Defect severity classification holds significant importance within industries that prioritize quality control. This study proposes a novel approach that applies machine learning with Stress Concentration Tomography (SCT) to effectively categorize defects’ severity. Through the utilization of machine learning algorithms, the objective is to enhance the precision and efficiency of defect severity classification.

The findings highlight the effectiveness of the technique, notably, the best model achieves a commendable accuracy rate of 90%. The study also underscores the importance of considering both defect variety and dataset size in refining machine learning models for pipeline defect severity prediction, thereby ensuring their applicability in real-world scenarios.