Intelligent algorithmic interpretation of pollutant discharges from multi-unit industrial complexes

Abstract

Groups of factories in which many units share a single site are common within the chemical industry. This clustering of a number of synthetic units leads to economies of scale through the sharing of resources, and minimization of direct costs such as those arising from the storage and transportation of chemicals. Among the resources usually shared is the system whose role is to dispose of liquid chemical waste. To control effectively the discharge of such waste from the plants on-site, a knowledge of the composition and quantity of waste produced by each factory is essential information, but extracting this from the available data is not a simple matter. In this paper we define a fuzzy relation to track backward from imprecise monitoring station data, and discuss the use of a genetic algorithm to assess the data, in order to calculate the individual outputs of each factory. This hybrid genetic-fuzzy approach can be used to effectively interpret waste flow data from multi-unit complexes up to industrial scale. © 1997 John Wiley & Sons, Inc.