Self-adaptive fault diagnosis for unseen working conditions based on digital twins and domain generalization

一般化 领域(数学分析) 断层(地质) 计算机科学 人工智能 可靠性工程 模式识别(心理学) 工程类 数学 地质学 数学分析 地震学
作者
Mehdi Saman Azari,Stefania Santini,Farid Edrisi,Francesco Flammini
出处
期刊:Reliability Engineering & System Safety [Elsevier BV]
卷期号:254: 110560-110560 被引量:57
标识
DOI:10.1016/j.ress.2024.110560
摘要

In recent years, intelligent fault diagnosis based on domain adaptation has been used to address domain shifts in cyber–physical systems; however, the need for acquiring target data sufficiently limits their applicability to unseen working conditions. To overcome such limitations, domain generalization techniques have been introduced to enhance the capacity of fault diagnostic models to operate under unseen working conditions. Nevertheless, existing approaches assume access to extensive labeled training data from various source domains, posing challenges in real-world engineering scenarios due to resource constraints. Moreover, the absence of a mechanism for updating diagnostic models over time calls for the exploration of self-adaptive generalized diagnosis models that are capable of autonomous reconfiguration in response to new unseen working conditions. In such a context, this paper proposes a self-adaptive fault diagnosis system that combines several paradigms, namely Monitor-Analyze-Plan-Execute over a shared Knowledge (MAPE-K), Domain Generalization Network Models (DGNMs), and Digital Twins (DT). The MAPE-K loop enables run-time adaptation to dynamic industrial environments without human intervention. To address the scarcity of labeled training data, digital twins are used to generate supplementary data and continuously tune parameters to reflect the dynamics of new unseen working conditions. DGNM incorporates adversarial learning and a domain-based discrepancy metric to enhance feature diversity and generalization. The introduction of multi-domain data augmentation enhances feature diversity and facilitates learning correlations among multiple domains, ultimately improving the generalization of feature representations. The proposed fault diagnosis system has been evaluated on three publicly available rotating machinery datasets to demonstrate its higher performance in cross-work operation and cross-machine tasks compared to other state-of-the-art methods. • Adoption of the MAPE-K loop for self-adaptive fault diagnosis in cyber–physical systems. • Integration of digital twins and appropriate updating strategies. • Leveraging multi-domain data augmentation. • Embedding domain discriminators and domain-based discrepancy metrics. • Experimental evaluation on a rotating machinery case-study shows higher performance.
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
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
刘扣扣UU的应助被机灵语山采纳,获得10
1秒前
丘比特的应助被kiluto采纳,获得10
2秒前
3秒前
3秒前
bszh完成签到,获得积分10
3秒前
4秒前
anfang发布了新的文献求助10
6秒前
准好好完成签到,获得积分10
6秒前
科研通AI6.2的应助被Mortal采纳,获得10
6秒前
鱼湘完成签到,获得积分10
7秒前
eight完成签到,获得积分10
7秒前
7秒前
joysa完成签到,获得积分10
7秒前
orixero的应助被Lora采纳,获得10
8秒前
感动代芙完成签到,获得积分10
8秒前
9秒前
春风暮雪发布了新的文献求助10
9秒前
9秒前
MAK完成签到,获得积分10
9秒前
准好好发布了新的文献求助10
9秒前
小铭发布了新的文献求助10
9秒前
桐桐的应助被caojie采纳,获得10
9秒前
10秒前
Z_butterfly完成签到,获得积分10
11秒前
zcx给zcx的求助进行了留言
11秒前
liberty发布了新的文献求助10
12秒前
12秒前
喝口可乐完成签到 ,获得积分10
13秒前
土豆完成签到,获得积分10
13秒前
烽火戏诸侯完成签到,获得积分10
13秒前
13秒前
bgt完成签到 ,获得积分10
13秒前
豆豆完成签到 ,获得积分10
14秒前
14秒前
钰小憨发布了新的文献求助10
14秒前
王誉霖完成签到,获得积分10
15秒前
16秒前
16秒前
111发布了新的文献求助10
16秒前
bobo完成签到,获得积分10
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Agyptische Geschichte der 21.30. Dynastie 510
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
基于界面调控的高效湿气发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8192723
求助须知:如何正确求助?哪些是违规求助? 9579144
关于积分的说明 21863903
捐赠科研通 7792268
什么是DOI,文献DOI怎么找? 3437013
关于科研通互助平台的介绍 2560633
邀请新用户注册赠送积分活动 2483864