基于PINNs的欧拉梁数字孪生模型构建  

Construction of a Digital Twin Model for Euler Beams Using Physics-Informed Neural Networks(PINNs)

在线阅读下载全文

作  者:吴腾 刘金杰 WU Teng;LIU Jinjie(School of Mechanical and Electronic Engineering,Wuhan University of Technology,Wuhan 430070,China)

机构地区:[1]武汉理工大学机电工程学院,湖北武汉430070

出  处:《数字制造科学》2024年第4期305-309,共5页

摘  要:针对目前数字孪生模型中人工智能算法大多以纯数据驱动的问题,采用了一种能够融合物理机理的物理信息神经网络(PINNs)算法,应用于欧拉梁的数字孪生模型构建。并以欧拉梁简支变力条件作为算例,结果表明孪生模型的求解结果与解析解的L2相对误差在4%以内,能够为分析决策提供一定的精度;最后基于Python开发了欧拉梁的可视化界面。为探索机械零部件的数字孪生及复杂装备的数字孪生技术路线提供参考价值。To address the limitation of pure data-driven approaches commonly used in current digital twin models,this study adopts a Physics-Informed Neural Networks(PINNs)algorithm that integrates physical mechanisms and applies it to the construction of a digital twin model for Euler beams.Using the simply supported Euler beam under variable force conditions as a case study,the results demonstrate that the relative L2 error between the twin model solutions and analytical solutions is within 4%,offering sufficient accuracy for analysis and decision-making.Additionally,a Python-based visualization interface for the Euler beam was developed.This study provides valuable insights for advancing digital twin technologies for mechanical components and complex equipment.

关 键 词:PINNs 欧拉梁 数字孪生 模型构建 

分 类 号:TV332.1[水利工程—水工结构工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象