Year: 2025
Type: article
Abstract: The identification tools and techniques in materials engineering using AI, computer vision, and natural language processing have advanced significantly to address limitations in traditional systems. Modern and advanced studies have emerged to drive innovation in the field of materials science. This contemporary shift enhances conventional methods by integrating AI-based techniques. This study emphasizes carbon fiber reinforced polymer (CFRP) composites, which are extensively used in aerospace, automotive, and structural applications. The identification of surface cracks and internal defects, such as delamination and voids, is essential for assessing structural integrity, performance, and service life. The methodology suggested is based on image processing and machine learning algorithms using computer vision to detect defects, extract features, and classify them, and provide automated analysis of the material conditions. AI provides algorithms and statistical pattern recognition techniques used for data analytics in materials science. AI rapidly enables the detection and analysis of defects, thereby transforming the field of materials engineering. Predictions and parameter estimations are dependent on data quality and material informatics. It has been shown through experiments that AI-based methods are effective in measuring structural integrity and performance evaluation due to enhanced detection accuracy, shorter processing time, and dependable defect classification measures in comparison to traditional inspection processes. Future studies are expected to incorporate quantum computing and AI systems for faster and more precise predictions and identifications. Prospective directions include improving material property predictions and optimizing simulations for computational analyses.
DOI: 10.33411/ijist/1701
Subfield: Industrial and Manufacturing Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7167808189