Loading…
Terahertz recognition of composite material interfaces based on ResNet-BiLSTM
•Presents a novel framework combining residual network (ResNet) with bidirectional long short-term memory network (BiLSTM) for enhanced terahertz signal analysis.•Introduces a sophisticated method for automatic defect detection and interface localization in non-metallic materials, surpassing traditi...
Saved in:
Published in: | Measurement : journal of the International Measurement Confederation 2024-06, Vol.233, p.114771, Article 114771 |
---|---|
Main Authors: | , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | •Presents a novel framework combining residual network (ResNet) with bidirectional long short-term memory network (BiLSTM) for enhanced terahertz signal analysis.•Introduces a sophisticated method for automatic defect detection and interface localization in non-metallic materials, surpassing traditional manual analysis in efficiency and accuracy.•Achieves interface positioning accuracy surpassing 80 µm in coating sample thickness, demonstrating superior performance to conventional approaches.•Provides robust validation against X-ray CT results, revealing an error margin of only 1.07% to 5.39% in detecting adhesive layer defects.
This manuscript presents a framework that integrates a residual network (ResNet) with a bidirectional long short-term memory network (BiLSTM) for effective feature extraction and interface positioning in terahertz signal analysis. This innovative approach employs spatial and temporal feature extraction modules to process terahertz signals, enabling the automatic detection of interfaces and defects in both coating and bonded structure samples. The experimental results indicate that the interface positioning accuracy of the method aligns with the manual analysis outcomes for coating samples exceeding 80 µm in thickness. Furthermore, it exhibits a high degree of consistency with X-ray CT detection results when detecting defects in the adhesive layer, with an error margin ranging from 1.07 % to 5.39 %. Significantly, we have also conducted preliminary analyses on actual samples, further underscoring the robustness and generalizability of our model. This method offers an efficient automated tool for terahertz signal analysis and holds promise for industrial detection applications. Future research will aim to broaden the range of samples and application scenarios, thereby increasing the technology’s practicality in quality control and production line detection. |
---|---|
ISSN: | 0263-2241 1873-412X |
DOI: | 10.1016/j.measurement.2024.114771 |