Abstract
Vibration-based data-driven structural damage identification methods have gained large popularity because of their independence of high-fidelity models of target systems. However, the effectiveness of existing methods is constrained by critical shortcomings. For example, the measured vibration responses may contain insufficient damage-sensitive features and suffer from high instability under the interference of random excitations. Moreover, the capability of conventional intelligent algorithms in damage feature extraction and noise influence suppression is limited. To address the above issues, a novel damage identification framework was established in this study by integrating massive datasets constructed by structural transmissibility functions (TFs) and a deep learning strategy based on one-dimensional convolutional neural networks (1D CNNs). The effectiveness and efficiency of the TF-1D CNN framework were verified using an American Society of Civil Engineers (ASCE) structural health monitoring benchmark structure, from which dynamic responses were captured, subject to white noise random excitations and a number of different damage scenarios. The damage identification accuracy of the framework was examined and compared with others by using different dataset types and intelligent algorithms. Specifically, compared with time series (TS) and fast Fourier transform (FFT)-based frequency-domain signals, the TF signals exhibited more significant damage-sensitive features and stronger stability under excitation interference. The utilization of 1D CNN, on the other hand, exhibited some unique advantages over other machine learning algorithms (e.g., traditional artificial neural networks (ANNs)), particularly in aspects of computation efficiency, generalization ability, and noise immunity when treating massive, high-dimensional datasets. The developed TF-1D CNN damage identification framework was demonstrated to have practical value in future applications.
Highlights
As an important topic in the field of structural health monitoring, vibration-based data-driven structural damage identification has been attracting increasing research interest in recent years [1,2,3,4,5]
This study presents a novel damage identification framework, wherein massive datasets consisting of a large number of transmissibility functions (TFs) signals are constructed and used as inputs to a 1D convolution neural network (CNN) model designed to extract signal features in an adaptive and efficient manner
Technology, which visualizes high-dimensional data by giving each datapoint a location in a two- or using 1D CNN show a significant tendency to cluster and can be distinguished to be associated accurately with their corresponding structural health states. It can be concluded from the visualization results that significant damage-associated features were included in the TF signals and, on the other hand, the 1D CNN is capable of extracting damage features contained in a TF signal with
Summary
One-Dimensional Convolutional Neural Networks: Verification on a Structural Health Monitoring. Tongwei Liu 1 , Hao Xu 2,3 , Minvydas Ragulskis 4 , Maosen Cao 1, * and Wiesław Ostachowicz 5. Received: 13 January 2020; Accepted: 13 February 2020; Published: 15 February 2020
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have