数据驱动的文献辅助管线钢产线落锤撕裂韧性内禀特征关联  

Prediction of the drop hammer-derived tear toughness of pipeline steel production lines using literature data and production line data

作　　者：商春磊 王传军 刘文月 朱德鑫 汪水泽 董林硕 吴桂林 高军恒 赵海涛 张朝磊[1,2] 吴宏辉 SHANG Chun-lei;WANG Chuan-jun;LIU Wen-yue;ZHU De-xin;WANG Shui-ze;DONG Lin-shuo;WU Gui-lin;GAO Jun-heng;ZHAO Hai-tao;ZHANG Chao-lei;WU Hong-hui(Beijing Advanced Innovation Center for Materials Genome Engineering,Beijing 100083,China;Carbon Neutral Innovation Institute,University of Science and Technology Beijing,Beijing 100083,China;State Key Laboratory of Metal Materials for Marine Equipment and Application,Anshan 114009,China;Ansteel Beijing Research Institute Co.LTD,Beijing 102200,China)

机构地区：[1]北京材料基因工程高精尖创新中心,北京100083 [2]北京科技大学碳中和创新研究院,北京100083 [3]海洋装备用金属材料及其应用国家重点实验室,鞍山114009 [4]鞍钢集团北京研究院有限公司,北京102200

出　　处：《工程科学学报》2023年第8期1390-1399,共10页Chinese Journal of Engineering

基　　金：国家自然科学基金面上资助项目(52071023)。

摘　　要：管道运输是当前长距离输送石油、天然气等能源最经济的方式之一,具有优异的低温韧性是保证管线钢安全运输的重要特征.落锤撕裂试验(Drop weight tear testing,DWTT)是衡量管线钢低温韧性的最有效的方法.在目前的工作中,根据钢厂提供的产线数据集和文献收集的管线钢数据集,建立了基于机器学习的DWTT剪切面积预测模型.基于纯产线数据和文献数据辅助的产线数据构造了两种机器学习策略方案,测试了不同机器学习算法,效果最好的均是随机森林模型,策略一的纯产线数据模型的性能指标皮尔逊相关系数(PCC)为0.64,策略二的文献数据辅助的产线数据模型的性能指标皮尔逊相关系数(PCC)为0.92,文献数据的增加有效提高了DWTT剪切面积预测精度.机器学习技术为优化和预测DWTT剪切面积提供了一种新的思路.Pipeline transportation is the most economical means of transporting oil,natural gas,and other energy sources over a long distance.With the increasingly harsh service environment of pipeline transportation,the requirements of pipeline steel in terms of strength,hydrogen-induced fracture resistance,and corrosion resistance have increased.In areas such as plateaus or deep seas,excellent low-temperature toughness is important to ensure the safe transportation of pipeline steel.Drop weight tear testing is one of the most effective methods for measuring the low-temperature toughness of pipeline steel.The test involves large specimens with full wall t hickness.Through the characterization of the ductile–brittle shear area and ligament width of the sample,the toughness and tear resistance of pipeline steel can be better reflected. However, the drop weight tear test is difficult, time-consuming, and laborious, and itconsumes a large amount of experimental resources. In this work, a machine learning-based model for predicting the drop weight teartest-derived shear area was established according to production line datasets provided by steel mills and pipeline steel datasets collectedfrom the literature. Different machine learning algorithms were tested using the two datasets. The best models were random forestmodels. Strategy I included only production line datasets, and the Pearson correlation coefficient (PCC), which is the performance index,predicted by the machine learning model was 0.64. Strategy II involved literature data and production line data, and the PCC predictedby the machine learning model was 0.92. The consideration of literature data effectively improved the prediction accuracy of the dropweight tear test shear area. Moreover, in strategy II, to avoid the overfitting of the machine learning model, a feature screening techniquewas adopted. Finally, a genetic programming-based symbolic regression approach was developed to establish a formula describing therelationship between the selected features and the

关 键 词：管线钢 落锤撕裂试验 机器学习 数据驱动设计 符号回归 

分 类 号：TG142[一般工业技术—材料科学与工程]