Electronic Thesis and Dissertation Repository

Thesis Format

Integrated Article


Doctor of Philosophy


Civil and Environmental Engineering


Sadhu, Ayan


Non-destructive testing (NDT) techniques have emerged as a valuable tool for detecting damage and evaluating the overall structural condition, leading to enhanced safety and optimized maintenance of large-scale structures. Acoustic Emission (AE) approach is one of the powerful NDT techniques that are suitable for damage detection due to its high sensitivity to localized damage. Depending on the nature of structures and loading conditions, a suite of AE parameters such as duration, signal strength, amplitude, rise time, counts, and energy indices reflect their as-is state and detect any anomalies. However, these parameters are sensitive to environmental conditions and background noise in the measured data, which often leads to misleading information (i.e., false alarms) about the existing condition of the monitored system. This thesis aims to develop a suite of improved AE waveform-based damage detection, localization and visualization approaches by employing advanced signal processing techniques and classification models. The primary aim is to revolutionize AE methods that are free of any user-defined AE parameters and do not involve manual and subjective preprocessing tasks (e.g., setting a threshold and using denoising filters). Over the course of this thesis, a suite of advanced signal processing techniques is employed to decompose the nonstationary AE waveform collected from structures using limited sensors and extract the key AE components containing damage signature. Furthermore, several classification and visualization tools are explored to detect and identify the presence of damage using denoised AE components. Overall, this research makes a paradigm shift from AE parameters-based analysis to AE waveform-based analysis by extracting the damage information directly from raw data.

When it comes to long-term monitoring of real-life structures using an AE monitoring system, it leads to massive AE data. Dealing with such big data becomes a time-consuming exercise using traditional feature extraction methods. In this thesis, a Deep Learning (DL) technique augmented with time-frequency decomposition is further explored to automate the process of damage prediction and classification by leveraging the capabilities of Artificial Intelligence. The performance of improved AE waveform-based methodologies is validated using a suite of experimental and full-scale studies. Overall, the proposed methodologies can undertake robust damage identification using time and time-frequency information of AE waveforms, making them suitable candidates for robust damage detection, classification, and visualization.

Summary for Lay Audience

Civil structures play an essential role in the economic growth and well-being of our society. However, they are subjected to damage due to exposure to unexpected loads, especially as climate change and extreme weather conditions impact aging structures. Enhancing the safety of aging structures and avoiding abnormal behavior can be achieved by adopting appropriate non-destructive techniques (NDT). Acoustic Emission (AE) approach is one of the popular NDT techniques that can be suitable for damage detection due to its high sensitivity to localized damage. Traditional parameters of measured AE signals, such as amplitude, rise time, duration, signal strength, energy, and counts, can provide valuable information about the existing condition of a monitored structure. However, dealing with traditional AE parameters can be time-consuming and computationally expensive due to the sizable amount of data and human intervention requirements. To address this challenge, there is a need for a suitable and affordable AE-based damage detection and identification tool. This doctoral thesis is focused on exploring improved AE-based approaches for structural damage identification and visualization using advanced signal processing and classification tools to analyze the time series of AE signals.

Firstly, novel signal processing methods are explored to decompose and obtain useful information from measured AE waveforms collected from structures. This approach can overcome the practical challenges associated with the traditional AE parameters-based method. Damage identification and visualization tools based on the time series response of AE waveforms are developed to identify, localize, and visualize the structural damage in various structural elements. This thesis further explores improved AE waveforms-based methodologies to enhance and automate the process of damage detection, identification, and visualization in structural elements using Deep Learning-based Artificial Intelligence techniques. The proposed methods can assess and evaluate the health and safety of structures by analyzing the time series response of AE signals collected from real-life structures.

Available for download on Thursday, May 01, 2025