优化混凝土裂检测:通过在Nvidia Jetson Nano上应用转移学习的研究
C Long Nguyen1, Andy Nguyen1, Jason Brown1
1School of Engineering, University of Southern Queensland, Springfield, QLD 4300, Australia.
Sensors (Basel, Switzerland)
|December 17, 2024
概括
人工智能 (AI) 在基础设施中的破解检测使用卷积神经网络 (CNN) 进行更快,更安全的检查. Resnet50实现了96%的准确性,使边缘设备上的结构健康监测能够高效.
科学领域:
- 土木工程 土木工程是指土木工程.
- 计算机科学 计算机科学
- 人工智能的人工智能
背景情况:
- 基础设施检查严重依赖于手工劳动,这是昂贵的,耗时的,潜在的危险.
- 使用人工智能 (AI) 的自动缺陷检测为提高检查效率和安全提供了一个有希望的替代方案.
研究的目的:
- 评估各种卷积神经网络 (CNN) 对于自动混凝土裂检测的有效性.
- 评估这些模型在实时结构健康监测 (SHM) 边缘计算设备上部署时的性能.
主要方法:
- 在3000张混凝土结构图像的数据集上使用转移学习训练了6个CNN模型 (Resnet18,Resnet50,GoogLeNet,MobileNetV2,MobileNetV3-Small,MobileNetV3-Large).
- 增加了盐和胡噪声和运动模糊的数据集,以提高模型的稳定性.
- 在Nvidia Jetson Nano上部署了表现最好的模型,用于实时推断.
主要成果:
- Resnet50在原始数据集和16.6个批量大小下显示了最高的验证准确性 (96%) 和F1得分 (95%).
- 经过训练的模型在实验室和现场环境中成功执行了实时裂检测.
- 边缘人工智能部署在自动裂检测方面被证明是有效的.
结论:
- 转移学习与边缘人工智能设备相结合,为在混凝土结构中自动检测裂提供了具有成本效益和高效的解决方案.
- 由人工智能驱动的SHM系统可以显著提高安全性并降低基础设施检查的成本.
相关概念视频
02:07Improving Translational Accuracy
8.8K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
8.8K
01:18Reducing Line Loss
144
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
144
01:20Microcracking in Concrete
100
Microcracking in concrete refers to the tiny cracks that can form within the material even before any external load is applied. These microcracks typically occur at the interface between the coarse aggregate and the hydrated cement paste, often as a result of differential volume changes prompted by variations in stress-strain behavior, as well as thermal and moisture movement. Initially, these microcracks remain stable and do not grow substantially until the concrete is stressed to about 30...
100
01:12Non-destructive Tests for Concrete Strength
107
The rebound hammer test, also known as the Schmidt hammer test, is a non-destructive technique for evaluating the hardness of concrete and, indirectly, the strength of concrete. It operates on the principle that the rebound of a spring-driven mass from a concrete surface correlates to the surface's hardness. The device comprises a mass within a tubular housing, a spring mechanism, and a plunger that strikes the concrete. Upon release, the energy imparted to the mass by the spring causes it...
107
01:05Difference from Background: Limit of Detection
5.8K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
5.8K
01:30Machines: Problem Solving II
296
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
296