Semi-active Damage Identification for a Composite Structural Missile Component using Minimal Passive Sensing with Data-driven Models

Structural health monitoring methods are broadly classified into two categories: data-driven methods via statistical pattern recognition and physics-based methods through finite elementmodel updating. Data-driven structural health monitoring faces the challenge of data insufficiency that renders the learned model limited in identifying damage scenarios that are not contained in the training data. Model-based methods are susceptible to modeling error due to model idealizations and simplifications that make the finite element model updating results deviate from the truth. This study attempts to combine the merits of data-driven and physics-based structural health monitoring methods via physics-guided machine learning, expecting that the damage identification performance can be improved. Physics-guided machine learning uses observed feature data with correct labels as well as the physical model output of unlabeled instances. In this study, physics-guided machine learning is realized with a physics-guided neural network. The original modal-property based features are extended with the damage identification result of finite element model updating. A physics-based loss function is designed to evaluate the discrepancy between the neural network model output and that of finite element model updating. With the guidance from the scientific knowledge contained in finite element model updating, the learned neural network model has the potential to improve the generality and scientific consistency of the damage detection results. The proposed methodology is validated by a numerical case study on a steel pedestrian bridge model and an experimental study on a three-story building model.

Download Full-text

Data-driven damage identification technique for steel truss railroad bridges utilizing principal component analysis of strain response

Structure and Infrastructure Engineering ◽

10.1080/15732479.2020.1785512 ◽

2020 ◽

pp. 1-17

Author(s):

Md Riasat Azim ◽

Mustafa Gül

Keyword(s):

Principal Component Analysis ◽

Damage Identification ◽

Principal Component ◽

Component Analysis ◽

Data Driven ◽

Strain Response ◽

Railroad Bridges ◽

Steel Truss ◽

Identification Technique

Download Full-text

The application of machine learning to structural health monitoring

Philosophical Transactions of The Royal Society A Mathematical Physical and Engineering Sciences ◽

10.1098/rsta.2006.1938 ◽

2006 ◽

Vol 365 (1851) ◽

pp. 515-537 ◽

Cited By ~ 163

Author(s):

Keith Worden ◽

Graeme Manson

Keyword(s):

Machine Learning ◽

Normal Condition ◽

Damage Identification ◽

Measured Data ◽

Data Driven ◽

High Fidelity ◽

Element Analysis ◽

Model Driven ◽

Statistical Representation ◽

Data Driven Approach

In broad terms, there are two approaches to damage identification. Model-driven methods establish a high-fidelity physical model of the structure, usually by finite element analysis, and then establish a comparison metric between the model and the measured data from the real structure. If the model is for a system or structure in normal (i.e. undamaged) condition, any departures indicate that the structure has deviated from normal condition and damage is inferred. Data-driven approaches also establish a model, but this is usually a statistical representation of the system, e.g. a probability density function of the normal condition. Departures from normality are then signalled by measured data appearing in regions of very low density. The algorithms that have been developed over the years for data-driven approaches are mainly drawn from the discipline of pattern recognition, or more broadly, machine learning. The object of this paper is to illustrate the utility of the data-driven approach to damage identification by means of a number of case studies.

Download Full-text

A Data-Driven Damage Identification Framework Based on Transmissibility Function Datasets and One-Dimensional Convolutional Neural Networks: Verification on a Structural Health Monitoring Benchmark Structure

Sensors ◽

10.3390/s20041059 ◽

2020 ◽

Vol 20 (4) ◽

pp. 1059 ◽

Cited By ~ 7

Author(s):

Tongwei Liu ◽

Hao Xu ◽

Minvydas Ragulskis ◽

Maosen Cao ◽

Wiesław Ostachowicz

Keyword(s):

Neural Networks ◽

Structural Health Monitoring ◽

Convolutional Neural Networks ◽

Health Monitoring ◽

Damage Identification ◽

Data Driven ◽

Intelligent Algorithms ◽

One Dimensional ◽

Structural Health ◽

Computation Efficiency

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.

Download Full-text

Data interpretation framework integrating machine learning and pattern recognition for self-powered data-driven damage identification with harvested energy variations

Engineering Applications of Artificial Intelligence ◽

10.1016/j.engappai.2019.08.004 ◽

2019 ◽

Vol 86 ◽

pp. 136-153 ◽

Cited By ~ 2

Author(s):

Hadi Salehi ◽

Subir Biswas ◽

Rigoberto Burgueño

Keyword(s):

Machine Learning ◽

Pattern Recognition ◽

Damage Identification ◽

Data Interpretation ◽

Data Driven ◽

Self Powered

Download Full-text

Methodologies of Damage Identification Using Non-Linear Data-Driven Modelling

Encyclopedia of Information Science and Technology, Third Edition ◽

10.4018/978-1-4666-5888-2.ch093 ◽

2015 ◽

pp. 978-991

Author(s):

Miguel Angel Torres Arredondo ◽

Diego Alexander Tibaduiza Burgos ◽

Inka Buethe ◽

Luis Eduardo Mujica ◽

Maribel Anaya Vejar ◽

...

Keyword(s):

Damage Identification ◽

Data Driven ◽

Non Linear

Download Full-text

A Principal Strain Data-Driven Method for Damage Identification of an Offshore Pile Structure

Volume 2A: Structures, Safety, and Reliability ◽

10.1115/omae2020-19284 ◽

2020 ◽

Author(s):

Xingxian Bao ◽

Guanlan Yang ◽

Hongwei Li ◽

Chen Shi

Keyword(s):

Structural Damage ◽

Damage Identification ◽

Time History ◽

Data Driven ◽

Principal Strain ◽

Detection Methods ◽

Strain Response ◽

Marine Structures ◽

Strain Data ◽

Principal Strains

Abstract Vibration-based damage identification technique, categorized as parametric and nonparametric methods, plays an important role in guaranteeing the success of offshore operations and the integrity management of marine structures. In the parametric approaches, modal parameters and their derivative are usually applied to obtain the damage-sensitive features. Nevertheless, there are still some challenging problems for the parametric method in application. Nonparametric (data-driven) approaches are aim to extract damage sensitive features directly from the measured data. For the data-driven approaches, it is vital to find which indicator derived from the response signal is sensitive to structural damage. Considering the derivatives of strain are more sensitive to small structural damage than that of displacement, the strain-related damage detection methods have currently gotten more attention. In this study, a principal strain data-driven method is proposed, which is derived from strain energy dispersion theory and directly employs the time history data of three principal strains of an intact and damaged structure to construct the damage identification indicator. The efficiency of the method is validated by a numerical offshore pile structure with several damage cases considering noise scenarios. Due to the difficulty of determine the correct three principal strains in the real experimental measurements, the approximation damage indicators are constructed based on one, two or three kinds of strain response among the axial, radial and hoop strains response, instead of the three principal strains response. The results show that satisfying damage identification results can still be gotten for both the single- and multiple-damage scenarios using only axial or hoop strain response even under noise conditions. The proposed principal strain data-driven damage identification method can be used as a viable and effective technique for damage localization and severity estimation of marine structures.

Download Full-text