Long-term simulation of physical and mechanical behaviors using curriculum-transfer-learning based physics-informed neural networks
This work addresses the problem of inaccurate and inefficient long-term simulations in physics-informed machine learning for researchers and engineers in computational physics and mechanics, representing an incremental improvement over existing PINN variants.
The paper tackled the challenge of long-term simulation in physical and mechanical systems by proposing a Curriculum-Transfer-Learning based physics-informed neural network (CTL-PINN), which decomposes problems into short-term subproblems and integrates curriculum and transfer learning to improve accuracy and efficiency, demonstrating superior performance in applications like nonlinear wave propagation and hydrodynamic modeling.
This paper proposes a Curriculum-Transfer-Learning based physics-informed neural network (CTL-PINN) for long-term simulation of physical and mechanical behaviors. The main innovation of CTL-PINN lies in decomposing long-term problems into a sequence of short-term subproblems. Initially, the standard PINN is employed to solve the first sub-problem. As the simulation progresses, subsequent time-domain problems are addressed using a curriculum learning approach that integrates information from previous steps. Furthermore, transfer learning techniques are incorporated, allowing the model to effectively utilize prior training data and solve sequential time domain transfer problems. CTL-PINN combines the strengths of curriculum learning and transfer learning, overcoming the limitations of standard PINNs, such as local optimization issues, and addressing the inaccuracies over extended time domains encountered in CL-PINN and the low computational efficiency of TL-PINN. The efficacy and robustness of CTL-PINN are demonstrated through applications to nonlinear wave propagation, Kirchhoff plate dynamic response, and the hydrodynamic model of the Three Gorges Reservoir Area, showcasing its superior capability in addressing long-term computational challenges.