A Review Paper on Cluster-Based Framework for Improving Steel production Quality

Abstract

Detecting defects on the surface of steel is crucial to enhance its quality. This process helps in improving the efficiency and quality of steel rolling, measured by a metric called Steel Rolling Smart Factor. This paper review on various methodology currently in used for building a hybrid model using various feature selection techniques and cluster-based methodologies for predicting the Steel Rolling Smart Factor and applicable to a Quality Complaint (QC) dataset with various defective numbers of physical features/attributes. The review paper various methodology involves data collection, preprocessing, feature selection, cluster-based methodologies, predictive model building, model evaluation, hybrid model creation, and model deployment. The hybrid model can improve accuracy and reliability by incorporating multiple predictive models and clustering similar data points together. The methodology can be used to identify the most important factors that affect the Steel Rolling Smart Factor and to predict the outcome of the steel rolling process based on those factors. This can be applied in various industries that involve similar manufacturing processes, enabling accurate predictions of product quality and process efficiency. The aim is to identify the most important factors that affect the Steel Rolling Smart Factor and to predict the outcome of the steel rolling process based on those factors. The hybrid model can improve accuracy and reliability by incorporating multiple predictive models and clustering similar data points together.