Optimization of Benzene Adsorption on Carbon-Alumina Aerogel Using an Artificial Neural Network Approach

Benzene is a hazardous volatile organic compound (VOC) with significant environmental and health risks. This study focuses on optimizing benzene adsorption efficiency on carbon-alumina (C/Al۲O۳) aerogel using an artificial neural network (ANN). Experimental data were collected from a fixed-bed reactor setup, considering three key input parameters: inlet benzene concentration, flow rate, and adsorbent dosage. The adsorption capacity was selected as the target output. A multi-layer perceptron (MLP) neural network was trained and validated to predict adsorption performance. The model demonstrated high accuracy in estimating benzene removal efficiency, with a correlation coefficient exceeding ۰.۹۵. The results indicate that ANN can effectively model and optimize adsorption behavior, providing a powerful tool for enhancing air purification technologies.

کلیدواژه ها:

Benzene adsorption ، Carbon-Alumina aerogel ، Artificial Neural Network ، Fixed-bed