1 Key Laboratory of Civil Aviation Wide Surveillance and Safety Operation Management & Control Technology, Civil Aviation University of China, Tianjin 300300, China
2 College of Safety Science and Engineering, Civil Aviation University of China, Tianjin 300300, China
3 Science and Technology Innovation Research Institute, Civil Aviation University of China, Tianjin 300300, China
To address the insufficient consideration of safety, the lack of temporal feature extraction, and the limited generalization ability in aircraft fuel-flow prediction, a safety-constrained LSR-TSO-SVR method for fuel flow prediction was proposed on the basis of A320 quick access recorder (QAR) data. The hyperparameters of support vector regression (SVR) were optimized by an improved tuna swarm optimization (TSO) algorithm. Lagged and sliding-window enhanced regression (LSR) and safety hard constraints were incorporated. An aircraft fuel-flow prediction model was then constructed. The results show that, in terms of accuracy, the LSR-TSO-SVR model achieves an average prediction error rate of only 0.94% for the A320, and the prediction accuracy of total fuel consumption reaches 99.97%, which is significantly better than those of the conventional SVR and extreme learning machine (ELM) models. In terms of generalization ability, the prediction error rates for the B737-900ER and C919 are 1.62 %and 1.19%, respectively, which indicates that cross-aircraft-type fuel flow prediction can be achieved by this method. In terms of safety, the predefined safety constraints are satisfied by the A320, B737-900ER, and C919.
SHI Tong-yu, JIAO Cai-jing, WANG Yan-tao.
Aircraft Fuel Flow Prediction Based on LSR-TSO-SVR under Safety Constraint[J].
Science Technology and Engineering, 2026, 26(29): 12810-12819 DOI:10.12404/j.issn.1671-1815.2507623
因此提出滞后与滑窗增强回归模型(lagged and sliding-window enhanced regression,LSR)。该模型引入时序特征,加入一阶差分ΔX、ΔY和二阶差分Δ2X、Δ2Y,让模型识别上升或下降趋势,增强对工况切换的敏感度,减少滞后误差;增加历史滑窗,采用5、15点历史滑动均值与历史滑动标准差,减少非平稳带来的系统性偏差,降低尖峰误判与过拟合。具体步骤如下。
IATA. Global outlook for air transport: economic performance of the airline industry[R]. Montreal: International Air Transport Association (IATA), 2024.
[2]
KrajcekN K, PapociP, NikolicD, et al. Fuel burn method assessment using automatic dependent surveillance-broadcast and European reanalysis data: limited flight sample analysis[J]. Aerospace, 2024, 11: 154.
[3]
DalmauR, PratsX, RamonjoanA, et al. Estimating fuel consumption from radar tracks: a validation exercise using FDR and radar tracks from descent trajectories[J]. CEAS Aeronaut, 2020, 11(2): 355-365.
ZhaoYifei, WangMengqi. Research on efficiency indicators of terminal area approach trajectory based on fuel consumption[J]. Journal of Safety and Environment, 2022, 22(6): 3403-3411.
[6]
QuC G, CaoH L, SunS, et al. Modelling of fuel flow in climb phase through multiple linear regression based on the data collected by quick access recorder[J]. Journal Européen des Systèmes Automatisés, 2019, 52(4): 409-413.
[7]
YantoJ, LiemR P. Cluster-based aircraft fuel estimation model for effective and efficient fuel budgeting on new routes[J]. Aerospace, 2022, 9(10): 62.
ChenMingqiang, ZhengWenhao, SunYanjun, et al. Fuel consumption prediction of general aviation aircraft based on regression tree and random forest[J]. Science Technology and Engineering, 2025, 25(7): 3026-3034.
[10]
MacitR, ÖzkanH. A, BaklaciogluT. Machine learning-based fuel flow rate prediction for Boeing 737-800 aircraft: a comprehensive approach across climb, cruise and descent flight phases[J]. Energy, 2025, 337: 13857.
ChenCong, LiLele, ChenHao, et al. Prediction about fuel flow of airplanes based on PLS-PSO-Elman[J]. Science Technology and Engineering, 2021, 21(5): 1963-1973.
ChenCong, HouLei, LiLele, et al. Prediction of aircraft fuel flow based on recurrent neural network[J]. Science Technology and Engineering, 2021, 21(27): 11663-11673.
[15]
TangW Z, DaiJ, LiY T. Aircraft range fuel prediction study based on WPD with IAPO optimized BiLSTM-KAN model[J]. Scientific Reports, 2025, 15: 12231.
[16]
WangB, ZouR Y, MaoJ F, et al. Developing an aircraft takeoff mass estimation model based on the hybrid KMI-DNN-BI model using quick access recorder (QAR) data[J]. Aerospace Science and Technology, 2025, 158: 109918.
[17]
AydınU, ÜlenginB. Analyzing air cargo flows of Turkish domestic routes: a comparative analysis of gravity models[J]. Journal of Air Transport Management, 2022, 102: 102217.
[18]
WangZ M, XueD B, WuL X, et al. A reliable predict-then-optimize approach for minimizing aircraft fuel consumption[J]. Transportation Research Part D: Transport and Environment. 2025, 142: 104693.
ChenCong, LiHaojie, ShiLizhong, et al. Aircraft fuel flow prediction based on NBEATS-MARS and calculation methods for aviation emission[J]. Journal of Aerospace Power, 2025, 41(5): 20250218.
CaoHuiling, JiaChao. Research of fuel flow regression model of aircraft climb phase based on QAR[J]. Journal of Civil Aviation University of China, 2013, 31(3): 31-35.
[23]
ZhaoY, WangZ, WangX, et al. Data driven fuel consumption prediction model for green aviation using radial basis function neural network[J]. Scientific Reports, 2025, 15(1): 26275.
[24]
XiongJ, ZouC L, WanY B, et al. Fuel consumption prediction for full flight phases toward sustainable aviation[J]. Sustainability, 2025, 17: 3358.
[25]
XieL, HanT, ZhouH. Tuna swarm optimization: a novel swarm-based metaheuristic algorithm for global optimization[J]. Computational Intelligence and Neuroscience, 2021, 2021: 920050.