Yang Xu, Shi Chao, Cao Hongwei, Sun Sicong, Liu Guangkui
China Special Equipment Inspection & Research Institute, Beijing100029, China.
ACS Omega. 2023 Feb 2;8(6):5300-5305. doi: 10.1021/acsomega.2c06004. eCollection 2023 Feb 14.
High chromium martensitic heat-resistant steel is considered as a candidate material for pressure components of the next generation of incinerators of the subcritical level or above in China due to its excellent high-temperature and corrosion resistance, but in the long-term service, aging will significantly affect the service safety of materials. So, accurate identification of its aging state is important to enhance the safety of a power plant. In this paper, an automatic aging grading model of high chromium martensite heat-resistant steel based on the depth residual network is proposed according to different scales of metallographic data. A multiscale data set is constructed by image reduction to verify the accuracy of the model in identifying microstructure images of high chromium martensitic heat-resistant steel with different scales. The experimental results show that the model using multiscale data sets performs well, and then, through feature pyramid network model training, the accuracy rate is further improved, and a relatively good prediction accuracy model is obtained. The validity of the deep learning method for the classification of damage and aging of P91 steel with different scales is verified.
高铬马氏体耐热钢因其优异的高温性能和耐腐蚀性，被认为是我国亚临界及以上等级下一代焚烧炉受压元件的候选材料，但在长期服役过程中，时效会显著影响材料的服役安全性。因此，准确识别其时效状态对于提高电厂安全性具有重要意义。本文根据金相数据的不同尺度，提出了一种基于深度残差网络的高铬马氏体耐热钢自动时效分级模型。通过图像缩放到构建多尺度数据集，验证模型在识别不同尺度高铬马氏体耐热钢微观组织图像时的准确性。实验结果表明，使用多尺度数据集的模型性能良好，然后通过特征金字塔网络模型训练，准确率进一步提高，得到了预测精度较高的模型。验证了深度学习方法对不同尺度P91钢损伤和时效分类的有效性。
