Published in Proceedings of the 2nd Conference on Information Sciences, Wrightsville Beach, N.C., USA, pp 324-327 (1995)

Intelligent algorithmic interpretation of pollutant discharges

from multi-unit industrial complexes

Hugh M. Cartwright *, Ben Jesson * and Les M. Sztandera^†

* Physical and Theoretical Chemistry Laboratory, Oxford University,

South Parks Road, Oxford, OX1 3QZ, UK

^† Computer Science Department, Philadelphia College of Textiles and Science, USA

Abstract

Groups of factories in which many units share a single site are common within the chemical industry. This clustering of a number of independent synthetic units leads to economies of scale through the sharing of resources, and minimisation of direct costs such as those arising from the storage and transport 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 liquid 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 information from the available data is not a simple matter. In this paper we discuss the use of a genetic algorithm to assess analytical data generated by monitoring stations 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.