Based on Long Short Time Memory (LSTM) model, a method of constructing the flight history data mining model, which can automatically extract the valuable target data in flight data is proposed. First, to obtain the data to be detected by sliding window method. Then, to train the pre-made training sample data into the constructed LSTM model to get the data mining model. And finally, to model the pattern recognition of the detected data into the trained LSTM model. The results show that this method of constructing flight data mining model has high generalization degree, and can be used to mine different kinds of target data. The result also show that the recognition rate has high engineering application value.
WANG Zhigang
,
WANG Yeguang
,
YANG Ning
,
MI Yufeng
,
QU Xiaolei
. Construction method of flight data mining model based on LSTM[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021
, 42(8)
: 525800
-525800
.
DOI: 10.7527/S1000-6893.2021.25800
[1] FAYYAD U, PIATETSKY-SHAPIRO G, SMYTH P. The KDD process for extracting useful knowledge from volumes of data[J]. Communications of the ACM, 1996, 39(11):27-34.
[2] 张美英, 何杰. 时间序列预测模型研究综述[J]. 数学的实践与认识, 2011, 41(18):189-195. ZHANG M Y, HE J. Summary on time series forecasting model[J]. Mathematics in Practice and Theory, 2011, 41(18):189-195(in Chinese).
[3] EZEKIEL M. Two methods of forecasting hog prices[J]. Journal of the American Statistical Association, 1927, 22(157):22-30.
[4] MCLEOD A I, LI W K. Diagnostic checking ARMA time series models using squared-residual autocorrelations[J]. Journal of Time Series Analysis, 1983, 4(4):269-273.
[5] 徐徐. 循环神经网络改进方法研究[D]. 上海:上海交通大学, 2017. XU X. Research and improvement of recurrent neural network[D]. Shanghai:Shanghai Jiao Tong University, 2017(in Chinese).
[6] CAI X D, ZHANG N, VENAYAGAMOORTHY G K, et al. Time series prediction with recurrent neural networks trained by a hybrid PSO-EA algorithm[J]. Neurocomputing, 2007, 70(13-15):2342-2353.
[7] HOCHREITER S. The vanishing gradient problem during learning recurrent neural nets and problem solutions[J]. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 1998, 6(2):107-116.
[8] 郝世林. 基于LSTM的上甑酒醅温度预测模型研究[D]. 武汉:湖北工业大学, 2020. HAO S L. Research on fermented grains temperature prediction model of make wine robot based on LSTM[D]. Wuhan:Hubei University of Technology, 2020(in Chinese).
[9] JIA G M, CHENG F Y, YANG J F, et al. Intelligent checking model of Chinese radiotelephony read-backs in civil aviation air traffic control[J]. Chinese Journal of Aeronautics, 2018, 31(12):2280-2289.
[10] 章树军, 蓝善祯, 卜琪, 等. 基于深度学习的动作识别方法简述[J]. 中国传媒大学学报(自然科学版), 2019, 26(5):44-49, 43. ZHANG S J, LAN S Z, BU Q, et al. A survey of action recognition based on deep learning[J]. Journal of Communication University of China (Science and Technology), 2019, 26(5):44-49, 43(in Chinese).
[11] 王志刚, 杨宁, 米禹丰. 基于动态时间规划和支持向量机的飞机机动动作识别方法[J]. 飞机设计, 2020, 40(4):35-40. WANG Z G, YANG N, MI Y F. Method on aircraft maneuver motion recognition based on dynamic time warping and support vector machine[J]. Aircraft Design, 2020, 40(4):35-40(in Chinese).
[12] 张秀林, 刘嘉, 张杨, 等. 一种飞行员最优控制模型加权系数计算方法[J]. 飞行力学, 2019, 37(3):15-19. ZHANG X L, LIU J, ZHANG Y, et al. A method for calculating the weighting coefficient of pilot optimal control model[J]. Flight Dynamics, 2019, 37(3):15-19(in Chinese).
[13] YUE Z J, LIU L, LONG T, et al. Virtual sensing method for monitoring vibration of continuously variable configuration structures using long short-term memory networks[J]. Chinese Journal of Aeronautics, 2020, 33(1):244-254.
[14] 成双, 郭渊博. 基于LSTM网络的异常操作行为检测方法[J]. 信息工程大学学报, 2019, 20(1):122-128. CHENG S, GUO Y B. Abnormal operation behavior detection method based on LSTM[J]. Journal of Information Engineering University, 2019, 20(1):122-128(in Chinese).
[15] 杨洪富, 贾晓亮. 基于LSTM的航空发动机排气温度预测[J]. 航空计算技术, 2018, 48(4):61-65. YANG H F, JIA X L. Aero engine exhaust gas temperature prediction based on LSTM[J]. Aeronautical Computing Technique, 2018, 48(4):61-65(in Chinese).
[16] MIKOLOV T, KOPECKY J, BURGET L, et al. Neural network based language models for highly inflective languages[C]//2009 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway:IEEE Press, 2009:4725-4728.
[17] GRAVES A, MOHAMED A R, HINTON G. Speech recognition with deep recurrent neural networks[C]//2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway:IEEE Press, 2013:6645-6649.
[18] MIKOLOV T, JOULIN A, CHOPRA S, et al. Learning longer memory in recurrent neural networks[EB/OL]. arXiv preprint:1412.7753, 2014.
[19] DING G, LEI D, YAO W. Aeroengine exhausted gas temperature prediction using process extreme learning machine[J]. Applied Mechanics and Materials, 2013, 423-426:2355-2362.
[20] DU J, DAI L R, HUO Q. Synthesized stereo mapping via deep neural networks for noisy speech recognition[C]//2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway:IEEE Press, 2014:1764-1768.
[21] XU Y, MO T, FENG Q W, et al. Deep learning of feature representation with multiple instance learning for medical image analysis[C]//2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway:IEEE Press, 2014:1626-1630.
CJA