Detecting defects in fused deposition modeling based on improved YOLO v4

Xu, Luyang; Zhang, Xiaoxun; Ma, Fang; Chang, Gaoyuan; Zhang, Cheng; Li, Jiaming; Wang, Shuxian; Huang, Yuanyou

doi:10.1088/2053-1591/acf6f9

Cited by 5 publications

(3 citation statements)

References 30 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, compared with general models, specialized parameter adjustments and structural improvements to the model will achieve better detection results. However, the cost of investment in this attempt cannot be ignored [ 42 , 43 ]. The method in this paper can label most of the pore defects in the image, even the smaller gas pores.…”

Section: Resultsmentioning

confidence: 99%

Simultaneous Pore Detection and Morphological Features Extraction in Laser Powder Bed Fusion with Image Processing

Li,

Zhang,

et al. 2024

Materials

Self Cite

View full text Add to dashboard Cite

Internal pore defects are inevitable during laser powder bed fusion (LPBF), which have a significant impact on the mechanical properties of the parts. Therefore, detecting pores and obtaining their morphology will contribute to the quality of LPBF parts. Currently, supervised models are used for defect image detection, which requires a large amount of LPBF sample data, image labeling, and computing power equipment during the training process, resulting in high detection costs. This study extensively collected LPBF sample data and proposed a method for pore defect classification by obtaining its morphological features while detecting pore defects in optical microscopy (OM) images under various conditions. Compared with other advanced models, the proposed method achieves better detection accuracy on pore defect datasets with limited data. In addition, quickly detecting pore defects in a large number of labeling ground truth images will also contribute to the development of deep learning. In terms of image segmentation, the average accuracy scores of this method in the test images exceed 85%. The research results indicate that the algorithm proposed in this paper is suitable for quickly and accurately identifying pore defects from optical microscopy images.

show abstract

Section: Resultsmentioning

confidence: 99%

Simultaneous Pore Detection and Morphological Features Extraction in Laser Powder Bed Fusion with Image Processing

Li,

Zhang,

et al. 2024

Materials

Self Cite

View full text Add to dashboard Cite

show abstract

“…Zhang et al [22] improved Faster R-CNN using an adaptive defect detection method based on the K-medoids clustering algorithm to detect lattice structures in CT slices of 3D printing. Xu et al [23] replaced the backbone structure of YOLO v4 with MobileNetV2 as an improved model to recognize defects in FDM 3D printing. Paraskevoudis et al [24] used an SSD model to analyze video clips to identify defects during the printing process, especially stringing defects.…”

Section: Introductionmentioning

confidence: 99%

Real-time defect detection for FDM 3D printing using lightweight model deployment

Hu,

Chang,

et al. 2024

Preprint

View full text Add to dashboard Cite

FDM 3D printing is one of the most widely used additive manufacturing methods, bringing great convenience to production manufacturing. However, various printing defects may occur during the printing process due to human factors or printer-related issues. Timely detection of defects and halting printing becomes a scenario of significant practical importance. This paper first analyzes the causes of the five most common defects in FDM 3D printing, and a defect dataset is created by deliberately designing defects. Subsequently, a real-time defect detection system for FDM 3D printing, based on an improved YOLOv8 detection head, is developed. By employing an optimization method using Group Convolution to share parameters, the detection head is lightweight, resulting in better model performance. Experimental results demonstrate that the mAP50 of the improved YOLOv8 model reaches 97.5%, with an 18.1% increase in FPS and a 32.9% reduction in GFLOPs. This enhancement maintains comparable detection accuracy to the original model while achieving faster detection speed and lower computational requirements. The improved model is integrated into the detection system as the detection model, and through testing, the real-time detection system promptly and accurately identifies and alerts any occurring defects. The practical significance of this system lies in its ability to enhance production efficiency, reduce resource wastage due to defective printing, and improve product quality and manufacturing safety, thereby providing strong support for the application of visual inspection technology in FDM 3D printing.

show abstract

“…For example, G. Bakas et al proposed a computer vision-based method for automatic defect detection in the fused deposition modelling (FDM) process [ 20 ]. Xu et al developed an improved one-stage model based on the You Only Look Once (YOLO) v4 to detect the print quality of the FDM process [ 21 ]. However, both works only focused on the material filling defects and did not cover the major defects that often occurred in the extrusion-based AM processes, such as scratches, holes, and impurities, which largely limited the detecting capability of the systems.…”

Section: Introductionmentioning

confidence: 99%

A Real-Time Defect Detection Strategy for Additive Manufacturing Processes Based on Deep Learning and Machine Vision Technologies

Wang,

Zhang

et al. 2023

Micromachines

View full text Add to dashboard Cite

Nowadays, additive manufacturing (AM) is advanced to deliver high-value end-use products rather than individual components. This evolution necessitates integrating multiple manufacturing processes to implement multi-material processing, much more complex structures, and the realization of end-user functionality. One significant product category that benefits from such advanced AM technologies is 3D microelectronics. However, the complexity of the entire manufacturing procedure and the various microstructures of 3D microelectronic products significantly intensified the risk of product failure due to fabrication defects. To respond to this challenge, this work presents a defect detection technology based on deep learning and machine vision for real-time monitoring of the AM fabrication process. We have proposed an enhanced YOLOv8 algorithm to train a defect detection model capable of identifying and evaluating defect images. To assess the feasibility of our approach, we took the extrusion 3D printing process as an application object and tailored a dataset comprising a total of 3550 images across four typical defect categories. Test results demonstrated that the improved YOLOv8 model achieved an impressive mean average precision (mAP50) of 91.7% at a frame rate of 71.9 frames per second.

show abstract

Detecting defects in fused deposition modeling based on improved YOLO v4

Cited by 5 publications

References 30 publications

Simultaneous Pore Detection and Morphological Features Extraction in Laser Powder Bed Fusion with Image Processing

Simultaneous Pore Detection and Morphological Features Extraction in Laser Powder Bed Fusion with Image Processing

Real-time defect detection for FDM 3D printing using lightweight model deployment

A Real-Time Defect Detection Strategy for Additive Manufacturing Processes Based on Deep Learning and Machine Vision Technologies

Contact Info

Product

Resources

About