论文信息 - A neural architecture to predict pollution in industrial areas

A neural architecture to predict pollution in industrial areas

In this paper a novel approach, based on a neural network structure, is introduced in order to face the problem of pollutant estimation in an industrial area. In particular a short-term prediction (six hours ahead) of the SO/sub 2/ pollutant mean value has been performed. A neural architecture, based essentially on a suitable number of MLPs devoted to predict alarm situations and to estimate the mean value of the pollutant, has been implemented. The strategy employed has been revealed to be particularly suitable, as it is shown in the results reported in the paper.

Luigi Fortuna | Salvatore Baglio | Giuseppe Nunnari | Paolo Arena | C. Castorina

[1] Luigi Fortuna,et al. Air pollution estimation via neural networks , 1995 .

[2] Jay Schulkin,et al. ES&T Features: The role of pollution in large-scale population disturbances. Part 2: terrestrial populations , 1992 .

[3] Stephen A. Billings,et al. Non-linear system identification using neural networks , 1990 .

[4] Kumpati S. Narendra,et al. Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[5] Giovanni Muscato,et al. A real-time implementation of a multi-layer perceptron with automatic tuning of learning parameters , 1991 .

[6] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..