Feature Extraction and Selection from Vibration Measurements for Structural Health Monitoring

2009 ◽  
pp. 213-224 ◽  
Author(s):  
Janne Toivola ◽  
Jaakko Hollmén
Keyword(s):  
Feature Extraction ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Vibration Measurements ◽  
Structural Health ◽  
Feature Extraction And Selection

scholarly journals Train Speed Estimation from Track Structure Vibration Measurements

2020 ◽  
Vol 10 (14) ◽  
pp. 4742
Author(s):  
Xinyue Wang ◽  
Xianfeng Shi ◽  
Jialiang Wang ◽  
Xun Yu ◽  
Baoguo Han
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Geometrical Parameters ◽  
Track Structure ◽  
Speed Estimation ◽  
Vibration Measurements ◽  
Structural Health ◽  
Treatment Techniques ◽  
Train Speed ◽  
Structure Vibration

This paper proposes a new method for train speed estimation from track structure vibration measurements for field track structural health monitoring. This method employed image treatment techniques, wavelet transform, and short-time Fourier transform into the signal processing. Afterward, the train speed was estimated by the combination of the extracted features and the geometrical parameters of the passing trains. A total of 240 measurements, gotten from 20 trains measured by 12 sensors, were implemented to verify the effectiveness and practicability of the proposed method. The results showed that the average differences of the train speed calculating by phase differences and the proposed method were 0.61% for slab displacement measurements, 1.39% for rail acceleration measurements, and 2.97% for slab acceleration measurements, respectively. Furthermore, the proposed method was proved to be effective in different test locations and track structure state. Therefore, it is concluded that the proposed method can estimate train speed from the vibration measurements automatically, reliably, and in real time with no need for additional speed measurement modules, which meets the requirement of speed estimation in the short-term, multi-location, and tough environment of structural health monitoring.

scholarly journals Big Data Analytics and Structural Health Monitoring: A Statistical Pattern Recognition-Based Approach

Sensors ◽  
2020 ◽  
Vol 20 (8) ◽  
pp. 2328 ◽  
Author(s):  
Alireza Entezami ◽  
Hassan Sarmadi ◽  
Behshid Behkamal ◽  
Stefano Mariani
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Big Data ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Statistical Pattern Recognition ◽  
Statistical Decision ◽  
Structural Health ◽  
Statistical Pattern ◽  
Arma Modeling

Recent advances in sensor technologies and data acquisition systems opened up the era of big data in the field of structural health monitoring (SHM). Data-driven methods based on statistical pattern recognition provide outstanding opportunities to implement a long-term SHM strategy, by exploiting measured vibration data. However, their main limitation, due to big data or high-dimensional features, is linked to the complex and time-consuming procedures for feature extraction and/or statistical decision-making. To cope with this issue, in this article we propose a strategy based on autoregressive moving average (ARMA) modeling for feature extraction, and on an innovative hybrid divergence-based method for feature classification. Data relevant to a cable-stayed bridge are accounted for to assess the effectiveness and efficiency of the proposed method. The results show that the offered hybrid divergence-based method, in conjunction with ARMA modeling, succeeds in detecting damage in cases strongly characterized by big data.

Fast unsupervised learning methods for structural health monitoring with large vibration data from dense sensor networks

2019 ◽  
Vol 19 (6) ◽  
pp. 1685-1710 ◽  
Author(s):  
Alireza Entezami ◽  
Hashem Shariatmadar ◽  
Stefano Mariani
Keyword(s):  
Feature Extraction ◽  
Structural Health Monitoring ◽  
Probability Measure ◽  
Health Monitoring ◽  
Damage Localization ◽  
Order Selection ◽  
Computational Burden ◽  
Structural Health ◽  
Leibler Divergence ◽  
Empirical Probability

