Wave-ConvNeXt: An Efficient and Precise Fault Diagnosis Method for IIoT Leveraging Tailored ConvNeXt and Wavelet Transform

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: L773:2327 4662 > (2024) > Wave-ConvNeXt :

Zhang, LiangweiDepartment of Industrial Engineering, Dongguan University of Technology, Dongguan, China (författare)

Wave-ConvNeXt : An Efficient and Precise Fault Diagnosis Method for IIoT Leveraging Tailored ConvNeXt and Wavelet Transform

Artikel/kapitelEngelska2024

Förlag, utgivningsår, omfång ...

2024
printrdacarrier

Nummerbeteckningar

LIBRIS-ID:oai:DiVA.org:mdh-67209
https://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-67209URI
https://doi.org/10.1109/jiot.2024.3386965DOI

Kompletterande språkuppgifter

Språk:engelska
Sammanfattning på:engelska

Ingår i deldatabas

SwePubSwePub

Klassifikation

Ämneskategori:ref swepub-contenttype
Ämneskategori:art swepub-publicationtype

Anmärkningar

The burgeoning field of the Industrial Internet of Things (IIoT) necessitates advanced fault diagnosis methods capable of navigating the dual challenges of high predictive accuracy and the constraints of edge computing environments. Our study introduces Wave-ConvNeXt, a novel fault diagnosis model that seamlessly integrates the state-of-the-art ConvNeXt architecture with Wavelet Transform. This innovative model stands out for its lightweight design yet delivers exceptional accuracy in fault diagnosis. In Wave-ConvNeXt, we re-engineer the ConvNeXt model for IIoT applications by adopting onedimensional convolution, tailored for processing high-frequency, non-periodic inputs. This adaptation is complemented by replacing the traditional “patchify” layer with a Wavelet transform layer, which simplifies input signals into sub-signals, thereby easing learning complexities and diminishing the dependence on elaborate deep architectures. Further enhancing this model, we incorporate a squeeze-and-excitation module, enriching its ability to prioritize channel-wise feature relevance, akin to self-attention mechanisms. This integration is rigorously validated through an ablation study. Wave-ConvNeXt epitomizes a holistic approach, enabling an end-to-end optimization of feature learning and fault classification. Our empirical analysis on two real-world IIoT datasets demonstrates Wave-ConvNeXt’s superiority over existing models. It not only elevates prediction accuracy but also significantly curtails computational complexity. Additionally, our exploration into the impact of various mother wavelets reveals the effectiveness of using wavelet basis functions with smaller support, bolstering diagnostic precision. The source code of Wave-ConvNeXt is available at https://github.com/leviszhang/waveConvNeXt.

Ämnesord och genrebeteckningar

NATURVETENSKAP Data- och informationsvetenskap Datorteknik hsv//swe
NATURAL SCIENCES Computer and Information Sciences Computer Engineering hsv//eng
Industrial Internet of Things (IIoT)
Fault Diagnosis
Wavelet Transform
ConvNeXt Architecture
Computational Efficiency

Biuppslag (personer, institutioner, konferenser, titlar ...)

Lin, JingMälardalens universitet,Innovation och produktrealisering,Division of Operation and Maintenance, University of Technology, Luleå, Sweden(Swepub:mdh)jln19 (författare)
Yang, ZheDepartment of Industrial Engineering, Dongguan University of Technology, Dongguan, China (författare)
Shao, HaidongCollege of Mechanical and Vehicle Engineering, State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, China (författare)
Liu, BiyuSchool of Economics and Management, Fuzhou University, Fuzhou, China (författare)
Li, ChuanDepartment of Industrial Engineering, Dongguan University of Technology, Dongguan, China (författare)
Department of Industrial Engineering, Dongguan University of Technology, Dongguan, ChinaInnovation och produktrealisering (creator_code:org_t)

Sammanhörande titlar

Ingår i:IEEE Internet of Things Journal, s. 1-12327-4662

Internetlänk

Hitta via bibliotek

IEEE Internet of Things Journal (Sök värdpublikationen i LIBRIS)

Till lärosätets databas

Hitta mer i SwePub

Av författaren/redakt...: Zhang, Liangwei; Lin, Jing; Yang, Zhe; Shao, Haidong; Liu, Biyu; Li, Chuan

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Datorteknik

Artiklar i publikationen: IEEE Internet of ...

Av lärosätet: Mälardalens universitet

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se