No abstract

No abstract

Artificial neural network (ANN) has been commonly used to deal with many problems. However, since this algorithm applies backpropagation algorithms based on gradient descent (GD) technique to look for the best solution, the network may face major risks of being entrapped in local minima. To overcome those drawbacks of ANN, in this work, we propose a novel ANN working parallel with metaheuristic algorithms (MAs) to train the network. The core idea is that first, (1) GD is applied to increase the convergence speed. (2) If the network is stuck in local minima, the capacity of the global search technique of MAs is employed. (3) After escaping from local minima, the GD technique is applied again. This process is applied until the target is achieved. Additionally, to increase the efficiency of the global search capacity, a hybrid of particle swarm optimization and genetic algorithm (PSOGA) is employed. The effectiveness of ANNPSOGA is assessed using both numerical models and measurement. The results demonstrate that ANNPSOGA provides higher accuracy than traditional ANN, PSO, and other hybrid ANNs (even a higher level of noise is employed) and also considerably decreases calculational cost compared with PSO.

No abstract

No abstract

Optimization algorithms (OAs) are a vital tool to deal with complex problems, and the improvement of OA is inseparable from practical strategies and mechanisms. Among the OAs, Bee Algorithm (BA) is an intelligent algorithm with a simple mechanism and easy implementation, in which effectiveness has been proven when handling optimization problems. Nevertheless, BA still has some fundamental drawbacks, which can hinder its effectiveness and accuracy. Therefore, this paper proposes a novel approach to tackle the shortcomings of BA by combining it with Genetic Algorithm (GA). The main intention is to combine the strengths of both optimization techniques, which are the exploitative search ability of BA and the robustness with the crossover and mutation capacity of GA. An investigation of a real-life suspension footbridge is considered to validate the effectiveness of the proposed method. A baseline Finite Element model of the bridge is constructed based on vibration measurement data and model updating, which is used to generate different hypothetical damage scenarios. The proposed HBGA is tested against BA, GA, and PSO to showcase its effectiveness in detecting damage for each scenario. The results show that the proposed algorithm is effective in dealing with the damage assessment problems of SHM.

In this paper, the feasibility of Structural Health Monitoring (SHM) employing a novel Fibonacy Sequence (FS)-based Optimization Algorithms (OAs) and up-to-date computing techniques is investigated for a large-scale railway bridge. During recent decades, numerous metaheuristic intelligent OAs have been proposed and immediately gained a lot of momentum. However, the major concern is how to employ OAs to deal with real-world problems, especially the SHM of large-scale structures. In addition to the requirement of high accuracy, a high computational cost is putting up a major barrier to the real application of OAs. Therefore, this article aims at addressing these two aforementioned issues. First, we propose employing the optimal ability of the golden ratio formulated by the well-known FS to remedy the shortcomings and improve the accuracy of OAs, specifically, a recently proposed new algorithm, namely Salp Swarm Algorithm (SSA). On the other hand, to deal with the high computational cost problems of OAs, we propose employing an up-to-date computing technique, termed superscalar processor to conduct a series of iterations in parallel. Moreover, in this work, the vectorization technique is also applied to reduce the size of the data. The obtained results show that the proposed approach is highly potential to apply for SHM of real large-scale structures.

No abstract