基于熵权法的飞机燃油流量全航程组合预测
|
摘要
在复杂的航班运行中,影响各飞行阶段的主要因素不尽相同。以当前使用范围较广的B737NG飞机所使用的快速存取记录器(quick access recorder,QAR)的大量数据进行研究,将航段划分为巡航、爬升、下降等阶段,利用熵权法确定不同预测模型的权系数,建立全航程组合预测模型。利用Pearson相关性系数分析筛选建模数据,以平稳小波Rigorous SURE的方法对数据进行预处理、滤波去噪。针对BP神经网络(误差反向传播网络)在飞行状态复杂的下降及地面阶段预测效果不理想,引入回归模型进行修正。以熵值法确定动态权系数,即结合飞行阶段进行分段预测,以飞行参数为基础建立燃油流量(fuel flow,FF)的全航程组合预测模型。通过仿真分析,并选取航班中普遍且具代表性的情况验证预测模型的精确度,误差范围均在±3. 5%内,证明该模型合理且具有较广的适用范围。
In the complicated flight operation,the main factors that affect the flight phases are different. Based on the large amount data of Quick Access Recorder( QAR) used by B737 NG aircraft,the flight segment is divided into cruise,climb and descent stages. The weight coefficients of different prediction models are determined by entropy weight method,and the combined prediction model of the whole flight is established. Pearson correlation coefficients are used to analyze and filter the modeling data,and stationary wavelet Rigorous SURE is used to preprocess and filter the data. Regression model is introduced to modify BP neural network( BP neural network) for the complex decline of flight state and the unsatisfactory prediction effect at ground stage. Entropy method is used to determine the dynamic weight coefficient,that is,combined with the flight phase to predict the segment,based on flight parameters to establish a combined forecasting model of fuel flow( FF) for the whole flight range. Through simulation analysis,the accuracy of the prediction model is verified by choosing the common and representative situation in the flight. The error range is within 3. 5%,which proves that the model is reasonable and has a wide range of application.
In the complicated flight operation,the main factors that affect the flight phases are different. Based on the large amount data of Quick Access Recorder( QAR) used by B737 NG aircraft,the flight segment is divided into cruise,climb and descent stages. The weight coefficients of different prediction models are determined by entropy weight method,and the combined prediction model of the whole flight is established. Pearson correlation coefficients are used to analyze and filter the modeling data,and stationary wavelet Rigorous SURE is used to preprocess and filter the data. Regression model is introduced to modify BP neural network( BP neural network) for the complex decline of flight state and the unsatisfactory prediction effect at ground stage. Entropy method is used to determine the dynamic weight coefficient,that is,combined with the flight phase to predict the segment,based on flight parameters to establish a combined forecasting model of fuel flow( FF) for the whole flight range. Through simulation analysis,the accuracy of the prediction model is verified by choosing the common and representative situation in the flight. The error range is within 3. 5%,which proves that the model is reasonable and has a wide range of application.
引文
1王少萍.大型飞机机载系统预测与健康管理关键技术[J].航空学报,2014,35(6):1459-1472Wang Shaoping.Prognostics and healthmanagement key technology of aircraft airborne system[J].Journal of Aeronautics,2014,35(6):1459-1472
2刘清贵.直面高油价的挑战---中国民航节油中的问题和建议[J].中国民用航空,2005,11(8):25-28Liu Qinggui.Facing the challenge of high oil price---the problems and suggestions in fuel saving of Chinese civil aviation[J].Chinese Civil Aviation,2005,11(8):25-28
3曹惠玲,贾超.基于QAR的民航发动机燃油流量控制规律研究[J].科学技术与工程,2013,13(13):3814-3817Cao Huiling,Jia Chao.Research on fuel flow control law of civil aviation engine based on QAR[J].Science Technology and Engineering,2013,13(13):3814-3817
4谷润平,黄磊,赵向领.基于QAR数据的飞机发动机性能异常检测[J].航空计算技术,2015,45(4):1-7Gu Runping,Huang Lei,Zhao Xiangling.Detecting anomalies of aircraft engine performance based on QAR data[J].Aeronautical Computing Technique,2015,45(4):1-7
5耿宏,揭俊.基于QAR数据的飞机巡航段燃油流量回归模型[J].航空发动机,2008,34(4):46-50Geng Hong,Jie Jun.Fuel flow regression model of aircraft cruise based on QAR data[J].Aero-engine,2008,34(4):46-50
