Real-time damage detection of bridges using adaptive time-frequency analysis and ANN

Abstract

Although traditional signal-based structural health monitoring algorithms have been successfully employed for small structures, their application for large and complex bridges has been challenging due to non-stationary signal characteristics with a high level of noise. In this paper, a promising damage detection algorithm is proposed by incorporation of adaptive signal processing and Artificial Neural Network (ANN). First, three adaptive signal processing techniques including Empirical Mode Decomposition (EMD), Local Mean Decomposition (LMD) and Hilbert Vibration Decomposition (HVD) are compared. The efficacy of these methods is examined for several numerically simulated signals to find a reliable signal processing tool. Then, three signal features are compared to find the most sensitive feature to damage. In the next step, an ANN ensemble is utilized as a classifier. Traditional statistical features and energy indices are used as the network input and output to make real-time detection of damage possible. The strength of this approach lies with training the network only based on healthy state of the structure. Having a trained ANN, online processing can be made to find a possible damage. Results show that the proposed algorithm has a good capacity as an online output-only damage detection method.

A swift neural network-based algorithm for demand estimation in concrete moment-resisting buildings

“…Levenberg-Marquardt, Quasi-Newton, Gradient Descent, and Back-Propagation) to prevent the NN outputs from deviating from the defined target values. The Levenberg-Marquardt learning method is the most widely used optimization algorithm in the body of NNs [31,32]. In this study, the sigmoid and linear functions were used as the activation functions for the hidden layers and output layer, respectively.…”

Prediction of reduced sound wave intensity in floor systems using machine learning methods

“…Nonetheless, certain elements cannot be standardized using the systematic methods for sound penetration prediction, which has contributed to the idea of using artificial intelligence for sound reduction estimation in different countries [16]. In recent years, Machine learning, as one of the soft computing techniques, has become one of the main areas of research in engineering fields, especially civil engineering [17] [18,19]. Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), and linear regression are among the powerful and efficient methods of machine learning that have been used by researchers in predicting and modeling complex systems due to their high capability.…”