Automatic defect prediction in glass fiber reinforced polymer based on THz-TDS signal analysis with neural networks

Abstract Detection of internal defects in glass fiber reinforced polymer (GFRP) is vital for aviation safety. In this work, we report a novel approach to predict the defect depths in GFRP based on terahertz time-domain spectroscopy signal analysis with neural networks. We exploit three neural network models, which can be trained and tested with the collected terahertz time-domain signals or the corresponding spectral signals, to carry out defect detection and classification based on the depth. Results show that in general the one-dimension convolutional neural network model outperforms the long-short term memory recurrent neural network (LSTM-RNN) and the bidirectional LSTM-RNN models. The corresponding recall rates are above 0.85 and can even reach 0.97, and the macro F1 score is larger than 0.91. Based on the automatic defect detection and classification, a terahertz image showing the locations and depths of defects can be efficiently reconstructed. We envision this work will advance the development of automatic nondestructive defect detection based on terahertz techniques and neural networks.

[1]  Guy Lapalme,et al.  A systematic analysis of performance measures for classification tasks , 2009, Inf. Process. Manag..

[2]  Huan Wang,et al.  A Novel Deeper One-Dimensional CNN With Residual Learning for Fault Diagnosis of Wheelset Bearings in High-Speed Trains , 2019, IEEE Access.

[3]  Hon Keung Kwan,et al.  A fuzzy neural network and its application to pattern recognition , 1994, IEEE Trans. Fuzzy Syst..

[4]  Nick Savage,et al.  Terahertz Radome Inspection , 2018 .

[5]  Hong-Liang Cui,et al.  Terahertz nondestructive imaging for foreign object detection in glass fibre-reinforced polymer composite panels , 2019, Infrared Physics & Technology.

[6]  Ning Zhang,et al.  Multi-Agent-Based Unsupervised Detection of Energy Consumption Anomalies on Smart Campus , 2019, IEEE Access.

[7]  Constantinos Soutis,et al.  Fibre reinforced composites in aircraft construction , 2005 .

[8]  Wei Li,et al.  Nondestructive Evaluation of Carbon Fiber Reinforced Polymer Composites Using Reflective Terahertz Imaging , 2016, Sensors.

[9]  F C Cruz,et al.  Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing , 2017, Ultrasonics.

[10]  Shuyu Yang,et al.  Recognition of ships based on vector sensor and bidirectional long short-term memory networks , 2020 .

[11]  Shuncong Zhong.  Progress in terahertz nondestructive testing: A review , 2019 .

[12]  X. Zhang,et al.  Pulsed terahertz tomography , 2004 .

[13]  Tianying Chang,et al.  Nondestructive imaging of hidden defects in aircraft sandwich composites using terahertz time-domain spectroscopy , 2019, Infrared Physics & Technology.

[14]  Clemente Ibarra-Castanedo,et al.  Automated defect classification in infrared thermography based on a neural network , 2019, NDT & E International.

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Chao Li,et al.  Exploring temporal representations by leveraging attention-based bidirectional LSTM-RNNs for multi-modal emotion recognition , 2020, Inf. Process. Manag..

[17]  Shijin Wang,et al.  One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes , 2020 .

[18]  Dharmendra Singh,et al.  A novel neural network based image reconstruction model with scale and rotation invariance for target identification and classification for Active millimetre wave imaging , 2014 .

[19]  Akshi Kumar,et al.  Sarcasm detection in mash-up language using soft-attention based bi-directional LSTM and feature-rich CNN , 2020, Appl. Soft Comput..

[20]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[21]  Zhenmao Chen,et al.  Quantitative evaluation of surface crack depth with laser spot thermography , 2017 .

[22]  Xavier Maldague,et al.  Neural network based defect detection and depth estimation in TNDE , 2002 .

[23]  Luis S. Rosado,et al.  Defect Characterization With Eddy Current Testing Using Nonlinear-Regression Feature Extraction and Artificial Neural Networks , 2013, IEEE Transactions on Instrumentation and Measurement.

[24]  Min Meng,et al.  Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks , 2017, Neurocomputing.

[25]  M. Omar,et al.  A neural network approach for quantifying defects depth, for nondestructive testing thermograms , 2018, Infrared Physics & Technology.