Ensemble Machine Learning Systems for the Estimation of Steel Quality Control

Abstract

Recent advances in the steel industry have encountered challenges in soliciting decision making solutions for quality control of products based on data mining techniques. In this paper, we present a steel quality control prediction system encompassing with real-world data as well as comprehensive data analysis results. The core process is cautiously designed as a regression problem, which is then best handled by grouping various learning algorithms with their massive resource of historical production datasets. The characteristics of the currently most popular learning models used in regression problem analysis are as well investigated and compared. The performance indicates our steel quality control prediction system based on ensemble machine learning model can offer promising result whilst delivering high usability for local manufacturers to address the production problem by aid of development of machine learning techniques. Furthermore, real-world deployment of this system is demonstrated and discussed. Finally, future directions and the performance expectation are pointed out.

Explainable Steel Quality Prediction System Based on Gradient Boosting Decision Trees

“…Local interpretable model-agnostic explanations (LIME) have also been used to interpret predictions. Ensemble machine learning models can be used as well to predict the properties of steel products as presented in [22], where algorithms that rely on boosting strategies, such as gradient boosting decision trees, LightGBM, and XGBoost, were found to perform better than traditional single-regression methods, such as linear regression, Ridge regression, and Lasso regression. In addition, Zhang et al [23] demonstrated that LightGBM provides both best predictive performance, but is also highly computationally effective compared to random forest, deep feedforward neural network and SVM.…”

“…• Novel gradient boosting-based surface quality prediction model: In [22], ensemble methods showed promising results for prediction accuracy; therefore, we use a gradient boosting decision tree-based machine learning model for the prediction of product surface quality early in the steel manufacturing process. We utilize the production, parameter, and surface quality inspection data of an actual steel plant as our dataset.…”

Quality Prediction of Continuous Casting Slabs Based on Weighted Extreme Learning Machine

“…They exploited an improved Particle Swarm Optimization (PSO) algorithm to optimize the structural parameters of the model to achieve high accuracy. Li et al [16] studied the performance of several ensemble algorithms in building mechanical property prediction models. They claimed that the ensemble machine learning system achieved a higher performance than the other baseline approaches.…”

An Inspection and Classification System for Automotive Component Remanufacturing Industry Based on Ensemble Learning

“…The main problem with deep learning methods is that they generally require an inspection of the prediction results that do not have a high confidence value. In order to achieve more stable models that are able to specialize in complex image features, model ensembles are used [24,25]. This strategy allows each individual model to learn certain details that the rest of the models do not have to learn, thus parallelizing the detection tasks and obtaining multiple detection "opinions".…”