Cart Summary
0 item(s) ($0.00)
Product Search
All Products
AIST Transactions
Books
Conference Proceedings
Industry Data
Iron & Steel Technology
About the AIST Resource Center
Product Details:

Predictive Modeling for Slidegate Refractory Wear: A Machine Learning Approach for Enhanced Condition Monitoring in Steelmaking Processes

In this work, the wear of the ladle slidegate plate was modeled and optimized to ensure operational safety, process stability and cost reduction associated with premature plate replacement. Adhering to established standards, such as limiting the maximum center hole size and maintaining crack-free conditions, prevents jamming and ensures steel flow control, thereby protecting both personnel and equipment. Premature replacement increases refractory, maintenance and labor costs while decreasing ladle availability. To address these challenges, a predictive tool was developed using a machine learning approach to estimate and track the wear of the center hole diameter and crack formation in the slidegate plate.
Product:
2026/07 AIST Iron & Steel Technology July
PR-PM0726-3
Franz Ramstorfer, Donaldo Silva Orosimbo, Ricardo Pereira Dias, Gilvan Nascimento De Souza, et al.
July 01, 2026
PDF
$25.00
$35.00
$35.00
Available for Immediate Download