MACHINE LEARNING APPROACHES FOR BRIDGE STRUCTURAL DAMAGE DETECTION AND LOCALIZATION

Most of the bridge structure monitoring systems are done by manual data processing. Monitoring is carried out only for a certain period, some of which are for a short period so the historical data is not properly collected. In addition, there is no early warning system to notify indications of da...

Full description

Saved in:
Bibliographic Details
Main Author: Aulia Akbar Kustiana, Willy
Format: Theses
Language:Indonesia
Online Access:https://digilib.itb.ac.id/gdl/view/57234
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Institut Teknologi Bandung
Language: Indonesia
id id-itb.:57234
spelling id-itb.:572342021-07-30T14:41:29ZMACHINE LEARNING APPROACHES FOR BRIDGE STRUCTURAL DAMAGE DETECTION AND LOCALIZATION Aulia Akbar Kustiana, Willy Indonesia Theses Damage detection and localization, dominant frequencies, magnitude, support vector machine, radial basis function kernel INSTITUT TEKNOLOGI BANDUNG https://digilib.itb.ac.id/gdl/view/57234 Most of the bridge structure monitoring systems are done by manual data processing. Monitoring is carried out only for a certain period, some of which are for a short period so the historical data is not properly collected. In addition, there is no early warning system to notify indications of damage. To provide information on the condition of the bridge, this study improves the existing system by utilizing certain features to detect damage and localization using a machine learning approach. The proposed system utilizes the vibrations obtained by the accelerometer-based wireless sensor nodes. The bridge acceleration data collected by the accelerometer wireless sensor node is transformed using the Fast Fourier Transform (FFT) to obtain the dominant frequencies and the appropriate magnitude as a machine learning feature. In this study, comparisons and selection of machine learning methods are also carried out to determine the most suitable method for detecting and localizing damage to bridges. The observed machine learning method is Multilayer Perceptron (MLP) classification method with the Adam optimizer and gradient descent, and the Support Vector Machine (SVM) classification method with a linear kernel and Radial Basis Function (RBF). The results were successfully tested in a bridge model, where the SVM method with the RBF kernel had the best performance with 97% accuracy and 96% precision, 97% recall rate, and 96% f1-score in terms of classifying and detecting damage and location detection. text
institution Institut Teknologi Bandung
building Institut Teknologi Bandung Library
continent Asia
country Indonesia
Indonesia
content_provider Institut Teknologi Bandung
collection Digital ITB
language Indonesia
description Most of the bridge structure monitoring systems are done by manual data processing. Monitoring is carried out only for a certain period, some of which are for a short period so the historical data is not properly collected. In addition, there is no early warning system to notify indications of damage. To provide information on the condition of the bridge, this study improves the existing system by utilizing certain features to detect damage and localization using a machine learning approach. The proposed system utilizes the vibrations obtained by the accelerometer-based wireless sensor nodes. The bridge acceleration data collected by the accelerometer wireless sensor node is transformed using the Fast Fourier Transform (FFT) to obtain the dominant frequencies and the appropriate magnitude as a machine learning feature. In this study, comparisons and selection of machine learning methods are also carried out to determine the most suitable method for detecting and localizing damage to bridges. The observed machine learning method is Multilayer Perceptron (MLP) classification method with the Adam optimizer and gradient descent, and the Support Vector Machine (SVM) classification method with a linear kernel and Radial Basis Function (RBF). The results were successfully tested in a bridge model, where the SVM method with the RBF kernel had the best performance with 97% accuracy and 96% precision, 97% recall rate, and 96% f1-score in terms of classifying and detecting damage and location detection.
format Theses
author Aulia Akbar Kustiana, Willy
spellingShingle Aulia Akbar Kustiana, Willy
MACHINE LEARNING APPROACHES FOR BRIDGE STRUCTURAL DAMAGE DETECTION AND LOCALIZATION
author_facet Aulia Akbar Kustiana, Willy
author_sort Aulia Akbar Kustiana, Willy
title MACHINE LEARNING APPROACHES FOR BRIDGE STRUCTURAL DAMAGE DETECTION AND LOCALIZATION
title_short MACHINE LEARNING APPROACHES FOR BRIDGE STRUCTURAL DAMAGE DETECTION AND LOCALIZATION
title_full MACHINE LEARNING APPROACHES FOR BRIDGE STRUCTURAL DAMAGE DETECTION AND LOCALIZATION
title_fullStr MACHINE LEARNING APPROACHES FOR BRIDGE STRUCTURAL DAMAGE DETECTION AND LOCALIZATION
title_full_unstemmed MACHINE LEARNING APPROACHES FOR BRIDGE STRUCTURAL DAMAGE DETECTION AND LOCALIZATION
title_sort machine learning approaches for bridge structural damage detection and localization
url https://digilib.itb.ac.id/gdl/view/57234
_version_ 1822002580027342848