ABSTRACT In a climate-changing environment, where global wastewater temperatures are rising, rapid organic and inorganic waste removal is required, which increases wet sludge production in the biological treatment process (BTP). Rapid wet sludge volume production creates challenges, including increased wastewater viscosity, nitrous oxide production, and the presence of toxic microorganisms in the BTP. Plant operators are then required to frequently analyze wastewater to avoid wet sludge production. Therefore, this article aims to develop a wet sludge volume model using a multilayer perceptron (MLP)-artificial neural network (ANN) algorithm. The model will incorporate climate temperature changes and will assist plant managers to predict the wet sludge volume expected, for efficient operation. The results showed that the wet sludge volume was positively. correlated with temperature (r=0.219** (** only apply to the correlation values)), indicating that an increase in climate temperature affects wet sludge production. The MLPANN algorithm was able to model wet sludge volume and produced mean squared error (0.1592), root mean squared error (0.399), and R2 (0.97277) during testing. The wet volume sludge model predicted that the climate temperature increases sludge production at a rate of 0.0102. Based on the performance evaluation, the wet sludge volume model is robust and superior and can be utilized by plant managers/operators with confidence.
Muloiwa et al. (Mon,) studied this question.