In recent decades, the integration of optimization methods and Machine Learning (ML) models has garnered significant attention within the research community. In the pursuit of establishing a symbiotic relationship between ML and optimization algorithms, this study focuses on the fusion of the African Vulture Optimization Algorithm (AVOA) - an optimization algorithm inspired by the foraging behavior of African vultures - with Deep Neural Networks (DNNs) - a prevalent model in ML for damage detection of a real large-scale bridge. In this research, AVOA, possessing a vast search space and the ability to autonomously adjust crucial parameters during the search process, such as flight velocity and learning rate, is employed to select informative features such as weight and biases of DNNs. This synergy allows the network to automatically adjust its potential. The technique is applied to a truss bridge, utilizing Finite Element Model (FEM) data that has been validated by real-world vibration measurements, resulting in precise damage identification even in the presence of white Gaussian noise. Evaluation criteria demonstrate enhanced accuracy and computational efficiency compared to the traditional neural network approach.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Prospective Technique for Damage Detection in Truss Structures Using the Fusion of DNN with AVOA


    Additional title:

    KSCE J Civ Eng


    Contributors:

    Published in:

    Publication date :

    2024-07-01


    Size :

    14 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English