Powder‑Spreading Defect Detection in Laser Powder Bed Fusion Based on Large Vision Model

Fig. 7. Powder-spreading defects and annotation example. (a) Super-elevation; (b) incompletion; (c) hopping; (d) streaking; (e) lattice; (f) pixel-wise annotation example

Download full size

Fig. 8. Comparison of segmentation results from different networks

Download full size

Table 1. Performance comparison of PSAM with different segmentation networks

View table

Table 1. Performance comparison of PSAM with different segmentation networks

Network	mIoU /%	IoU for per category /%
Network	mIoU /%	Background	Super-elevation	Incompletion	Hopping	Streaking	Lattice
Deeplab v3	56.50±0.23	97.85±0.75	36.74±2.40	49.38±0.89	32.05±2.81	44.71±2.61	78.26±1.48
U-Net	59.71±0.86	98.61±0.08	49.38±0.61	60.06±0.01	30.36±1.72	42.56±2.20	77.24±1.77
PSAM	65.02±0.40	98.66±0.03	50.10±0.65	69.97±1.51	42.51±1.61	51.26±1.14	77.65±1.24

Table 2. Ablation experimental results
View table
Table 2. Ablation experimental results
Group Adapter Auto-prompt mIoU /% Improvement
1 53.69±0.28
2 √ 57.23±0.75 +3.54 percentage points
3 √ 58.79±1.23 +5.10 percentage points
4 √ √ 65.02±0.40 +11.33 percentage points

Tools

Get Citation

Copy Citation Text

Kunpeng Tan, Jiafeng Tang, Zhibin Zhao, Chenxi Wang, Xingwu Zhang, Weifeng He, Xuefeng Chen. Powder‑Spreading Defect Detection in Laser Powder Bed Fusion Based on Large Vision Model[J]. Chinese Journal of Lasers, 2024, 51(10): 1002319

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites