Gearbox compound fault diagnosis method based on deep adversarial graph convolution transfer learning network under low label ratios

鉴别器 计算机科学 分类器(UML) 人工智能 学习迁移 模式识别(心理学) 深度学习 特征提取 图形 断层(地质) 数据挖掘 理论计算机科学 电信 探测器 地震学 地质学
作者
Xiaojia Kong,Yuanhao Su,Liang Meng,Xiaosheng Lan,Yunfeng Li,Tongle Xu
出处
期刊:Measurement Science and Technology [IOP Publishing]
卷期号:34 (8): 085010-085010 被引量:6
标识
DOI:10.1088/1361-6501/acd13a
摘要

Abstract Advancement in measurement techniques has dramatically contributed to the development of the modern manufacturing industry. As the primary fault causing unplanned downtime of mechanical equipment, gearbox compound faults are usually coupled by single faults with unequal severity and are difficult to obtain. In industrial scenarios, monitoring data for extreme operating conditions is not available in advance, and labeling samples is time-consuming and costly. However, current research on unseen compound fault diagnosis relies on numerous labeled samples to train the model, and few studies are conducted on transfer learning and unseen compound fault diagnosis under low label ratios. To address the issue, a gearbox compound fault diagnosis method based on deep adversarial graph convolution transfer learning network (DAGCTLN) under low label ratios is proposed. Specifically, a novel DAGCTLN model, including a feature extractor, two label classifiers, and a discriminator, is constructed to realize the diagnosis of faults in the transfer domain and unseen compound faults in the source and target domains. The feature extractor of a three-layer graph convolutional network is presented to achieve deep extraction of fault features under low label ratios. Then a domain space adversarial mechanism between the feature extractor and discriminator is used to achieve global alignment of the source and target domain features. Furthermore, two label classifiers are constructed, and the adversarial adaptation of the decision boundary is realized by maxi-min the classifier difference to achieve subdomain alignment of the same class features in all domains. Experimental results indicate that DAGCTLN can achieve the highest fault diagnosis accuracy in the transfer domain compared to state-of-the-art algorithms. The average diagnosis accuracy of compound faults in all domains can reach 98.41% even if the label ratio is only 0.1, which provides guiding significance for the safe operation and predictive maintenance of mechanical equipment.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
脑洞疼应助lewe采纳,获得10
刚刚
1秒前
Anyixx完成签到 ,获得积分10
2秒前
Dale完成签到,获得积分10
3秒前
laoji完成签到,获得积分10
3秒前
研友_8KAOBn发布了新的文献求助10
4秒前
weijiechi完成签到,获得积分10
4秒前
武广敏完成签到,获得积分10
5秒前
浩然发布了新的文献求助10
6秒前
wcuzhl发布了新的文献求助10
6秒前
7秒前
9秒前
风车车发布了新的文献求助10
10秒前
鲜艳的帅哥完成签到,获得积分10
11秒前
16秒前
17秒前
ahxb完成签到,获得积分10
18秒前
HEHNJJ完成签到,获得积分10
18秒前
20秒前
宋宋完成签到,获得积分10
20秒前
TJJ发布了新的文献求助10
20秒前
灵巧荆发布了新的文献求助10
22秒前
22秒前
nihui完成签到 ,获得积分10
22秒前
25秒前
学术混子发布了新的文献求助10
25秒前
orixero应助fandada采纳,获得10
26秒前
认真的灵竹完成签到 ,获得积分10
27秒前
28秒前
lewe发布了新的文献求助10
30秒前
执着的仇血完成签到,获得积分10
30秒前
发嗲的雨筠完成签到,获得积分10
34秒前
汉堡包应助满眼星辰采纳,获得10
35秒前
悦耳傥完成签到 ,获得积分10
35秒前
高高的山兰完成签到 ,获得积分10
35秒前
llj完成签到,获得积分20
35秒前
火星上冥茗完成签到,获得积分10
36秒前
lewe完成签到,获得积分10
36秒前
高分求助中
Thinking Small and Large 500
Algorithmic Mathematics in Machine Learning 500
Advances in Underwater Acoustics, Structural Acoustics, and Computational Methodologies 400
Getting Published in SSCI Journals: 200+ Questions and Answers for Absolute Beginners 300
The Monocyte-to-HDL ratio (MHR) as a prognostic and diagnostic biomarker in Acute Ischemic Stroke: A systematic review with meta-analysis (P9-14.010) 240
The Burge and Minnechaduza Clarendonian mammalian faunas of north-central Nebraska 206
Fatigue of Materials and Structures 200
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 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3831507
求助须知:如何正确求助?哪些是违规求助? 3373721
关于积分的说明 10481076
捐赠科研通 3093686
什么是DOI,文献DOI怎么找? 1702910
邀请新用户注册赠送积分活动 819201
科研通“疑难数据库(出版商)”最低求助积分说明 771307