The process of damage identification in Structural Health Monitoring (SHM) gives us a lot of practical information about the current status of the inspected structure. The target of the process is to detect damage status by processing data collected from sensors, followed by identifying the difference between the damaged and the undamaged states. Different machine learning techniques have been applied to attempt to extract features or knowledge from vibration data, however, they need to learn prior knowledge about the factors affecting the structure. In this paper, a novel method of structural damage detection is proposed using convolution neural network and recurrent neural network. A convolution neural network is used to extract deep features while recurrent neural network is trained to learn the long-term historical dependency in time series data. This method with combining two types of features increases discrimination ability when compares with it to deep features only. Finally, the neural network is applied to categorize the time series into two states - undamaged and damaged. The accuracy of the proposed method was tested on a benchmark dataset of Z24-bridge (Switzerland). The result shows that the hybrid method provides a high level of accuracy in damage identification of the tested structure.

Recently, Structural Health Monitoring (SHM) has become a critical component of the maintenance and safety of lifeline infrastructures such as dams, skyscrapers, and bridges, thanks to its ability to detect structural failures at the early stages. In this paper, we evaluate the performance of the SHM damage identification tool using a novel metaheuristic algorithm called the Artificial Hummingbird Algorithm (AHA). The proposed approach is evaluated by two case studies of different bridge structures in Vietnam with different simulated damage scenarios. The potency of the AHA is compared against the other well-known metaheuristic algorithms such as Cuckoo Search (CS), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Teaching-Learning Based Optimization (TLBO). The results show that the AHA performs much better than the other algorithms in terms of accuracy and computational cost. The application of AHA can help to reduce the cost and time required for structural maintenance significantly, as well as improve the lifecycle of the structure.

This paper presents an enhanced version of the Artificial Rabbit Optimization (ARO) algorithm designed for identifying structural damage in bridge structures. The original ARO draws inspiration from survival observed in wild rabbits. However, it demands a substantial investment of computational time. Therefore, in this paper, the Improved ARO (IARO) algorithm incorporating elements of the Grey Wolf Optimizer (GWO) through hybridization, is employed to deal with optimization problems. The central concept of this approach involves infusing predator-hunting characteristics into the prey-rabbit during the hunting process, thereby enabling more effective predator evasion. The proposed method is evaluated through a series of simulations related to two real bridges: a simple supported beam structure and a steel truss bridge. The results show a significant improvement in accuracy and efficiency in determining structural damage while considering factors such as damage location, severity, and computation time. These findings underscore the potential of the proposed approach for real-world applications in structural health monitoring and damage detection.