Qingjing Wang | Searcharxiv

arXiv2024

Estimation of railway vehicle response for track geometry evaluation using branch Fourier neural operator

In railway transportation, the evaluation of track geometry is an indispensable requirement to ensure the safety and comfort of railway vehicles. A promising approach is to directly use vehicle dynamic responses to assess the impact of track geometry defects. However, the computational cost of obtaining the dynamic response of the vehicle body using dynamics simulation methods is large. Thus, it is important to obtain the dynamic response of the vehicle-track coupled system efficiently and accurately. In this work, a branch Fourier neural operator (BFNO) model is proposed to obtain the dynamic response of the vehicle-track coupled system. The model takes into account the nonlinear relationship of the vehicle-track coupled system and realizes the fast and accurate estimation of the system dynamic response. The relative loss (rLSE) of BFNO model is 2.04%, which is reduced by 64%, compared with the traditional neural network (CNN-GRU). In the frequency domain, BFNO model achieves the effective estimation of the dynamic response of the system within the primary frequency range. Compared with the existing methods, our proposed model can make predictions at unseen time steps, enabling predictions from low to high time resolutions. Meanwhile, our proposed model is superior to commercial software in terms of efficiency. In the evaluation of track geometry, users can use pre-trained BFNO to obtain the dynamic response with almost no computational cost.

physics.app-ph↗

arXiv2023

Solving Coupled Differential Equation Groups Using PINO-CDE

As a fundamental mathmatical tool in many engineering disciplines, coupled differential equation groups are being widely used to model complex structures containing multiple physical quantities. Engineers constantly adjust structural parameters at the design stage, which requires a highly efficient solver. The rise of deep learning technologies has offered new perspectives on this task. Unfortunately, existing black-box models suffer from poor accuracy and robustness, while the advanced methodologies of single-output operator regression cannot deal with multiple quantities simultaneously. To address these challenges, we propose PINO-CDE, a deep learning framework for solving coupled differential equation groups (CDEs) along with an equation normalization algorithm for performance enhancing. Based on the theory of physics-informed neural operator (PINO), PINO-CDE uses a single network for all quantities in a CDEs, instead of training dozens, or even hundreds of networks as in the existing literature. We demonstrate the flexibility and feasibility of PINO-CDE for one toy example and two engineering applications: vehicle-track coupled dynamics (VTCD) and reliability assessment for a four-storey building (uncertainty propagation). The performance of VTCD indicates that PINO-CDE outperforms existing software and deep learning-based methods in terms of efficiency and precision, respectively. For the uncertainty propagation task, PINO-CDE provides higher-resolution results in less than a quarter of the time incurred when using the probability density evolution method (PDEM). This framework integrates engineering dynamics and deep learning technologies and may reveal a new concept for CDEs solving and uncertainty propagation.

cs.LG↗