JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Substance flow analysis combined with neural networks for predicting and reducing lead pollution in the secondary lead industry

  • 0Institute of Circular Economy, Beijing University of Technology, Beijing, P. R. China.
Waste Management & Research : the Journal of the International Solid Wastes and Public Cleansing Association, Iswa +

|

September 28, 2025

|

September 28, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

Recycling lead-acid batteries is vital but creates pollution. This study identifies water-quenched slag as a key lead release pathway and uses a GA-ANN model for accurate pollutant prediction.

Area Of Science

  • Environmental Science
  • Chemical Engineering
  • Materials Science

Background

  • Spent lead-acid battery recycling is essential for lead supply but generates significant pollutants.
  • Pollutants like lead dust, water-quenched slag (WQS), and wastewater threaten soil and groundwater.
  • Key processes influencing pollutant discharge include crushing, separation, smelting, refining, and slag production.

Purpose Of The Study

  • To quantify lead (Pb) flows in battery recycling processes.
  • To identify primary pollutant-generating processes, particularly WQS formation.
  • To develop a predictive model for real-time pollutant estimation and environmental control.

Main Methods

  • Substance flow analysis to quantify Pb flows.
  • Optimization of an artificial neural network (ANN) model using a genetic algorithm (GA).
  • Development of a GA-ANN model for real-time estimation of pollutant generation in slag production.

Main Results

  • Water-quenched slag (WQS) was identified as the primary pathway for Pb release.
  • The GA-ANN model achieved high prediction accuracy (MSE = 0.0003).
  • The model enables estimation of Pb content in WQS using key input parameters.

Conclusions

  • The developed GA-ANN model provides accurate, real-time pollutant estimation for lead-acid battery recycling.
  • Data-driven adjustments to process parameters can mitigate pollution.
  • This approach offers actionable insights for enhanced environmental control in industrial production.

Keywords: