---

An effective method utilizing the differential evolution algorithm (DEA) as an optimisation solver is suggested here to detect the location and extent of single and multiple damages in structural systems using time domain response method. Changes in acceleration response of structure are considered as a criterion for damage occurrence. The acceleration of structures is obtained using Newmark method. Damage is simulated by reducing the elasticity modulus of structural members. Three illustrative examples are numerically investigated, considering also measurement noise effect. All the numerical results indicate the high accuracy of the proposed method for determining the location and severity of damage.

---

An efficient method is proposed by using time domain responses and topology optimization to identify the location and severity of damages in two-dimensional structures under plane stress assumption. Damage is assumed in the form of material density reduction in the finite element model of the structure. The time domain responses utilized here, are the nodal accelerations measured at certain points of the structure. The responses are obtained by the Newmark method and contaminated with uniformly random noise in order to simulate real conditions. Damage indicators are extracted from the time domain responses by using Singular Value Decomposition (SVD). The problem of damage detection is presented as a topology optimization problem and the Solid Isotropic Material with Penalization (SIMP) method is used for appropriate damage modeling. The objective function is formed based on the difference of singular values of the Hankel matrix for responses of real structure and the analytical model. In order to evaluate the correctness of the proposed method, some numerical examples are examined. The results indicate efficiency of the proposed method in structural damage detection and its parameters such as resampling length in SVD, penalty factor in the SIMP method and number and location of sensors are effective parameters for improving the results.

---

Accurate detection and localization of impacts in structural systems are crucial for safety and enabling effective structural health monitoring (SHM). This paper aims to identify multiple consecutive impacts in framed structures with unknown dynamic properties, using time-domain acceleration data. Traditional methods often struggle under complex conditions such as noisy environments and multiple impacts. To overcome these limitations, we propose a deep learning-based framework utilizing Convolutional Neural Networks (CNNs) to extract intricate patterns from acceleration signals. Input data are generated through high-fidelity numerical simulations based on the Finite Element Method (FEM), allowing precise control over impact characteristics and their spatial distribution. A fixed-length sliding window is employed to segment the acceleration time series, enabling the model to perform localized and near-real-time impact detection. To further improve model performance, Bayesian optimization is utilized for hyperparameter tuning, enhancing accuracy and efficiency over traditional grid search. The proposed model is numerically evaluated on two-dimensional structures: a steel pin-jointed camel-back truss and a shear frame. The results reveal that the proposed strategy achieves high accuracy in estimating the location, timing, and magnitude of impacts, even under noisy conditions. The key novelty of this research lies in combining deep learning with advanced optimization techniques to solve the impact detection problem in structures with unknown parameters. These findings establish a robust framework for advancing intelligent, data-driven SHM systems, with direct applications in real-world infrastructure. The proposed methodology demonstrates significant potential to mitigate economic costs and safety risks associated with structural failures under impact loading.