Hosein Naderpour

Structural damage detection is vital for ensuring the safety, integrity, and serviceability of reinforced concrete (RC) structures, which are inherently susceptible to progressive deterioration over time. This study presents an advanced model updating framework enhanced with metaheuristic optimization algorithms for accurate and robust identification of structural damage. A novel objective function was formulated by integrating three critical dynamic features: natural frequencies, mode shapes, and modal strain energy. To validate the effectiveness and robustness of the proposed approach, five metaheuristic algorithms—GOA, WOA, MRFO, SBOA, and AOA—were employed and their performance evaluated across two predefined damage scenarios under three levels of simulated noise (0%, 3%, and 10%). Comparative results indicated that while MRFO and SBOA achieved higher accuracy and noise resistance, GOA demonstrated faster convergence rates. To overcome limitations observed in individual algorithms, a novel hybrid optimization algorithm, MSOA, was developed. MSOA effectively balanced exploration and exploitation tendencies, improved convergence behavior, and reduced the risk of premature convergence, particularly under noisy conditions. The error between simulated and estimated results, averaged over twenty runs for each damage scenario, was less than 4 percent. The results demonstrate that the proposed model updating framework, which integrates a novel objective function with the MSOA algorithm, provides high accuracy and robustness for structural damage detection in RC frames, even under conditions of measurement uncertainty.

Zero‐shot learning approaches have emerged as promising techniques for structural health monitoring (SHM) due to their ability to learn representations without labeled data. With the practical design of such models, the shift from traditional structure‐dependent techniques to potentially large‐scale implementations becomes feasible, effectively addressing the challenge of gathering labeled data. Autoencoders (AEs), a class of deep neural networks, align well with zero‐shot SHM settings due to their architecture, loss function, and optimization process. In AEs, the reconstruction error is expected to increase for novel data patterns (i.e., potential damage data), while the encoded manifold in their bottleneck layers enables the discrimination of complex patterns. However, for practical SHM applications, rigorous evaluation of (variational) AEs and the robustness of reconstruction loss‐ or manifold‐based designs in handling real‐world scenarios remains necessary. Accordingly, this article employs two SHM benchmarks to evaluate the effectiveness of manifold learning compared to the reconstruction errors of (variational) AEs in a zero‐shot setting. The comparison encompasses metrics such as reconstruction fidelity, preservation of structural characteristics, and the ability to generalize to unseen structural conditions. Furthermore, an unbiased normalization‐based ensemble methodology is proposed, combining both approaches with the goal of enhancing damage detection performance and delivering more reliable results in zero‐shot learning contexts. The proposed ensemble strategy, integrating both reconstruction error and manifold representations, adds robustness to the damage detection process, a crucial feature in the uncertain domain of zero‐shot structural damage detection. The findings suggest that neither reconstruction loss nor manifold data consistently outperform the other; structural differences may render one approach more effective than the other in specific contexts, and based on these observations, a zero‐shot damage severity index is suggested and tested on the benchmark data. Nevertheless, the proposed ensemble method demonstrates superior performance over individual models in estimating damage severity in an unsupervised setting. These results highlight the efficacy of variational AEs for zero‐shot SHM, offering insights into their strengths and limitations and aiding users in selecting appropriate zero‐shot damage detection strategies in the absence of labeled data.

This study aimed to rigorously evaluate the impact of tuned mass dampers (TMDs) on structural response under seismic excitation. By strategically placing TMDs at various levels within the structures, the research sought to determine their effectiveness in mitigating structural movement. A single-degree-of-freedom (SDOF) system incorporating TMDs was utilized to model structures of 10, 13, and 16 stories, each configured with TMDs at different heights. The structures were subjected to near-fault earthquakes to assess the efficacy of TMDs in reducing structural response. The findings revealed significant enhancements in structural performance when TMDs were optimally positioned. Specifically, a 50% reduction in both acceleration and displacement, alongside a 65% decrease in maximum drift, underscored the effectiveness of TMD deployment. Furthermore, the study demonstrated that distributing multiple TMDs along the height of the structure provided superior drift control. Notably, positioning TMDs within the upper one-third of the structure yielded the most pronounced improvements in acceleration, displacement, and maximum drift. Finally, the research indicates that the strategic incorporation of TMDs can significantly enhance the seismic resilience of structures. The results highlight the substantial benefits of TMDs in optimizing acceleration, displacement, and drift, thereby affirming their critical role in seismic design and retrofitting strategies.