Safety is a primary concern for the civil aviation industry. Airlines record high-frequency but potentially low-severity unsafe events, i.e., incidents, in their reports. Over the past few decades, civil aviation security practitioners have made efforts to analyze these issues. The information in incident reports is valuable for risk analysis. However, incident reports were inefficiently utilized due to incoherence, large volume, and poor structure. In this study, we proposed a technical scheme to intelligently classify and extract risk factors from Chinese civil aviation incident reports. Firstly, we adopted machine learning classifiers and vectorization strategies to classify incident reports into 11 categories. Grid search was used to adjust the parameters of the classifier. In the preliminary experiment, the combination of the extreme gradient boosting (XGBoost) classifier and the occurrence position (OC-POS) vectorization strategy outperformed with an 0.85 weighted F1-score. In addition, we designed a rule-based system to identify the factors related to the occurrence of incidents from 25 empirical causes, which included equipment, human, environment, and organizational causes. For cause identification, we used rules obtained through manual analysis with keywords and discourse. F1-score above 0.90 was obtained on the test set using the causes identification model derived from the training set. The proposed system permits insights into unsafe factors in aviation incidents and prevents reoccurrence. Future works can proceed on this study, such as exploring the causal relationship between causes and incidents.

Low-altitude unstable approach (UA) is one of the crucial risks that threaten flight safety. In this study, we proposed a technical program for detecting low-altitude UA events. The detection logic was to optimize the step-wise regression model with iterative surveys with more than 20 experienced pilots. Accordingly, the frequencies of UA events occurring around each airport in January 2018 were calculated for all the airports within mainland China. Finally, the spatial distribution characteristics of UA events were analyzed via exploratory spatial data analysis. In addition, Pearson’s correlation coefficient and the geographically weighted correlation coefficient were used to explore the correlations between UA frequency and the altitude elevation, wind level, and bad weather. The experimental results revealed that the proposed method can accurately detect the occurrence of low-altitude UA and quantitatively characterize risks. It was found that UA exhibits obvious differences in spatial distribution. Moreover, significantly strong correlations were found between UA and altitude elevation, wind level, and bad weather, and correlation differences were also reflected in different regions in China.