Loading

Journal of Mineral and Material Science
[ ISSN : 2833-3616 ]


Digital Transformation of Coke Oven Batteries: A Path to Efficiency

Review Article
Volume 5 - Issue 3 | Article DOI : 10.54026/JMMS/1089


Manish Dev Patel1, Bipan Tudu2, Rajib Bandyopadhyay2 and Prabal Patra1*

1 Automation Division, TATA Steel Ltd, Jamshedpur, India

2 Department of Instrumentation and Electronics Engineering, Jadavpur University, Kolkata, India

Corresponding Authors

Prabal Patra, Automation Division, TATA Steel Ltd, Jamshedpur, India

Keywords

Machine Learning; Fuzzy Logic; Artificial Intelligence; Coke Plant; CSR; CET; CDQ

Received : July 22, 2024
Published : August 07, 2024

Abstract

Digitalization improves the production, quality, health & safety. This paper is about the digital models developed and integrated into Coke Oven Scheduling & Heating Monitoring System. Explored first principal methods, conditional based algorithms, various machine learning and artificial intelligence techniques, namely XGBoost, Random Forest, Decision tree & GLM to build predictive, prescriptive & descriptive models. Descriptive analysis & exploratory data analysis have been done to get insights from the data. Machine learning models were tuned for their optimum hyperparameters using grid search algorithms iteratively. Models with high accuracy have been deployed. Good operating zone/ranges have been defined for controllable parameters using Partial dependency plots.