Analyzing commercial aircraft fuel consumption during descent: A case study using an improved K-means clustering algorithm

Abstract The analysis of aircraft fuel consumption remains an important topic as fuel consumption constitutes a large portion of airline operational costs, and exhaust emissions generated by aircraft gradually have become an essential aspect of urban air pollution, especially during takeoff and descent. Previous studies have focused mainly on optimizing fuel loss and greenhouse gases emission via three key methods: reducing additional aircraft load, using inventive air transfer control methods, and identifying the best-performing aviation systems for all conditions. However, there are few studies that have considered the relationships among fuel consumption, pilot behavior, and flight factors. This study fills this gap by focusing on the relationships between fuel consumption and three factors during the descent phase: altitude, weight, and speed. Further, we propose an improved K-means clustering algorithm to analyze the flight data, conducting clustering analysis on multi-dimensional data based on real flight records of Boeing 737s operated by China Eastern Airlines. We conclude the highlights of this study into three aspects: (1) the relationship between aircraft descent and fuel consumption is investigated through clustering analysis to find a fuel-efficient aircraft descent. (2) an improved K-means clustering algorithm is proposed to analyze flight data. (3) the better aircraft descent is the suggestion for pilots by analyzing the clustering results, which is a good supplement to the Flight Crew Operating Manual (FCOM). In the case study, the improved K-means algorithm is used for the cluster analysis of data from the quick access recorders of two aircraft descending into Chengdu Shuangliu Airport (CTU) in China. Compared with the method that does not use the analysis results for the descending, the average fuel consumption per unit of time decreases by 17.5% when we use our proposed method. In the Shanghai Pudong Airport (PVG), our proposed method reduces average fuel consumption per unit of time by 19.3%.

[1]  Mehmet Melikoglu,et al.  Modelling and forecasting the demand for jet fuel and bio-based jet fuel in Turkey till 2023 , 2017 .

[2]  Gianfranco Chicco,et al.  Electrical Load Pattern Grouping Based on Centroid Model With Ant Colony Clustering , 2013, IEEE Transactions on Power Systems.

[3]  Kenneth Button,et al.  International air transportation and economic development , 2000 .

[4]  Youhua Tang,et al.  Evaluating ammonia (NH3) predictions in the NOAA National Air Quality Forecast Capability (NAQFC) using in situ aircraft, ground-level, and satellite measurements from the DISCOVER-AQ Colorado campaign , 2016 .

[5]  Joosung J. Lee,et al.  Can we accelerate the improvement of energy efficiency in aircraft systems , 2010 .

[6]  R. Ramaprabha,et al.  Comprehensive analysis on the role of array size and configuration on energy yield of photovoltaic systems under shaded conditions , 2015 .

[7]  N.D. Hatziargyriou,et al.  Two-Stage Pattern Recognition of Load Curves for Classification of Electricity Customers , 2007, IEEE Transactions on Power Systems.

[8]  Antonio Franco,et al.  Stochastic analysis of fuel consumption in aircraft cruise subject to along-track wind uncertainty , 2017 .

[9]  Z. Vale,et al.  Daily wind power profiles determination using clustering algorithms , 2012, 2012 IEEE International Conference on Power System Technology (POWERCON).

[10]  Mirkin Boris,et al.  Clustering: A Data Recovery Approach , 2012 .

[11]  Sujit Das,et al.  Energy and emissions saving potential of additive manufacturing: the case of lightweight aircraft components , 2016 .

[12]  Debashisha Jena,et al.  Modeling of photovoltaic system for uniform and non-uniform irradiance: A critical review , 2015 .

[13]  Vladimir Makarenkov,et al.  Optimal Variable Weighting for Ultrametric and Additive Trees and K-means Partitioning: Methods and Software , 2001, J. Classif..

[14]  Nicole Adler,et al.  Aircraft trip cost parameters: A function of stage length and seat capacity , 2006 .

[15]  Wei-Shen Tai,et al.  Apply extended self-organizing map to cluster and classify mixed-type data , 2011, Neurocomputing.

[16]  Z. Vale,et al.  An electric energy consumer characterization framework based on data mining techniques , 2005, IEEE Transactions on Power Systems.

[17]  Zhenhong Yu,et al.  Evaluation of PM emissions from two in-service gas turbine general aviation aircraft engines , 2017 .

[18]  Antonio A. Trani,et al.  A Neural Network Model to Estimate Aircraft Fuel Consumption , 2004 .

