Physics-informed neural networks for V-notch stress intensity factor calculation

IF 5 2区工程技术 Q1 ENGINEERING, MECHANICAL

Theoretical and Applied Fracture Mechanics Pub Date : 2024-10-10 DOI:10.1016/j.tafmec.2024.104717

Mengchen Yu , Xiangyun Long , Chao Jiang , Zhigao Ouyang

{"title":"Physics-informed neural networks for V-notch stress intensity factor calculation","authors":"Mengchen Yu , Xiangyun Long , Chao Jiang , Zhigao Ouyang","doi":"10.1016/j.tafmec.2024.104717","DOIUrl":null,"url":null,"abstract":"<div><div>This paper proposes a physics-informed neural networks (PINNs) based approach for elastic structures with a V-notch, by which the displacement field, stress field as well as the V-notch stress intensity factor (NSIF) can be obtained through artificial neural networks. A PINN model is established for V-notch structures, integrating physical information into a deep neural network to ensure adherence to physical laws while fitting observational data. Subsequently, an adaptive local sampling strategy for V-notch structures is adopted, generating locally dense Gaussian points sampling around regions of stress concentration. Based on this, a sequential PINNs approach for V-notch structures is then established to calculate the NSIF for V-notch structures with arbitrary notch angles. Finally, the effectiveness of the proposed method is validated through three numerical examples. The results demonstrate the method can accurately predict the NSIFs for V-notch structures across a spectrum of opening angles. Compared to the traditional data-driven method, the proposed method is able to more effectively compute the NSIF of V-notch structures due to the integration of physical information and observational data.</div></div>","PeriodicalId":22879,"journal":{"name":"Theoretical and Applied Fracture Mechanics","volume":null,"pages":null},"PeriodicalIF":5.0000,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Theoretical and Applied Fracture Mechanics","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167844224004671","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}

引用次数: 0

Abstract

This paper proposes a physics-informed neural networks (PINNs) based approach for elastic structures with a V-notch, by which the displacement field, stress field as well as the V-notch stress intensity factor (NSIF) can be obtained through artificial neural networks. A PINN model is established for V-notch structures, integrating physical information into a deep neural network to ensure adherence to physical laws while fitting observational data. Subsequently, an adaptive local sampling strategy for V-notch structures is adopted, generating locally dense Gaussian points sampling around regions of stress concentration. Based on this, a sequential PINNs approach for V-notch structures is then established to calculate the NSIF for V-notch structures with arbitrary notch angles. Finally, the effectiveness of the proposed method is validated through three numerical examples. The results demonstrate the method can accurately predict the NSIFs for V-notch structures across a spectrum of opening angles. Compared to the traditional data-driven method, the proposed method is able to more effectively compute the NSIF of V-notch structures due to the integration of physical information and observational data.

查看原文本刊更多论文

用于计算 V 型缺口应力强度因子的物理信息神经网络

本文提出了一种基于物理信息神经网络（PINNs）的 V 型缺口弹性结构方法，通过人工神经网络获得位移场、应力场以及 V 型缺口应力强度因子（NSIF）。针对 V 型缺口结构建立了 PINN 模型，将物理信息整合到深度神经网络中，以确保在拟合观测数据的同时遵循物理规律。随后，针对 V 型缺口结构采用了自适应局部采样策略，在应力集中区域周围生成局部密集的高斯点采样。在此基础上，建立了 V 型缺口结构的顺序 PINNs 方法，以计算任意缺口角度的 V 型缺口结构的 NSIF。最后，通过三个数值实例验证了所提方法的有效性。结果表明，该方法可以准确预测各种开口角度的 V 型缺口结构的 NSIF。与传统的数据驱动方法相比，由于整合了物理信息和观测数据，所提出的方法能够更有效地计算 V 型缺口结构的 NSIF。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Theoretical and Applied Fracture Mechanics 工程技术-工程：机械

CiteScore

8.40

自引率

18.90%

发文量

435

审稿时长

37 days

期刊介绍： Theoretical and Applied Fracture Mechanics'' aims & scopes have been re-designed to cover both the theoretical, applied, and numerical aspects associated with those cracking related phenomena taking place, at a micro-, meso-, and macroscopic level, in materials/components/structures of any kind. The journal aims to cover the cracking/mechanical behaviour of materials/components/structures in those situations involving both time-independent and time-dependent system of external forces/moments (such as, for instance, quasi-static, impulsive, impact, blasting, creep, contact, and fatigue loading). Since, under the above circumstances, the mechanical behaviour of cracked materials/components/structures is also affected by the environmental conditions, the journal would consider also those theoretical/experimental research works investigating the effect of external variables such as, for instance, the effect of corrosive environments as well as of high/low-temperature.