Automatic Detection of Sorbite Content in High Carbon Steel Wire Rod
Open Access
Abstract
This paper presents a method for the automatic detection of sorbite content in high-carbon steel wire rods. A semantic segmentation model of sorbite based on DeepLabv3+ is established. The sorbite structure is segmented, and the prediction results are analyzed and counted based on the metallographic images of high-carbon steel wire rods marked manually. For the problem of sample imbalance, the loss function of Dice loss + focal loss is used, and the perturbation processing of training data is added. The results show that this method can realize the automatic statistics of sorbite content. The average pixel prediction accuracy is as high as 94.28%, and the average absolute error is only 4.17%. The composite application of the loss function and the enhancement of the data perturbation significantly improve the prediction accuracy and robust performance of the model. In this method, the detection of sorbite content in a single image only takes 10 s, which is 99% faster than that of 10 min using the manual cut-off method. On the premise of ensuring detection accuracy, the detection efficiency is significantly improved and the labor intensity is reduced.Keywords
Funding Information
- The Science and Technology Program of Jiangsu Provincial Administration for Market Regulation (KJ21125122, KJ2022062, KJ204115)
This publication has 14 references indexed in Scilit:
- Machine Learning Approach on Steel Microstructure Classification2020
- Dice Loss for Data-imbalanced NLP Tasks2020
- A survey on Image Data Augmentation for Deep LearningJournal of Big Data, 2019
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- Advanced Steel Microstructural Classification by Deep Learning MethodsScientific Reports, 2018
- Focal Loss for Dense Object Detection2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Image driven machine learning methods for microstructure recognitionComputational Materials Science, 2016
- Deep Residual Learning for Image Recognition2016