Non-Destructive Testing of Steel-Lined Concrete Structure Using Multiple Agents With Deep Prior

Non-destructive testing (NDT) is a cornerstone of structural integrity assessment that enables internal evaluation of materials without inflicting damage. Among various imaging methods, ultrasonic model-based iterative reconstruction (UMBIR) has gained attention for its ability to enhance ultrasonic imaging by incorporating physical and statistical priors. Notably, UMBIR and its extension, Multi-Frequency UMBIR (MF-UMBIR), have shown improved accuracy over traditional techniques. However, their performance in highly complex structures. In this paper, we propose Deep-MACE, a novel reconstruction framework that integrates multi-frequency forward model agents with a deep learning prior using the consensus equilibrium formulation. By combining data consistency across different excitation frequencies with the expressive power of a learned U-Net prior, Deep-MACE enables high-fidelity imaging in acoustically heterogeneous environments. Experimental results demonstrate that both UMBIR and MF-UMBIR suffer from limitations in defect visibility and robustness when applied to steel-lined concrete structures. In contrast, Deep-MACE consistently produces clearer reconstructions, successfully identifying all internal rebars with fewer artifacts and improved spatial resolution. These results highlight the potential of integrating deep priors into multi-agent frameworks for advanced ultrasonic NDT.