scholarly journals Embedding principal component analysis for data reduction in structural health monitoring on low-cost IoT gateways

2019 ◽  
Author(s):  
Alessio Burrello ◽  
Alex Marchioni ◽  
Davide Brunelli ◽  
Luca Benini
Keyword(s):  
Principal Component Analysis ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Data Reduction ◽  
Low Cost ◽  
Principal Component ◽  
Component Analysis ◽  
Structural Health

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.

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.

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 Advances in the Structural Health Monitoring of Bridges Using Piezoelectric Transducers

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4312 ◽  
Author(s):  
Yunzhu Chen ◽  
Xingwei Xue
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Piezoelectric Materials ◽  
Low Cost ◽  
Rapid Development ◽  
Concrete Strength ◽  
Steel Corrosion ◽  
Fast Response ◽  
Future Application ◽  
Structural Health

With the rapid development of the world’s transportation infrastructure, many long-span bridges were constructed in recent years, especially in China. However, these bridges are easily subjected to various damages due to dynamic loads (such as wind-, earthquake-, and vehicle-induced vibration) or environmental factors (such as corrosion). Therefore, structural health monitoring (SHM) is vital to guarantee the safety of bridges in their service lives. With its wide frequency response range, fast response, simple preparation process, ease of processing, low cost, and other advantages, the piezoelectric transducer is commonly employed for the SHM of bridges. This paper summarizes the application of piezoelectric materials for the SHM of bridges, including the monitoring of the concrete strength, bolt looseness, steel corrosion, and grouting density. For each problem, the application of piezoelectric materials in different research methods is described. The related data processing methods for four types of bridge detection are briefly summarized, and the principles of each method in practical application are listed. Finally, issues to be studied when using piezoelectric materials for monitoring are discussed, and future application prospects and development directions are presented.

scholarly journals Reliable Data Acquisition System for a Low-Cost Accelerograph Applied to Structural Health Monitoring

2020 ◽  
Vol 3 (2) ◽  
pp. 181-194
Author(s):  
Milton Muñoz ◽  
Remigio Guevara ◽  
Santiago González ◽  
Juan Carlos Jiménez
Keyword(s):  
Structural Health Monitoring ◽  
Data Acquisition ◽  
Health Monitoring ◽  
Seismic Event ◽  
Low Cost ◽  
Recording System ◽  
Continuous Recording ◽  
Remote Communication ◽  
Structural Health ◽  
Hydroelectric Dam

This paper presents and evaluates a continuous recording system designed for a low-cost seismic station. The architecture has three main blocks. An accelerometer sensor based on MEMS technology (Microelectromechanical Systems), an SBC platform (Single Board Computer) with embedded Linux and a microcontroller device. In particular, the microcontroller represents the central component which operates as an intermediate agent to manage the communication between the accelerometer and the SBC block. This strategy allows the system for data acquisition in real time. On the other hand, the SBC platform is used for storing and processing data as well as in order to configure the remote communication with the station. This proposal is intended as a robust solution for structural health monitoring (i.e. in order to characterize the response of an infrastructure before, during and after a seismic event). The paper details the communication scheme between the system components, which has been minutely designed to ensure the samples are collected without information loss. Furthermore, for the experimental evaluation the station was located in the facilities on a relevant infrastructure, specifically a hydroelectric dam. The system operation was compared and verified with respect to a certified accelerograph station. Results prove that the continuous recording system operates successfully and allows for detecting seismic events according to requirements of structural health applications (i.e. detects events with a frequency of vibration less than 100 Hz). Specifically, through the system implemented it was possible to characterize the effect of a seismic event of 4 MD reported by the regional seismology network and with epicenter located about 30 Km of the hydroelectric dam. Particularly, the vibration frequencies detected on the infrastructure are in the range of 13 Hz and 29 Hz. Regarding the station performance, results from experiments reveals an average CPU load of 51%, consequently the processes configured on the SBC platform do not involve an overload. Finally, the average energy consumption of the station is close to 2.4 W, therefore autonomy provided by the backup system is aroud of 10 hours.

scholarly journals Structural reliability assessment based on optical monitoring system: case study

2016 ◽  
Vol 9 (2) ◽  
pp. 297-305 ◽  
Author(s):  
E. Mesquita ◽  
P. Antunes ◽  
A. A. Henriques ◽  
A. Arêde ◽  
P. S. André ◽  
...  
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Structural Reliability ◽  
Extreme Values ◽  
Low Cost ◽  
Reliability Assessment ◽  
Water Reservoir ◽  
Optical Systems ◽  
Structural Health

ABSTRACT Optical systems are recognized to be an important tool for structural health monitoring, especially for real time safety assessment, due to simplified system configuration and low cost when compared to regular systems, namely electrical systems. This work aims to present a case study on structural health monitoring focused on reliability assessment and applying data collected by a simplified optical sensing system. This way, an elevated reinforced concrete water reservoir was instrumented with a bi-axial optical accelerometer and monitored since January 2014. Taking into account acceleration data, the natural frequencies and relative displacements were estimated. The reliability analysis was performed based on generalized extreme values distribution (GEV) and the results were employed to build a forecast of the reliability of the water elevated reservoir for the next 100 years. The results showed that the optical system combined with GEV analysis, implemented in this experimental work, can provide adequate data for structural reliability assessment.

Sign in / Sign up

Export Citation Format

Share Document