Segmenting hydrogen-induced cracking defects in steel through scanning acoustic microscopy and deep neural networks

Abstract

Hydrogen-induced cracking (HIC) presents a significant concern in industries, such as oil and gas, petrochemicals, and aerospace, where high-strength steel is prevalently used. This phenomenon compromises the structural integrity of steel pipelines and equipment. Accurate detection and monitoring of HIC are crucial for the safety and reliability of these assets. While traditional defect detection methods are usually costly and easily affected by human physiological state, deep learning approaches offer both time and financial benefits along with high accuracy. This study focuses on employing deep learning to segment HIC in steel, utilizing the robust and state-of-the-art YOLOv8-seg architecture for defect identification and segmentation. The process involves acquiring two-dimensional B-scan images through a scanning acoustic microscopy (SAM) system, followed by employing the YOLOv8-seg architecture to address the segmentation task within these images. The experimental results demonstrate the effectiveness of the YOLOv8-seg model, achieving a mean average precision (mAP) score greater than ˜0.95. Notably, this research pioneers the development of a framework for reconstructing HIC within steel based on B-scan image segmentation results, offering researchers and professionals a comprehensive understanding of internal defects in steel blocks. This work underscores the potential of YOLOv8-seg architecture for accurate detection and segmentation of HIC in steel, providing a valuable tool for inspection and maintenance activities.