Process identification using a modified Elman neural net

In this paper, a modified Elman neural network (1990) is utilized to identify industrial processes. The basic structure of the Elman network is introduced and one of its modified versions is presented. A specific learning algorithm is developed which optimizes not only the feedforward but also the self-feedback connections of such partially recurrent neural networks. The identification system proposed is arranged in a parallel pattern. Numerical results for the identification of a pH neutralization process are also included.<
>