Identifying Three Linear Systems Using Only Single Neural Model

This paper introduces a new approach based on artificial neural networks (ANNs) to identify a number of linear dynamic systems using single neural model. The structure of single neural model is capable of dealing with up-to three systems. Single neural model is trained by the back propagation with momentum learning algorithm. Total nine systems from first to third orders have been used to validate the approach presented in this work. The results have shown that single neural model is capable to identify not only one system but also two and three different systems very successfully. The new identification approach presented in this work provides simplicity, accuracy and compactness. This might bring new aspects to system identification, modelling and control applications.