Review on Fuzzy and Neural Prediction Interval Modelling for Nonlinear Dynamical Systems

The existing uncertainties during the operation of processes could strongly affect performance forecasting systems, control strategies and fault detection systems when they are not considered in design. Because that, study uncertainty quantification has gained more attention among researchers past decades. From this field study, prediction intervals arise as one techniques most used literature to represent effect over future process behavior. Thus, have focused on developing based use fuzzy neural networks, thanks their usefulness for a wide range universal approximators. In work, review state-of-the-art methodologies interval modelling networks is presented. main characteristics each method construction presented some recommendations given selecting appropriate specific applications. To illustrate advantages these methodologies, comparative analysis selected methods presented, using benchmark series real data from solar power generation microgrid.