State-space prediction model for chaotic time series

1998 ◽  
Vol 58 (2) ◽  
pp. 2640-2643 ◽  
Author(s):  
A. K. Alparslan ◽  
M. Sayar ◽  
A. R. Atilgan
2014 ◽  
Vol 31 (2) ◽  
pp. 020503 ◽  
Author(s):  
Jian-Ling Qu ◽  
Xiao-Fei Wang ◽  
Yu-Chuan Qiao ◽  
Feng Gao ◽  
Ya-Zhou Di

2016 ◽  
Vol 2016 ◽  
pp. 1-12 ◽  
Author(s):  
Congqing Wang ◽  
Linfeng Wu

The dynamic model of a planar free-floating flexible redundant space manipulator with three joints is derived by the assumed modes method, Lagrange principle, and momentum conservation. According to minimal joint torque’s optimization (MJTO), the state equations of the dynamic model for the free-floating redundant space manipulator are described. The PD control using the tracking position error and velocity error in the manipulator is introduced. Then, the chaotic dynamic behavior of the manipulator is analyzed by chaotic numerical methods, in which time series, phase plane portrait, Poincaré map, and Lyapunov exponents are used to analyze the chaotic behavior of the manipulator. Under certain conditions for the joint torque optimization and initial values, chaotic vibration motion of the space manipulator can be observed. The chaotic time series prediction scheme for the space manipulator is presented based on the theory of phase space reconstruction under Takens’ embedding theorem. The trajectories of phase space can be reconstructed in embedding space, which are equivalent to the original space manipulator in dynamics. The one-step prediction model for the chaotic time series and the chaotic vibration was established by using support vector regression (SVR) prediction model with RBF kernel function. It has been proved that the SVR prediction model has a good performance of prediction. The experimental results show the effectiveness of the presented method.


IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 44288-44299
Author(s):  
Mingyang Lv ◽  
Xiaogang Zhang ◽  
Hua Chen ◽  
Chuanwu Ling ◽  
Jianmin Li

2014 ◽  
Vol 989-994 ◽  
pp. 1348-1351 ◽  
Author(s):  
Can Yuan ◽  
Qi Cai ◽  
Gang Liu ◽  
Feng Yan

The paper has established a combinatorial prediction model of chaotic time series based on history data and coupling data. Through the study of the flow characteristic about natural circulation under rolling motion, the single variable reconstruction and coupling multivariate reconstruction are discussed for chaotic time series based on phase space reconstruction technique, and the combinatorial prediction model has been built which bases on developing trend of history data and coupling relationship of correlative data. The paper also studied an example of coolant volume flow prediction with a relative precision of 0.9804 with the established model. The result indicated that the model with high precision and robustness could apply for natural circulation coolant volume flow prediction under rolling motion.


Sign in / Sign up

Export Citation Format

Share Document