Dynamic Bayesian networks model for causal-time series coupling in aircraft takeoff attitude and flight operations

doi:10.16511/j.cnki.qhdxxb.2024.22.022

PDF(12220 KB)

Journal of Tsinghua University(Science and Technology) ›› 2024, Vol. 64 ›› Issue (6) : 1070-1081. DOI: 10.16511/j.cnki.qhdxxb.2024.22.022

PUBLIC SAFETY

Dynamic Bayesian networks model for causal-time series coupling in aircraft takeoff attitude and flight operations

{{article.zuoZhe_EN}}

Author information +

History +

Abstract

[Objective] During takeoff of civil aviation aircraft, pilot operational errors can easily lead to accidents, such as tail strikes. The aircraft takeoff attitude is closely related to flight operations. Therefore, focused on the decoupling problem between aircraft takeoff attitude and flight operations, guided by the "Safety II" mode, the coupling mechanism between aircraft takeoff attitude and flight operations is studied. This investigation considers the risk response performance throughout the entire process of aircraft takeoff.[Methods] The research is based on the flight quick access recorder (QAR) data of a domestic airline's A319 fleet. A coupling model of aircraft takeoff attitude, flight operations, aircraft performance, and flight environment is established using dynamic Bayesian networks (DBN) and Genie software for parameter learning and modeling. Daily flight data are deeply explored and fully utilized to study the causal-time series coupling mechanism between flight operations and aircraft takeoff attitude. Initially, based on the theory of safety resilience, the causal-time series coupling (CTC) model is developed to analyze the aircraft takeoff attitude and flight operations. Then, based on the QAR data of 1 359 flight segments of a domestic airline's A319 fleet, the CTC-DBN model is quantified and validated using Genie software. Results show that the CTC-DBN model can effectively analyze the dynamic formation mechanism of aircraft takeoff attitude. Finally, single and combined scenarios, such as heavy load, light load, downwind, and headwind, are selected to determine the optimal flight operation mode by adjusting the probability distribution of key flight operation nodes. The coupling mechanism between aircraft takeoff attitude and flight operations under different scenarios is studied, ultimately improving the pilot's ability to respond to risks in advance.[Results] The results indicate that the model can effectively analyze the dynamic formation mechanism of aircraft takeoff attitude. (1) The difference in aircraft weight is mainly reflected in the different throttle commands in the moment of rotation and the varied pitch commands in the moment of takeoff. A relatively large weight of the aircraft indicates considerable throttle in the moment of rotation and rapid pitch command in the moment of takeoff to obtain sufficient lift for the aircraft. (2) The different wind directions are mainly manifested by varied throttle commands at three distinct moments. The throttle of the headwind scenario is greater than that of the tailwind scenario in all three instances, thereby overcoming the wind speed and obtaining sufficient airspeed to ultimately ensure sufficient lift for the aircraft. (3) Compared with the optimal flight operation modes of four single scenarios, the combination of two scenarios increases the throttle commands due to heavy weight and headwinds. The throttle command exhibits a decreasing trend owing to its small weight and downwind. The pitch command at the time of takeoff in various scenarios has immediately become the main mode.[Conclusions] The causal-time series coupling mechanism between flight operations and aircraft takeoff attitude is studied using the CTC-DBN model. This research ultimately provides guidance for pilot operations and improves the risk response ability of pilots during the aircraft takeoff process. Subsequent research should combine other data, such as terrain, meteorology, and pilot characteristics, to conduct in-depth studies on different types of takeoff and landing.

Key words

aircraft attitude / flight operations / risk response / quick access recorder (QAR) data / dynamic Bayesian networks (DBN)

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

ZHANG Xiuyan, WANG Qi. Dynamic Bayesian networks model for causal-time series coupling in aircraft takeoff attitude and flight operations[J]. Journal of Tsinghua University(Science and Technology). 2024, 64(6): 1070-1081 https://doi.org/10.16511/j.cnki.qhdxxb.2024.22.022

