Artificial neural network (ANN) and adaptive neuro fuzzy (ANFIS) modelling techniques have been applied in this study to model and optimize the chemical oxygen demand (COD) adsorptive removal in produced water. The models were well trained and showed minimum error values for predicted data when compared to experimental data. The error values were 0.4035 and 0.2886 for sum of squared error (SSE), 0.1628 and 0.0832 for mean square error (MSE) and 0.13 and 0.23% for average relative error (ARE) using ANN and ANFIS, respectively. Error analysis and coefficient of determination (R2) of the models determined that ANFIS was better than ANN for the prediction of COD adsorption on the biochar. Also, ANFIS required minimum run time as compared to ANN. Both artificial intelligence (AI) based techniques well predicted the optimized values of adsorption process, when compared with the experimental values. It is concluded that the use of AI techniques can inevitably pave the way in the water treatment sector using adsorption for improved efficiency and process automation.
CITATION STYLE
Khurshid, H., Mustafa, M. R. U., & Ho, Y. C. (2022). Application of Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy (ANFIS) Techniques for the Modelling and Optimization of COD Adsorption Process. In Lecture Notes in Electrical Engineering (Vol. 758, pp. 525–537). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-2183-3_49
Mendeley helps you to discover research relevant for your work.