TY - JOUR
T1 - The adsorption of Pb2+ and Ni2+ ions utilizing modified chitosan beads
T2 - A response surface methodology and artificial neural network modelling study
AU - Igberase, Ephraim
AU - Sithole, Nastassia Thandiwe
N1 - Publisher Copyright:
©2024The Authors.
PY - 2024/5/15
Y1 - 2024/5/15
N2 - This work investigates the application of artificial neural networks (ANN) and response surface methodology (RSM) in developing a technique for removing Pb2+ and Ni2+ ions from wastewater using chitosan derivative. The materials including chitosan beads (CS) and grafted chitosan beads (MCS) were evaluated using infrared spectroscopy (FTIR) and a scanning electron microscope (SEM). The process factors were modeled and optimized using the central composite design (CCD) derived from RSM. Removal efficiency was described as the response for the output layer. However, the input layer feed data consists of pH, adsorbent dose, contact duration, temperature, and concentration. Two neurons were used as the ANN algorithm's output layers, which correspond to the adsorption of Pb2+ and Ni2+ ions. Both models were measured using statistical metrics like average relative errors (ARE), coefficient of determination (R2), Marquart's percentage standard deviation (MPSD), mean squared error (MSE), Pearson's Chi-square (X2), root means square errors (RMSE), and the sum of squares of errors (SSE). The ideal trained neural network depicts the training, validation, and testing phases, with R2 values of 1.0, 0.968, and 0.961, respectively. The findings, however, showed that the ANN technique is superior to the RSM-CCD model approach. At pH 5, starting concentration of 100 mg/L, an adsorbent mass of 6.0 g, a reaction time of 55 min, and a temperature of 40o C, the RSM-CCD model's optimization results for the process variables were achieved. The greatest removal percentages for Pb2+ and Ni2+ ion was 98.14% and 98.12%, respectively. The findings suggest that ANN can be utilized in forecasting the removal of adsorbates from wastewater.
AB - This work investigates the application of artificial neural networks (ANN) and response surface methodology (RSM) in developing a technique for removing Pb2+ and Ni2+ ions from wastewater using chitosan derivative. The materials including chitosan beads (CS) and grafted chitosan beads (MCS) were evaluated using infrared spectroscopy (FTIR) and a scanning electron microscope (SEM). The process factors were modeled and optimized using the central composite design (CCD) derived from RSM. Removal efficiency was described as the response for the output layer. However, the input layer feed data consists of pH, adsorbent dose, contact duration, temperature, and concentration. Two neurons were used as the ANN algorithm's output layers, which correspond to the adsorption of Pb2+ and Ni2+ ions. Both models were measured using statistical metrics like average relative errors (ARE), coefficient of determination (R2), Marquart's percentage standard deviation (MPSD), mean squared error (MSE), Pearson's Chi-square (X2), root means square errors (RMSE), and the sum of squares of errors (SSE). The ideal trained neural network depicts the training, validation, and testing phases, with R2 values of 1.0, 0.968, and 0.961, respectively. The findings, however, showed that the ANN technique is superior to the RSM-CCD model approach. At pH 5, starting concentration of 100 mg/L, an adsorbent mass of 6.0 g, a reaction time of 55 min, and a temperature of 40o C, the RSM-CCD model's optimization results for the process variables were achieved. The greatest removal percentages for Pb2+ and Ni2+ ion was 98.14% and 98.12%, respectively. The findings suggest that ANN can be utilized in forecasting the removal of adsorbates from wastewater.
KW - Adsorption
KW - Chitosan beads
KW - Heavy metal
KW - Neural network
KW - Response surface
UR - http://www.scopus.com/inward/record.url?scp=85194229093&partnerID=8YFLogxK
U2 - 10.6092/issn.2281-4485/18471
DO - 10.6092/issn.2281-4485/18471
M3 - Article
AN - SCOPUS:85194229093
SN - 2039-9898
VL - 61
SP - 1
EP - 15
JO - EQA
JF - EQA
ER -