[19]  Mehrdad Kazerani,et al.  A Clustering-Based Method for Quantifying the Effects of Large On-Grid PV Systems , 2010, IEEE Transactions on Power Delivery.

[20]  G H Ball,et al.  A clustering technique for summarizing multivariate data. , 1967, Behavioral science.

[21]  Megan S. Ryerson,et al.  The impact of airline mergers and hub reorganization on aviation fuel consumption , 2014 .

[22]  Marc A. Rosen,et al.  Relationship between fuel consumption and altitude for commercial aircraft during descent: Preliminary assessment with a genetic algorithm , 2012 .

[23]  B. Asaei,et al.  Clustering-based optimal sizing and siting of photovoltaic power plant in distribution network , 2012, 2012 11th International Conference on Environment and Electrical Engineering.

[24]  George J. Tsekouras,et al.  A new classification pattern recognition methodology for power system typical load profiles , 2008 .

[25]  George J. Tsekouras,et al.  A new pattern recognition methodology for classification of load profiles for ships electric consumers , 2009 .

[26]  Ozgur Balli,et al.  Exergy modeling for evaluating sustainability level of a high by-pass turbofan engine used on commercial aircrafts , 2017 .

[27]  Gianfranco Chicco,et al.  Load pattern clustering for short-term load forecasting of anomalous days , 2001, 2001 IEEE Porto Power Tech Proceedings (Cat. No.01EX502).

[28]  Morton E. O'Kelly,et al.  Fuel burn rates of commercial passenger aircraft: variations by seat configuration and stage distance , 2014 .

[29]  Megan S. Ryerson,et al.  Integrating airline operational practices into passenger airline hub definition , 2013 .

[30]  P. Postolache,et al.  Customer Characterization Options for Improving the Tariff Offer , 2002, IEEE Power Engineering Review.

[31]  Yunming Ye,et al.  Weighting Method for Feature Selection in K-Means , 2007 .

[32]  Marion Steven,et al.  The influence of strategic airline alliances in passenger transportation on carbon intensity , 2013 .

[33]  Tolga Baklacioglu,et al.  Modeling the fuel flow-rate of transport aircraft during flight phases using genetic algorithm-optimized neural networks , 2016 .

[34]  C. Senabre,et al.  Development of a methodology for clustering electricity-price series to improve customer response initiatives , 2010 .

[35]  Changxu Wu,et al.  An analysis of flight Quick Access Recorder (QAR) data and its applications in preventing landing incidents , 2014, Reliab. Eng. Syst. Saf..

[36]  Trevor M. Young,et al.  Simplified Thrust and Fuel Consumption Models for Modern Two-Shaft Turbofan Engines , 2008 .

[37]  Shanlin Yang,et al.  Household monthly electricity consumption pattern mining: A fuzzy clustering-based model and a case study , 2017 .

[38]  Hiroyuki Mori,et al.  Application of preconditioned Generalized radial Basis Function Network to prediction of photovoltaic power generation , 2012, 2012 3rd IEEE PES Innovative Smart Grid Technologies Europe (ISGT Europe).

[39]  Yan Zhang,et al.  Big data-informed energy efficiency assessment of China industry sectors based on K-means clustering , 2018 .

[40]  F. Gubina,et al.  Determining the load profiles of consumers based on fuzzy logic and probability neural networks , 2004 .

[41]  Michael K. Ng,et al.  An optimization algorithm for clustering using weighted dissimilarity measures , 2004, Pattern Recognit..

[42]  Dries Verstraete,et al.  On the energy efficiency of hydrogen-fuelled transport aircraft , 2015 .

[43]  J. V. Milanovic,et al.  Wind Farm Model Aggregation Using Probabilistic Clustering , 2013, IEEE Transactions on Power Systems.

[44]  B. P. Collins,et al.  Estimation of aircraft fuel consumption , 1982 .

[45]  Walid Abdallah,et al.  On the design of an embedded wireless sensor network for aircraft vibration monitoring using efficient game theoretic based MAC protocol , 2017, Ad Hoc Networks.

[46]  B. Langrand,et al.  Coupled fluid-structure computational methods for aircraft ditching simulations , 2017 .

[47]  Ray C. Chang,et al.  Examination of excessive fuel consumption for transport jet aircraft based on fuzzy-logic models of flight data , 2015, Fuzzy Sets Syst..