South Korean Scientists Develop AI to Detect Hidden Cracks in Structures With Unprecedented Precision

Challenges of traditional non-destructive testing

Signals measured by physical sensors, such as ultrasonic or electromagnetic waves, are often distorted by factors including geometry, material properties, and complex real-world conditions. These interferences impose inherent physical limitations on the accurate determination of defect location and size, thereby constraining conventional diagnostic performance.

Introducing DiffectNet: diffusion-enabled defect reconstruction AI

In a new breakthrough, a research team from South Korea led by Sooyoung Lee, Assistant Professor and Principal Investigator of the Industrial Artificial Intelligence Laboratory in the School of Mechanical Engineering at Chung-Ang University, has designed DiffectNet, a diffusion-enabled conditional target generation network with the potential to produce high-fidelity and defect-aware ultrasonic images. Their findings were published online in the journal Mechanical Systems and Signal Processing.

AI overcomes the physical limits of defect detection

Prof. Lee remarks: "If the limitations of traditional methods can be overcome through the learning and reasoning capabilities of AI, it becomes possible to elevate the integrity and safety standards of industrial systems to an entirely new level. The proposed technology is not merely an attempt to apply AI to engineering problems, but a fundamental breakthrough. It involves the development of a generative AI technology capable of reconstructing hidden cracks inside structures in real time, thereby overcoming the physical limitations of traditional methods."

Applications across reliability-critical industries

If AI can detect and accurately reconstruct internal defects within structures, it will enable accident prevention, even in environments that are difficult or dangerous for humans to access. For example, in power plants, even a microscopic crack can cause catastrophic accidents. With AI-based real-time monitoring of internal structures, early warnings of potential anomalies become possible.

In semiconductor or advanced manufacturing facilities, AI can virtually reconstruct internal defects without interrupting operations, enabling continuous quality control and maintaining productivity. Similarly, real-time monitoring of buildings and bridges could significantly enhance urban safety management systems.

Redefining intelligent engineering and structural safety

These applications demonstrate how AI is enabling new engineering capabilities that were once considered impossible, ushering in an era of intelligent engineering. By allowing AI to act as the "eyes" of a structure, this study opens pathways for real-time defect reconstruction and predictive diagnostics in high-reliability sectors such as aerospace, energy, semiconductors, and civil infrastructure.

AI’s evolving role in next-generation engineering

"AI is evolving beyond a mere tool for data analysis and learning, it is becoming an active agent that expands the very boundaries of engineering itself. Moving forward, our laboratory will continue to lead research in developing AI-driven engineering technologies, pioneering an era in which AI redefines the field of engineering," concludes Prof. Lee.

Safeguarding safety and reliability through AI innovation

Overall, this pioneering research demonstrates the transformative potential of AI to ensure the safety and reliability of modern industries and everyday life, marking a critical milestone in the convergence of artificial intelligence and engineering integrity.