用于预测边界元弱奇异积分的新型樽海鞘-神经网络模型

doi:10.6040/j.issn.1672-3961.0.2023.156

山东大学学报 (工学版) ›› 2023, Vol. 53 ›› Issue (6): 8-15.doi: 10.6040/j.issn.1672-3961.0.2023.156

• 机器学习与数据挖掘 • 上一篇

用于预测边界元弱奇异积分的新型樽海鞘-神经网络模型

李源^1,2,张妮¹,张艳娜^1,2,刘士豪¹,李学辉³

1.河南师范大学计算机与信息工程学院, 河南新乡453007;2.智慧商务与物联网技术河南省工程实验室, 河南新乡453007;3.新乡市和协饲料机械制造有限公司, 河南新乡453131

发布日期:2023-12-19
作者简介:李源(1989— ),女,河南新乡人,副教授,硕士生导师,博士,主要研究方向为计算力学、机器学习、边界元法. E-mail: liyuan2015097@163.com
基金资助:
河南省自然科学基金资助项目(232300421390);河南省高等学校重点科研资助项目(23A510003)

A novel salp swarm algorithm-neural network model for predicting weak singular integrals of boundary elements

LI Yuan^1,2, ZHANG Ni¹, ZHANG Yanna^1,2, LIU Shihao¹, LI Xuehui³

1. College of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, Henan, China;
2. Engineering Lab of Intelligence Business &
Internet of Things, Henan Province, Xinxiang 453007, Henan, China;
3. Hexie Feed Machinery Manufacturing Co., Ltd., Xinxiang 453131, Henan, China

Published:2023-12-19

摘要/Abstract

摘要： 为解决传统奇异积分计算方案复杂、计算成本高昂的问题,提出一种构建神经网络代理模型的方法,用于在线阶段预测边界元弱奇异积分结果。从理论上探讨使用机器学习方法预测边界元奇异积分的可行性,利用离线阶段收集的边界元弱奇异积分数据作为训练样本,通过坐标空间转换法解决训练空间和预测空间不一致的问题;引入灰狼等级制位置更新方法和自适应优化策略,提出一种改进的自适应樽海鞘(improved adaptive salp swarm algorithm, IASSA)优化方法,提高神经网络模型预测精度,解决标准樽海鞘优化算法收敛速度慢、后期种群多样性差的问题。试验结果表明,基于IASSA优化的神经网络代理模型能够将预测精度提高约54.50%,IASSA的收敛速度比标准樽海鞘优化算法提高约66.67%,降低了离线阶段代理模型的训练时间。

关键词: 边界元法, 奇异积分, 神经网络, 代理模型, 优化算法

中图分类号:

TP181

李源,张妮,张艳娜,刘士豪,李学辉. 用于预测边界元弱奇异积分的新型樽海鞘-神经网络模型[J]. 山东大学学报 (工学版), 2023, 53(6): 8-15.

LI Yuan, ZHANG Ni, ZHANG Yanna, LIU Shihao, LI Xuehui. A novel salp swarm algorithm-neural network model for predicting weak singular integrals of boundary elements[J]. Journal of Shandong University(Engineering Science), 2023, 53(6): 8-15.

参考文献

[1] 姚振汉, 王海涛. 边界元法[M]. 北京: 高等教育出版社, 2010.
[2] CHENG A H D, CHENG D T. Heritage and early history of the boundary element method[J]. Engineering Analysis with Boundary Elements, 2005, 29(3): 268-302.
[3] FENG S Z, HAN X, LI Z, et al. Ensemble learning for remaining fatigue life prediction of structures with stochastic parameters: a data-driven approach[J]. Applied Mathematical Modelling, 2022, 101: 420-431.
[4] NIKOLOPOULOS S, KALOGERIS I, PAPADOPOULOS V. Machine learning accelerated transient analysis of stochastic nonlinear structures[J]. Engineering Structures, 2022, 257: 114020.
[5] GANTALA T, BALASUBRAMANIAM K. DPAI: a data-driven simulation-assisted-Physics learned AI model for transient ultrasonic wave propagation[J]. Ultrasonics, 2022, 121: 106671.
[6] LIANG L, LIU M, MARTIN C, et al. A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis[J]. Journal of the Royal Society Interface, 2018, 15: 20170844.
[7] 陈泽彬. 基于深度学习的有限元计算研究[D]. 哈尔滨: 哈尔滨工业大学, 2020. CHEN Zebin. Study of the finite element modeling and analysis based deep learning[D]. Harbin: Harbin Institute of Technology, 2020.
[8] NIE Z, JIANG H, KARA L B. Stress field prediction in cantilevered structures using convolutional neural networks[J]. Journal of Computing and Information Science in Engineering, 2020, 20(1): 011002.
[9] CHENG R, YIN X, CHEN L. Machine learning enhanced boundary element method: prediction of gaussian quadrature points[J]. Computer Modeling in Engineering & Sciences, 2022, 131(1): 445-464.
[10] 常宏宇, 朱仁传, 黄山. 基于机器学习的脉动源格林函数预报初探[J]. 海洋工程, 2020, 38(6): 131-141. CHANG Hongyu, ZHU Renchuan, HUANG Shan. Preliminary study on prediction of pulsating source Green function based on machine learning[J]. Ocean Engineering, 2020, 38(6): 131-141.
[11] HUANG S, ZHU R C A, CHANG H Y, et al. Machine learning to approximate free-surface Green's function and its application in wave-body interactions[J]. Engineering Analysis with Boundary Elements, 2021, 134: 35-48.
[12] GUO H, ZHUANG X, RABCZUK T. A deep collocation method for the bending analysis of Kirchhoff plate[J]. Computers, Materials and Continua, 2019, 59(2): 433-456.
[13] 郭宏伟, 庄晓莹. 采用两步优化器的深度配点法与深度能量法求解薄板弯曲问题[J]. 固体力学学报, 2021, 42(3): 249-266. GUO Hongwei, ZHUANG Xiaoying. The application of deep collocation method and deep energy method with a two-step optimizer in the bending analysis of kirchhoff thin plate[J]. Acta Mechanica Solida Sinica, 2021, 42(3): 249-266.
[14] LI Y, MAO W, WANG G, et al. A general-purpose machine learning framework for predicting singular integrals in boundary element method[J]. Engineering Analysis with Boundary Elements, 2020, 117: 41-56.
[15] 李源. 弹性动力学问题的时域边界面法[D]. 长沙: 湖南大学, 2015. LI Yuan. Elastodynamic analysis with time-domain boundary face method[D]. Changsha: Hunan University, 2015.
[16] HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feedforward networks are universal approximators[J]. Neural Networks, 1989, 2(5): 359-366.
[17] MIRJALILI S, GANDOMI A H, MIRJALILI S Z, et al. Salp swarm algorithm: a bio-inspired optimizer for engineering design problems[J]. Advances in Engineering Software, 2017, 114: 163-191.
[18] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323: 533-536.
[19] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501.
[20] JIANG Q H, ZHU L J, SHU C, et al. An efficient multilayer RBF neural network and its application to regression problems[J]. Neural Computing and Applications, 2022, 34: 4133-4150.
[21] XUE J, SHEN B. A novel swarm intelligence optimi-zation approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 22-34.
[22] EBERHART R, KENNEDY J. A new optimizer using particle swarm theory[C] //MHS95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science. Piscataway, USA: IEEE Press, 2002: 39-43.
[23] NIU P, NIU S, LIU N, et al. The defect of the Grey Wolf optimization algorithm and its verification method[J]. Knowledge-Based Systems, 2019, 171: 37-43.
[24] SALGOTRA R, SINGH U, SINGH S, et al. Self-adaptive salp swarm algorithm for engineering optimization problems[J]. Applied Mathematical Modelling, 2021, 89(1): 188-207.

