n-Dimensional Chaotic Time Series Prediction Method

Chaotic time series have been involved in many fields of production and life, so their prediction has a very important practical value. However, due to the characteristics chaotic series, such as internal randomness, nonlinearity, long-term unpredictability, most methods cannot achieve high-precision intermediate or predictions. Thus, an (ILTP) method for n-dimensional is proposed solve this problem. Initially, order model determined by optimizing preprocessing constructing joint calculation strategy, that observation sequence can be decomposed reorganized accurately. Furthermore, RBF neural network introduced construct multi-step future sequences, with feedback recursion mechanism. Compared existing methods, error ILTP reduced 1–6 orders magnitude, step increased 10–20 steps. The provide reference technology application characteristics.