Black-Box Modeling with State-Space Neural Networks

Neural network black-box modeling is usually performed using nonlinear inputoutput models. The goal of this paper is to show that there are advantages in using nonlinear state-space models, which constitute a larger class of nonlinear dynamical models, and their corresponding state-space neural predictors. We recall the fundamentals of both input-output and state-space black-box modeling, and show the state-space neural networks to be potentially more efficient and more parsimonious than their conventional input-output counterparts. This is examplified on simulated processes as well as on a real one, the hydraulic actuator of a robot arm. 1. Introduction During the past few years, several authors [Narendra and Parthasarathy 1990, Nerrand et al. 1994] have suggested neural networks for nonlinear dynamical blackbox modeling. The problem of designing a mathematical model of a process using only observed data has attracted much attention, both from an academic and an industrial point of v..