Chaotic time series prediction of nonlinear systems based on various neural network models

This paper discusses the chaos prediction of nonlinear systems using various neural networks based on the modified substructure data-driven modeling architecture. In the modeling step, we construct two-coefficient loss functions according to the linear multi-step method to improve the prediction acc...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Chaos, solitons and fractals Ročník 175; s. 113971
Hlavní autori: Sun, Ying, Zhang, Luying, Yao, Minghui
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.10.2023
Predmet:
Chaos prediction
Encoder-decoder model
LSTM model
Neural networks
Time series
Encoder-decoder model
Chaos prediction
Neural networks
LSTM model
Time series
ISSN:0960-0779, 1873-2887
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper discusses the chaos prediction of nonlinear systems using various neural networks based on the modified substructure data-driven modeling architecture. In the modeling step, we construct two-coefficient loss functions according to the linear multi-step method to improve the prediction accuracy of neural networks. Then, the predicted response data of the system is given by the forward Euler method and neural networks. Under such architecture, chaos forecasting is carried out on a five-degree-of-freedom duffing oscillator system via the feedforward neural network (FNN), long short-term memory (LSTM) network and LSTM encoder-decoder (LSTM ED). The numerical simulation results show that the model can predict chaotic time series even if a small amount of information and samples are known, and the prediction window is twice that of the observation window. Among these models, LSTM ED exhibits the highest accuracy in both short-term and long-term chaos prediction. Furthermore, the prediction results mainly involve three evaluation indicators: absolute error, mean absolute error, normalized root mean square error. Through error analysis and noise processing, LSTM ED shows superior stability, robustness and extrapolation ability. Its prediction error is about half of FNN and the maximum increase in accuracy is 71.3 %. •Two-coefficient loss functions are constructed in the modeling step.•The forward Euler method is combined with neural networks in the prediction step.•Chaotic time series prediction based on various neural networks is investigated.•The accuracy, robustness and extrapolation ability of models are compared.
ISSN:0960-0779
1873-2887
DOI:10.1016/j.chaos.2023.113971