飛行安全一直是各航空公司、政府與國際組織重視的一環，雖然航空事故的發生率相較其他交通工具極低，但每起事故皆對及社會都造成重大的傷害。根據美國波音公司數據統計，有四分之一的死亡事故發生在進場階段。聚焦回台灣國內，國家運輸安全調查委員會的統計數據也顯示出一樣的結果，因此本研究試圖從天氣與飛行員操作中找出其關聯性。本研究收集了2019年國內某一航空公司在松山機場、台中機場與高雄機場的快速存取紀錄器(Quick Access Recorder, QAR)資料與機場的定時天氣預報(Terminal Aviation Routine Weather Report, METAR)。利用QAR與MEATR建立分析資料集，從QAR中我們將參數分為兩部分，空速、俯仰角等用來偵測事件，操縱桿的輸入訊號則用來估算飛行員的操作強度，而從METAR中獲得有關天氣的一些訊息，例如風速，溫度等，再依照各機場不同的氣候型態加以分類。透過相關性分析有助於我們找出關鍵的氣象參數，而接著關聯規則探勘的Apriori演算法，能夠得到事件與天氣參數之間更進一步的關聯性，找到與事件最相關的天氣參數，最後利用快速傅立葉轉換與能量譜密度估計飛行員操作強度，機率密度函數顯示Roll、Pitch和Yaw三個操作參數強度在三個機場中被不同天氣條件影響下的分佈。結果表明，所有機場的風速和側風風速皆對飛行員的操作強度產生影響，尤其是在高雄機場側風的影響更加明顯。台北松山機場的其他重大天氣狀況是降雨、側風和低能見度，台中機場是低溫，高雄機場是低能見度和低雲幕高。

In flight operation, the approach phase is one of the critical phase in the entire flight. According to Boeing statistics, around 25% of fatal accidents occurred during the approach. Human errors and meteorology are the primary factors contributing to such accidents. The statistics from the Taiwan Transportation Safety Board concur with this assumption. This study is an attempt to determine the relationship between pilot operation and meteorological factors. Therefore, we collected Quick Access Recorder (QAR) data from a domestic airline and the Meteorological Terminal Aviation Routine Weather Report (METAR) at three airports in Taiwan in 2019, including Song Shan Airport, Taichung Airport, and Kaohsiung Airport. QAR and METAR were used to build the database. From METAR, we extracted some weather information, including wind, temperature, etc. A correlation analysis was carried out to determine the key meteorological parameters. Through the use of an association rule mining Apriori algorithm, the association rule between events and weather conditions was obtained. Lastly, we estimated the pilot intensity using the Fast Fourier Transform. The probability density function demonstrated the distribution of different weather conditions at the three airports. The results showed that both wind speed and crosswind speed at all airports have an impact on pilot’s operating intensity, especially at Kaohsiung Airport. Other significant weather conditions included rain, crosswinds, and low visibility at Taipei Song Shan Airport, low temperature at Taichung Airport, and low visibility and low ceiling height at Kaohsiung Airport.

[1] B. C. Airplanes, "Statistical summary of commercial jet airplane accidents," Worldwide Operations, vol. 2008, 1959.
[2] T. T. S. Board, "Taiwan Aviation Occurrence Statistics 2010-2019," 2020.
[3] L. Wang, C. Wu, and R. Sun, "An analysis of flight Quick Access Recorder (QAR) data and its applications in preventing landing incidents," Reliability Engineering & System Safety, vol. 127, pp. 86-96, 2014.
[4] X. Lu, D. Chen, and F. Zhang, "Grey Correlation Analysis of Hard Landing Based on QAR Data," in 2019 IEEE 1st International Conference on Civil Aviation Safety and Information Technology (ICCASIT), 2019: IEEE, pp. 79-83.
[5] J. Xie, H. Sun, Y. Jiao, and B. Lu, "Association rules mining with QAR data: An analysis on unstable approaches," in 2019 IEEE 1st International Conference on Civil Aviation Safety and Information Technology (ICCASIT), 2019: IEEE, pp. 603-606.
