Research Article

A YOLOv8-Integrated Educational Platform for Design-Oriented Experiential Learning in Injection Molding Defect Detection

Lu-Hong Liu 1, Jui-Hung Cheng 1 * , Hsin-Yu Yeh 1, Yung-Fang Huang 1, Shih-Chieh Wang 1
More Detail
1 Department of Mold and Die Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan* Corresponding Author
Innovation on Design and Culture, 5(1), March 2026, 11-18, https://doi.org/10.35745/idc2026v05.01.0002
Submitted: 13 November 2025, Published: 30 March 2026
OPEN ACCESS   19 Views   29 Downloads
Download Full Text (PDF)

ABSTRACT

As artificial intelligence and smart manufacturing continue to shape modern industry, vocational education must evolve toward interdisciplinary and practice-oriented learning. To bridge the gap between academic knowledge and industrial AI applications, this study presents an educational YOLOv8-based injection molding defect detection platform. The system modularizes an end-to-end computer vision workflow that includes data collection, labeling, model training, deployment, and real-time inference, using entirely open-source tools such as Python, OpenCV, and PyTorch. On a custom dataset containing bubbles, burn marks, and short shots, the model achieved an mAP@0.5 of 92.5 percent with an average inspection time of less than five seconds per part, confirming both technical reliability and pedagogical feasibility. Classroom implementation demonstrated stronger student engagement, improved comprehension of AI concepts, and enhanced collaboration in problem-solving activities. This open-source and participatory AI workflow not only strengthens technical competence but also reflects a broader cultural shift toward accessible smart-manufacturing education and open design practices, supporting the development of data-driven thinking, interdisciplinary competence, and AI literacy that are essential for future industrial innovation.
Keywords: YOLOv8, Defect detection, Injection molding, Deep learning, Educational system, Real-Time inspection, Smart manufacturing

CITATION (APA)

Liu, L.-H., Cheng, J.-H., Yeh, H.-Y., Huang, Y.-F., & Wang, S.-C. (2026). A YOLOv8-Integrated Educational Platform for Design-Oriented Experiential Learning in Injection Molding Defect Detection. Innovation on Design and Culture, 5(1), 11-18. https://doi.org/10.35745/idc2026v05.01.0002

REFERENCES

  1. Adhisaputra, S., & Harefa, J. (2024). Detection of defects in plastic cup production using YOLO method. In Proceedings of the 2024 International Conference on Data Science and Its Applications (ICoDSA), Bandung, Indonesia, 24–26 July 2024; IEEE: Piscataway, NJ, USA, pp. 393–396. https://doi.org/10.1109/ICoDSA62899.2024.10651829
  2. Çelik, M. T., Arslankaya, S., & Yildiz, A. (2024). Real-time detection of plastic part surface defects. IEEE Access, 12, 18436–18445. https://doi.org/10.1109/ACCESS.2024.3359412
  3. Chen, T., Cai, C., Zhang, J., Dong, Y., & Yang, M. (2024). RER-YOLO: Improved method for surface defect detection of aluminum ingot alloy based on YOLOv5. Optics Express, 32(6), 8763–8777. https://doi.org/10.1364/OE.515107
  4. Chen, W., Zou, B., Yang, G., Zheng, Q., Lei, T., Huang, C., & Li, L. (2024). A real-time detection system for multiscale surface defects of 3D-printed ceramic parts based on deep learning. Ceramics International, 50(8), 13101–13112. https://doi.org/10.1016/j.ceramint.2024.01.220
  5. Gupta, C., Patel, R., & Singh, A. (2025). Surface defect detection on bolt surfaces using a real-time fine-tuned YOLO model. Journal of Big Data, 12(3), 198. https://doi.org/10.1186/s40537-025-01226-2
  6. He, L., Wang, J., Xu, H., & Zhang, Y. (2025). FMV-YOLO: A steel surface defect detection algorithm for improved accuracy. Electronics, 14(6), 1143. https://doi.org/10.3390/electronics14061143
  7. Jiao, F., Yin, Y., Min, X., Yang, C., Han, J., Wei, Q., & Qin, W. (2025). Basalt visible-light image recognition optimization algorithm based on YOLOv8. Minerals Engineering, 234, 109735. https://doi.org/10.1016/j.mineng.2025.109735
  8. Jo, C. M., Jang, W. K., Seo, Y. H., & Kim, B. H. (2024). In situ surface defect detection in polymer tube extrusion: AI-based real-time monitoring approach. Sensors, 24(6), 1791. https://doi.org/10.3390/s24061791
  9. Kang, J., Cen, Y., Wang, K., & Liu, Y. (2025). CFIS-YOLO: A lightweight multi-scale fusion network for edge-deployable wood defect detection. Wood Material Science & Engineering, 20(2), 1–14. https://doi.org/10.1080/17480272.2025.2532147
  10. Li, J., Wu, J., & Shao, Y. (2024). FSNB-YOLOv8: Improvement of object detection model for surface defects inspection in online industrial systems. Applied Sciences, 14(17), 7913. https://doi.org/10.3390/app14177913
  11. Ma, Y., Yin, J., Huang, F., & Li, Q. (2024). Surface defect inspection of industrial products with object detection deep networks: A systematic review. Artificial Intelligence Review, 57(12), 333. https://doi.org/10.1007/s10462-024-10956-3
  12. Ruan, S., Zhan, C., Liu, B., Wan, Q., & Song, K. (2025). A high-precision YOLO model for surface defect detection based on PyConv and CISBA. Scientific Reports, 15, 15841. https://doi.org/10.1038/s41598-025-91930-z
  13. Wu, H., Zeng, L., Chen, M., Wang, T., He, C., Xiao, H., & Luo, S. (2024). Weak surface defect detection for production-line plastic bottles with multi-view imaging system and LFF YOLO. Optics and Lasers in Engineering, 181, 108369. https://doi.org/10.1016/j.optlaseng.2024.108369
  14. Zhang, R., Li, Y., & Guan, Z. (2024). Research on injection-molded parts defect detection algorithm based on multiplicative feature fusion and improved attention mechanism. Scientific Reports, 14, 30864. https://doi.org/10.1038/s41598-024-81430-x
  15. Zhou, H., Fang, Y., & Lin, P. (2025). An efficient and lightweight algorithm for detecting surface defects of steel based on SCCI-YOLO. Scientific Reports, 15, 36276. https://doi.org/10.1038/s41598-025-20154-y