Yundong Li

Warm-Up-Calibrated Adaptive Weighting for Spatiotemporal Residual-Derivative Balance in Gradient-Enhanced PINNs

Neural-network methods are widely used for partial differential equations (PDEs). Within this framework, gradient-enhanced physics-informed neural networks (gPINNs) incorporate first-order residual derivatives, while fixed directional weighting may unbalance spatial and temporal...

STRANGE NONCHAOTIC ATTRACTORS AND COMPLICATED QUASI-PERIODIC CASCADES INDUCED BY BIFURCATIONS IN A DRY-FRICTION OSCILLATOR UNDER QUASI-PERIODIC EXCITATION

This paper explores the crossing bifurcation, switching-sliding and grazing-sliding bifurcations in a dry-friction oscillator on a moving belt under quasi-periodic excitation with two frequencies. We present a concrete method to approximate the largest Lyapunov exponent. By apply...