Liu Yang1, Peipei Liu2, Kiyoon Yi1

  • 1Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, The Republic of Korea.

Ultrasonics
|January 7, 2026
PubMed
概括

一个新的缺陷参数化物理信息神经网络 (DP-PINN) 准确地使用激光超声波特征金属元件的亚毫米表面缺陷. 这种非破坏性评估方法从有限的数据中重建完整的波场,确保结构完整性.