Prediction of hot-rolled strip crown based on Boruta and extremely randomized trees algorithms

The quality of hot-rolled steel strip is directly affected by the strip crown.Traditional machine learning models have shown limitations in accurately predicting the strip crown,particularly when dealing with imbalanced data.This limitation results in poor production quality and efficiency,leading to increased production costs.Thus,a novel strip crown prediction model that uses the Boruta and extremely randomized trees(Boruta-ERT)algorithms to address this issue was proposed.To improve the accuracy of our model,we utilized the synthetic minority over-sampling technique to balance the imbalance data sets.The Boruta-ERT prediction model was then used to select features and predict the strip crown.With the 2160 mm hot rolling production lines of a steel plant serving as the research object,the experimental results showed that 97.01% of prediction data have an absolute error of less than 8 lm.This level of accuracy met the control requirements for strip crown and demonstrated significant benefits for the improvement in production quality of steel strip.

Prediction of mechanical properties of cold rolled strip based on improved extreme random tree

Taking the 2130 cold rolling production line of a steel mill as the research object,feature dimensionality reduction and decoupling processing were realized by fusing random forest and factor analysis,which reduced the generation of weak decision trees while ensured its diversity.The base learner used a weighted voting mechanism to replace the traditional average method,which improved the prediction accuracy.Finally,the analysis method of the correlation between steel grades was proposed to solve the problem of unstable prediction accuracy of multiple steel grades.The experimental results show that the improved prediction model of mechanical properties has high accuracy:the prediction accuracy of yield strength and tensile strength within the error of±20 MPa reaches 93.20%and 97.62%,respectively,and that of the elongation rate under the error of±5%has reached 96.60%.

Instance-Specific Algorithm Selection via Multi-Output Learning

Instance-specific algorithm selection technologies have been successfully used in many research fields,such as constraint satisfaction and planning. Researchers have been increasingly trying to model the potential relations between different candidate algorithms for the algorithm selection. In this study, we propose an instancespecific algorithm selection method based on multi-output learning, which can manage these relations more directly.Three kinds of multi-output learning methods are used to predict the performances of the candidate algorithms：（1）multi-output regressor stacking;（2） multi-output extremely randomized trees; and（3） hybrid single-output and multioutput trees. The experimental results obtained using 11 SAT datasets and 5 Max SAT datasets indicate that our proposed methods can obtain a better performance over the state-of-the-art algorithm selection methods.