典型文献
Local parameter identification with neural ordinary differential equations
文献摘要：
The data-driven methods extract the feature information from data to build system models,which enable estimation and identification of the systems and can be uti-lized for prognosis and health management(PHM).However,most data-driven models are still black-box models that cannot be interpreted.In this study,we use the neural ordinary differential equations(ODEs),especially the inherent computational relation-ships of a system added to the loss function calculation,to approximate the governing equations.In addition,a new strategy for identifying the local parameters of the system is investigated,which can be utilized for system parameter identification and damage detec-tion.The numerical and experimental examples presented in the paper demonstrate that the strategy has high accuracy and good local parameter identification.Moreover,the proposed method has the advantage of being interpretable.It can directly approximate the underlying governing dynamics and be a worthwhile strategy for system identification and PHM.
文献关键词：
中图分类号：
作者姓名：
Qiang YIN;Juntong CAI;Xue GONG;Qian DING
作者机构：
Department of Mechanics,Tianjin University,Tianjin 300350,China
文献出处：
引用格式：
[1]Qiang YIN;Juntong CAI;Xue GONG;Qian DING-.Local parameter identification with neural ordinary differential equations)[J].应用数学和力学（英文版）,2022(12):1887-1900
A类：
B类：
Local,identification,neural,ordinary,differential,equations,data,driven,methods,extract,feature,information,from,build,models,which,enable,estimation,systems,prognosis,health,management,PHM,However,most,are,still,black,box,that,cannot,interpreted,In,this,study,use,ODEs,especially,inherent,computational,relation,ships,added,loss,function,calculation,approximate,governing,addition,new,strategy,identifying,local,parameters,investigated,utilized,damage,detec,numerical,experimental,examples,presented,paper,demonstrate,has,high,accuracy,good,Moreover,proposed,advantage,being,interpretable,It,directly,underlying,dynamics,worthwhile
AB值：
0.571168
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
