使用Grad-CAM对二进制腐蚀图像分类进行可解释的深度学习框架.
Muhammad Amir Imran Aminudin1, Mohd Na'im Abdullah1, Faizal Mustapha1
1Department of Aerospace Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, Malaysia.
Sensors (Basel, Switzerland)
|November 27, 2025
概括
本研究引入了用于金属材料自动腐蚀检测的深度学习模型,实现高精度. 像Grad-CAM这样的可解释AI (XAI) 技术被用于可视化和验证模型预测,提高腐蚀分析的可靠性.
科学领域:
- 材料科学 材料科学 材料科学
- 计算机科学 计算机科学
- 人工智能的人工智能
背景情况:
- 金属材料腐蚀带来了重要的维护和安全挑战.
- 传统的视觉检查方法效率低下,需要专家解释.
- 需要自动化解决方案来准确可靠地检测腐蚀.
研究的目的:
- 调查深度学习模型对腐蚀二进制图像分类的有效性.
- 整合可解释的人工智能 (XAI) 技术,以实现模型可解释性.
- 为了比较四个预训练的卷积神经网络 (CNN) 架构的性能.
主要方法:
- 使用了四个预先训练好的CNN:ResNet50,MobileNetV2,NASNetMobile和EfficientNetV2B0.0. 这四个CNN都是使用的.
- 在一个由9636张增强图像 (腐蚀与非腐蚀) 的数据集上训练模型.
- 应用梯度加权类激活映射 (Grad-CAM) 为XAI可视化决策.
主要成果:
- ResNet50实现了最高的分类准确性 (96.58%).
- 移动NetV2提供了最快的培训时间.
- 通过Grad-CAM,EfficientNetV2B0通过Grad-CAM在腐蚀地区显示出稳定的训练,最小的过和高激活.
结论:
- 深度学习模型,特别是CNN,显示了自动腐蚀检测的巨大潜力.
- 像Grad-CAM这样的XAI技术提高了模型透明度和对腐蚀分析的信任.
- EfficientNetV2B0和ResNet50在腐蚀分类和可解释性方面呈现出有希望的性能特征.
相关概念视频
01:31Classification of Systems-II
447
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
447
01:26Classification of Systems-I
543
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
543
01:22Force Classification
2.3K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.3K