Forecasting for Chaotic Time Series Based on GRP-lstmGAN Model: Application to Temperature Series of Rotary Kiln

被引:10
作者
Hu, Wenyu [1 ]
Mao, Zhizhong [1 ]
机构
[1] Northeastern Univ, Sch Informat & Sci, Shenyang 110819, Peoples R China
关键词
chaotic time series; global recurrence plot; generative adversarial network; long short-term memory; PHASE-SPACE RECONSTRUCTION; TEXTURE CLASSIFICATION; RECURRENCE PLOTS;
D O I
10.3390/e25010052
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Rotary kiln temperature forecasting plays a significant part of the automatic control of the sintering process. However, accurate forecasts are difficult owing to the complex nonlinear characteristics of rotary kiln temperature time series. With the development of chaos theory, the prediction accuracy is improved by analyzing the essential characteristics of time series. However, the existing prediction methods of chaotic time series cannot fully consider the local and global characteristics of time series at the same time. Therefore, in this study, the global recurrence plot (GRP)-based generative adversarial network (GAN) and the long short-term memory (LSTM) combination method, named GRP-lstmGAN, are proposed, which can effectively display important information about time scales. First, the data is subjected to a series of pre-processing operations, including data smoothing. Then, transforming one-dimensional time series into two-dimensional images by GRP makes full use of the global and local information of time series. Finally, the combination of LSTM and improves GAN models for temperature time series prediction. The experimental results show that our model is better than comparison models.
引用
收藏
页数:13
相关论文
共 25 条
  • [1] Ahonen T, 2004, LECT NOTES COMPUT SC, V3021, P469
  • [2] Face description with local binary patterns:: Application to face recognition
    Ahonen, Timo
    Hadid, Abdenour
    Pietikainen, Matti
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (12) : 2037 - 2041
  • [3] Deep-Gap: A deep learning framework for forecasting crowdsourcing supply-demand gap based on imaging time series and residual learning
    Ben Said, Ahmed
    Erradi, Abdelkarim
    [J]. 11TH IEEE INTERNATIONAL CONFERENCE ON CLOUD COMPUTING TECHNOLOGY AND SCIENCE (CLOUDCOM 2019), 2019, : 279 - 286
  • [4] A thermal model for the rotary kiln including heat transfer within the bed
    Boateng, AA
    Barr, PV
    [J]. INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER, 1996, 39 (10) : 2131 - &
  • [5] Burning condition recognition of rotary kiln based on spatiotemporal features of flame video
    Chen, Hua
    Yan, Tingting
    Zhang, Xiaogang
    [J]. ENERGY, 2020, 211
  • [6] Recognition of the Temperature Condition of a Rotary Kiln Using Dynamic Features of a Series of Blurry Flame Images
    Chen, Hua
    Zhang, Xiaogang
    Hong, Pengyu
    Hu, Hongping
    Yin, Xiang
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2016, 12 (01) : 148 - 157
  • [7] RECURRENCE PLOTS OF DYNAMIC-SYSTEMS
    ECKMANN, JP
    KAMPHORST, SO
    RUELLE, D
    [J]. EUROPHYSICS LETTERS, 1987, 4 (09): : 973 - 977
  • [8] INFORMATION AND ENTROPY IN STRANGE ATTRACTORS
    FRASER, AM
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 1989, 35 (02) : 245 - 262
  • [9] Prediction of chaotic time series based on the recurrent predictor neural network
    Han, M
    Xi, JH
    Xu, SG
    Yin, FL
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2004, 52 (12) : 3409 - 3416
  • [10] Short-term wind power forecast based on chaotic analysis and multivariate phase space reconstruction
    Ji, Tianyao
    Wang, Jin
    Li, Mengshi
    Wu, Qinghua
    [J]. ENERGY CONVERSION AND MANAGEMENT, 2022, 254