Prediction of Compressive Strength of Biomass–Humic Acid Limonite Pellets Using Artificial Neural Network Model

Autor: Haoli Yan, Xiaolei Zhou, Lei Gao, Haoyu Fang, Yunpeng Wang, Haohang Ji, Shangrui Liu
Jazyk: angličtina
Rok vydání: 2023
Předmět:
Zdroj: Materials, Vol 16, Iss 14, p 5184 (2023)
Druh dokumentu: article
ISSN: 1996-1944
DOI: 10.3390/ma16145184
Popis: Due to the detrimental impact of steel industry emissions on the environment, countries worldwide prioritize green development. Replacing sintered iron ore with pellets holds promise for emission reduction and environmental protection. As high-grade iron ore resources decline, research on limonite pellet technology becomes crucial. However, pellets undergo rigorous mechanical actions during production and use. This study prepared a series of limonite pellet samples with varying ratios and measured their compressive strength. The influence of humic acid on the compressive strength of green and indurated pellets was explored. The results indicate that humic acid enhances the strength of green pellets but reduces that of indurated limonite pellets, which exhibit lower compressive strength compared to bentonite-based pellets. Furthermore, artificial neural networks (ANN) predicted the compressive strength of humic acid and bentonite-based pellets, establishing the relationship between input variables (binder content, pellet diameter, and weight) and output response (compressive strength). Integrating pellet technology and machine learning drives limonite pellet advancement, contributing to emission reduction and environmental preservation.
Databáze: Directory of Open Access Journals
Nepřihlášeným uživatelům se plný text nezobrazuje