Automated measurement system for detecting carbonation depth: Image-processing based technique applied to concrete sprayed with phenolphthalein

This paper aims at discussing an automated measurement system for detecting carbonation depth in concrete sprayed with phenolphthalein. Image processing and Convolutional Neural Networks strategies are exploited to accurately separate the carbonated non-carbonated areas remove those aggregates on front that could bring a wrong evaluation of depth. Very strong correlation (R2 = 0.96) is found between results provided by proposed approach method suggested EN 13295 standard. The expanded uncertainty (coverage factor k 2) this novel 0.08 mm. ANOVA analysis performed multi-operator tests proved highest source system, which, other hand, robust changes operator performing measurement.