相关文章 15

[1]	韦修喜,陶道,黄华娟. 改进果蝇算法优化BP神经网络预测汽油辛烷值[J]. 山东大学学报 (工学版), 2023, 53(5): 20-28.
[2]	陈雷,赵耀帅,林彦,郭晟楠,万怀宇,林友芳. 交通流量预测的时间异质性图注意力网络[J]. 山东大学学报 (工学版), 2023, 53(5): 29-36.
[3]	那绪博,张莹,李沐阳,陈元畅,华云鹏. 基于ODCG的网约车需求预测模型[J]. 山东大学学报 (工学版), 2023, 53(5): 48-56.
[4]	于泓,杜娟,魏琳,张利. 计及行为特征的市场化用户电量数据拟合方法[J]. 山东大学学报 (工学版), 2023, 53(4): 113-119.
[5]	李浩源,于景明,张桂林,张斌. 基于智能算法的光纤预制棒芯层制备工艺参数优化[J]. 山东大学学报 (工学版), 2023, 53(4): 149-156.
[6]	范海雯,郝旭东,赵康,邢法财,蒋哲,李常刚. 基于卷积神经网络的含分布式光伏配电网静态等值[J]. 山东大学学报 (工学版), 2023, 53(4): 140-148.
[7]	刘庆鑫,齐琦,贾鹤鸣,李霓. 混合改进策略的阿奎拉鹰优化算法[J]. 山东大学学报 (工学版), 2023, 53(4): 93-103.
[8]	袁钺,王艳丽,刘勘. 基于空洞卷积块架构的命名实体识别模型[J]. 山东大学学报 (工学版), 2022, 52(6): 105-114.
[9]	王智伟,徐海超,郭相阳,马炯,褚云龙,陈前昌,卢治. 基于卷积神经网络和层次分析的新能源电源调频能力智能预测方法[J]. 山东大学学报 (工学版), 2022, 52(5): 70-76.
[10]	孙东磊, 鉴庆之, 李智琦, 韩学山, 王明强, 陈博, 付一木. 源网协调的电力系统均匀性规划[J]. 山东大学学报 (工学版), 2022, 52(5): 92-101.
[11]	孟祥飞,张强,胡宴才,张燕,杨仁明. 欠驱动船舶自适应神经网络有限时间跟踪控制[J]. 山东大学学报 (工学版), 2022, 52(4): 214-226.
[12]	黄皓,周丽华,黄亚群,姜懿庭. 基于混合深度模型的虚假信息早期检测[J]. 山东大学学报 (工学版), 2022, 52(4): 89-98.
[13]	尹旭,刘兆英,张婷,李玉鑑. 基于弱监督和半监督学习的红外舰船分割方法[J]. 山东大学学报 (工学版), 2022, 52(2): 99-106.
[14]	王心哲,邓棋文,王际潮,范剑超. 深度语义分割MRF模型的海洋筏式养殖信息提取[J]. 山东大学学报 (工学版), 2022, 52(2): 89-98.
[15]	张学思,张婷,刘兆英,江天鹏. 基于轻量型卷积神经网络的海面红外显著性目标检测方法[J]. 山东大学学报 (工学版), 2022, 52(2): 41-49.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

用于预测边界元弱奇异积分的新型樽海鞘-神经网络模型

A novel salp swarm algorithm-neural network model for predicting weak singular integrals of boundary elements

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

多维度评价

本文评价

推荐阅读 0