A MODEL BASED ON ARTIFICIAL NEURAL NETWORK FOR RISK ASSESSMENT TO POLYCYCLIC AROMATIC HYDROCARBONS IN WORKPLACE

摘要

Polycyclic aromatic hydrocarbons (PAHs) are formed during incomplete combustion in different production processes; exposure to PAH-containing substances increases the risk of cancer in humans. The environmental monitoring used to assess human exposure to airborne PAHs during work, generally involves the employment of diagnostic methods derived from analytical chemistry, characterised by an elevated cost and the use of a "trial and error" approach. The aim of this study is to develop a decision support tool that, through the characteristic parameters of a workplace and using an artificial neural network, simulates the concentration of different species of pollutants (PAHs groups) statistically present in the environment. In this way it is possible to perform a preliminary risk assessment that, besides allowing an immediate perception of the level of risk to which workers are exposed, can undertake environmental monitoring analysis on the detection of a limited number of pollutant species, in order to reduce costs and increase the sustainability of the production system.