Vibration-based damage detection using online learning algorithm for output-only structural health monitoring

2017 ◽  
Vol 17 (4) ◽  
pp. 727-746 ◽  
Author(s):  
Seung-Seop Jin ◽  
Hyung-Jo Jung
Keyword(s):  
Principal Component Analysis ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Normal Condition ◽  
Environmental Variability ◽  
Principal Component ◽  
Component Analysis ◽  
Baseline Model ◽  
Structural Health ◽  
Natural Change

Damage-sensitive features such as natural frequencies are widely used for structural health monitoring; however, they are also influenced by the environmental condition. To address the environmental effect, principal component analysis is widely used. Before performing principal component analysis, the training data should be defined for the normal condition (baseline model) under environmental variability. It is worth noting that the natural change of the normal condition may exist due to an intrinsic behavior of the structural system. Without accounting for the natural change of the normal condition, numerous false alarms occur. However, the natural change of the normal condition cannot be known in advance. Although the description of the normal condition has a significant influence on the monitoring performance, it has received much less attention. To capture the natural change of the normal condition and detect the damage simultaneously, an adaptive statistical process monitoring using online learning algorithm is proposed for output-only structural health monitoring. The novelty aspect of the proposed method is the adaptive learning capability by moving the window of the recent samples (from normal condition) to update the baseline model. In this way, the baseline model can reflect the natural change of the normal condition in environmental variability. To handle both change rate of the normal condition and non-linear dependency of the damage-sensitive features, a variable moving window strategy is also proposed. The variable moving window strategy is the block-wise linearization method using k-means clustering based on Linde–Buzo–Gray algorithm and Bayesian information criterion. The proposed method and two existing methods (static linear principal component analysis and incremental linear principal component analysis) were applied to a full-scale bridge structure, which was artificially damaged at the end of the long-term monitoring. Among the three methods, the proposed method is the only successful method to deal with the non-linear dependency among features and detect the structural damage timely.

Strukturüberwachung von Straßenbrücken durch Bauwerksmonitoring – Teil 2: Anomalieerkennung mittels Hauptkomponentenanalyse/Structural health monitoring of road bridges – Part 2: Anomaly detection with principal component analysis

Bauingenieur ◽  
2021 ◽  
Vol 96 (10) ◽  
pp. 349-357
Author(s):  
Andreas Jansen ◽  
Karsten Geißler
Keyword(s):  
Principal Component Analysis ◽  
Structural Health Monitoring ◽  
Anomaly Detection ◽  
Health Monitoring ◽  
Principal Component ◽  
Component Analysis ◽  
Structural Health

Die messtechnische Strukturüberwachung von Brücken hat das Potenzial, sich langfristig als wichtiges ergänzendes Instrument zur kontinuierlichen Zustandsbewertung zu etablieren. Die jüngere Forschung auf diesem Gebiet setzt verstärkt auf Signalmerkmale unterschiedlicher Sensortypen sowie auf Methoden des maschinellen Lernens. Daran anknüpfend wird im Teil 2 dieses Aufsatzes erläutert, wie Bauwerksschäden mithilfe der Anomalieerkennung mit Modellen des maschinellen Lernens identifiziert werden können. Im Teil 1 wurde dazu ein Signalmerkmal vorgestellt, das auf Einflusslinien basiert: die R-Signatur. Durch Simulationen kann gezeigt werden, dass die R-Signatur deutlich empfindlicher auf einen Bauwerksschaden reagiert als die betrachteten Eigenfrequenzen. Im Teil 2 wird ein Verfahren zur Anomalieerkennung beschrieben, das Bauwerksschäden durch eine Veränderung der Korrelationsstruktur der R-Signatur identifiziert. Das zugrunde liegende Datenmodell nutzt dabei die Hauptkomponentenanalyse. Der vorgestellte Ansatz wurde mit den Messdaten einer Straßenbrücke verifiziert.

