Sub-Macroscopic Inclusion Classification in Bearing Steels Based on LFCN and Ultrasonic Testing

Abstract

With the improvement of science and technology, the demand for advanced steel with excellent performance has gradually increased. Therefore, the evaluation of steel internal cleanness is an important indicator for the evaluation of material quality. Sub-macroscopic inclusions, which size from 50μm to 400μm and cannot be detected under the domestic and international bearing steel testing standard, are bound to affect the quality, stability and service life of bearing steel seriously. Hence, the researches of inclusion control technology has gradually attracted attention in the academia and industrial manufacture field. In this paper, we propose an end-to-end Long Short-term Memory Fully Convolutional Network (LFCN) classification model, and verify the effectiveness on the large-scale sub-macroscopic inclusion signal data set collected by ultrasonic experiments. To the best of our knowledge, this study is the first one in this field that has acquire such large amount of experimental sub-macroscopic signal data and solve the classification task by FCN. Especially, our framework can accurately detect the features of sub-macroscopic inclusions, which meets the urgent need of the metallurgical industry. The accuracy rate of proposed model is 88.97%, which is state-of-the-art experimental result among other strong time series classifiers.