Developing an adaptive neuro-fuzzy inference system based on particle swarm optimization model for forecasting Cr(VI) removal by NiO nanoparticles

The treatment of wastewater from heavy metal ions such as hexavalent chromium Cr(VI) is considered as an important issue in recent years, which is harmful to human health and environment. Since, in engineering, performing the experiments to solve problems is time-consuming and costly. In this study, adaptive neuro-fuzzy inference system (ANFIS) was coupled with particle swarm optimization (PSO) algorithm to develop a predictive model for modeling of Cr(VI) removal percent on NiO nanoparticle. To this end, the trace of four initial parameters containing contact time, Cr(VI) initial concentration, NiO adsorbent dosage, and pH on removing Cr(VI) was investigated. The performance of the developed algorithm was evaluated by statistical parameters such as mean absolute relative deviation mean squared error (MSE) maximum absolute error and, R-2 and graphic methods. The ANFIS-PSO shows high-performance modeling of Cr(VI) removal with R-2 = 0.998, MSE = 0.0014, and AARD = 0.0011 compare to the established model in previous works.

Automated summary

This study successfully developed a predictive model for the removal of Cr(VI) on NiO nanoparticles using the ANFIS-PSO algorithm, showing superior performance. The analysis of four initial parameters on the removal of Cr(VI) was conducted to assess the model's effectiveness.