Long-term guided wave structural health monitoring in an uncontrolled environment through long short-term principal component analysis

2021 ◽  
pp. 147592172110355
Author(s):  
Kang Yang ◽  
Sungwon Kim ◽  
Rongting Yue ◽  
Haotian Yue ◽  
Joel B. Harley
Keyword(s):  
Principal Component Analysis ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Principal Component ◽  
Component Analysis ◽  
Guided Wave ◽  
Mitigation Strategies ◽  
Reconstruction Method ◽  
Short Term ◽  
Structural Health

Environmental effects are a significant challenge in guided wave structural health monitoring systems. These effects distort signals and increase the likelihood of false alarms. Many research papers have studied mitigation strategies for common variations in guided wave datasets reproducible in a lab, such as temperature and stress. There are fewer studies and strategies for detecting damage under more unpredictable outdoor conditions. This article proposes a long short-term principal component analysis reconstruction method to detect synthetic damage under highly variational environments, like precipitation, freeze, and other conditions. The method does not require any temperature or other compensation methods and is tested by approximately seven million guided wave measurements collected over 2 years. Results show that our method achieves an area under curve score of near 0.95 when detecting synthetic damage under highly variable environmental conditions.

Deep principal component analysis: An enhanced approach for structural damage identification

2018 ◽  
Vol 18 (5-6) ◽  
pp. 1444-1463 ◽  
Author(s):  
Moisés Silva ◽  
Adam Santos ◽  
Reginaldo Santos ◽  
Eloi Figueiredo ◽  
Claudomiro Sales ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Structural Health Monitoring ◽  
Environmental Factors ◽  
Damage Detection ◽  
Health Monitoring ◽  
Principal Component ◽  
Component Analysis ◽  
Data Normalization ◽  
Structural Health ◽  
Detection And Quantification

The structural health monitoring relies on the continuous observation of a dynamic system over time to identify its actual condition, detect abnormal behaviors, and predict future states. The regular changes in environmental factors have been reported as one of the main challenges for the application of structural health monitoring systems. These influences in the structural responses are in general nonlinear, affecting the damage-sensitive features in the most varied forms. The usual process to remove these normal changes is referred to as data normalization. In that regard, principal component analysis is probably the most studied algorithm in structural health monitoring, having numerous versions to learn strong nonlinear normal changes. However, in most cases, not all variability is properly accounted for via the existing nonlinear principal component analysis approaches, resulting in poor damage detection and quantification performances. In this article, a new paradigm based on deep principal component analysis, rooted in the deep learning field, is presented to overcome these limitations. This approach extracts the most salient underlying feature distributions by stacking multiple feedforward neural networks trained to learn an identity mapping of the input variables, where the network inputs are reproduced into the outputs. Similar to the traditional nonlinear principal component analysis–based approach, our approach identifies a nonlinear output-only model of an undamaged structure by comprising modal features into an internal bottleneck layer, which implicitly represents the independent environmental factors. The proposed technique is validated through the application on a progressively damaged prestressed concrete bridge and a three-span suspension bridge. The experimental results demonstrate that capturing the most slight nonlinear variations in the data can lead to improved data normalization and, consequently, better damage detection and quantification performances.

scholarly journals A framework for data compression and damage detection in structural health monitoring applied on a laboratory three-story structure

2016 ◽  
Vol 8 (2) ◽  
pp. 129
Author(s):  
Manoel Afonso Pereira de Lima ◽  
Claudomiro Sales ◽  
Adam Santos ◽  
Reginaldo Santos ◽  
Moisés Silva ◽  
...  
Keyword(s):  
Structural Health Monitoring ◽  
Damage Detection ◽  
Data Compression ◽  
Health Monitoring ◽  
Principal Component ◽  
Component Analysis ◽  
Strong Impact ◽  
Story Structure ◽  
Compression Algorithms ◽  
Structural Health

Structural Health Monitoring (SHM) is an important technique used to preserve many types of structures in the short and long run, using sensor networks to continuously gather the desired data. However, this causes a strong impact in the data size to be stored and processed. A common solution to this is using compression algorithms, where the level of data compression should be adequate enough to allow the correct damage identification. In this work, we use the data sets from a laboratory three-story structure to evaluate the performance of common compression algorithms which, then, are combined with damage detection algorithms used in SHM. We also analyze how the use of Independent Component Analysis, a common technique to reduce noise in raw data, can assist the detection performance. The results showed that Piecewise Linear Histogram combined with Nonlinear PCA have the best trade-off between compression and detection for small error thresholds while Adaptive PCA with Principal Component Analysis perform better with higher values.

