A new mesh smoothing method based on a neural network

• Published in: Computational mechanics Vol. 69; no. 2; pp. 425 - 438
• Main Authors: Guo, Yufei, Wang, Chuanrui, Ma, Zhe, Huang, Xuhui, Sun, Kewu, Zhao, Rongli
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-02-2022; Springer; Springer Nature B.V
• Subjects: Analysis; Classical and Continuum Physics; Computational linguistics; Computational Science and Engineering; Engineering; Finite element method; Heuristic methods; Language processing; Mathematical analysis; Methods; Natural language interfaces; Neural networks; Optimization; Original Paper; Quality control; Smoothing; Theoretical and Applied Mechanics; Mesh; Mesh smoothing; Neural network; Optimization-based smoothing
• ISSN: 0178-7675; 1432-0924
• DOI: 10.1007/s00466-021-02097-z

As an elementary mesh quality improvement technique, smoothing has been widely used in finite element (FE) analysis. Heuristic smoothing methods and optimization-based smoothing methods are the two main smoothing types. The former is efficient. However, it operates heuristically and may create low-quality elements. In contrast, optimization-based smoothing is very effective at improving mesh quality. However, it suffers from high computational cost since it calculates the optimal position of a free node iteratively. In this paper, we present a new smoothing method. The proposed method imitates the optimization-based smoothing based on a neural network, but it calculates the optimal position of a free node straightforwardly. Hence, the proposed method is more efficient than these optimization-based smoothing methods while being comparable in terms of mesh quality. We present various testing results to illustrate the effectiveness of the proposed method.