arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.09073physics.comp-phnlin.CD
收藏

基于深度学习的参数化Fokker-Planck方程的伪解析密度解

The pseudo-analytical density solution to parameterized Fokker-Planck equations via deep learning

Xiaolong Wang, Jing Feng, Gege Wang, Tong Li, Yong Xu

AI总结:

本文提出基于深度学习的伪解析密度方法,用高斯混合分布和深度残差网络在单次训练中同时求解连续参数范围内的Fokker-Planck方程,显著加速多参数多维随机非线性系统的响应分析。

摘要:

高效求解Fokker-Planck方程(FPE)对于理解动力系统中随机粒子的概率演化至关重要,然而解析解或密度函数仅在特定情形下可获得。为加速含有多个系统参数的参数化FPE的求解过程,我们提出一种基于深度学习的方法来获得伪解析密度(PAD)。不同于以往需要对每一组系统参数分别求解FPE的数值方法,PAD在单次训练阶段内同时处理预定义连续系统参数范围内的所有FPE。该方法利用高斯混合分布(GMD)来表示平稳概率密度,即FPE的解。通过利用深度残差网络,将每个系统参数配置映射到GMD的参数,确保高斯分量的权重、均值和方差自适应地与相应的真实密度函数对齐。进一步开发了一种无网格算法来有效训练残差网络,从而得到满足必要归一化和边界条件的可行PAD。大量数值研究验证了该方法的准确性和效率,有望在多参数、多维随机非线性系统的响应分析中实现显著加速。

英文摘要:

Efficiently solving the Fokker-Planck equation (FPE) is crucial for understanding the probabilistic evolution of stochastic particles in dynamical systems, however, analytical solutions or density functions are only attainable in specific cases. To speed up the solving process of parameterized FPEs with several system parameters, we introduce a deep learning-based method to obtain the pseudo-analytical density (PAD). Unlike previous numerical methodologies that necessitate solving the FPE separately for each set of system parameters, the PAD simultaneously addresses all the FPEs within a predefined continuous range of system parameters during a single training phase. The approach utilizes a Gaussian mixture distribution (GMD) to represent the stationary probability density, the solution to the FPE. By leveraging a deep residual network, each system parameter configuration is mapped to the parameters of the GMD, ensuring that the weights, means, and variances of the Gaussian components adaptively align with the corresponding true density functions. A grid-free algorithm is further developed to effectively train the residual network, resulting in a feasible PAD obeying necessary normalization and boundary conditions. Extensive numerical studies validate the accuracy and efficiency of our method, promising significant acceleration in the response analysis of multi-parameter, multi-dimensional stochastic nonlinear systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