Related Experiment Video
Updated: Jun 12, 2026
11:34
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
Published on: May 15, 2017
The State of the Art in Defect Monitoring Technologies for Selective Laser Melting Processes
Zhiwen Li1,2, Yonghong Zhu1, Ruixiang Cao2
1School of Mechanical and Electronic Engineering, Jingdezhen Ceramic University, Jingdezhen, China.
3D Printing and Additive Manufacturing
|June 11, 2026
Summary
Selective laser melting (SLM) is a promising additive manufacturing technology. This review explores defect monitoring and machine learning for real-time process control in SLM.
Area of Science:
- Additive Manufacturing
- Materials Science
- Manufacturing Engineering
Background:
- Selective Laser Melting (SLM) is a key additive manufacturing technology for complex components.
- Challenges include process instability, real-time quality monitoring, and parameter adjustment.
- Defect occurrence significantly impacts SLM quality control.
Purpose of the Study:
- To review common defect types and their generation mechanisms in SLM.
- To describe SLM process signals (acoustic, optical, thermal) and monitoring methods.
- To summarize machine learning techniques for signal data processing in SLM.
Main Methods:
- Literature review of SLM defects and monitoring techniques.
- Analysis of acoustic, optical, and thermal signals during SLM.
- Summary of machine learning applications for defect detection and process control.
Main Results:
- Identified common SLM defects and their formation pathways.
- Detailed various signal monitoring approaches for SLM processes.
- Highlighted the role of machine learning in processing SLM data for quality control.
Conclusions:
- Real-time defect monitoring and feedback are crucial for SLM quality.
- Machine learning offers significant potential for intelligent SLM monitoring and control.
- Future research should focus on advanced machine learning for adaptive SLM parameter adjustment.
