A Neural Network with Minimal Structure for Maglev System Modeling and Control

Mostafa Lairi (1, 2) , Gérard Bloch (1, 2)

1 CRAN - Centre de Recherche en Automatique de Nancy
2 UHP - Université Henri Poincaré - Nancy 1

The paper is concerned with the determination of a minimal structure of a one hidden layer perceptron for system identification and control. Structural identification is a key issue in neural modeling. Decreasing the size of the neural networks is a way to avoid overfitting and bad generalization and leads moreover to simpler models which are required for real time applications, particularly in control. A learning algorithm and a pruning method both based on a criterion robust to outliers are presented. Their performances are illustrated on a real example, the inverse model identification of a MagLev system, which is nonlinear, dynamical and rapid. This inverse model is used in a feedforward neural control scheme. Very satisfactory approximation performances are obtained for a network with very few parameters.

Keywords: one hidden layer perceptron; pruning; robust criterion; magnetic levitation

Domains: Machine Learning [cs.LG]; Automatic Control Engineering; Neural and Evolutionary Computing [cs.NE]; Automatic; Machine Learning [stat.ML]; Other Statistics [stat.ML]

Mostafa Lairi, Gérard Bloch. A Neural Network with Minimal Structure for Maglev System Modeling and Control. IEEE International Symposium on Intelligent Control / Intelligent Systems & Semiotics, ISIC/ISAS'99, Sep 1999, Cambridge, MA, United States. pp.40-45, ⟨10.1109/ISIC.1999.796627⟩. ⟨hal-00405124⟩