基于材料组织量化的DWTT性能优化探究  

Study on DWTT property optimization based on the quantification of microstructures

作　　者：邢钊[1] 梁晓军[1] 郝英敏 XING Zhao;LIANG Xiaojun;HAO Yingmin(Research Institute,Baoshan Iron & Steel Co. ,Ltd. , Shanghai 201999, China)

机构地区：[1]宝山钢铁股份有限公司中央研究院,上海201999

出　　处：《宝钢技术》2021年第1期24-28,共5页Baosteel Technology

摘　　要：以一种新型管线钢试制过程中DWTT性能改进为例,基于PIDAS提供的工艺—性能数据,通过机器学习与图像识别方法对材料组织进行信息量化分析。结合不同工艺量化信息对比改进工艺参数,通过有限次数试制获得的工艺—组织—性能数据,结合专家经验找出三者之间关联性,进行工艺分析优化设计,快速确定达成良好DWTT性能的工艺设计。This study takes the performance improvement of DWTT during the trial production of a new type of pipeline steel as an example.Based on the process-property data provided by PIDAS,the microstructures characteristics are quantitatively analyzed through machine learning and image recognition methods.Process parameters were improved by comparing different process quantization information.The process-structure-property data obtained by trial production are combined with expert experience to find out their correlations,assist process analysis and optimization design,and quickly determine the process design to achieve good DWTT property.

关 键 词：DWTT性能 组织 信息量化 工艺—组织—性能 

分 类 号：TG344.9[金属学及工艺—金属压力加工]