A Bayesian non-parametric clustering approach for semi-supervised Structural Health Monitoring

Rogers, Timothy J.; Worden, Keith; Fuentes, Ramón; Dervilis, Nikolaos; Tygesen, Ulf T.; Cross, Elizabeth J.

doi:10.1016/j.ymssp.2018.09.013

Cited by 76 publications

(49 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite their success, a significant issue with supervised methods for feature extraction is their dependence on labelled data. This renders their application irrelevant for many practical SHM systems, which look to run online, with limited data, and in an adaptive manner [13,29]. Furthermore, these problems highlight the need for an alternative approach to feature selection/extraction with high-dimensional engineering data, when conventional unsupervised techniques prove unsuitable.…”

Section: Conventional Methods: Feature Selection and Dimension Reductionmentioning

confidence: 99%

“…transmissiblities or frequency response functions) are often high-dimensional. Considering the curse of dimensionality, an impracticable number of observations are required to build a reliable statistical model; therefore, the high-dimensionality of measured data remains a major issue for vibration monitoring [2,7,8] -particularly systems that hope to run online [29]. Conventional engineering techniques, applied to compress high-dimensional data, are summarised below.…”

Section: Outlier Analysis In High-dimensional Feature Spacementioning

confidence: 99%

“…In real settings, it is infeasable to collect data relating to the damaged states before an SHM system is built. Furthermore, more practical methods (that run online, or use limited labelling [13,29]) can only include the new information from novel data once they are discovered.…”

Section: Case Study Ii: Dimension Reduction -Gnat Aircraft Datamentioning

confidence: 99%

See 2 more Smart Citations

Outlier ensembles: A robust method for damage detection and unsupervised feature extraction from high-dimensional data

Bull

Worden

Fuentes

et al. 2019

Journal of Sound and Vibration

Self Cite

View full text Add to dashboard Cite

Section: Conventional Methods: Feature Selection and Dimension Reductionmentioning

confidence: 99%

Section: Outlier Analysis In High-dimensional Feature Spacementioning

confidence: 99%

See 1 more Smart Citation

Outlier ensembles: A robust method for damage detection and unsupervised feature extraction from high-dimensional data

Bull

Worden

Fuentes

et al. 2019

Journal of Sound and Vibration

Self Cite

View full text Add to dashboard Cite

“…Moreover, they often assume the data contains examples of every possible fault type [24]. However, such data sets are not always available in industrial environments [25,26]. In those applications, even a limited historical data set such as the [27] proposes can be challenging to obtain.…”

Section: Need For Ai-based Fleet Monitoring Approachesmentioning

confidence: 99%

A general anomaly detection framework for fleet-based condition monitoring of machines

Hendrickx

Meert

Mollet

et al. 2020

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

Machine failures decrease up-time and can lead to extra repair costs or even to human casualties and environmental pollution. Recent condition monitoring techniques use artificial intelligence in an effort to avoid time-consuming manual analysis and handcrafted feature extraction. Many of these only analyze a single machine and require a large historical data set. In practice, this can be difficult and expensive to collect. However, some industrial condition monitoring applications involve a fleet of similar operating machines. In most of these applications, it is safe to assume healthy conditions for the majority of machines. Deviating machine behavior is then an indicator for a machine fault.This work proposes an unsupervised, generic, anomaly detection framework for fleet-based condition monitoring. It uses generic building blocks and offers three key advantages. First, a historical data set is not required due to online fleet-based comparisons. Second, it allows incorporating domain expertise by user-defined comparison measures. Finally, contrary to most black-box artificial intelligence techniques, easy interpretability allows a domain expert to validate the predictions made by the framework.Two use-cases on an electrical machine fleet demonstrate the applicability of the framework to detect a voltage unbalance by means of electrical and vibration signatures.

show abstract

“…Worden et al suggested the damage detection to be addressed in the framework of outlier detection, especially in the case of low-level damage detection [21]. Rogers et al developed a Bayesian non-parametric clustering approach for damage detection [23]. Unlike damage detection, VIV happens only at some specific wind conditions, and; therefore, studies addressing the automatic detection of VIV are rather limited.…”

Section: Introductionmentioning

confidence: 99%

Automatic Identification of Bridge Vortex-Induced Vibration Using Random Decrement Method

Huang

Hua

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Vortex-induced vibration (VIV) has been occasionally observed on a few long-span steel box-girder suspension bridges. The underlying mechanism of VIV is very complicated and reliable theoretical methods for prediction of VIV have not been established yet. Structural health monitoring (SHM) technology can provide a large amount of data for further understanding of VIV. Automatic identification of VIV events from massive, continuous long-term monitoring data is a non-trivial task. In this study, a method based on the random decrement technique (RDT) is proposed to identify the VIV response automatically from the massive acceleration response without manual intervention. The raw acceleration data is first processed by RDT and it is found that the RDT-processed data show different characteristics for the VIV response and conventional random response. A threshold based on the coefficient of variation (COV) of peak values of processed data is defined to distinguish between the two kinds of responses. Both random vibration and VIV for a three-DOF (degree-of-freedom) mass-spring-damper system are obtained by numerical simulation to verify the proposed method. The method is finally applied to the Xihoumen suspension bridge for identifying VIV response from three-month monitoring data. It is shown that the proposed method performs comparably with the method of novelty detection. A total of 60 VIV events have been successfully identified. Vortex-induced vibrations for the second to ninth vertical modes with modal frequency within 0.1~0.5 Hz occurs at wind velocity 5–18 m/s, with wind direction nearly perpendicular to bridge axis. Amplitude of VIV generally decreases with increase of wind turbulence intensity; however, noticeable VIV amplitude are still observed for turbulence intensity up to 13% in some cases.

show abstract

A Bayesian non-parametric clustering approach for semi-supervised Structural Health Monitoring

Cited by 76 publications

References 50 publications

Outlier ensembles: A robust method for damage detection and unsupervised feature extraction from high-dimensional data

Outlier ensembles: A robust method for damage detection and unsupervised feature extraction from high-dimensional data

A general anomaly detection framework for fleet-based condition monitoring of machines

Automatic Identification of Bridge Vortex-Induced Vibration Using Random Decrement Method

Contact Info

Product

Resources

About