Local parameter identification with neural ordinary differential equations

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 utilized 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 relationships 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 detection. 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.     

Numerical solution of nonlinear ordinary differential equation for a turning point problem

By using the method in[3],several useful estimations of the derivatives of the solutionof the boundary value problem for a nonlinear ordinary differential equation with a turningpoint are obtained.With the help of the technique in[4],the uniform convergence on thesmall parameterεfor a difference scheme is proved.At the end of this paper,a numericalexample is given.The numerical result coincides with theoretical analysis.     

变截面压杆稳定非线性微分方程边值问题的最优化算法研究

针对任意约束类型的变截面受压杆件的稳定临界载荷计算问题,结合非线性微分方程数值算法和最优化方法,以起点边界的初始条件、待求临界荷载和附加约束力为设计变量;以终点边值条件满足的函数关系与位型条件构建目标函数,提出变截面压杆临界载荷和稳定位型的优化求解算法。应用VB编制通用的优化计算程序,分析了典型算例;通过对比发现,本文以较少设计变量实现了临界载荷的高精度计算,为工程应用提供参考。