A novel contrastive learning framework for multi-parameter optimization in 3D printing

Jieyang Peng

doi:10.1016/j.engappai.2025.112209

A novel contrastive learning framework for multi-parameter optimization in 3D printing

2025-09-17

0

PRE

AI

DOI：10.1016/j.engappai.2025.112209

Original

Original request for help

Save

Abstract

En 中文

• Supervised contrastive learning for 3D printing boosts anomaly detection accuracy. • Unified framework spots and sorts multi-parameter faults in one holistic quality check. • Real-world tests prove robust use across varied AM scenarios.

A novel contrastive learning framework for multi-parameter optimization in 3D printing

Abstract

Journal

Organization