ANN-based sensing and control developments in the water industry: A decade of innovation

Compared to other process industries, the technology employed by the water industry is of a relatively low level, although this deficit has been reduced in recent years mainly due to the increased competitiveness in the privatised market place. In general, however, methods of process regulation are far from ideal, leading to inefficient plant operation, occurrence of unnecessary costs and in some cases low water quality. Improvements in control and supervision methods have been recognised as one means of achieving higher water quality and efficiency objectives in the potable water industry. The lack of research in this application area is evident from the paucity of published literature, especially when compared to wastewater treatment control. Attempts to improve the performance of water treatment works through the application of improved control and measurement have had variable success. The most quoted reason for this is that the individual dynamic operations defining the treatment cycle are complex, highly non-linear and poorly understood. These problems are compounded by the use of faulty or badly maintained sensors. The efficient and robust operation of any industrial system is critically dependent on the quality of the measurements made. Also, the structure of the control policy and choice of the individual controller parameters are important decisions to the economic operation. Because of their ability to capture non-linear information very efficiently, artificial neural networks (ANNs) have found great popularity amongst the 'control community' and other disciplines. This paper discusses a recent application of ANNs at surface water treatment works. The study is used to describe how the introduction of ANNs has resulted in more reliable system measurement and consequently improved coagulation control.