Optimizing material and process parameters in laser engineered net shaping using liquid neural networks

Abstract This study introduces a physics-based Liquid Neural Network (LNN) framework for optimization of material and process parameters in Laser Engineered Net Shaping (LENS). The model combines neural differential equations with dynamic liquid weight mechanism, and enables adaptive learning under...

Полное описание

Библиографические подробности

Главные авторы:	Haijiang Tian, Ismail Saad, Tianshu Chen, Teng Gao, Houpin Yoong, Bih Lii Chua
Формат:	Artigo
Язык:	Inglês
Опубликовано:	Nature Portfolio 2026-05-01
Серии:	Scientific Reports
Предметы:	LNN—Liquid Neural Network LENS—Laser Engineered Net Shaping CUI—Cladding Uniformity Index RL—Reinforcement Learning RSM—Response Surface Methodology PR—Polynomial Regression
Online-ссылка:	https://doi.org/10.1038/s41598-026-52507-6
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!