References

[1] 黄正.防止高原机场超轮速[J].科技创新导报, 2013(17):81. HUANG Z. Preventing excessive wheel speed at high altitude airports[J]. Science and Technology Innovation Herald, 2013(17):81.(in Chinese)
[2] 钱宇,龙涛.基于主成分回归的运输飞机超轮速诱因研究[J].计算机仿真, 2022, 39(10):34-39, 65. QIAN Y, LONG T. Study on the inducement of transport aircraft exceeding tire speed rating based on principal component regression[J]. Computer Simulation, 2022, 39(10):34-39, 65.(in Chinese)
[3] ALLIGIER R. Predictive distribution of mass and speed profile to improve aircraft climb prediction[J]. Journal of Air Transportation, 2020, 28(3):114-123.
[4] 张一山,余江.民航飞机起飞超轮速的分析与研究[J].民航学报, 2021, 5(2):79-84. ZHANG Y S, YU J. Analysis and research on excessive wheel speed in civil aircraft take-off[J]. Journal of Civil Aviation, 2021, 5(2):79-84.(in Chinese)
[5] 孙瑞山,杨绎煊.飞机起飞擦机尾事件的风险预测研究[J].安全与环境工程, 2016, 23(2):153-156. SUN R S, YANG Y X. Risk prediction of aircraft tail strike events during take-off phase[J]. Safety and Environmental Engineering, 2016, 23(2):153-156.(in Chinese)
[6] 杨星月,汪磊.基于飞行员模型的民机擦机尾事件分析[J].飞行力学, 2022, 40(5):89-94. YANG X Y, WANG L. Analysis of civil aircraft tail striking event based on pilot model[J]. Flight Dynamics, 2022, 40(5):89-94.(in Chinese)
[7] NOH K S. A study on B737NG aircraft tail strike during takeoff[J]. Journal of the Korean Society for Aviation and Aeronautics, 2009, 17(4):70-75.
[8] WANG X, WANG H F, YU L L. Aircraft tail strike events during take-off phase:A risk evaluation model[C]//Proceedings of the 12th International Conference on Reliability, Maintainability, and Safety. Shanghai, 2018:142-145.
[9] DRESSLER R F. New approach to air safety statistics[J]. Journal of Aircraft, 1967, 4(4):347-355.
[10] MOSLEH A, GROTH K M, WANG C, et al. Methodology and software platform for multi-layer causal modeling[C]//Proceedings of 2008 Annual Conference of the European Society for Reliability. Valencia, Spain, 2008:3-12.
[11] ORIOLA A O, ADEKUNLE A K. Assessment of runway accident hazards in Nigeria aviation sector[J]. International Journal for Traffic and Transport Engineering, 2015, 5(2):82-92.
[12] CHEN Y Q, HOU Y J, HU D F, et al. Research about optimizing the wake turbulence separation for takeoff of CSPRs under crosswind conditions[C]//Proceedings of the 2nd International Conference on Smart Vehicular Technology, Transportation, Communication and Applications. Cham, Switzerland:Springer, 2018:457-464.
[13] HUIJBRECHTS E J A M, KOOLSTRA H J, MULDER J A. Using V_mcg-limited V₁ controllability issues on contaminated runways and in crosswind[J]. Journal of Aircraft, 2019, 56(4):1342-1352.
[14] HAM D H. Safety-II and resilience engineering in a nutshell:An introductory guide to their concepts and methods[J]. Safety and Health at Work, 2021, 12(1):10-19.
[15] 李升友.安全系统思想及其理论核心研究[J].中国安全科学学报, 2016, 26(1):28-33. LI S Y. Research on core theories of safety system thoughts[J]. China Safety Science Journal, 2016, 26(1):28-33.(in Chinese)
[16] 黄浪,吴超,杨冕,等.韧性理论在安全科学领域中的应用[J].中国安全科学学报, 2017, 27(3):1-6. HUANG L, WU C, YANG M, et al. Application of resilience theory in field of safety science[J]. China Safety Science Journal, 2017, 27(3):1-6.(in Chinese)
