Prediction of mechanical properties of micro-alloyed steels via neural networks learned by water wave optimization

doi:10.1007/s00521-019-04149-1

	Prediction of mechanical properties of micro-alloyed steels via neural networks learned by water wave optimization
	Liu, Ao 2,5; Li, Peng 3; Sun, Weiliang 4; Deng, Xudong 2,5; Li, Weigang 1; Zhao, Yuntao 1; Liu, Bo 3
刊名	NEURAL COMPUTING & APPLICATIONS
	2020-05-01
卷号	32 期号:10 页码:5583-5598
关键词	Neural networks Water wave optimization Meta-Lamarckian learning Prediction of mechanical properties
ISSN号	0941-0643
DOI	10.1007/s00521-019-04149-1
英文摘要	Searching optimal parameters for neural networks can be formulated as a multi-modal optimization problem. This paper proposes a novel water wave optimization (WWO)-based memetic algorithm to identify the optimal weights for neural networks. In the proposed water wave optimization-based memetic algorithm (WWOMA), we employ WWO to perform global search by both individual improvement and population co-evolution and then employ several local search components to enhance its local refinement ability. Moreover, an effective Meta-Lamarckian learning strategy is utilized to choose a proper local search component to concentrate computational efforts on more promising solutions. We carry out simulation experiments on six well-known neural network designing benchmark problems, both the simulation results and statistical comparisons demonstrate the feasibility, effectiveness and efficiency of applying WWOMA to design neural networks. Furthermore, we apply WWOMA to design neural networks and use well-trained neural networks to predict tensile strength of micro-alloyed steels. Evaluation on a practical industrial case with 2489 sample data shows that, in comparison with other algorithms, WWOMA-based neural networks can obtain notable and robust prediction accuracy, which further demonstrates that WWOMA is a promising and efficient algorithm for designing neural networks. It is worth mentioning that, to the best of our knowledge, this is the first report about applying water wave optimization to train neural networks.
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER LONDON LTD
WOS记录号	WOS:000529745200024
内容类型	期刊论文
源URL	[http://ir.amss.ac.cn/handle/2S8OKBNM/51399]
专题	中国科学院数学与系统科学研究院
通讯作者	Liu, Bo
作者单位	1.Wuhan Univ Sci & Technol, Sch Informat Sci & Engn, Wuhan 430081, Peoples R China 2.Wuhan Univ Sci & Technol, Ctr Serv Sci & Engn, Wuhan 430065, Peoples R China 3.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China 4.Tianjin Univ, Sch Chem Engn & Technol, Tianjin 300350, Peoples R China 5.Wuhan Univ Sci & Technol, Sch Management, Wuhan 430065, Peoples R China
推荐引用方式 GB/T 7714	Liu, Ao,Li, Peng,Sun, Weiliang,et al. Prediction of mechanical properties of micro-alloyed steels via neural networks learned by water wave optimization[J]. NEURAL COMPUTING & APPLICATIONS,2020,32(10):5583-5598.
APA	Liu, Ao.,Li, Peng.,Sun, Weiliang.,Deng, Xudong.,Li, Weigang.,...&Liu, Bo.(2020).Prediction of mechanical properties of micro-alloyed steels via neural networks learned by water wave optimization.NEURAL COMPUTING & APPLICATIONS,32(10),5583-5598.
MLA	Liu, Ao,et al."Prediction of mechanical properties of micro-alloyed steels via neural networks learned by water wave optimization".NEURAL COMPUTING & APPLICATIONS 32.10(2020):5583-5598.