Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 6, 2026Scientific ReportsOpen Access

Evaluation of different defect-inspection setups for injection molding parts based on the deep learning method

View Full Paper
Ask AI
Bookmark
Share

Authors

EBEnrico BovoUniversity of PaduaXWXi Vincent WangLanzhou University of TechnologyGLGiovanni LucchettaUniversity of Padua

Discussion

Loading...

Member takes

Implication

Randomized trial evaluates defect detection in injection molding parts, suggesting AI enhances quality control.

Key Points

  • This research aims to evaluate different setups using deep learning for detecting surface defects in injection-molded parts.
  • Assessed three inspection setups: static frontal imaging, belt conveyor inspection, and robotic-assisted inspection.
  • Used deep learning-based automatic optical inspection strategies for analysis.
  • Compared defect detection capabilities across different setups.
  • Robotic-assisted inspection showed superior defect detection accuracy due to optimized camera positions.
  • Clear differences in detection capabilities among the inspection methods were confirmed.
  • The proposed methodology allows systematic evaluation and optimization of inspection setups.

Cite This Study

Bovo et al. (2026) studied this question.

synapsesocial.com/papers/6a7437f4764cddc9499d5c63https://doi.org/10.1038/s41598-026-52635-z
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Efficient Detection Model of Steel Strip Surface Defects Based on YOLO-V72022 · 222 citations
  2. 2Fabric Defect Detection With Deep Learning and False Negative Reduction2021 · 45 citations
  3. 3Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set2020 · 88 citations
  4. 4CNN-Based Defect Inspection for Injection Molding Using Edge Computing and Industrial IoT Systems2021 · 54 citations