Related Experiment Video
Updated: May 5, 2026
13:46
A Facile and Eco-friendly Route to Fabricate PolyLactic Acid Scaffolds with Graded Pore Size
Published on: October 17, 2016
9.1K
Enhanced Chroma-YOLO Framework for Effective Defect Detection and Fatigue Life Prediction in 3D-Printed Polylactic
Liang Wang1, Zhibing Liu1, Ting Lv2
1School of Mechanical Engineering, Beijing Institute of Technology, No.5 Zhongguancun South Street, Haidian District, Beijing 100081, China.
Materials (Basel, Switzerland)
|November 27, 2025
Summary
This study introduces Chroma-YOLO, an advanced AI model for detecting internal defects in 3D-printed Polylactic Acid (PLA). The framework accurately predicts material fatigue life, improving upon traditional methods.
Area of Science:
- Materials Science
- Additive Manufacturing
- Artificial Intelligence
Background:
- Internal defects are common in 3D-printed Polylactic Acid (PLA), impacting material properties.
- Detecting these defects and predicting their effect on fatigue life remains challenging.
Purpose of the Study:
- To develop an integrated framework for detecting internal defects in PLA 3D prints.
- To establish a model linking defect detection to accurate fatigue life prediction.
Main Methods:
- An improved YOLOv11n model (Chroma-YOLO) integrating an HSV defect extraction module.
- A random forest prediction model combined with HSV defect detection for fatigue life analysis.
Main Results:
- Chroma-YOLO demonstrated significant improvements in mAP50 (6.9%) and mAP50-95 (7.3%) over baseline YOLOv11n.
- The random forest model achieved high accuracy (96.25% test, 99.09% validation) in predicting PLA fatigue life.
Conclusions:
- The Chroma-YOLO framework effectively enhances defect detection and localization in 3D-printed PLA.
- This integrated approach provides a robust method for predicting material fatigue life, outperforming conventional techniques.
