COST-EFFECTIVE WATER CLARIFICATION CONTROL USING A NEURALLY INFORMED CONTROL STRATEGY

The abstraction, treatment and supply of potable (drinking) water pres ents a range of special problems. Early attempts at introducing and ex tending the range of automatic control at a water treatment plant were invariably compromised by the poor quality of the instrumentation ava ilable. Improved sensor technology and the advent of microprocessor ba sed programmable controllers has allowed the implementation of non-sta ndard solutions. This paper describes the steps followed in developing an accurate feedforward automatic clarification control strategy, The existing strategy was occasionally compromised when a colour measurem ent was corrupted, usually under conditions of high turbidity. It shou ld be emphasised that the colour monitor used is being asked to operat e at and beyond the range of its original design specification. This o ccurs because there ave no other alternative instruments. The paper sh ows how the use of an artificial neural network produces a solution to a seemingly intractable problem.