Prediction and optimization of struvite recovery from wastewater by machine learning

Journal Title: Energy Environmental Protection - Year 2023, Vol 37, Issue 6

Abstract

The recovery of nitrogen and phosphorus from simulated wastewater in the form of struvite was investigated through a Machine Learning (ML)-based approach. The Extreme Gradient Boosting Algorithm (XGBoost) and Random Forest (RF) models were used for single-objective and multi-objective prediction of the recovery rates of N and P, respectively. The effects of seven process conditions on struvite crystallization were identified. The results showed that XGBoost outperformed RF in both single-objective (R^2=0.91~0.93) and multi-objective (R^2=0.89) predictions. Furthermore, experimental validation was conducted with initial phosphorus concentrations of 10 mg/L and 1000 mg/L to determine the optimized process conditions for struvite recovery using the multi-objective model. The optimal conditions were found to be: N∶P ratio of 1.2∶1, Mg∶P ratio of 1∶1, pH of 9.5, reaction time of 80 min, reaction temperature of 25 ℃, and stirring rate of 240 r/min.

Authors and Affiliations

TONG Ying|School of Energy Science and Engineering, Central South University, China, JIANG Shaojian|School of Energy Science and Engineering, Central South University, China, KANG Bingyan|School of Energy Science and Engineering, Central South University, China, LENG Lijian*|School of Energy Science and Engineering, Central South University, China, LI Hailong|School of Energy Science and Engineering, Central South University, China

Keywords

Related Articles

Electrocatalytic oxidation of Pd/Ti anode for the treatment of reverse osmosis concentrates from coking wastewater

In this study, a Pd -loaded porous titanium anode was prepared using a simple spraying method, and an electrocatalytic oxidation system was constructed with Pd/Ti as anode and titanium mesh as cathode to achieve the effi...

Study on the Efficiency of Denitrification and Phosphorus Removal in Municipal Wastewater Enhanced by Elemental Sulfur

The treatment of sulfur-containing wastewater from industries such as petroleum refineries and tanneries can produce significant amounts of low-cost elemental sulfur (S0). In recent years, numerous studies have investiga...

Situation and prospects of treatment technologies for mine water containing ammonia nitrogen

As the discharge standards for mine water treatment become more stringent, the requirements for effective removal of ammonia nitrogen from mine water are strongly needed. While there are several methods available for tre...

Main factors influencing the electro-methanation of CO_2 in microbial electrolytic cells and the role of electron intermediates

Greenhouse gas emissions from fossil fuel combustion have led to global ecological degradation and energy crisis. Therefore, it is urgent to explore new technologies for the conversion, reuse and clean energy production...

Study on the performance and mechanism of high-efficiency deep oxidation of butyl acetate over Pd/CeO_2

In the field of new energy vehicles and related sectors, treating butyl acetate (BA), a typical oxygen-containing volatile organic compound (VOC), is becoming increasingly important. The surface structure and physicochem...

Download PDF file
  • EP ID EP738049
  • DOI 10.20078/j.eep.20231102
  • Views 87
  • Downloads 0

How To Cite

TONG Ying, JIANG Shaojian, KANG Bingyan, LENG Lijian*, LI Hailong (2023). Prediction and optimization of struvite recovery from wastewater by machine learning. Energy Environmental Protection, 37(6), -. https://europub.co.uk/articles/-A-738049