6黄永芳,黄圣国,孙同江.QAR数据译码的航班划分[J].交通运输工程学报,2004,4(1):114-117Huang Yongfang,Huang Shengguo,Sun Tongjiang.Flight dividing in QAR(Quick Access Recorder)data decoding[J].Journal of Trafic and Transportation Engineering,2004,4(1):114-117
7孙秀娟,陆新秀,刘法胜,等.基于熵权法的交通流组合预测模型研究[J].山东科技大学学报(自然科学版),2018,37(4):111-117Sun Xiujuan,Lu Xinxiu,Liu Fasheng,et al.Research on combination prediction model of traffic flow based on entropy weight method[J].Journal of Shandong University of Science and Technology(Natural and Science),2018,37(4):111-117
8高扬,王向章.基于快速存取记录仪数据的航空发动机整机性能综合评估研究[J].科学技术与工程,2016,16(25):322-326Gao Yang,Wang Xiangzhang.Research on performance assessment of overall aero-engine based on QAR data[J].Science Technology and Engineering,2016,16(25):322-326
9王超,周宣任,王蕾.基于轨迹数据的空中交通燃油消耗估算[J].空军工程大学学报(自然科学版),2018,19(4):25-30Wang Chao,Zhou Xuanren,Wang Lei.Research on the estimation of air traffic fuel consumption based on trajectory data[J].Journal of Air Force Engineering University(Natural Science Edition),2018,19(4):25-30
10李书明,任沛,黄燕晓.航空发动机基线方程的拟合[J].机械工程与自动化,2016(1):153-157Li Shuming,Ren Pei,Huang Yanxiao.Baseline equation fitting of aeroengine[J].Mechanical Engineering and Automation,2016(1):153-157
11汪冬华.多元统计分析与SPSS应用[M].上海:华东理工大学出版社,2010:81-82Wang Donghua.Multivariate statistical analysis and SPSS application[M].Shanghai:East China University of Science and Technology Press,2010:81-82
12齐敏,黄世震.基于Matlab的小波去噪算法研究[J].电子器件,2012,35(1):103-106Qi Min,Huang Shizhen.Research on wavelet threshold denoising method based on Matlab[J].Electronic Device,2012,35(1):103-106
13蔡艳平,李艾华,胡重庆,等.平稳小波自适应去噪用于曲轴瞬时角加速度测量[J],振动测试与诊断,2010,30(3):310-314Cai Yanping,Li Aihua,Hu Chongqing,et al.Measurement of instantaneous angular acceleration of crankshaft using adaptive stationary wavelet denoising[J],Vibration Testing and Diagnosis,2010,30(3):310-314
14杨恢先,王绪四,谢鹏鹤.改进阈值与尺度间相关的小波红外图像去噪[J].自动化学报,2011,37(10):1167-1174Yang Huixian,Wang Xusi,Xie Penghe.Infrared image denoising based on improved threshold and inter-scale correlations of wavelet transform[J].ACTA AutomaticSinica,2011,37(10):1167-1174
15陈晓曦,王延杰,刘恋.小波阈值去噪法的深入研究[J].激光与红外,2012,42(1):105-110Chen Xiaoxi,Wang Yanjie,Liu Lian.Deep study on wavelet threshold method for image noise removing[J],Laser&Infrared,2012,42(1):105-110
16彭玉华.一种改进的小波变换阈值去噪方法[J].通信学报,2004,25(8):119-123Peng Yuhua.An improved thresholding method in wavelet transform domain for denosing[J].Journal of China Institute of Communications,2004,25(8):119-123
17陈雯柏.人工神经网络原理与实践[M].西安:西安电子科技大学出版社,2016:44-45Chen Wenbo.Principle and practice of artificial neural network[M].Xi’an:Xi'an University of Electronic Science and Technology Press,2016:44-45
18张捍东.粒子群优化BP算法在液压系统故障诊断中应用[J].系统仿真学报,2016,28(5):1186-1190Zhang Handong.Application of particle swarm optimization BP algorithm in fault diagnosis of hydraulic system[J].Journal of System Simulation,2016,28(5):1186-1190
19郭倩旎.航空故障诊断与健康管理技术[M].北京:航空工业出版社,2013Guo Qianni.Aviation fault diagnosis and health management technology[M].Beijing:Aviation Industry Press,2013
20陈华友.熵值法及其在确定组合预测权系数中的应用[J].安徽大学学报,2003,27(4):1-6Chen Huayou.Entropy method and application to determine weights of combination forecasting[J].Journal of Anhui University,2003,27(4):1-6
21孙海蓉,王蕊,耿军亚.基于信息熵的BP网络在热工系统建模中的应用[J].系统仿真学报,2017,29(1):226-233Sun Hairong,Wang Rui,Geng Junya.Thermal system modeling based on entropy and BP neural network[J].Journal of System Simulation,2017,29(1):226-233
2刘清贵.直面高油价的挑战---中国民航节油中的问题和建议[J].中国民用航空,2005,11(8):25-28Liu Qinggui.Facing the challenge of high oil price---the problems and suggestions in fuel saving of Chinese civil aviation[J].Chinese Civil Aviation,2005,11(8):25-28
3曹惠玲,贾超.基于QAR的民航发动机燃油流量控制规律研究[J].科学技术与工程,2013,13(13):3814-3817Cao Huiling,Jia Chao.Research on fuel flow control law of civil aviation engine based on QAR[J].Science Technology and Engineering,2013,13(13):3814-3817