[17] 张秀艳,王琪.基于PEE动态韧性模型的安全系统风险应对机制[J].综合运输, 2023, 45(12):71-76, 165. ZHANG X Y, WANG Q. The risk response mechanism of safety system based on PEE dynamical resilience model[J]. China Transportation Review, 2023, 45(12):71-76, 165.(in Chinese)
[18] 刘洋.基于独立性验证和因果推理的贝叶斯网络结构学习[D].长春:吉林大学, 2021. LIU Y. Structure learning of Bayesian networks based on independence verification and causal inference[D]. Changchun:Jilin University, 2021.(in Chinese)
[19] 张少中,章锦文,张志勇,等.面向大规模数据集的贝叶斯网络参数学习算法[J].计算机应用, 2006, 26(7):1689-1691. ZHANG S Z, ZHANG J W, ZHANG Z Y, et al. Parameter learning for Bayesian networks with large data set[J]. Computer Applications, 2006, 26(7):1689-1691.(in Chinese)
[20] TABANDEH A, GARDONI P, MURPHY C, et al. Societal risk and resilience analysis:Dynamic Bayesian network formulation of a capability approach[J]. ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A:Civil Engineering, 2019, 5(1):04018046.
[21] 周毅,胡锡健.动态贝叶斯网络在战争身份识别中的应用[J].山西师范大学学报(自然科学版), 2014, 28(3):9-13. ZHOU Y, HU X J. Application of dynamic Bayesian network in combat identification[J]. Journal of Shanxi Normal University (Natural Science Edition), 2014, 28(3):9-13.(in Chinese)
[22] 钱宇,龙涛.基于云贝叶斯网络的运输飞机超轮速风险评估[J].航空工程进展, 2022, 13(3):171-178. QIAN Y, LONG T. Risk assessment on transport aircraft exceeding tire speed rating based on cloud Bayesian network[J]. Advances in Aeronautical Science and Engineering, 2022, 13(3):171-178.(in Chinese)
[23] 李明,洪梅.基于动态贝叶斯网络的海战场自然环境评估与预测[J].军事运筹与系统工程, 2018, 32(1):37-43. LI M, HONG M. Assessment and forecast of sea-battlefield natural environment based on dynamic Bayesian network[J]. Military Operations Research and Systems Engineering, 2018, 32(1):37-43.(in Chinese)
[24] 汪磊,孙景陆,王文超,等.基于QAR数据的着陆超限风险贝叶斯网络分析模型[J].安全与环境学报, 2023, 23(1):26-34. WANG L, SUN J L, WANG W C, et al. Bayesian network analysis model on landing exceedance risk based on flight QAR data[J]. Journal of Safety and Environment, 2023, 23(1):26-34.(in Chinese)
[25] 任佳,高晓光,茹伟.目标数据缺失下离散动态贝叶斯网络的参数学习[J].系统工程与电子技术, 2011, 33(8):1885-1890. REN J, GAO X G, RU W. Parameter learning of discrete dynamic Bayesian network with missing target data[J]. Systems Engineering and Electronics, 2011, 33(8):1885-1890.(in Chinese)
[26] KAMMOUH O, GARDONI P, CIMELLARO G P. Probabilistic framework to evaluate the resilience of engineering systems using Bayesian and dynamic Bayesian networks[J]. Reliability Engineering&System Safety, 2020, 198:106813.
[27] SUN J, SUN J. A dynamic Bayesian network model for real-time crash prediction using traffic speed conditions data[J]. Transportation Research Part C:Emerging Technologies, 2015, 54:176-186.
[28] 于培永,郭志刚,刘月浩.基于动态贝叶斯网络的三维电力检修系统[J].自动化技术与应用, 2023, 42(9):180-182. YU P Y, GUO Z G, LIU Y H. Three dimensional power maintenance system based on dynamic Bayesian network[J]. Techniques of Automation and Applications, 2023, 42(9):180-182.(in Chinese)
[29] 刘浩,王昊,孟光磊,等.基于动态贝叶斯网络和模糊灰度理论的飞行训练评估[J].航空学报, 2021, 42(8):525838. LIU H, WANG H, MENG G L, et al. Flight training evaluation based on dynamic Bayesian network and fuzzy gray theory\[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(8):525838.(in Chinese)
[30] BERINGER D B, WILLIGES R C, ROSCOE S N. The transition of experienced pilots to a frequency-separated aircraft attitude display:A flight experiment[J]. Proceedings of the Human Factors Society Annual Meeting, 1974, 18(1):62-70.