A data-driven machine learning approach to predict the hardenability curve of boron steels and assist alloy design

Journal of Materials Science - Boron steel is one of the most valuable lightweight steels for automobile due to its high strength after hot stamping and low cost. In order to ensure service...     

Chemometric methods applied to industrial optimization and materials optimal design

Based on the methods of multivariate data processing of the data records for complicated chemical reaction systems, computer software named `process analyzer' and `materials research advisor' has been built. The methods used include some new methods of pattern recognition, such as back-mapping methods, local-structure view and data transformation methods. These new computational techniques have been widely used in the chemical, petrochemical and metallurgical industries for industrial optimization and materials design with good results.     

基于BAS算法优化的电弧增材制造焊道尺寸预测

目的 为提高实际应用中电弧增材制造对工艺参数的选取效率及成形形貌的控制效果,建立高效且精准的成形尺寸预测模型,实现对焊道尺寸的合理预测。方法 在单层单道CMT电弧增材制造实验的基础上,建立基于天牛须搜索算法(Beetle Antennae Search,BAS)优化BP神经网络的焊道尺寸预测模型,利用BAS算法实现对BP神经网络初始权值和阈值的优化,可以实现预测不同工艺参数(焊接速度、送丝速度、干伸长)下焊道的成形尺寸(熔宽、余高)。利用试验验证BAS-BP预测模型的性能,与现有模型进行对比,结果 结果表明该模型具有较高精度的预测效果,能够有效映射工艺参数与焊道尺寸之间的非线性关系,印证了该模型具有良好的拟合和泛化能力,同时其对焊道熔宽和余高的预测误差分别不超过0.2、0.12 mm,预测平均误差率均不超过6%,相对于其他预测模型表现出较好的准确性和稳定性。结论 BAS-BP神经网络预测模型的输出误差较小,网络训练收敛速度加快,避免了过拟合及欠拟合的风险,有效提高了预测模型的泛化能力和预测精度,可以实现一定工艺参数范围内的焊道尺寸预测,为后续电弧增材的实时预测及控制参数应用提供了技术支持。     

Application of atomic simulation for studying hydrogen embrittlement phenomena and mechanism in iron-based alloys

High-strength iron-based alloys serving in hydrogen-containing environments often faces a critical problem of hydrogen embrittlement, which involves intricate mechanisms across multiple lengths and time scales resulting in catastrophic consequences. It is challenging to track the evolution or/and nanoscale distribution of hydrogen atoms via experiments directly, whereas atomic simulation displays its great advantages in revealing the hydrogen-related behaviors and interaction mechanism. Most studies on hydrogen embrittlement mechanisms via atomic simulations focused on iron, as it is the matrix composition of steel. Herein, we summarize recent advances about applying atomic simulations, including density functional theory and molecular dynamics, in understanding the interaction between hydrogen atoms and various defects in iron-based alloys. Finally, some scientific issues and challenges in this field are discussed to provide insight for future researches.     

热等静压技术在透明陶瓷研究中的应用进展

透明陶瓷具有与单晶材料相媲美的光学、力学和热学等性能，被广泛应用在透明装甲、红外窗口、高功率激光器、白光照明、医学诊疗等民用和军事领域。影响透明陶瓷光学透过率的主要因素是气孔，而热等静压（HIP）后处理是消除气孔，获得高质量透明陶瓷的有效办法之一。本文综述了近期利用热等静压技术研究透明陶瓷取得的成果和提出的一些机理，进而对热等静压技术开发透明陶瓷进行了讨论和展望。