A5011531962- Thermography and Photoacoustic Techniques
- Advanced Image Fusion Techniques
- Ultrasonics and Acoustic Wave Propagation
- Terahertz technology and applications
- Advanced Measurement and Detection Methods
- Risk and Safety Analysis
- Advanced Image Processing Techniques
- Image Enhancement Techniques
- Infrared Target Detection Methodologies
- Calibration and Measurement Techniques
- Occupational Health and Safety Research
- Advanced Chemical Sensor Technologies
- Image Processing Techniques and Applications
- Anomaly Detection Techniques and Applications
- Reliability and Maintenance Optimization
- Optical measurement and interference techniques
- Fault Detection and Control Systems
- Advanced Fiber Optic Sensors
- Fatigue and fracture mechanics
- Environmental Quality and Pollution
- Remote-Sensing Image Classification
- Photonic and Optical Devices
- Image and Video Quality Assessment
- Multi-Criteria Decision Making
- Industrial Vision Systems and Defect Detection
Wuhan Textile University
2024
Air Force Engineering University
2019-2024
Fudan University
2024
Shandong Academy of Sciences
2024
Carbon fiber reinforced polymer (CFRP) has been increasingly used in aviation industry since it significantly enhances the performance of aircraft. However, imperfections inside CFRP structures pose a threat to safety. Apart from defect shape and size, flaw depth is crucial assess severity. In this work, we utilize laser infrared thermography (LIT) system inspect an sheet adopt long-short term memory recurrent neural network (LSTM-RNN) determine depth. Thermographic sequences obtained by LIT...
A new infrared preprocessing modality called sequence differential processing is proposed. Different from the cold image subtraction which only decreases background noise, proposed takes parallel test into account to preprocess raw thermal data prior applying advanced postprocessing techniques such as principal component thermography and pulsed phase thermography. The results show that method not effectively reduces influence of uneven laser energy distribution on detection efficiency but...
The rapid growth of the aviation industry highlights need for strong safety management. Analyzing data on unsafe events is crucial preventing risks. This paper presents a new method that integrates Transformer network model, clustering analysis, and feature modeling to analyze Chinese text events. Initially, model used generate summaries event texts, performance three pre-trained models evaluated compared. Next, Jieba tool applied segment both summarized original texts extract key features...
In this paper, we propose a Terahertz image Super-Resolution (SR) method based on very deep Convolutional Networks (VDCN) in non-destructive testing (NDT) application. Glass fiber reinforced plastic (GFRP) with prefabrication defects is used as test specimen. Through fast scanning imaging by domain spectrometer, obtained the single original image. Then HR can be generated trained VDCN. Experimental results show that restored our has higher peak signal-to-noise ratio (PSNR) and structural...
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 signal extraction proposed article. First, surface reflection echo removed applying time correction, and then segmented according to thickness sample. Finally, high-quality images are obtained image fusion technology. All methods, including traditional ones,...
The direct utilization of low-light images hinders downstream visual tasks. Traditional image enhancement (LLIE) methods, such as Retinex-based networks, require pairs. A spiking-coding methodology called intensity-to-latency has been used to gradually acquire the structural characteristics an image. convLSTM connect features. This study introduces a simplified DCENet achieve unsupervised LLIE well spiking coding mode neural network. It also applies comprehensive features improve subjective...
Due to the information non-independence of attributes, combined with a complex and changeable environment, analysis risks faces great difficulties. In view this problem, paper proposes new three-way decision-making (3WD) method, prospect theory non-additive measure, cope multi-source incomplete risk systems. Prospect improves loss function original 3WD model, combination measurement probability provides perspective understand meaning decision-making, which could measure relative degree by...
Abstract Composite structures have played a significant role in enhancing airplane’s performance However, defects inside can be potential threat to flight safety. To resolve the hazard. FMECA was applied defect analysis of composite on wing. And failure mode highest criticality found impact damage. Then test typical laminates carried out. The caused damage qualitatively analysed and proved low energy brings latent risk. Practical solution put forward improve safety or reliability composites airplane.
Abstract With the development of equipment, complexity China’s military aviation system continues to increase. The risk is transformed from initial independent factor cross-influence factor, which makes control difficult. In order maintain safety level system, factors affecting are analysed five aspects: personnel, machine, environment, management and logistics. analytic hierarchy process (ANP) used construct model dynamics method establish evolution simulation model, quantitatively analyse...