10 December 2019 in Smart Materials and Structures
In this paper, convolutional neural network (CNN) is employed for crack damage detection in thin aluminum plates. Identifying a successful damage feature is a critical step in computationally efficient damage detection and characterization process; however, such feature identification process is generally time-consuming and often difficult to execute. The CNN model is a deep learning model that can be trained to represent high dimensional data for which traditional mathematical model is ill to describe. This study first formalizes the nondestructive evaluation (NDE) problem of notch-type crack damage detection in thin metal plates into an image classification problem in the machine learning domain, which is then solved with a deep CNN model trained using Lamb wave data converted images. Analytical formulas have been derived for generating Lamb wave signals subsequently used for training and validation test of the proposed crack damage detection technique for thin metal plates. Experimental test data from aluminum plate with simulated notch damage has also been used to independently validate the CNN model. The study results show its potential as a promising NDE tool for crack damage detection in thin plate structures.
21 January 2020 in Structure and Infrastructure Engineering
This paper presents a deep learning-based bridge condition rating data modeling approach using selected data from the National Bridge Inventory (NBI) database. The objective of this research is to develop a data-driven approach that enables prediction of future conditions of highway bridge components from historical inspection data. The problem is solved by training a Convolutional Neural Network (CNN) model with online available NBI data. One prominent feature of the CNN model is that if well-trained it can represent the high dimensional data in the dataset abstractions for which conventional mathematical models may be difficult to describe. A case study of Maryland and Delaware highway bridges using historical data (1992–2017) sourced from the NBI database has been performed to demonstrate the proposed method. CNN models for three primary components of these highway bridges including the deck, superstructure, and substructure have been established. Optimization of model parameters is achieved through a parametric study. Research findings suggest that the deep learning model offers a promising tool as a data-driven condition forecasting approach for bridge components with a demonstrated prediction accuracy over 85%.
1 February 2019 in Measurement
1 October 2018 in Journal of Constructional Steel Research
21 September 2021 in Structure and Infrastructure Engineering
This paper presents a deep learning-aided deterioration modeling approach for highway bridge components (i.e., decks, superstructures, and substructures). The method trains a set of deep learning models for the maximum likelihood estimation of parameters in a Markov chain. The likelihood function is based on observed numbers of transitions between different condition states. The deep learning is leveraged for efficient representation of various factors that influence the deterioration process. Aided by deep learning, the proposed method is suitable for deterioration modeling using large-scale and high-dimensional bridge datasets. The study demonstrates an application of this approach using the historical National Bridge Inventory database from 1993 to 2019. The Convolutional Neural Network is adopted as the deep learning model. The proposed method is validated with ten-fold cross-validation that encompasses a nationwide selection of 88,596, 101,414, and 96,244 bridge decks, superstructures, and substructures, respectively. The validation shows this approach achieved a robust and low prediction error with the maximum mean-squared-error near 0.5 in a 26-years-forecast. The proposed method is also compared with the conventional Artificial Neural Network and four selected Markov-chain based deterioration modeling approaches. The study shows this approach can be a promising data-driven tool for deterioration modeling of highway bridge components.
23 February 2022 in Separation and Purification Technology