arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.12293cs.LGcs.NEphysics.comp-ph
收藏

通用傅里叶特征物理信息极限学习机(GFF-PIELM)用于高频偏微分方程

General Fourier Feature Physics-Informed Extreme Learning Machine (GFF-PIELM) for High-Frequency PDEs

Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东省科学院));Shandong Institute of Mechanical Design and Research(山东省机械设计研究院);Yale University(耶鲁大学);Shandong University(山东大学);University of Leeds(利兹大学)

Fei Ren, Sifan Wang, Pei-Zhi Zhuang, Hai-Sui Yu, He Yang

AI总结:

针对传统PIELM难以求解高频和变频PDE的问题,提出GFF-PIELM,通过集成傅里叶激活函数、分配频率系数及基于输出权重的初始化方法,在不增加训练成本下显著提升精度。

摘要:

传统的物理信息极限学习机(PIELM)在求解涉及高频和变频行为的偏微分方程(PDEs)时常常面临挑战。为了解决这些挑战,我们提出了一种通用傅里叶特征物理信息极限学习机(GFF-PIELM)。我们证明,直接将多个傅里叶特征映射(FFMs)与极限学习机(ELM)网络拼接在一起,很难确定与频率相关的超参数。幸运的是,我们找到了一种替代方案,通过三个主要步骤建立GFF-PIELM。首先,我们将FFM的一种变体作为基于傅里叶的激活函数集成到ELM中,因此GFF-PIELM框架中仍然只有一个隐藏层。其次,我们为隐藏神经元分配一组频率系数,这使得ELM网络能够捕获目标解的各种频率成分。最后,我们通过监测ELM输出权重的分布,为这些超参数开发了一种创新且简单的初始化方法。GFF-PIELM不仅保留了PIELM框架的高精度、高效率和简单性,还继承了FFMs有效处理高频问题的能力。我们进行了五个案例研究,共十个数值示例,以突出所提出的GFF-PIELM的可行性和有效性,涉及高频、变频、多尺度行为、不规则边界和反问题。与传统PIELM相比,GFF-PIELM方法在不增加训练时间和架构复杂性的情况下显著提高了预测精度。我们的结果证实,PIELM可以扩展到高精度求解高频和变频PDEs,并且我们的初始化策略可能进一步启发其他物理信息机器学习(PIML)框架的进展。

英文摘要:

Conventional physics-informed extreme learning machine (PIELM) often faces challenges in solving partial differential equations (PDEs) involving high-frequency and variable-frequency behaviors. To address these challenges, we propose a general Fourier feature physics-informed extreme learning machine (GFF-PIELM). We demonstrate that directly concatenating multiple Fourier feature mappings (FFMs) and an extreme learning machine (ELM) network makes it difficult to determine frequency-related hyperparameters. Fortunately, we find an alternative to establish the GFF-PIELM in three main steps. First, we integrate a variation of FFM into ELM as the Fourier-based activation function, so there is still one hidden layer in the GFF-PIELM framework. Second, we assign a set of frequency coefficients to the hidden neurons, which enables ELM network to capture diverse frequency components of target solutions. Finally, we develop an innovative, straightforward initialization method for these hyperparameters by monitoring the distribution of ELM output weights. GFF-PIELM not only retains the high accuracy, efficiency, and simplicity of the PIELM framework but also inherits the ability of FFMs to effectively handle high-frequency problems. We carry out five case studies with a total of ten numerical examples to highlight the feasibility and validity of the proposed GFF-PIELM, involving high frequency, variable frequency, multi-scale behaviour, irregular boundary and inverse problems. Compared to conventional PIELM, the GFF-PIELM approach significantly improves predictive accuracy without additional cost in training time and architecture complexity. Our results confirm that that PIELM can be extended to solve high-frequency and variable-frequency PDEs with high accuracy, and our initialization strategy may further inspire advances in other physics-informed machine learning (PIML) frameworks.

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。

↑