Meta-Learning With Distributional Similarity Preference for Few-Shot Fault Diagnosis Under Varying Working Conditions

计算机科学 人工智能 机器学习 加权 相似性(几何) 稳健性(进化) 一般化 任务(项目管理) 融合机制 数据挖掘 数学 工程类 放射科 图像(数学) 基因 生物 脂质双层融合 病毒学 系统工程 病毒 化学 生物化学 数学分析 医学
作者
Chao Ren,Bin Jiang,Ningyun Lu,Silvio Simani,Furong Gao
出处
期刊:IEEE transactions on cybernetics [Institute of Electrical and Electronics Engineers]
卷期号:54 (5): 2746-2756 被引量:2
标识
DOI:10.1109/tcyb.2023.3338768
摘要

Few-shot fault diagnosis is a challenging problem for complex engineering systems due to the shortage of enough annotated failure samples. This problem is increased by varying working conditions that are commonly encountered in real-world systems. Meta-learning is a promising strategy to solve this point, open issues remain unresolved in practical applications, such as domain adaptation, domain generalization, etc. This article attempts to improve domain adaptation and generalization by focusing on the distribution-shift robustness of meta-learning from the task generation perspective. In fact, few-shot fault diagnosis under varying working conditions allows to address the distribution shift problem in a natural way. An unsupervised across-tasks meta-learning strategy with distributional similarity preference is proposed, where the core is the distribution-distance-weighting mechanism. Differently from the naive random meta-train task generation strategy used in existing meta-learning methods, the source instances that present a more similar distribution with respect to the target instances gain larger weightings in the task generation. This strategy leads to a meta-task training set that is enough diverse, and at the same time can be easily learned due to the distribution similarity features of the source tasks. The proposed method introduces the concept of maximum mean discrepancy that is applied to derive the distribution distance of the measurements. Moreover, a model-agnostic meta-learning is applied to realize few-shot fault diagnosis under varying working conditions. The proposed solutions are verified and compared by considering two public datasets used for bearing fault diagnosis. The results show that the proposed strategy outperforms different related few-shot fault diagnosis methods under varying working conditions. Moreover, it is thus proved that, meta-learning with distribution similarity feature represents an effective approach for domain adaptation and generalization.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
淡紫珊瑚完成签到 ,获得积分20
刚刚
啦啦咔嘞完成签到,获得积分10
1秒前
2秒前
Orange应助水娃采纳,获得10
3秒前
布通发布了新的文献求助10
3秒前
4秒前
Hao发布了新的文献求助10
5秒前
甜蜜浩然完成签到,获得积分10
5秒前
杨宇彤发布了新的文献求助10
5秒前
研通芳完成签到,获得积分10
5秒前
燚一发布了新的文献求助20
5秒前
5秒前
香蕉觅云应助sulh采纳,获得10
6秒前
6秒前
未解的波发布了新的文献求助10
7秒前
mxzan完成签到,获得积分10
8秒前
332535完成签到 ,获得积分10
8秒前
9秒前
淡紫珊瑚关注了科研通微信公众号
10秒前
爆米花应助枯木逢春采纳,获得10
10秒前
10秒前
小杜发布了新的文献求助10
11秒前
13秒前
欣慰完成签到,获得积分20
13秒前
13秒前
15秒前
Riggle G完成签到,获得积分10
15秒前
16秒前
16秒前
水娃发布了新的文献求助10
17秒前
finoa完成签到,获得积分10
18秒前
Coffey完成签到 ,获得积分10
18秒前
。。。。。。完成签到,获得积分10
18秒前
深情安青应助未解的波采纳,获得10
19秒前
小杜完成签到,获得积分10
19秒前
20秒前
梁超完成签到,获得积分10
20秒前
20秒前
cnx完成签到,获得积分10
21秒前
宋佳发布了新的文献求助10
21秒前
高分求助中
Sustainability in Tides Chemistry 2000
Microlepidoptera Palaearctica, Volumes 1 and 3 - 13 (12-Volume Set) [German] 1122
Дружба 友好报 (1957-1958) 1000
The Data Economy: Tools and Applications 1000
Mantiden - Faszinierende Lauerjäger – Buch gebraucht kaufen 700
PraxisRatgeber Mantiden., faszinierende Lauerjäger. – Buch gebraucht kaufe 700
A Dissection Guide & Atlas to the Rabbit 600
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3101245
求助须知:如何正确求助?哪些是违规求助? 2752689
关于积分的说明 7620005
捐赠科研通 2404773
什么是DOI,文献DOI怎么找? 1275998
科研通“疑难数据库(出版商)”最低求助积分说明 616673
版权声明 599058