[论文解读] MLography: An Automated Quantitative Metallography Model for Impurities Anomaly Detection using Novel Data Mining and Deep Learning Approach

Matan Rusanovsky, Gal Oren+2 more|arXiv (Cornell University)|Feb 27, 2020

Mineral Processing and Grinding参考文献 14被引用 4

一句话总结

MLography 提出了一种新颖的深度学习与数据挖掘框架，用于在工程合金的金相杂质中实现自动化、定量的异常检测。该方法引入了三种互补的异常度量——空间、形状和面积——分别基于距离度量、自编码器和市场聚类，以识别并打分异常夹杂物，验证结果表明模型预测的异常与物理检测结果高度一致。

ABSTRACT

The micro-structure of most of the engineering alloys contains some inclusions and precipitates, which may affect their properties, therefore it is crucial to characterize them. In this work we focus on the development of a state-of-the-art artificial intelligence model for Anomaly Detection named MLography to automatically quantify the degree of anomaly of impurities in alloys. For this purpose, we introduce several anomaly detection measures: Spatial, Shape and Area anomaly, that successfully detect the most anomalous objects based on their objective, given that the impurities were already labeled. The first two measures quantify the degree of anomaly of each object by how each object is distant and big compared to its neighborhood, and by the abnormally of its own shape respectively. The last measure, combines the former two and highlights the most anomalous regions among all input images, for later (physical) examination. The performance of the model is presented and analyzed based on few representative cases. We stress that although the models presented here were developed for metallography analysis, most of them can be generalized to a wider set of problems in which anomaly detection of geometrical objects is desired. All models as well as the data-set that was created for this work, are publicly available at: https://github.com/matanr/MLography.

研究动机与目标

• 开发一种客观、定量的替代方案，以取代金相分析中依赖专家判断的异常评估方法。
• 利用人工智能自动化检测和打分工程合金中的杂质异常。
• 创建一个公开的数据集和模型，以支持定量金相研究的可重复性。
• 通过多尺度异常评分实现对潜在缺陷材料区域的早期识别。

提出的方法

• 提出一种基于到第k个最近邻距离的空间异常度量，并根据物体面积进行调整。
• 引入一种基于自编码器重建杂质轮廓并量化其与正常形状偏差的形状异常评分方法。
• 采用市场聚类将杂质分组为区域，并基于聚类的紧密度和异常值包含情况计算面积异常评分。
• 将空间和形状异常评分相乘，为每个聚类生成综合异常评分。
• 使用仅包含正常杂质的训练自编码器，在测试图像中检测形状异常。
• 根据公式2对聚类按异常评分排序，以优先选择需进行物理检查的区域。

实验结果

研究问题

• RQ1 基于数据驱动和深度学习的方法是否能够可靠地检测金相图像中的异常夹杂物，而无需依赖专家意见？
• RQ2 如何结合空间、形状和面积异常度量以提升对合金中潜在缺陷区域的检测能力？
• RQ3 模型预测的异常评分在多大程度上与微硬度和成分等物理缺陷指标相关？
• RQ4 当物理测试未显示可测量差异时，模型能否区分正常与异常夹杂物？

主要发现

• 该模型在测试扫描中成功将最异常的聚类排在前1588、1642和916位（共1653个聚类），最异常的聚类均位于前十分位内。
• 在微硬度或EDS成分方面，异常夹杂物与正常夹杂物之间未发现显著差异，表明视觉异常并不总是与物理性能变化相关。
• 空间和形状异常度量有效识别出与正常模式显著偏离的区域，即使物理测试未确认缺陷。
• 通过市场聚类实现的面积异常度量，成功突出了内部异常评分较高的聚类，从而实现了对需进一步检查区域的优先排序。
• 模型的异常评分随异常程度单调递增，验证了评分框架的数学一致性。
• 该模型（包括243张标注的金相扫描图像数据集）已公开发布于 https://github.com/matanr/MLography。