Air Quality Indices and their Modelling by Hierarchical Fuzzy Inference Systems

摘要

The paper presents the overview of current methods for air quality evaluation, i.e. air stress indices and, especially, air quality indices. Traditional air quality indices are determined as mean values of selected air pollutants. Thus, air quality evaluation depends on strictly given limits without taking into account specific local conditions and synergic relations between air pollutants and other meteorological factors. The stated limitations can be eliminated e.g. using systems based on fuzzy logic. Therefore, the paper presents a design of air quality indices based on hierarchical fuzzy inference systems. Tree and cascade hierarchical fuzzy inference systems of Mamdani type are proposed as alternative air quality indices. For selected localities, they provide both the resulting class of air quality and the degree of membership to each class.