铝合金加速腐蚀形貌灰度特征提取方法

Research on the Gray-Scale Feature Extractionfrom Corrosion Morphology of Aluminum Alloys

摘要:

基于腐蚀图像包含大量腐蚀信息的客观现象,将数字图像技术和概率统计理论应用于腐蚀图像预处理和特征提取,用腐蚀图像统计特征值的变化来表征腐蚀形貌的演化过程。结合LY12CZ铝合金在EXCO溶液中加速腐蚀试验,计算得到加速腐蚀不同时间的试验件表面6个典型灰度统计特征值。分析表明:试验件表面灰度统计特征值随着腐蚀时间的增加呈现规律性变化,平均亮度、一致性随腐蚀时间的增加而减少,而平均对比度、相对平滑度、第3阶矩、熵值等随腐蚀时间的增加而增加,说明随着腐蚀时间的增加,试件表面蚀坑逐渐变大变深,腐蚀越来越严重,腐蚀形貌越来越复杂。

Abstract:

Digital image technique and theory of probability and statistics were applied to the feature extraction of corrosion morphology based on corrosion images containing a large amount of corrosion information. The change of statistical feature of corrosion image was used to express the evolution of corrosion morphology. Combining with accelerated corrosion test in EXCO (exfoliation corrosion) solution, six representative statistical characteristic values were computed with different accelerated corrosion time. Results showed that the statistical feature changed regularly with accelerated corrosion time. Average brightness and consistency decreased, meantime the third moment contrast smoothness and entropy increased. Corrosion pits on the surface of specimen became bigger and deeper, corrosion became serious and corrosion morphology became complicated.