[6] L. Li, S. Das, R. John Hansman, R. Palacios, and A. N. Srivastava, "Analysis of flight data using clustering techniques for detecting abnormal operations," Journal of Aerospace information systems, vol. 12, no. 9, pp. 587-598, 2015.
[7] M. Baak, R. Koopman, H. Snoek, and S. Klous, "A new correlation coefficient between categorical, ordinal and interval variables with Pearson characteristics," Computational Statistics & Data Analysis, vol. 152, p. 107043, 2020.
[8] X. Wu et al., "Top 10 algorithms in data mining," Knowledge and information systems, vol. 14, no. 1, pp. 1-37, 2008.
[9] R. K. Remple and M. B. Tischler, Aircraft and rotorcraft system identification: engineering methods with flight-test examples. American Institute of Aeronautics and Astronautics, 2006.
[10] H. Ji, R. Chen, L. Lu, and M. D. White, "Pilot workload investigation for rotorcraft operation in low-altitude atmospheric turbulence," Aerospace Science and Technology, vol. 111, p. 106567, 2021.
[11] A. Airbus, "Statistical Analysis of Commercial Aviation Accidents 1958-2019," ed: Blagnac Cedex, France: printed by Art & Caractère, 2020.
[12] A. T. Center, "Flight Data Monitoring on ATR Aircraft," 2016.
[13] L. Wang, C. Wu, and R. Sun, "Pilot operating characteristics analysis of long landing based on flight QAR data," in International Conference on Engineering Psychology and Cognitive Ergonomics, 2013: Springer, pp. 157-166.
[14] S.-H. Chung, H.-L. Ma, M. Hansen, and T.-M. Choi, "Data science and analytics in aviation," ed: Elsevier, 2020.
[15] I. Gultepe et al., "A review of high impact weather for aviation meteorology," Pure and applied geophysics, vol. 176, no. 5, pp. 1869-1921, 2019.
[16] S. Kotsiantis and D. Kanellopoulos, "Association rules mining: A recent overview," GESTS International Transactions on Computer Science and Engineering, vol. 32, no. 1, pp. 71-82, 2006.
[17] T. Kumar, Y. Gu, H. Chao, and M. B. Rhudy, "Flight data analysis of pilot-induced-oscillations of a remotely controlled aircraft," in AIAA Guidance, Navigation, and Control (GNC) Conference, 2013, p. 5010.
[18] J. Mazon, J. Rojas, M. Lozano, D. Pino, X. Prats, and M. Miglietta, "Influence of meteorological phenomena on worldwide aircraft accidents, 1967–2010," Meteorological Applications, vol. 25, no. 2, pp. 236-245, 2018.
[19] D. T. McRuer, "Aviation safety and pilot control: Understanding and preventing unfavorable pilot-vehicle interactions," 1997.
[20] I. B. Mugtussids, "Flight data processing techniques to identify unusual events," Virginia Tech, 2000.
[21] J. Oehling and D. J. Barry, "Using machine learning methods in airline flight data monitoring to generate new operational safety knowledge from existing data," Safety science, vol. 114, pp. 89-104, 2019.
[22] X.-b. ZHAO, L. Bin, and C.-g. WANG, "There is a gold mine in flight data: A framework of data Mining in Civil Aviation," DEStech Transactions on Social Science, Education and Human Science, no. meit, 2017.
[23] M. Al-Maolegi and B. Arkok, "An improved Apriori algorithm for association rules," arXiv preprint arXiv:1403.3948, 2014.
[24] N. Maille, "On the use of data-mining algorithms to improve FOQA tools for airlines," in 2013 IEEE Aerospace Conference, 2013: IEEE, pp. 1-8.
[25] 楊鐵忠, "不符合穩定進場條件對跑道安全危害之探討," 航空安全及管理季刊, vol. 2, no. 4, pp. 388-399, 2015.
[26] 林怡伶, "飛安績效指標建立與關聯分析研究," 淡江大學資訊管理學系碩士班學位論文, pp. 1-74, 2006.
[27] 葉聿珮, "飛航操作品保系統成功因素之探討," 成功大學交通管理科學系學位論文, pp. 1-77, 2004.