Data-Driven Long-Landing Event Detection and Interpretability Analysis in Civil Aviation

Yang, Xiong1; Ren, Jin1,2; Li, Junchen3; Zhang, Haigang1; Yang, Jinfeng1

2022

10.1109/ACCESS.2022.3182796

IEEE Access   Impact Factor & Quartile

2169-3536

Long-landing Events (LLEs) can occur as a result of pilot's improper operation, resulting in shorter available runways and higher operating costs. The LLE can be effectively pinpointed by analyzing data from the Quick Access Recorder (QAR), which records all of the pilot's operations during takeoff and landing. Traditionally, domain experts inspect LLEs by manually setting thresholds on uni-dimensional data. However, they cannot detect effectively the defects caused by the pilot's maneuvering technique because the potential mutual information between different features in the large amount of data is not considered. This paper proposes a data-driven LLE detection and causation analysis workflow, which can automatically mine and analyze the mutual information, to overcome the existing problems. Firstly, a dataset is established based on the extracted QAR data from 2002 flights, considering the landing phase of the aircraft. Subsequently, this paper proposes a Hybrid Feature Selection (HFS) method for selecting features that are highly correlated with LLEs in both supervised and unsupervised ways. A categorical Light Gradient Boosting Machine (LGBM) with a Bayesian optimization (LGBMBO) model is used to determine the performance improvement. Furthermore, the model is visualized to analyze the marginal effect of key parameters for the LLEs by using SHapley Additive exPlanations (SHAP). The experimental results demonstrate that our model reduces computational cost and achieves better performance. Additionally, this paper demonstrates that LLEs can be avoided during the landing phase by maintaining the appropriate descent speed, aircraft altitude, and descent angle.

Aircraft Data models Atmospheric modeling Feature extraction Accidents Predictive models Anomaly detection Flight safety long-landing event anomaly detection shapley additive explanations feature engineering machine learning

SCI ; EI

English

Others

National Natural Science Foundation of China[62076166] ; China Postdoctoral Science Foundation[2021M703371] ; Shenzhen Science and Technology Program[RCBS20200714114940262] ; Postdoctoral Foundation Project of Shenzhen Polytechnic[6021330002K] ; General Higher Education Project of Guangdong Provincial Education Department["2020ZDZX3082","2020ZDZX3085"]

Computer Science ; Engineering ; Telecommunications

Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications

WOS:000814550400001

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

20222612276826

Aircraft accidents ; Aircraft detection ; Cost reduction ; Feature extraction ; Fighter aircraft ; Learning systems ; Operating costs

Aircraft, General:652.1 ; Military Aircraft:652.1.2 ; Radar Systems and Equipment:716.2 ; Cost and Value Engineering; Industrial Economics:911 ; Cost Accounting:911.1 ; Industrial Economics:911.2 ; Management:912.2 ; Accidents and Accident Prevention:914.1

Web of Science

1.Shenzhen Polytech, Guangdong Hong Kong Macao Greater Bay Area, Inst Appl Artificial Intelligence, Shenzhen 518055, Peoples R China
2.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518055, Peoples R China
3.Southern Univ Sci & Technol, Coll Engn, Shenzhen 518055, Peoples R China

Yang, Xiong,Ren, Jin,Li, Junchen,et al. Data-Driven Long-Landing Event Detection and Interpretability Analysis in Civil Aviation[J]. IEEE Access,2022,10:64257-64269.

Yang, Xiong,Ren, Jin,Li, Junchen,Zhang, Haigang,&Yang, Jinfeng.(2022).Data-Driven Long-Landing Event Detection and Interpretability Analysis in Civil Aviation.IEEE Access,10,64257-64269.

Yang, Xiong,et al."Data-Driven Long-Landing Event Detection and Interpretability Analysis in Civil Aviation".IEEE Access 10(2022):64257-64269.