摘要
随着计算机技术的发展,“材料基因组计划”的推行促进了数据驱动技术在材料加工中的应用发展。人工神经网络因具有自学习、信息存储、联想记忆及高速寻求最优解等能力而广泛应用于材料设计、材料性能预测、工艺条件最优参数确定等材料科学技术研究方面,改变了传统上采用“试错法”进行的实验研究。综述了人工神经网络的基本理论及发展历程,对其在国内外在材料性能预测、材料设计优化和相变规律预测3个方面的应用发展进行了概括性总结,探究了人工神经网络在材料加工方面存在的不足,并对其未来的发展进行了展望。
In recent years,with the development of computer technology,the implementation of“Material Genome Initiative(MGI)”has promoted the application and development of data-driven technology in material processing.Artificial neural networks are widely used in material science and technology research such as material design,material performance prediction,and optimal parameter determination of process conditions because of their capabilities of self-learning,information storage,associative memory,and high-speed search for optimal solutions.It is difficult to use the“trial and error method”to carry out experimental research.In this paper,the basic theory and development history of artificial neural network at home and abroad are reviewed.The application development of material performance prediction,material design optimization and phase change rule prediction are summarized.The shortcomings of artificial neural network in material processing are explored and the future development is prospected.
作者
杨西荣
权强强
田倩炆
刘晓燕
罗雷
王敬忠
YANG Xirong;QUAN Qiangqiang;TIAN Qianwen;LIU Xiaoyan;LUO Lei;WANG Jingzhong(College of Metallurgical Engineering,Xi'an University of Architecture&Technology,Xi'an 710055,China;Shaanxi Key Laboratory of Nanomaterial and Technology,Xi'an 710055,China)
出处
《中国材料进展》
CAS
CSCD
北大核心
2023年第11期896-901,共6页
Materials China
基金
陕西省医用金属材料重点实验室开放基金项目(SXBMM-201903)
西安建筑科技大学自然科学专项基金项目(ZR19043)。
关键词
人工神经网络
材料加工
性能预测
材料设计
相变规律
artificial neural network
material processing
performance prediction
material design
phase transition rule
