Search

Due to the complexity of the factors influencing membrane fouling in membrane bioreactors (MBR), it is difficult to accurately predict membrane fouling. This paper proposes a multi-strategy of integration aquila optimizer deep belief network (MAO-DBN) based membrane fouling prediction method. The method is developed to improve the accuracy and efficiency of membrane fouling prediction. Firstly, partial least squares (PLS) are used to reduce the dimensionality of many membrane fouling factors to improve the algorithm's generalization ability. Secondly, considering the drawbacks of deep belief network (DBN) such as long training time and easy overfitting, piecewise mapping is introduced in aquila optimizer (AO) to improve the uniformity of population distribution, while adaptive weighting is used to improve the convergence speed and prevent falling into local optimum. Finally, the prediction of membrane fouling is carried out by utilizing membrane fouling data as the research object. The experimental results show that the method proposed in this paper can achieve accurate prediction of membrane fluxes, with an 88.45% reduction in RMSE and 87.53% reduction in MAE compared with the DBN model before improvement. The experimental results show that the model proposed in this paper achieves a prediction accuracy of 98.61%, both higher than other comparative models, which can provide a theoretical basis for membrane fouling prediction in the practical operation of membrane water treatment. [ABSTRACT FROM AUTHOR]

Taste and odor problems can impede public trust in drinking water and impose major costs on water utilities. The ability to forecast taste and odor events in source waters, in advance, is shown for the first time in this paper. This could allow water utilities to adapt treatment, and where effective treatment is not available, consumers could be warned. A unique 24-year time series, from an important drinking water reservoir in Saskatchewan, Canada, is used to develop forecasting models of odor using chlorophyll a, turbidity, total phosphorus, temperature, and the following odor producing algae taxa: Anabaena spp., Aphanizemenon spp., Oscillatoria spp., Chlorophyta, Cyclotella spp., and Asterionella spp. We demonstrate, using linear regression and random forest models, that odor events can be forecast at 0-26 week time lags, and that the models are able to capture a significant increase in threshold odor number in the mid-1990s. Models with a fortnight time-lag show a high predictive capacity (R² = 0.71 for random forest; 0.52 for linear regression). Predictive skill declines for time lags from 0 to 15 weeks, then increases again, to R² values of 0.61 (random forest) and 0.48 (linear regression) at a 26-week lag. The random forest model is also able to provide accurate forecasting of TON levels requiring treatment 12 weeks in advance--93% true positive rate with a 0% false positive rate. Results of the random forest model demonstrate that phytoplankton taxonomic data outperform chlorophyll a in terms of predictive importance. [ABSTRACT FROM AUTHOR]

Artificial neural network (ANN) technology has evolved from the experimental stage into actual industrial applications. To achieve this significant transition, careful planning and adjustment are required. This paper illustrates such an example in the water treatment industry. The project objective is to upgrade the ANN models from a previous research project and install the system on-line in the Rossdale Water Treatment Plant in Edmonton, Alberta, Canada, to forecast raw water colour one day ahead. The article discusses the important issues and techniques to upgrade the neural network model to the actual application. Furthermore, sufficient communication is also required between the designers and the users to address the applicability and user friendly issues in model implementation. Failure in communication can render the whole process ineffective. Possible improvements are also recommended for the future on-line applications. [ABSTRACT FROM AUTHOR]