Surface depression recognition of spring plate based on feature construction and improved AdaBoost algorithm

Machine learning has introduced novel solutions for the surface quality inspection of spring plates. Hence, an improved method was proposed based on logistic regression and AdaBoost (LR-RBAdaBoost) for recognizing surface depressions in spring plates. In order to obtain the measured attributes for spring plates, feature construction methods were adopted. Then, logistic regression was used to analyze and rank the attributes of the spring plate and the filter method was used for the feature selection process. To improve the predicted performance of AdaBoost, RBAdaBoost was proposed in this paper, which is used in the issue of recognition of surface defects in spring steel plates. The effectiveness and sophistication of LR-RBAdaBoost are validated on a real spring steel plate sampling dataset. The results show that the accuracy of LR-RBAdaBoost is 0.968 and f1-score is 0.967, which can be better than the results of only using AdaBoost, random forest, and CatBoost. Furthermore, the results prove that the research has a certain reference value for the recognition of spring plate as well.