This study tackles the numerical challenges posed by solutions with steep gradients in the Burgers equation, particularly poor stability in high-gradient regions and the ill-posedness of inverse problems in shock wave modeling. We propose a Weak-Form Physics-Informed Neural Network (WF-PINN) that fundamentally enhances both forward and inverse problem solving. Key innovations include: (i) a weak-form integral formulation of the PDE loss, which improves training stability near shocks; (ii) enforcement of an entropy condition to ensure unique and physically consistent shock capture; (iii) a dual-network architecture for inverse problems, where an auxiliary network dedicated to initial condition reconstruction is coupled with the main solver via consistency constraints. Numerical experiments show that WF-PINNs achieve significantly higher accuracy and convergence robustness compared to strong-form PINNs, accurately resolving shock locations and amplitudes while enabling precise identification of unknown initial conditions and viscosity coefficients. The framework offers a unified and generalizable approach for solving conservation laws with discontinuities.
In this article, we proposed a compact difference-Galerkin spectral method for the fourth-order equation in multi-dimensional space with the time-fractional derivative order . The novel compact difference-Galerkin spectral method can effectively address the issue of high-order derivative accuracy and handle complex boundary problems. Simultaneously, the main conclusions of this article, including the stability, convergence, and solvability of the method, are derived. Finally, some computational experiments are illustrated to demonstrate the superiority of the compact difference-Galerkin spectral method.
An efficient numerical approach utilizing a variational weak form, grounded in 2D elastic theory and variational principles, is proposed for analyzing the in-plane vibrational behavior of rectangular plates resting on elastically restrained boundaries. The differential and integral operators can be discretized into matrix representations employing the differential quadrature method (DQM) and Taylor series expansion techniques. The discretization of dynamics equations stems directly from a weak formulation that circumvents the need for any transformation or discretization of higher-order derivatives encountered in the corresponding strong equations. Utilizing the matrix elementary transformation technique, the displacements of boundary and internal nodes are segregated, subsequently leading to the derivation of the generalized eigenvalue problem pertaining to the free vibration analysis of the Functionally Graded Material (FGM) rectangular plate. Furthermore, the study examines the impact of the gradient parameter, aspect ratio, and elastic constraints on the dimensionless frequency characteristics of the FGM rectangular plate. Ultimately, the modal properties of an in-plane FGM rectangular plate are investigated.
In the field of direction of arrival (DOA) estimation, a common assumption is that array noise follows a uniform Gaussian white noise model. However, practical systems often encounter non-ideal noise conditions, such as non-uniform or colored noise, due to sensor characteristics and external environmental factors. Traditional DOA estimation techniques experience significant performance degradation in the presence of colored noise, necessitating the exploration of specialized DOA estimation methods for such environments. This study introduces a DOA estimation method for acoustic vector arrays based on a spectrum attention mechanism (SAM). By employing SAM as an adaptive filter and constructing a double-branch model combining a convolutional neural network (CNN) and long short-term memory (LSTM), the method extracts the spatial and temporal features of signals, and effectively reduces the frequency components of colored noise, enhancing DOA estimation accuracy in colored noise scenarios. At an SNR of −5 dB, it achieves an accuracy rate of 85% while maintaining a low RMSE of only 2.03°.
24 September 2025 in Circuits, Systems, and Signal Processing