International Journal of Heat and Mass Transfer, Journal Year: 2025, Volume and Issue: 240, P. 126682 - 126682
Published: Jan. 10, 2025
Language: Английский
International Journal of Heat and Mass Transfer, Journal Year: 2025, Volume and Issue: 240, P. 126682 - 126682
Published: Jan. 10, 2025
Language: Английский
Applied Thermal Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 125524 - 125524
Published: Jan. 1, 2025
Language: Английский
Citations
1Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)
Published: Jan. 6, 2025
The Insulated Gate Bipolar Transistor (IGBT) is a crucial power semiconductor device, and the integrity of its internal structure directly influences both electrical performance long-term reliability. However, precise semantic segmentation IGBT ultrasonic tomographic images poses several challenges, primarily due to high-density noise interference visual distortion caused by target warping. To address these this paper constructs dedicated tomography (IUT) dataset using Scanning Acoustic Microscopy (SAM) proposes lightweight Multi-Scale Fusion Network (LMFNet) aimed at improving accuracy processing efficiency in analysis. LMFNet adopts deep U-shaped encoder-decoder architecture, with backbone designed inverted residual blocks optimize feature transmission while maintaining model compactness. Additionally, we introduce two flexible, plug-and-play modules: Context Feature (CFF) module, which effectively integrates multi-scale contextual information skip connection layers, Perception Aggregation (MPA) focuses on extracting fusing features bottleneck layers. Experimental results demonstrate that performs exceptionally well IUT dataset, significantly outperforming existing methods terms lightweighting performance.
Language: Английский
Citations
0International Journal of Heat and Mass Transfer, Journal Year: 2025, Volume and Issue: 240, P. 126682 - 126682
Published: Jan. 10, 2025
Language: Английский
Citations
0