Searcharxiv⌕ Search

arXiv subjects

Luowei Yin

Publications and source records attributed to Luowei Yin.

4 recordsLinked to original sources

AI4Plasma I: Data-Efficient Surrogate Modeling of Capacitively Coupled Plasma Fields

Reference capacitively coupled plasma (CCP) simulations provide spatially resolved plasma fields but are costly to generate across operating conditions. We compare the data efficiency of five surrogate architectures--Coordinate MLP, PCA-Net, U-Net, Fourier neural operator (FNO), and Transolver--for predicting RF-cycle-averaged electron density, ion density, electric potential, and electron temperature in 1D planar and 2D axisymmetric GEC CCP benchmarks. We assess the number of reference simulations needed to achieve 1% and 2% mean relative L2 error for parameter-interior and parameter-boundary test cases, and examine architecture-specific mechanisms. FNO achieves the lowest or joint-lowest reference-case requirement in seven of eight comparisons. In 1D, FNO reaches 1% interior error with 50 training cases, compared with 100 for Transolver and 200 for U-Net. In 2D, FNO and U-Net each reach 1% interior error with 100 cases; FNO and Transolver each reach 2% parameter-boundary error with 200 cases, compared with 400 for U-Net. At the stricter 1% 2D parameter-boundary target, Transolver requires 400 cases versus 800 for FNO. Additional analyses investigate FNO spectral modes and padding, U-Net skip connections, Transolver adaptive slicing, and PCA-Net projection versus prediction error. The results support FNO as a data-efficient baseline for the tested CCP settings, while showing that the preferred architecture depends on the accuracy target and operating-parameter region.

cs.LG↗

AI4Plasma II: Geometry-Aware Surrogate Modeling for Variable Electrode Gap GEC Plasmas

Industrial plasma process development requires broad exploration of operating and geometric parameters. Geometric parameters, particularly electrode spacing, affect discharge structure and processing uniformity. Exploring these parameter spaces through repeated high-fidelity simulations can be computationally expensive. Surrogate models can offer rapid predictions, but geometric variation complicates their application because the computational domain and discretization may change across samples. In this work, six geometry-aware surrogate models based on prescribed and learned geometry mappings, extended-domain representation, continuous coordinates, and geometry-native discretizations are compared in terms of their data requirements for accurate predictions of full plasma fields and ion density profiles near the wafer. The simulation dataset spans pressure, voltage, frequency, and electrode gap, with each reference case requiring an average simulation cost of 5.32 CPU h. To achieve a 2% mean error across the four plasma fields, prescribed-mapping Geo-FNO and Transolver require 100 training cases, compared with 250-1000 for the other models. Predicting ion density profiles near the wafer is more demanding and reveals larger differences among models, with prescribed-mapping Geo-FNO requiring the fewest training cases for the profile accuracy targets considered. To further reduce the data required for accurate predictions near the wafer, we introduce charge-separation weighting into the training loss, which reduces the prescribed-mapping Geo-FNO's minimum tested training requirement for a 5% profile error from 1000 to 100 cases. These results support prescribed-mapping Geo-FNO as a practical starting point for the variable-gap problem studied here when a suitable geometry mapping is available, while Transolver achieves the highest prediction accuracy with sufficient training data.

cs.LG↗

An asymptotic-preserving reduced-order method for parametrised rarefied gas flow by proper generalised decomposition

Modelling rarefied gas flow using the Boltzmann equation is vital in many areas. Because of the high dimensionality and coexistence of multiple characteristic scales, conventional solution strategies for this equation incur prohibitively high computational costs and are inadequate for rapid response in engineering design simulations. Based on proper generalised decomposition (PGD), we propose an a priori, asymptotic-preserving reduced-order method for the high-dimensional parameterised Shakhov kinetic model equation. Separated representations reduce the kinetic problem to a set of low-dimensional problems. We incorporate synthetic equations into the PGD iteration so that, in the hydrodynamic limit, the iteration reduces to solving the Navier-Stokes equations, whose solution naturally exhibits a low-rank structure. Furthermore, treating the rarefaction parameter as an additional coordinate yields a solution over the whole range of rarefaction in one offline computation. It enables fast online queries to any point in the parameter space. Numerical examples using this method show reasonable precision and a significant reduction in computational cost.

math.NA↗

A Review of Neural Network Solvers for Second-order Boundary Value Problems

Deep learning-based partial differential equation(PDE) solvers have received much attention in the past few years. Methods of this category can solve a wide range of PDEs with high accuracy, typically by transforming the problems into highly nonlinear optimization problems of neural network parameters. This work reviews several deep learning solvers proposed a few years ago, including PINN, WAN, DRM, and VPINN. Numerical results are provided to make comparisons amongst them and address the importance of loss formulation and the optimization method. A rigorous error analysis for PINN is also presented. Finally, we discuss the current limitations and bottlenecks of these methods.

math.NA↗