B. Cathers

Application of artificial neural networks to the real time operation of water treatment plants

The water industry is facing increased pressure to produce higher quality treated water at a lower cost. The efficiency of a treatment process closely relates to the operation of the plant. To improve the operating performance, an artificial neural network (ANN) paradigm has been applied to a water treatment plant. An ANN which is able to learn the non-linear performance relationships of historical data of a plant, has been proved to be capable of providing operational guidance for plant operators. A backpropagation network is used to determine the alum and polymer dosages. The results show that the ANN model is most promising. The correlation coefficients (r) between the actual and predicted values for the alum and polymer dosages were both 0.97 and the average absolute percentage errors were 4.09% and 8.76% for the alum and polymer dosages respectively. The application of the ANN model is illustrated using data from Wyong Shire Councils Wyong Water Treatment Plant on the Central Coast of NSW.

Proactive management of estuarine algal blooms using an automated monitoring buoy coupled with an artificial neural network

Algae proliferate when favourable biological, chemical and physical conditions are present. Algal blooms within the Hawkesbury River, NSW, are a regular feature of seasonal cycles and develop in response to non-periodic disturbances. To improve the understanding of processes that lead to algal blooms, an autonomous buoy has been deployed (since 2002) which has generated a high resolution, temporal data set. Parameters monitored at 15?min intervals include Chlorophyll-a, temperature (water and air), salinity and photosynthetically available radiation. This data set is used to configure an Artificial Neural Network (ANN) to predict (one, three and seven days in advance) the mean, 10th and 90th percentile, daily Chlorophyll-a concentrations. The prediction accuracy of the ANNs progressively decreased from one to seven days in advance. Incorporating predictive models coupled with near real time data sourced from automated, telemetered monitoring buoys enables environmental managers to implement proactive algal bloom management strategies. An autonomous monitoring buoy is deployed to measure estuarine water quality parameters.Chlorophyll-a, temperature and salinity have been monitored at 15?min intervals since 2002.Artificial Neural Network predicts Chlorophyll-a concentrations one, three and seven days ahead.A proactive, rather than reactive, estuarine algal bloom management approach is proposed.

Modelling for environmental engineering students using MATLAB and SIMULINK

A teaching project is being developed with the aim of enabling students to quickly develop their own simulation models of water based eco-systems without the need to write computer programs. The vehicle for this is the commercial software MATLAB and SIMULINK. Initially, the method is being applied to model dissolved oxygen and BOD in a water body receiving a waste discharge. Simulations can include reaeration, nitrification, photosynthesis and respiration. Students are supplied with field data and their task is to identify the dominant processes, configure an appropriate model, select values for the kinetic constants and carry out model runs.