获得积分10
5秒前
5秒前
5秒前
6秒前
乐乐应助骑驴找马采纳,获得10
7秒前
7秒前
芹菜煎蛋发布了新的文献求助10
8秒前
9秒前
刘菲清发布了新的文献求助10
10秒前
所所应助细心的语蓉采纳,获得10
11秒前
fx完成签到,获得积分20
11秒前
云珂完成签到,获得积分10
12秒前
洁净斑马发布了新的文献求助10
12秒前
12秒前
bkagyin应助跳跃火车采纳,获得10
12秒前
穆亦擎完成签到 ,获得积分10
12秒前
小强发布了新的文献求助10
12秒前
Akim应助科研通管家采纳,获得30
14秒前
ding应助科研通管家采纳,获得10
14秒前
NexusExplorer应助科研通管家采纳,获得10
14秒前
深情安青应助科研通管家采纳,获得20
14秒前
七七完成签到,获得积分10
14秒前
星辰大海应助科研通管家采纳,获得10
14秒前
wu8577应助科研通管家采纳,获得30
14秒前
星辰大海应助科研通管家采纳,获得10
14秒前
15秒前
奋斗发布了新的文献求助10
15秒前
芹菜煎蛋完成签到,获得积分10
16秒前
隐形曼青应助Camille采纳,获得10
16秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3971441
求助须知:如何正确求助?哪些是违规求助? 3516161
关于积分的说明 11181180
捐赠科研通 3251322
什么是DOI,文献DOI怎么找? 1795788
邀请新用户注册赠送积分活动 876026
科研通“疑难数据库(出版商)”最低求助积分说明 805228