Data-driven damage localization is an important step of vibration-based structural health monitoring. Statistical pattern recognition based on the prominent steps of feature extraction and statistical decision-making provides an effective and efficient framework for structural health monitoring. However, these steps may become time-consuming or complex when there are large volumes of vibration measurements acquired by dense sensor networks. To deal with this issue, this study proposes fast unsupervised learning methods for feature extraction through autoregressive modeling and damage localization through a new distance measure called Kullback–Leibler divergence with empirical probability measure. The feature extraction approach consists of an iterative algorithm for order selection and parameter estimation aiming to extract residuals in the training phase and another iterative process aiming to extract residuals only in the monitoring phase. The key feature of the proposed approach is the use of correlated residual samples of the autoregressive model as a new time series at each iteration, rather than handling the measured vibration response of the structure. This is shown to highly reduce the computational burden of order selection and feature extraction; moreover, it effectively provides low-order autoregressive models with uncorrelated residuals. The Kullback–Leibler divergence with empirical probability measure method exploits a segmentation technique to subdivide random data into independent sets and provides a distance metric based on the theory of empirical probability measure with no need to explicitly compute the actual probability distributions at the training and monitoring stages. Numerical and experimental benchmarks are then used to assess accuracy and performance of the proposed methods and compare them with some state-of-the-art approaches. Results show that the proposed approaches are successful in feature extraction and damage localization, with a reduced computational burden.

Feature extraction approach insensitive to temperature variations for impedance-based structural health monitoring

2019 ◽  
Vol 13 (4) ◽  
pp. 536-543 ◽  
Author(s):  
Fernando de Souza Campos ◽  
Bruno Albuquerque de Castro ◽  
Danilo Ecidir Budoya ◽  
Fabricio Guimarães Baptista ◽  
José Alfredo Covolan Ulson ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Temperature Variations ◽  
Structural Health

Schwingungsuntersuchungen mit dem Smartphone und Tablet/Vibration measurements and analysis with smartphones and tablet PCs

Bauingenieur ◽  
2017 ◽  
Vol 92 (05) ◽  
pp. 200-211
Author(s):  
C. Kögel ◽  
P. Agne ◽  
A. Feldbusch ◽  
H. Sadegh-Azar
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Mobile App ◽  
Vibration Measurements ◽  
Structural Health ◽  
Tablet Pcs

Die heute gängigen Smartphones und Tablets besitzen in der Regel leistungsstarke Schwingungssensoren, welche für schwingungstechnische Untersuchungen genutzt werden können. Am Fachgebiet Statik und Dynamik der Tragwerke der TU Kaiserslautern, wurde hierfür speziell eine entsprechende App „iDynamics“ entwickelt und erprobt. Mit dieser App können beliebige Schwingungs- und Erschütterungsmessungen und Systemidentifikationsanalysen (z. B. Bestimmung der Frequenz und Dämpfung) durchgeführt werden. Zudem kann die App für eine Zustandsüberwachung der Struktur „Structural Health Monitoring“ eingesetzt werden. Somit können Änderungen der dynamischen Eigenschaften der Struktur detektiert und ausgewertet werden. In diesem Beitrag werden die schwingungstechnischen Eigenschaften der Sensoren gängiger Smartphones und Tablets analysiert und mit professionellen Schwingungssensoren verglichen. Im Anschluss wird die sachgerechte Anwendung der App demonstriert und die Parameter und Rahmenbedingungen für eine zuverlässige Schwingungsuntersuchung ermittelt. Anhand zahlreicher Anwendungsfälle aus der Praxis werden die Einsatzmöglichkeiten eruiert und die Ergebnisse mit denen aus professionellen Schwingungsuntersuchungen verglichen. Die App ermöglicht und eignet sich für den Einsatz in der „Forschenden Lehre“. Mit der App wird die Grundlage für ein experimentelles dynamisches Labor als mobile App für Studierende verschiedener Fachrichtungen (u. a. Bauingenieurwesen und Maschinenbau) geschaffen. In der breiten Öffentlichkeit kann die App als Tool für grobe Schwingungs- und Erschütterungsmessungen eingesetzt werden, um zum Beispiel. eine Überschreitung der zulässigen Erschütterung in Gebäuden an Gleisanlagen, neben viel befahrenen Straßen oder am Arbeitsplatz (z. B. in Industrieanlagen oder auf dem Lkw) zu beurteilen.

Sign in / Sign up

Export Citation Format

Share Document