PIKFNNs‐DPIM for Stochastic Response Analysis of Underwater Acoustic Propagation

International journal of mechanical system dynamics, Journal Year: 2025, Volume and Issue: unknown

Published: April 17, 2025

ABSTRACT This paper proposes a hybrid algorithm based on the physics‐informed kernel function neural networks (PIKFNNs) and direct probability integral method (DPIM) for calculating density of stochastic responses structures in deep marine environment. The underwater acoustic information is predicted utilizing PIKFNNs, which integrate prior physical information. Subsequently, novel uncertainty quantification analysis method, DPIM, introduced to establish response model propagation. effects random load, variable sound speed, fluctuating ocean density, material properties shell pressure are numerically analyzed, providing probabilistic insight assessing mechanical behavior

Language: Английский

---

Numerical study of underwater acoustic radiation and propagation induced by structural vibration in ocean environments using FEM-BMSBM

Applied Ocean Research, Journal Year: 2024, Volume and Issue: 153, P. 104294 - 104294

Published: Nov. 1, 2024

Language: Английский

---

A meshless Runge-Kutta-based Physics-Informed Neural Network framework for structural vibration analysis

Engineering Analysis with Boundary Elements, Journal Year: 2024, Volume and Issue: 170, P. 106054 - 106054

Published: Nov. 30, 2024

Language: Английский

---

A novel spatial-temporal collocation solver for long-time transient diffusion with time-varying source terms

Engineering Analysis with Boundary Elements, Journal Year: 2024, Volume and Issue: 171, P. 106060 - 106060

Published: Dec. 5, 2024

Language: Английский

---