Boosting biogas production through innovative data-driven modeling and optimization methods at NJWTP

Abstract

This study presents an innovative approach to enhancing biogas production through the anaerobic digestion of Nanjing Jiangnan Wastewater Treatment Plant (NJWTP). Utilizing data-driven modeling and optimization methods, the research focuses on improving the sustainability and cost-effectiveness of waste-to-energy conversion processes. The core of the study involves the comparison of three distinct models: Deep Belief Network (DBN), DBN with Osprey Optimization Algorithm (DBN-OOA), and DBN with Boosted Osprey Optimization Algorithm (DBN-BOOA). In total, 180 data points were gathered from 2016 to 2018 for the purpose of the current study. Among the models evaluated, the Deep Belief Network (DBN) coupled with Boosted Osprey Optimization Algorithm (BOOA) emerged as the superior method, demonstrating high accuracy and optimization capabilities. The DBN-BOOA model achieved remarkable performance metrics, including a correlation coefficient (R) of 0.98, a root mean square error (RMSE) of 0.41 m³/min, and an index of agreement (IA) of 0.99, significantly outperforming the standalone DBN and DBN-OOA models. Furthermore, the DBN-BOOA model identified optimal operational parameters that maximized biogas production to 31.35 m³/min, surpassing the outputs of the other models. This method’s success is attributed to its robust optimization algorithm, which efficiently navigates a diverse search space to locate the global optimum without necessitating input variable pre-processing. Consequently, the DBN-BOOA model offers a practical and user-friendly solution for MWTP operators, enabling real-time adjustments to operational parameters for increased biogas yields and reduced sludge production.