Researchers from Chung-Ang University in South Korea have achieved a major breakthrough in non-destructive testing (NDT) with the development of a new AI-driven ultrasonic imaging system capable of detecting and reconstructing internal material defects in real time.
Led by Assistant Professor Sooyoung Lee, Principal Investigator of the Industrial Artificial Intelligence Laboratory in the School of Mechanical Engineering, the research team has introduced DiffectNet—a diffusion-enabled conditional target generation network that leverages generative AI to produce high-fidelity, defect-aware ultrasonic images. The results were published in the journal Mechanical Systems and Signal Processing on November 1, 2025.
The study addresses a long-standing challenge in industrial inspection: conventional NDT methods often struggle to capture microscopic cracks or internal flaws due to signal distortion caused by geometry, material complexity, and environmental factors. DiffectNet overcomes these limitations by simulating and analyzing internal material defects through AI-powered virtual defect engineering.
Prof. Lee explained the significance of this advancement, stating: “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.”
By integrating AI with ultrasonic imaging, the system enables defect detection without causing any physical damage, while addressing data scarcity and improving diagnostic reliability across applications. The technology could play a transformative role in semiconductors, energy, automotive, aerospace, and civil infrastructure—industries where micro-scale flaws can lead to catastrophic failures.
The researchers envision wide-ranging implications. In power plants, the system could provide early warnings of potential failures by monitoring internal structures continuously. In semiconductor manufacturing, it could reconstruct defects virtually without interrupting production. Likewise, bridges and buildings could be monitored in real time to enhance public safety.
By allowing AI to act as the “eyes” of a structure, this innovation ushers in a new era of intelligent engineering—where machines can perceive, analyze, and predict defects beyond human capability.
As Prof. Lee noted: “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.”
The research underscores a paradigm shift in NDT technology, combining advanced ultrasonic diagnostics with AI-based reasoning to set new standards in reliability, safety, and predictive maintenance for high-stakes industries worldwide.
