Parameter estimation and prediction of a nonlinear storage model: an algebraic approach

Generally, parameters that are nonlinear in system models are estimated by nonlinear least-squares optimization algorithms. In this paper, if a nonlinear discrete-time model with a polynomial quotient structure in input, output, and parameters, a method is proposed to re-parameterize the model such that the model becomes linear in its new parameters. The new parameters can then be estimated by ordinary least squares. Finally, the model is rewritten in predictor form. A model of an agricultural storage facility with real data is presented to demonstrate the procedure and show the improved predictive performance. Some technical problems are indicated and solutions are proposed.