AI Science Tracker
EN

Research Center of Structural Health Monitoring and Prognosis

1 discovery from 2021

Discoveries

Fatigue Crack Evaluation with the Guided Wave-Convolutional Neural Network Ensemble and Differential Wavelet Spectrogram.

Source check: Source checked. Not independent scientific confirmation.

Finding: A guided-wave CNN ensemble estimated fatigue-crack length on a tested lap-joint specimen; on held-out specimen D6 the reported RMSE was 1.7 mm, with crack lengths followed during fatigue loading.

Technology: Differential time-frequency spectrograms from guided-wave signals were inputs to 20 CNNs; trained on specimens D1–D5, Methods §§2–3.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Differential time-frequency spectrograms from guided-wave signals were inputs to 20 CNNs; trained on specimens D1–D5, Methods §§2–3.
Test and result
Results §4 evaluates specimen D6 and reports agreement with measured crack lengths; maximum error 3 mm and RMSE 1.7 mm.
Limitation / still unknown
One held-out specimen, 77 training images and laboratory fatigue testing; authors note small training data and dependence on collected training data.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://europepmc.org/article/MED/35009843 · https://pmc.ncbi.nlm.nih.gov/articles/PMC8749601/?report=xml · https://pubmed.ncbi.nlm.nih.gov/35009843/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.