The rapid growth of the aviation industry highlights the need for strong safety management. Analyzing data on unsafe aviation events is crucial for preventing risks. This paper presents a new method that integrates the Transformer network model, clustering analysis, and feature network modeling to analyze Chinese text data on unsafe aviation events. Initially, the Transformer model is used to generate summaries of event texts, and the performance of three pre-trained Chinese models is evaluated and compared. Next, the Jieba tool is applied to segment both summarized and original texts to extract key features of unsafe events and prove the effectiveness of the pre-trained Transformer model in simplifying lengthy and redundant original texts. Then, cluster analysis based on text similarity categorizes the extracted features. By solving the correlation matrix of these features, this paper constructs a feature network for unsafe aviation events. The network’s global and individual metrics are calculated and then used to identify key feature nodes, which alert aviation professionals to focus more on the decision-making process for safety management. Based on the established network and these metrics, a data-driven hidden danger warning strategy is proposed and illustrated. Overall, the proposed method can effectively analyze Chinese texts of unsafe aviation events and provide a basis for improving aviation safety management.
1 March 2020 in IOP Conference Series: Materials Science and Engineering
Composite structures have played a significant role in enhancing airplane’s performance However, defects inside can be a potential threat to flight safety. To resolve the hazard. FMECA was applied to the defect analysis of composite structures on airplane’s wing. And the failure mode of the highest criticality was found to be the impact damage. Then impact test on typical composite laminates was carried out. The caused damage was qualitatively analysed and proved impact of low energy brings latent risk. Practical solution was put forward to improve the safety or reliability of the applied composites in the airplane.
Due to the information non-independence of attributes, combined with a complex and changeable environment, the analysis of risks faces great difficulties. In view of this problem, this paper proposes a new three-way decision-making (3WD) method, combined with prospect theory and a non-additive measure, to cope with multi-source and incomplete risk information systems. Prospect theory improves the loss function of the original 3WD model, and the combination of non-additive measurement and probability measurement provides a new perspective to understand the meaning of decision-making, which could measure the relative degree by considering expert knowledge and objective data. The theoretical basis and framework of this model are illustrated, and this model is applied to a real in-service aviation equipment structures risk evaluation problem involving multiple incomplete risk information sources. When the simulation analysis is carried out, the results show that the availability of this method is verified. This method can also evaluate and rank key risk factors in equipment structures, which provides a reliable basis for decisions in aviation safety management.
1 July 2023 in Russian Journal of Nondestructive Testing
The broadening use of carbon-fiber reinforced plastics (CFRP) in various industries has raised safety concerns. To control the hazard, infrared thermography inspection techniques, capable of large-area scanning, instantaneous imaging, and completely non-contact detection, has been increasingly adopted to detect flaws inside CFRP structures. And in practical engineering, post-processing algorithms are required to eliminate noise and enhance defect detectability after initial inspection course. However, rapid updates of infrared camera bring high-resolution thermograms yet. Whereas classic algorithms have encountered data explosion problem which led to low efficiency and engineering infeasibility. Therefore, to promote the efficiency of postprocessing algorithms, we propose equal interval sampling (EIS) method to sample raw thermal data. Two CFRP laminates with embedded artificial Teflon inserts of different sizes at different depths are inspected by a laser infrared thermography system. The obtained raw thermal videos made up of 500 frame thermal images with 512 × 640 pixels were converted to 3D thermographic data. We apply EIS to sample the data by setting different intervals. And the sampled data are fed to classic post-processing algorithms, thermal signal reconstruction (TSR) and principal component analysis (PCA), which have prevailed in processing thermographic data. Regarding different intervals of EIS as variables, the processing efficiency, and the defect detection performance of EIS-TSR and EIS-PCA are studied. The results demonstrate that EIS-TSR method fails to promote processing speed and maintain the performance of defect detection at the same time. In contrast, the EIS-PCA method attains a remarkable efficiency and intact defect detectability simultaneously, manifesting its adequacy in engineering practice.