Related Experiment Video
Updated: Jun 6, 2025
11:34
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
Published on: May 15, 2017
11.1K
A layer-wise melting defects mitigation method in laser powder bed fusion process based on machine learning and fuzzy
1Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, China.
ISA Transactions
|November 27, 2024
Summary
This study introduces an image-based control for Laser Powder Bed Fusion (LPBF) to reduce melting defects. A convolutional neural network (CNN) and fuzzy logic control (FIC) system improve part quality and surface roughness.
Area of Science:
- Additive Manufacturing
- Materials Science
- Artificial Intelligence in Manufacturing
Background:
- Melting defects like lack of fusion (LOF) and over-melting (OM) in Laser Powder Bed Fusion (LPBF) significantly degrade part quality and performance.
- Previous control methods using local melt pool data are limited by sensor and data processing demands, and lack representativeness.
Purpose of the Study:
- To develop an image-based LPBF control strategy to mitigate melting defects and enhance surface quality.
- To improve the mechanical properties and manufacturing quality of 3D printed components.
Main Methods:
- A quality identification module using convolutional neural networks (CNN) for layer-by-layer melting quality evaluation.
- A fuzzy control strategy (FIC) integrated with a historical state consistency check mechanism (HSCCM) for optimal control actions.
- Experimental validation of the proposed control strategy.
Main Results:
- The CNN achieved up to 98.2% accuracy in identifying melting quality.
- The FIC integrated with HSCCM effectively reduced surface melting defects.
- Enhanced surface roughness and overall manufacturing quality of components were observed.
Conclusions:
- The proposed image-based control approach offers a novel and effective method for online quality monitoring and improvement in LPBF processes.
- This strategy successfully mitigates melting defects, leading to superior part quality and reliability.
