Time series prediction based on NARX neural networks: An advanced approach

The NARX network is a dynamical neural architecture commonly used for input-output modeling of nonlinear dynamical systems. When applied to time series prediction, the NARX network is designed as a feedforward time delay neural network (TDNN), i.e., without the feedback loop of delayed outputs, reducing substantially its predictive performance. In this paper, it is shown that the original architecture of the NARX network can be easily and efficiently applied to prediction of time series using embedding theory to reconstruct the input of NARX network. We evaluate the proposed approach using a real-world data set, which is the vibration data measured from a Co2 compressor. The results show that the proposed approach consistently outperforms standard neural network based predictors, such as the TDNN architecture.