Sandeep Sony

In this paper, a novel method is proposed based on a windowed one-dimensional convolutional neural network (1D CNN) for multiclass damage identification using vibration responses of a full-scale bridge. The measured data are first augmented by extracting samples of windows of raw acceleration time series to alleviate the problem of a limited training data set. 1D CNN is developed to classify the windowed time series into multiple damage classes. The damage is quantified using the predicted class probabilities, and the damage is localized if the predicted class is equal to the assigned damage class, exceeding a threshold associated with majority voting. The proposed network is optimally tuned with respect to various hyperparameters such as window size and random initialization of weights to achieve the best classification performance using a global 1D CNN model. The proposed method is validated using a benchmark bridge data for multiclass classification for two different damage scenarios, namely, pier settlement and rupture of tendons, under the various extents of damage. The damage identification is carried out on various bridge components to collectively identify the structural component with a damaged signature. The results show that the proposed windowed 1D CNN method achieves an accuracy of 97%, and performs well with different types of damage.

In this paper, a novel method is proposed for detecting and localizing structural damage by classifying acceleration responses of a structure using a long short-term memory (LSTM) network. Windows of samples are extracted from acceleration responses in a novel data pre-processing pipeline, and an LSTM network is developed to classify the signals into multiple classes. A predicted classification of a signal by the LSTM network into one of the damage levels indicates a damage detection. Furthermore, multiple signals obtained from the vibration sensors placed on a structure are provided as input to the LSTM model, and the resulting predicted class probabilities are used to identify the locations with high probability of damage. The proposed method is validated on the experimental setup of the Qatar University Grandstand Simulator (QUGS) for binary classification, as well as, full-scale study of the Z24 bridge benchmark data for multi-class damage classification. Experiments show that the proposed LSTM-based method performs on par with 1D convolutional neural networks (1D CNN) on the QUGS dataset, and outperforms the 1D CNN on the Z24 dataset. The novelty of this study lies in the use of recurrent neural network based LSTM for vibration data for multi-class damage identification and localization.

In this paper, a novel method is proposed based on windowed-one dimensional convolutional neural network for multiclass damage detection using acceleration responses. The data is pre-processed and augmented by extracting samples of windows of the original acceleration time-series. 1D CNN is developed to classify the signals in multiple classes. The damage is detected if the predicted classification is one of the indicated damage levels. The damage is quantified using the predicted class probabilities. Various signals from the accelerometers are provided as input to 1D CNN model, and the resulting class probabilities are used to identify the location of the damage. The proposed method is validated using Z24 bridge benchmark data for multiclass classification for two damage scenarios. The results show that the proposed 1D CNN methods performs with superior accuracy for severe damage cases and works well with different type of damage types.

The abstract is available in the body of the thesis.

Effective monitoring and retrofitting of large-scale infrastructure subjected to natural hazards such as strong wind, severe earthquakes or man-made excitation are critical to ensure structural integrity and prevent any premature failure. With the aid of structural health monitoring, it is now possible to acquire rich vibration data, estimate the hidden structural information, and evaluate the existing structural performance. The nonstationary component of vibration response resulting from natural hazards poses difficulty in analysis using traditional modal identification methods that are based on the stationarity assumption of vibration response. Apart from the excitation-induced nonstationarity, inherent damages in the structure also cause frequency-dependent nonstationarity in the response. With such a combination of both amplitude and frequency-dependent nonstationary response, the modal identification becomes a significantly challenging task. In this paper, Cauchy continuous wavelet transform is integrated with the tensor decomposition to track time-varying characteristics of modal responses and detect any progressive damage. The proposed technique is validated using a suite of numerical studies as well as a laboratory experiment where the progressive damage is simulated in the members by heating them using a butane torch. Unlike detection of discrete damage, the proposed method is one of introductory approaches to assess progressive damage in structures.