Machine Learning Optimization of Waste Salt Pyrolysis: Predicting Organic Pollutant Removal and Mass Loss DOI Open Access
Run Zhou,

Qing Gao,

Qiuju Wang

и другие.

Sustainability, Год журнала: 2025, Номер 17(7), С. 3216 - 3216

Опубликована: Апрель 4, 2025

Pyrolysis presents a promising solution for the complete purification and recycling of waste salt. However, presence organic pollutants in salts significantly hinders their practical application, owing to diverse sources strong resistance degradation. This study developed predictive models removal from salt using three machine learning techniques: Random Forest (RF), Support Vector Machine, Artificial Neural Network. The were evaluated based on total carbon (TOC) rate mass loss rate, with RF model demonstrating high accuracy, achieving R2 values 0.97 0.99, respectively. Feature engineering revealed that contribution components was minimal, rendering them redundant. importance analysis identified temperature as most critical factor TOC removal, while moisture content nitrogen key determinants loss. Partial dependence plots further elucidated individual interactive effects these variables. validated both literature data laboratory experiments, user interface Python GUI library. provides novel insights into pyrolysis process establishes foundation optimizing its application.

Язык: Английский

Short process recovery of silver and purification mechanism of crystalline silicon deep etching from end-of-life photovoltaic cells DOI
Fuyao Chen, Yang Yang, Mengjing Zhou

и другие.

Chemical Engineering Journal, Год журнала: 2025, Номер unknown, С. 161651 - 161651

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

2
Machine Learning Optimization of Waste Salt Pyrolysis: Predicting Organic Pollutant Removal and Mass Loss DOI Open Access
Run Zhou,

Qing Gao,

Qiuju Wang

и другие.

Sustainability, Год журнала: 2025, Номер 17(7), С. 3216 - 3216

Опубликована: Апрель 4, 2025

Pyrolysis presents a promising solution for the complete purification and recycling of waste salt. However, presence organic pollutants in salts significantly hinders their practical application, owing to diverse sources strong resistance degradation. This study developed predictive models removal from salt using three machine learning techniques: Random Forest (RF), Support Vector Machine, Artificial Neural Network. The were evaluated based on total carbon (TOC) rate mass loss rate, with RF model demonstrating high accuracy, achieving R2 values 0.97 0.99, respectively. Feature engineering revealed that contribution components was minimal, rendering them redundant. importance analysis identified temperature as most critical factor TOC removal, while moisture content nitrogen key determinants loss. Partial dependence plots further elucidated individual interactive effects these variables. validated both literature data laboratory experiments, user interface Python GUI library. provides novel insights into pyrolysis process establishes foundation optimizing its application.

Язык: Английский

Процитировано

0