基于太赫兹时域光谱的一维顺序模型对 GFRP 蜂窝中液体侵入的分类。

Classification of Liquid Ingress in GFRP Honeycomb Based on One-Dimension Sequential Model Using THz-TDS.

机构信息

School of Armament Science and Technology, Xi'an Technological University, Xi'an 710064, China.

School of Mechatronic Engineering, Xi'an Technological University, Xi'an 710064, China.

出版信息

Sensors (Basel). 2023 Jan 19;23(3):1149. doi: 10.3390/s23031149.

DOI:10.3390/s23031149

PMID:36772188

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9921085/

Abstract

Honeycomb structure composites are taking an increasing proportion in aircraft manufacturing because of their high strength-to-weight ratio, good fatigue resistance, and low manufacturing cost. However, the hollow structure is very prone to liquid ingress. Here, we report a fast and automatic classification approach for water, alcohol, and oil filled in glass fiber reinforced polymer (GFRP) honeycomb structures through terahertz time-domain spectroscopy (THz-TDS). We propose an improved one-dimensional convolutional neural network (1D-CNN) model, and compared it with long short-term memory (LSTM) and ordinary 1D-CNN models, which are classification networks based on one dimension sequenced signals. The automated liquid classification results show that the LSTM model has the best performance for the time-domain signals, while the improved 1D-CNN model performed best for the frequency-domain signals.

摘要

蜂窝结构复合材料由于其高强度重量比、良好的耐疲劳性和低成本在飞机制造中所占的比例越来越大。然而，空心结构非常容易进水。在这里，我们通过太赫兹时域光谱（THz-TDS）报告了一种快速、自动的分类方法，用于对玻璃纤维增强聚合物（GFRP）蜂窝结构中的水、酒精和油进行分类。我们提出了一种改进的一维卷积神经网络（1D-CNN）模型，并将其与基于一维序列信号的分类网络长短期记忆（LSTM）和普通 1D-CNN 模型进行了比较。自动液体分类结果表明，LSTM 模型对时域信号的性能最好，而改进的 1D-CNN 模型对频域信号的性能最好。