Application of machine learning in ultrasonic pretreatment of sewage sludge: prediction and optimization.

Abstract

In this research, typical industrial scenarios were analyzed optimized by machine learning algorithms, which fills the gap of massive data and industrial requirements in ultrasonic sludge treatment. Principal component analysis showed that the ultrasonic density and ultrasonic time were positively correlated with soluble chemical oxygen demand (SCOD), total nitrogen (TN), and total phosphorus (TP). Within five machine learning models, the best model for SCOD prediction was XG-boost (R²=0.855), while RF was the best for TN and TP (R²=0.974 and 0.957, respectively). In addition, SHAP indicated that the importance feature for SCOD, TN, and TP was ultrasonic time, and sludge concentration, respectively. Finally, the typical industrial scenario of ultrasonic pretreatment of sludge was analyzed. In the secondary sludge, treatment volume at 0.6 L, the pH at 7.0, and the ultrasonic time at 20 min was best to improve the SCOD. In the ultrasonic pretreatment primary sludge, treatment volume of 0.3 L, pH of 7.0, and ultrasonic time of 15 min was best to improve the SCOD. Furthermore, the ultrasonic power at 700 W and ultrasonic time at 20 min were best to improve the C/N and C/P in the secondary sludge. In the primary sludge, the ultrasonic power at 600 W, and the ultrasonic time at 15 min were best to improve C/N and C/P. This study lays a foundation for the practical application of ultrasonic pretreatment of sludge and provides basic information for typical industrial scenarios.