Prediction of Mechanical Properties of Cold-Rolled Steel Based on Improved Graph Attention Network

doi:10.3390/sym16020188

IR > 计算机与通信学院

	Prediction of Mechanical Properties of Cold-Rolled Steel Based on Improved Graph Attention Network
	Luo, Xiaoyang 1; Guo, Rongping 2; Zhang, Qiwen2 ; Tang, Xingchang3,4
	2024-02
发表期刊	SYMMETRY-BASEL
卷号	16 期号:2
摘要	The prediction of mechanical properties of cold-rolled steel is very important for the quality control, process optimization, and cost control of cold-rolled steel, but it is still a challenging task to predict accurately. For the existing graph structure of graph attention networks, it is difficult to effectively establish the complex coupling relationship and nonlinear causal relationship between variables. At the same time, it is considered that the process of cold-rolled steel has typical full-flow process characteristics and the graph attention network makes it difficult to extract the path information between the central node and its higher-order neighborhood. The neural Granger causality algorithm is used to extract the latent relationship between variables, and the basic graph structure of mechanical property prediction data is constructed. Secondly, the node embedding layer is added before the graph attention network, which leverages the symmetry nature of Node2vec method by incorporating both breadth-first and depth-first exploration strategies. This ensures a balanced exploration of diverse paths in the graph, capturing not only local structures but also higher-order relationships. The combined graph attention networks are then able to effectively capture the symmetry path information between nodes and dependencies between variables. The accuracy and superiority of this method are verified by experiments in real cold-rolled steel production cases.
关键词	mechanical properties graph attention networks nonlinear causal relationship neural Granger causality Node2vec
DOI	10.3390/sym16020188
收录类别	SCIE
语种	英语
资助项目	National Natural Science Foundation of China
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:001172295800001
出版者	MDPI
原始文献类型	Article
EISSN	2073-8994
引用统计	无
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/169831
专题	计算机与通信学院省部共建有色金属先进加工与再利用国家重点实验室
通讯作者	Guo, Rongping
作者单位	1.Hongxing Iron & Steel Co Ltd, Carbon Steel& Thin Slab Rolling Plant, Gansu JISCO Grp, Jiayuguan 735100, Peoples R China; 2.Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou 730050, Peoples R China; 3.State Key Lab Adv Proc & Recycling Nonferrous Met, Lanzhou 730050, Peoples R China; 4.Lanzhou Univ Technol, Coll Mat Sci & Engn, Lanzhou 730050, Peoples R China
通讯作者单位	兰州理工大学
推荐引用方式 GB/T 7714	Luo, Xiaoyang,Guo, Rongping,Zhang, Qiwen,et al. Prediction of Mechanical Properties of Cold-Rolled Steel Based on Improved Graph Attention Network[J]. SYMMETRY-BASEL,2024,16(2).
APA	Luo, Xiaoyang,Guo, Rongping,Zhang, Qiwen,&Tang, Xingchang.(2024).Prediction of Mechanical Properties of Cold-Rolled Steel Based on Improved Graph Attention Network.SYMMETRY-BASEL,16(2).
MLA	Luo, Xiaoyang,et al."Prediction of Mechanical Properties of Cold-Rolled Steel Based on Improved Graph Attention Network".SYMMETRY-BASEL 16.2(2024).