scholarly journals Vibration-Based Structural Health Monitoring Using Piezoelectric Transducers and Parametric t-SNE

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1716
Author(s):  
David Agis ◽  
Francesc Pozo
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Structural Changes ◽  
Computational Cost ◽  
Principal Component ◽  
Piezoelectric Transducers ◽  
Majority Voting ◽  
Structural Health

In this paper, we evaluate the performance of the so-called parametric t-distributed stochastic neighbor embedding (P-t-SNE), comparing it to the performance of the t-SNE, the non-parametric version. The methodology used in this study is introduced for the detection and classification of structural changes in the field of structural health monitoring. This method is based on the combination of principal component analysis (PCA) and P-t-SNE, and it is applied to an experimental case study of an aluminum plate with four piezoelectric transducers. The basic steps of the detection and classification process are: (i) the raw data are scaled using mean-centered group scaling and then PCA is applied to reduce its dimensionality; (ii) P-t-SNE is applied to represent the scaled and reduced data as 2-dimensional points, defining a cluster for each structural state; and (iii) the current structure to be diagnosed is associated with a cluster employing two strategies: (a) majority voting; and (b) the sum of the inverse distances. The results in the frequency domain manifest the strong performance of P-t-SNE, which is comparable to the performance of t-SNE but outperforms t-SNE in terms of computational cost and runtime. When the method is based on P-t-SNE, the overall accuracy fluctuates between 99.5% and 99.75%.

scholarly journals Structural Health Monitoring under Nonlinear Environmental or Operational Influences

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Jyrki Kullaa
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Linear Models ◽  
Nonlinear Models ◽  
Novelty Detection ◽  
Minimum Mean Square Error ◽  
Simulated Data ◽  
Principal Component ◽  
Gaussian Mixture ◽  
Structural Health

Vibration-based structural health monitoring is based on detecting changes in the dynamic characteristics of the structure. It is well known that environmental or operational variations can also have an influence on the vibration properties. If these effects are not taken into account, they can result in false indications of damage. If the environmental or operational variations cause nonlinear effects, they can be compensated using a Gaussian mixture model (GMM) without the measurement of the underlying variables. The number of Gaussian components can also be estimated. For the local linear components, minimum mean square error (MMSE) estimation is applied to eliminate the environmental or operational influences. Damage is detected from the residuals after applying principal component analysis (PCA). Control charts are used for novelty detection. The proposed approach is validated using simulated data and the identified lowest natural frequencies of the Z24 Bridge under temperature variation. Nonlinear models are most effective if the data dimensionality is low. On the other hand, linear models often outperform nonlinear models for high-dimensional data.

scholarly journals Cointegration: a novel approach for the removal of environmental trends in structural health monitoring data

2011 ◽  
Vol 467 (2133) ◽  
pp. 2712-2732 ◽  
Author(s):  
Elizabeth J. Cross ◽  
Keith Worden ◽  
Qian Chen
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Environmental Variability ◽  
Stationary Time Series ◽  
New Approach ◽  
Operational Conditions ◽  
Structural Health ◽  
Original Dataset ◽  
Novel Approach ◽  
Static Responses

Before structural health monitoring (SHM) technologies can be reliably implemented on structures outside laboratory conditions, the problem of environmental variability in monitored features must be first addressed. Structures that are subjected to changing environmental or operational conditions will often exhibit inherently non-stationary dynamic and quasi-static responses, which can mask any changes caused by the occurrence of damage. The current work introduces the concept of cointegration , a tool for the analysis of non-stationary time series, as a promising new approach for dealing with the problem of environmental variation in monitored features. If two or more monitored variables from an SHM system are cointegrated, then some linear combination of them will be a stationary residual purged of the common trends in the original dataset. The stationary residual created from the cointegration procedure can be used as a damage-sensitive feature that is independent of the normal environmental and operational conditions.

Sign in / Sign up

Export Citation Format

Share Document