Electronics and Electrical Engineering and Control

Online prediction of non-stationary chaotic time series with noise based on combinational NARX neural network

  • Jiahao GE ,
  • Jinwu XIANG ,
  • Daochun LI
Expand
  • School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China
E-mail: ryange@buaa.edu.cn

Received date: 2024-01-09

  Revised date: 2024-03-04

  Accepted date: 2024-03-21

  Online published: 2024-03-29

Supported by

Postdoctoral Fellowship Program of CPSF(GZC20233371)

Abstract

In response to the complex evolution of chaotic time series, as well as the serious impact of non-stationary features and noise on the short-term prediction accuracy of chaotic time series, an online combination prediction method of Non-stationary Noisy Chaotic Time Series (NNCTS) is proposed based on Forward Difference, Improved Wavelet Packet Denoising, and Nonlinear Auto-Regressive with eXogeneous inputs network (FD-IWPD-NARX). In the framework of moving horizons, the forward difference is used to the stabilize time series data in each window. The wavelet packet denoising threshold function is improved to enhance the data denoising effect. The stabilized denoised chaotic time series is then trained and tested using a series parallel closed-loop NARX neural network. The results show that the forward difference and the proposed improved wavelet packet denoising can effectively improve the predictive performance of the NARX neural network. Compared with the windowless NARX neural network, Recurrent Neural Network (RNN), and standard Long and Short-Term Memory network (LSTM), the FD-IWPD-NARX network proposed can complete model training based on a smaller amount of data, having advantages in prediction accuracy. The average model training time in each window is shortened to 0.12 s, which has the potential for online application.

Cite this article

Jiahao GE , Jinwu XIANG , Daochun LI . Online prediction of non-stationary chaotic time series with noise based on combinational NARX neural network[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2024 , 45(21) : 330128 -330128 . DOI: 10.7527/S1000-6893.2024.30128

