The Application of tree-based ML algorithm in steel plates Ffaults identification

In the production of steel plates, it is essential to detect the surface quality effectively in real time. If the faults are not identified quickly and correctly, and the production technology is not corrected in time, the production of such faulty steel plates will cause huge economic losses to the company. In the traditional manufacturing process, the manual detection methods are often used to identify these faults, which is inefficient, inaccurate and timeconsuming. Steel plate fault classification can be regarded as a typical classification problem in machine learning fields, which can be conducted more efficiently, quickly and accurately with the help of efficient algorithm. Rapid classification of faults allows operators to find issues more easily and improve the production processes. We apply a series of classical machine learning algorithms based on decision trees (Decision Tree, Adaboosting, Bagging, Random Forest) to verify the ten fold cross-validation of the steel plate fault data. It is found that Bagging algorithm outperforms the other methods and achieves 96.30% and 90% accuracy on the training and testing set, respectively. This will allow us to find abnormalities on the surface of the steel plate timely and reduce losses. Based on these algorithms, we can cooperate with iron and steel practitioners to design more appropriate algorithms to achieve higher recognition accuracy in the future.