4谷润平,黄磊,赵向领.基于QAR数据的飞机发动机性能异常检测[J].航空计算技术,2015,45(4):1-7Gu Runping,Huang Lei,Zhao Xiangling.Detecting anomalies of aircraft engine performance based on QAR data[J].Aeronautical Computing Technique,2015,45(4):1-7
5耿宏,揭俊.基于QAR数据的飞机巡航段燃油流量回归模型[J].航空发动机,2008,34(4):46-50Geng Hong,Jie Jun.Fuel flow regression model of aircraft cruise based on QAR data[J].Aero-engine,2008,34(4):46-50
6黄永芳,黄圣国,孙同江.QAR数据译码的航班划分[J].交通运输工程学报,2004,4(1):114-117Huang Yongfang,Huang Shengguo,Sun Tongjiang.Flight dividing in QAR(Quick Access Recorder)data decoding[J].Journal of Trafic and Transportation Engineering,2004,4(1):114-117
7孙秀娟,陆新秀,刘法胜,等.基于熵权法的交通流组合预测模型研究[J].山东科技大学学报(自然科学版),2018,37(4):111-117Sun Xiujuan,Lu Xinxiu,Liu Fasheng,et al.Research on combination prediction model of traffic flow based on entropy weight method[J].Journal of Shandong University of Science and Technology(Natural and Science),2018,37(4):111-117
8高扬,王向章.基于快速存取记录仪数据的航空发动机整机性能综合评估研究[J].科学技术与工程,2016,16(25):322-326Gao Yang,Wang Xiangzhang.Research on performance assessment of overall aero-engine based on QAR data[J].Science Technology and Engineering,2016,16(25):322-326
9王超,周宣任,王蕾.基于轨迹数据的空中交通燃油消耗估算[J].空军工程大学学报(自然科学版),2018,19(4):25-30Wang Chao,Zhou Xuanren,Wang Lei.Research on the estimation of air traffic fuel consumption based on trajectory data[J].Journal of Air Force Engineering University(Natural Science Edition),2018,19(4):25-30
10李书明,任沛,黄燕晓.航空发动机基线方程的拟合[J].机械工程与自动化,2016(1):153-157Li Shuming,Ren Pei,Huang Yanxiao.Baseline equation fitting of aeroengine[J].Mechanical Engineering and Automation,2016(1):153-157
11汪冬华.多元统计分析与SPSS应用[M].上海:华东理工大学出版社,2010:81-82Wang Donghua.Multivariate statistical analysis and SPSS application[M].Shanghai:East China University of Science and Technology Press,2010:81-82
12齐敏,黄世震.基于Matlab的小波去噪算法研究[J].电子器件,2012,35(1):103-106Qi Min,Huang Shizhen.Research on wavelet threshold denoising method based on Matlab[J].Electronic Device,2012,35(1):103-106
13蔡艳平,李艾华,胡重庆,等.平稳小波自适应去噪用于曲轴瞬时角加速度测量[J],振动测试与诊断,2010,30(3):310-314Cai Yanping,Li Aihua,Hu Chongqing,et al.Measurement of instantaneous angular acceleration of crankshaft using adaptive stationary wavelet denoising[J],Vibration Testing and Diagnosis,2010,30(3):310-314
14杨恢先,王绪四,谢鹏鹤.改进阈值与尺度间相关的小波红外图像去噪[J].自动化学报,2011,37(10):1167-1174Yang Huixian,Wang Xusi,Xie Penghe.Infrared image denoising based on improved threshold and inter-scale correlations of wavelet transform[J].ACTA AutomaticSinica,2011,37(10):1167-1174
15陈晓曦,王延杰,刘恋.小波阈值去噪法的深入研究[J].激光与红外,2012,42(1):105-110Chen Xiaoxi,Wang Yanjie,Liu Lian.Deep study on wavelet threshold method for image noise removing[J],Laser&Infrared,2012,42(1):105-110
16彭玉华.一种改进的小波变换阈值去噪方法[J].通信学报,2004,25(8):119-123Peng Yuhua.An improved thresholding method in wavelet transform domain for denosing[J].Journal of China Institute of Communications,2004,25(8):119-123
17陈雯柏.人工神经网络原理与实践[M].西安:西安电子科技大学出版社,2016:44-45Chen Wenbo.Principle and practice of artificial neural network[M].Xi’an:Xi'an University of Electronic Science and Technology Press,2016:44-45
18张捍东.粒子群优化BP算法在液压系统故障诊断中应用[J].系统仿真学报,2016,28(5):1186-1190Zhang Handong.Application of particle swarm optimization BP algorithm in fault diagnosis of hydraulic system[J].Journal of System Simulation,2016,28(5):1186-1190
19郭倩旎.航空故障诊断与健康管理技术[M].北京:航空工业出版社,2013Guo Qianni.Aviation fault diagnosis and health management technology[M].Beijing:Aviation Industry Press,2013
20陈华友.熵值法及其在确定组合预测权系数中的应用[J].安徽大学学报,2003,27(4):1-6Chen Huayou.Entropy method and application to determine weights of combination forecasting[J].Journal of Anhui University,2003,27(4):1-6
21孙海蓉,王蕊,耿军亚.基于信息熵的BP网络在热工系统建模中的应用[J].系统仿真学报,2017,29(1):226-233Sun Hairong,Wang Rui,Geng Junya.Thermal system modeling based on entropy and BP neural network[J].Journal of System Simulation,2017,29(1):226-233