Performance Improvements at Surface Water Treatment Works Using ANN-Based Automation Schemes

• Published in: Chemical engineering research & design Vol. 78; no. 7; pp. 1026 - 1039
• Main Authors: Adgar, A., Cox, C.S., Böhme, T.J.
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Rugby Elsevier B.V 01.10.2000; Institution of Chemical Engineers
• Subjects: Applied sciences; artificial neural networks; Drinking water and swimming-pool water. Desalination; Exact sciences and technology; neuro control; Pollution; potable water treatment; process control; sensor failure detection; Water treatment and pollution; artificial neural networks; sensor failure detection; process control; neuro control; potable water treatment; Drinking water treatment; Automation; Drinking water treatment plant; Process control; Flocculation; pH; Neural network
• ISSN: 0263-8762
• DOI: 10.1205/026387600528148

Due to 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 some recent applications of the ANNs at surface water treatment works. The range of application is quite diverse and covers modelling, simulation, condition monitoring, fault detection and control strategy design and implementation. 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. Three examples are used to describe how the introduction of ANNs has resulted in more reliable system measurement and more efficient pH and coagulation control. A final example, shows an approach to the use of an ANN to provide ‘assistance’ to a conventional proportional-integral controller in the form of automatic on-line tuning of the controller parameters.