Carbon fiber reinforced polymer (CFRP) has been increasingly used in aviation industry since it significantly enhances the performance of aircraft. However, imperfections inside the CFRP structures pose a threat to aviation safety. Apart from the defect shape and size, flaw depth is crucial to assess the defect severity. In this work, we utilize a laser infrared thermography (LIT) system to inspect an aviation CFRP sheet and adopt a long-short term memory recurrent neural network (LSTM-RNN) to determine the defect depth. Thermographic sequences obtained by LIT are processed using thermographic signal reconstructions (TSR) method. Raw data and TSR processed data are separately used to train and test the LSTM-RNN. Results show that background noises in the original thermal signals can be effectively reduced by the TSR method, which is helpful for the models to learn the signal characteristics. Compared with two traditional methods, recurrent neural network (RNN) and convolutional neural network (CNN), we find the LSTM-RNN outperforms.

Recently, terahertz (THz) nondestructive testing technology has prevailed in the defect detection of composite materials yet is limited by identifying deeper flaws. To solve this problem, a time-domain piecewise imaging method based on terahertz signal extraction is proposed in this article. First, the surface reflection echo signal is removed by applying a time correction, and the time-domain signal is then segmented according to the thickness of the sample. Finally, high-quality terahertz images are obtained by image fusion technology. All imaging methods, including traditional ones, are utilized to detect defects in glass fiber reinforced plastic (GFRP) sample then the signal-to-noise ratio (SNR) and defect edge contrast of each method are calculated. The experimental results show that the proposed method can effectively improve the terahertz imaging of deeper defects in GFRP sample especially for multi-depth defects and possesses the highest SNR and defect edge contrast.

Super-Resolution (SR) techniques for image restoration have recently been gaining attention due to their excellent performance. For powerful learning abilities, Generative Adversarial Networks (GANs) have been proven to have achieved great success. In this paper, we propose an Enhanced Generative Adversarial Network (EGAN) for improving its effects for a real-time Super-Resolution task. The main content of this paper are as follows: (1) We adopted the Laplacian pyramid framework as a pre-trained module, which is beneficial for providing multiscale features for our input. (2) At each feature block, a convolutional skip-connections network, which may contain some latent information, was significant for the generative model to reconstruct a plausible-looking image. (3) Considering that the edge details usually play an important role in image generation, a perceptual loss function was defined to train and seek the optimal parameters. Quantitative and qualitative evaluations were demonstrated so that our algorithm not only took full advantage of the Convolutional Neural Networks (CNNs) to improve the image quality, but also performed better than other algorithms in speed and performance for real-time Super-Resolution tasks.

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.

The radome composing of GFRP with sandwich structure is easy to generate impact damage, core material shedding and fiber delamination during the service causing the structural strength and the performance of the waves to fall. Then it affects the normal operation of the radar antenna system. The characteristics of terahertz wave contain the low photon energy, the strong penetrating ability of dielectric material, the transient, broadband and coherence. The simulation experiment of reflective NDT (nondestructive testing) of overlapped multi-delamination defects in the skin of the radome was realized by terahertz wave in CST STUDIO SUITE software simulation platform. The energy, reflection and transmission coefficient of THz wave were analyzed in time domain and frequency domain, and a relatively ideal result had been obtained by using the principle of THz-TDS technology. The paper verified a favorable effect of the related technology of THz at NDT and the exploration of material characteristics on composites with sandwich structure.