Jadwal Sholat

Memuat jadwal sholat…

Teknik & Rekayasa editorial

Open AccessOA2025

Automated Anomaly Detection and Causal Analysis for Civil Aviation Using QAR Data

MAD-XFP automates anomaly detection and causal analysis for civil aviation using QAR data, enabling multiple event monitoring and interpretable results.
Xin Dang; Cong-Cong Hua; Chui-Tian Rong· Applied Sciences· 2025· DOI 10.3390/app15052250

The core problem

Flight Operations Quality Assurance (FOQA) is an internationally recognized solution to ensure the safety of civil aircraft flights based on Quick Access Recorder (QAR) data. The traditional approach to anomaly detection in civil aviation is to detect the over-limit values of monitoring parameters for each monitoring event based on the standards issued by civil aviation authorities. Usually, for each anomaly detection operation routine, this only works for one monitoring event. Furthermore, the causal analyses for the detected anomaly events are based on the relevant worker’s expertise. In order to improve the efficiency of FOQA, this paper proposes an automated anomaly detection and causal analysis method called MAD-XFP.

Innovation

Due to the unique industry characteristics of QAR data and the requirements of FOQA, feature engineering and hyper-parameter optimization techniques are utilized to enhance the machine learning model. The proposed method can monitor multiple events in one routine and provide a causal analysis. In the causal analysis process, the Shapley additive interpretation method is applied to produce analysis report for detected anomalies.
Introduction
Flight Operations Quality Assurance (FOQA) is an internationally recognized solution to ensure the safety of civil aircraft flights based on Quick Access Recorder (QAR) data. The traditional approach to anomaly detection in civil aviation is to detect the over-limit values of monitoring parameters for each monitoring event based on the standards issued by civil aviation authorities. Usually, for each anomaly detection operation routine, this only works for one monitoring event. Furthermore, the causal analyses for the detected anomaly events are based on the relevant worker’s expertise. In order to improve the efficiency of FOQA, this paper proposes an automated anomaly detection and causal analysis method called MAD-XFP.

Why it matters

The MAD-XFP method addresses the limitations of traditional FOQA by automating anomaly detection and causal analysis. By leveraging feature engineering and hyper-parameter optimization, the machine learning model is tailored to QAR data characteristics. The use of SHAP provides interpretable causal analysis, reducing reliance on expert judgment. The method's ability to monitor multiple events in one routine enhances efficiency. Experimental results demonstrate high precision in detecting abnormal events during the approach phase, indicating practical applicability. Future work may extend to other flight phases and further refine causal analysis.

Who should read this

Pembaca Research Digest dan praktisi rumpun ini.

Opening member content…