References

1 赵德敏. 非线性颤振系统的分岔与混沌[D]. 天津: 天津大学, 2010.
  ZHAO D M. Bifurcation and chaos of nonlinear flutter system[D].Tianjin: Tianjin University, 2010 (in Chinese).
2 张淑华. 飞机机翼的非线性混沌研究[J]. 甘肃科技200521(8): 93-94, 85.
  ZHANG S H. Study on nonlinear chaos of aircraft wings[J]. Gansu Science and Technology200521(8): 93-94, 85 (in Chinese).
3 张志浩, 姚宏, 苏磊. 飞机大迎角纵向机动稳定性及混沌分析[C]∥中国力学大会, 2013.
  ZHANG Z H, YAO H, SU L. Stability and chaos analysis of aircraft longitudinal maneuver at high angles of attack [C]∥China Mechanics Conference, 2013 (in Chinese).
4 马建仓, 刘琦, 马艳玲. 飞机发动机混沌振动信号盲分离检测方法[J]. 航空学报200930(1): 81-85.
  MA J C, LIU Q, MA Y L. Detection of chaotic vibration signals of aero-engines with blind separation[J]. Acta Aeronautica et Astronautica Sinica200930(1): 81-85 (in Chinese).
5 郭阳明, 蔡小斌, 付琳娟, 等. 基于回声状态网络的飞机混沌时间序列预测模型[J]. 西北工业大学学报201230(4): 607-611.
  GUO Y M, CAI X B, FU L J, et al. An effective prediction model for aircraft chaos time series based on echo state networks (ESN)[J]. Journal of Northwestern Polytechnical University201230(4): 607-611 (in Chinese).
6 张永芳, 吕延军, 黑棣, 等. 轴向槽气体轴承—非线性转子系统的分岔和混沌[J]. 机械工程学报201450 (5): 216-217.
  ZHANG Y F, LV Y J, HEI D, et al. Bifurcation and chaos of an axial grooved gas bearing nonlinear rotor system[J]. Journal of Mechanical Engineering201450(5): 216-217 (in Chinese).
7 RAHMAN M M, SHAKERI M, KHATUN F, et al. A comprehensive study and performance analysis of deep neural network-based approaches in wind time-series forecasting[J]. Journal of Reliable Intelligent Environments20239(2): 183-200.
8 袁全勇. 风速时间序列非线性分析及短期预测[D]. 上海: 上海理工大学, 2018.
  YUAN Q Y. Nonlinear analysis and short-term prediction of wind speed time series[D]. Shanghai: University of Shanghai for Science & Technology, 2018 (in Chinese).
9 GOUDARZI S, JAFARI S, MORADI M H, et al. NARX prediction of some rare chaotic flows: Recurrent fuzzy functions approach[J]. Physics Letters A2016380(5-6): 696-706.
10 BLANCHARD T, SAMANTA B. Wind speed forecasting using neural networks[J]. Wind Engineering202044(1): 33-48.
11 李应求, 安勃, 李恒通. 基于NARX及混沌支持向量机的短期风速预测[J]. 电力系统保护与控制201947(23): 65-73.
  LI Y Q, AN B, LI H T. Short-term wind speed prediction based on NARX and chaos-support vector machine[J]. Power System Protection and Control201947(23): 65-73 (in Chinese).
12 XIU Y, ZHANG W. Multivariate chaotic time series prediction based on NARX neural networks[C]∥Proceedings of the 2017 2nd International Conference on Electrical, Automation and Mechanical Engineering (EAME 2017). Paris: Atlantis Press, 2017.
13 陈开民, 顾宏斌, 李鹏, 等. 一种基于NARX神经网络的纵向飞行动力学建模方法[J]. 飞行力学202341(5): 37-43, 51.
  CHEN K M, GU H B, LI P, et al. A longitudinal flight dynamics modeling method based on NARX neural network [J]. Flight Dynamics202341(5):37-43, 51 (in Chinese).
14 杨洁. 城市供水管网系统的预测建模研究[D]. 杭州: 杭州电子科技大学, 2015.
  YANG J. Study on predictive modeling of urban water supply pipe network system[D]. Hangzhou: Hangzhou Dianzi University, 2015 (in Chinese).
15 ACU?A G, RAMIREZ C, CURILEM M. Comparing NARX and NARMAX models using ANN and SVM for cash demand forecasting for ATM[C]∥The 2012 International Joint Conference on Neural Networks (IJCNN). Piscataway: IEEE Press, 2012: 1-6.
16 张旭冉. 基于LSTM和NARX的风电场短期风电功率预测研究[D]. 济南: 山东建筑大学, 2021.
  ZHANG X R. Study on short-term wind power forecasting of wind farm based on LSTM and NARX[D]. Jinan: Shandong Jianzhu University, 2021 (in Chinese).
17 WANG H, SONG G B. Innovative NARX recurrent neural network model for ultra-thin shape memory alloy wire[J]. Neurocomputing2014134: 289-295.
18 王玉. 基于深度学习的风电场短期风速预测组合模型[D]. 合肥: 中国科学技术大学, 2021.
  WANG Y. Combination model of short-term wind speed forecasting for wind farm based on deep learning[D]. Hefei: University of Science and Technology of China, 2021 (in Chinese).
19 ABDULKADIR S J, YONG S P. Scaled UKF–NARX hybrid model for multi-step-ahead forecasting of chaotic time series data[J]. Soft Computing201519(12): 3479-3496.
20 CADENAS E, RIVERA W, CAMPOS-AMEZCUA R, et al. Wind speed forecasting using the NARX model, case: La Mata, Oaxaca, México[J]. Neural Computing and Applications201627(8): 2417-2428.
21 张泰豪. 基于NARX改进的风速预测网络与风功率预测关键技术研究[D]. 成都: 四川大学, 2021.
  ZHANG T H. Research on key technologies of wind speed prediction network and wind power prediction based on NARX improvement[D]. Chengdu: Sichuan University, 2021 (in Chinese).
22 张鑫卓, 杨新林. 基于Spearman-NARX神经网络的风速预测研究[J]. 电子技术202352(2): 81-83.
  ZHANG X Z, YANG X L. Study on wind speed prediction based on Spearman-NARX neural network[J]. Electronic Technology202352(2): 81-83 (in Chinese).
23 KRIVEC T, PAPA G, KOCIJAN J. Simulation of variational Gaussian process NARX models with GPGPU[J]. ISA Transactions2021109: 141-151.
24 崔西明, 邱志鹏, 魏嘉, 等. 基于数据驱动的结构钢表面应力磁巴克豪森噪声表征方法[J]. 航空学报202344(8): 427237.
  CUI X M, QIU Z P, WEI J, et al. Data-driven method for characterization of structural steel surface stress of magnetic Barkhausen noise[J]. Acta Aeronautica et Astronautica Sinica202344(8): 427237 (in Chinese).
25 宿常鹏, 王雪梅, 许哲, 等. 基于新阈值函数的小波阈值去噪方法研究[J]. 战术导弹技术2020(3): 66-72.
  SU C P, WANG X M, XU Z, et al. Research on wavelet threshold de-noising method based on new threshold function[J]. Tactical Missile Technology2020(3): 66-72 (in Chinese).
26 乔云, 李琼, 钱浩东, 等. 基于VMD与改进小波阈值的地震信号去噪方法研究[J]. 物探化探计算技术202143(6): 690-696.
  QIAO Y, LI Q, QIAN H D, et al. Seismic signal denoising method based on VMD and improved wavelet threshold[J]. Computing Techniques for Geophysical and Geochemical Exploration202143(6): 690-696 (in Chinese).
27 韩旭. 基于代理模型的大跨度桥上列车横风随机响应预测[D]. 成都: 西南交通大学, 2022.
  HAN X. Prediction of random cross-wind response of trains on long-span bridges based on proxy model[D]. Chengdu: Southwest Jiaotong University, 2022 (in Chinese).
28 NASIRI H, EBADZADEH M M. MFRFNN: Multi-functional recurrent fuzzy neural network for chaotic time series prediction[J]. Neurocomputing2022507: 292-310.
Outlines

/