轻量化模型让边缘设备实时检测结构裂缝
On-Device Crack Segmentation for Edge Structural Health Monitoring
- 用精简卷积核与深度可分离卷积降低资源占用
- 在仅25%滤波器数量下仍保持良好分割精度
- 适合低功耗物联网结构健康监测场景
裂纹分割在结构健康监测（SHM）中至关重要，可精确识别裂纹尺寸与位置，实现长期损伤追踪。然而，在资源受限的微控制器上部署深度学习模型面临内存、算力和能耗瓶颈。本文针对TinyML应用，探索轻量化U-Net架构，采用三种优化策略：滤波器数量减少、网络深度缩减及使用深度可分离卷积（DWConv2D）。结果表明，将滤波器数量降至25%、网络深度压缩至四层块，并结合深度卷积，显著降低内存与闪存占用及推理时间，虽有轻微精度损失但整体性能与资源消耗达到良好平衡。该模型适用于低功耗的TinyML场景，为能量自供的边缘SHM系统提供可能。
原文摘要 · Abstract (English)
Crack segmentation can play a critical role in Structural Health Monitoring (SHM) by enabling accurate identification of crack size and location, which allows to monitor structural damages over time. However, deploying deep learning models for crack segmentation on resource-constrained microcontrollers presents significant challenges due to limited memory, computational power, and energy resources. To address these challenges, this study explores lightweight U-Net architectures tailored for TinyML applications, focusing on three optimization strategies: filter number reduction, network depth reduction, and the use of Depthwise Separable Convolutions (DWConv2D). Our results demonstrate that reducing convolution kernels and network depth significantly reduces RAM and Flash requirement, and inference times, albeit with some accuracy trade-offs. Specifically, by reducing the filer number to 25%, the network depth to four blocks, and utilizing depthwise convolutions, a good compromise between segmentation performance and resource consumption is achieved. This makes the network particularly suitable for low-power TinyML applications. This study not only advances TinyML-based crack segmentation but also provides the possibility for energy-autonomous edge SHM systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。