Physics-Informed Neural Networks for Solving High-Index Differential-Algebraic Equation Systems Based on Radau Methods

Table 2

Hessenberg-DAEs systems: Measure the average absolute error of differential function variables for different numbers of Radau IIA stages and time-step sizes h.

	h
	0.025	0.05	0.1
2
3
5
7

Bold values indicate the optimal accuracy achieved at each time step and show the Radau IIA method stages v used for optimal accuracy.