Condition monitoring of distributed systems using two-stage Bayesian inference data fusion

Jaramillo, Víctor Hugo González; Ottewill, James R.; Dudek, Rafał; Lepiarczyk, D.; Pawlik, Paweł

doi:10.1016/j.ymssp.2016.10.004

Cited by 46 publications

(24 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The thresholds are calculated based on Kernel Density Estimation, which is described, for example in [11], [17], [18], as an accurate method when the exact distribution of the data is unknown. The kernel density estimators were constructed from healthy data for each feature and a 95 % confidence interval (values of considered variables are only positive) was determined.…”

Section: B Threshold Settingmentioning

confidence: 99%

“…Recent work [11] proposed a two-stage Bayesian inference approach. The approach combines data fusion at both a local and a global level, or in other words at component and system-wide levels respectively.…”

Section: Bayesian Inferencementioning

confidence: 99%

“…Aydin et al [10] used Bayesian classification to detect bearing faults in induction motors and classify motor conditions according to phase spaces. Recently Jaramillo et al [11], presented a twostage Bayesian inference approach, in which data is fused at both a local, or component, level, as well as at a global, or system-wide level. The approach was shown to refine the diagnostic assessment of machinery comprised of a number of interacting components.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Two Stage Data Fusion of Acoustic, Electric and Vibration Signals for Diagnosing Faults in Induction Motors

Stief¹,

Ottewill²,

Orkisz³

et al. 2017

ElAEE

Self Cite

View full text Add to dashboard Cite

Abstract-The increasing demand for predictive maintenance is a main driver of the development of better fault diagnosis algorithms. Each condition monitoring approach has its own strengths and weaknesses; there is not a single technique that can diagnose all types of faults. As a result, it can be a challenge to find the root cause of a problem when only a single feature is monitored. There is also a greater risk of missed-or false-alarms. It has been shown that data fusion, combining multiple features, can improve the effectiveness of fault diagnosis. In recent work, a two-stage Bayesian inference approach, in which data is fused at both a local, or component, level, as well as at a global, or system-wide level has been shown to refine the diagnostic assessment of machinery comprised of a number of interacting components. In this paper, we show that the approach may also be applied to combine information from multiple, diverse condition monitoring systems. Acoustic, electric and vibration signals were measured from healthy and faulty induction motors, operating under normal and noisy working conditions. The proposed method was shown to increase the reliability of the health assessment of the induction motors, reducing the risk of missed and false alarms.

show abstract

Section: B Threshold Settingmentioning

confidence: 99%

Section: Bayesian Inferencementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Two Stage Data Fusion of Acoustic, Electric and Vibration Signals for Diagnosing Faults in Induction Motors

Stief¹,

Ottewill²,

Orkisz³

et al. 2017

ElAEE

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [15,16] the artificial intelligence methods were used for diagnosing the machines operating at variable loads. Complex Bayesian inference [17] was also used in detection of damage type for various load and rotational speed variants [18]. The other approach was a method of separating the components related to the variable rotational speed and load [19].…”

Section: Introductionmentioning

confidence: 99%

The diagnostic method of rolling bearing in planetary gearbox operating at variable load

Pawlik¹

2019

Diagnostyka

View full text Add to dashboard Cite

Diagnostics of machines operating at variable loads has been widely described in literature. The methods of analysing the vibroacoustic signals generated by such machines have been developed since the 1980s. They involve a synchronous sampling of signals which carry diagnostic information, where the sampling frequency depends on the machine rotational speed. Presently, there are many methods in the literature used for synchronization of signals with rotational speed based on signal decimation, subsampling or Gabor transform. However, these methods do not totally solve the problem of diagnosing the machines operating at various loads. The change of machine load also affects the amplitudes of diagnostic parameters.The paper attempts to develop a diagnostic method that is independent of the system load change. The method is based on parameterization of amplitudes of characteristic orders. Single-number statistical parameters have been proposed for diagnostics of rolling bearings operating at variable loads. Tests have been conducted on a laboratory rig where the tested object was a rolling bearing on an output shaft of a planetary gearbox. The bearing was damaged by removing the grease which is a frequent type of damage in industry and can lead to a quick bearing seizure.Keywords: vibroacoustic diagnostics, bearing diagnostics, order analysis, variable load.METODA DIAGNOZOWANIA ŁOŻYSKA TOCZNEGO PRZEKŁADNI PLANETARNEJ PRACUJĄCEJ PRZY ZMIENNYM OBCIĄŻENIU Streszczenie Diagnostyka maszyn pracujących przy zmiennym obciążeniu jest problemem szeroko opisywanym w literaturze. Metody analizy sygnałów wibroakustycznych pochodzący od tego typu maszyn rozwijane były już od lat 80-tych. Polegają one na synchronicznym próbkowaniu sygnałów niosących informację diagnostyczną, gdzie zmienna częstotliwość próbkowania zależy od sygnału prędkości obrotowej diagnozowanej maszyny. Obecnie w literaturze znaleźć można wiele metod służących do synchronizacji sygnałów z prędkością obrotową opartych na decymacji sygnału, subsamplingu czy transformacji Gabora. Jednak zastosowanie tych metod nie rozwiązuje do końca problemu diagnozowania maszyn pracujących przy zmiennym obciążeniu. Zmiana obciążenia maszyny ma również wpływ na zmianę wartości amplitud parametrów diagnostycznych.W pracy podjęto problem opracowania metody oceny stanu technicznego niewrażliwej na zmianę obciążenia badanego układu. Metoda bazuje na parametryzacji przebiegów amplitud rzędów charakterystycznych. Zaproponowano jednoliczbowe parametry statystyczne do diagnozowania łożysk tocznych pracujących przy zmiennym obciążeniu. Przeprowadzono badana na stanowisku laboratoryjnym gdzie badanym obiektem było łożysko toczne na wale wyjściowym przekładni planetarnej. Diagnozowane łożysko uszkodzono poprzez wypłukanie smaru, co jest często spotykanym uszkodzeniem w przemyśle i może prowadzić do szybkiego zatarcia łożyska.Słowa kluczowe: diagnostyka wibroakustyczna, diagnostyka łożysk, analiza rzędów, zmienne obciążenie.

show abstract

“…Bayesian inference has been described as a suitable method for fault detection and fault classification in condition monitoring systems [23], [24]. Recently, Jaramillo et al [25] proposed a two-stage Bayesian inference approach to monitor the condition of a system composed of several subsystems. The first stage of the sensor fusion takes place at the subsystem level, while the second stage fuses the result of the first stage at the decision level in order to determine the health state of the whole system.…”

mentioning

confidence: 99%

A PCA and Two-Stage Bayesian Sensor Fusion Approach for Diagnosing Electrical and Mechanical Faults in Induction Motors

Stief

Ottewill

Baranowski

et al. 2019

IEEE Trans. Ind. Electron.

Self Cite

View full text Add to dashboard Cite

Induction motors are widely used in industrial plants for critical operations. Stator faults, bearing faults or rotor faults can lead to unplanned downtime with associated cost and safety implications. Different sensors may be used to monitor the health state of induction motors with each sensor typically being better suited to diagnosing different faults. Condition monitoring approaches which fuse data from multiple sensors have the potential to diagnose a greater number of faults. A sensor fusion approach based on the combination of a two-stage Bayesian method and Principal Component Analysis is proposed for diagnosing both electrical and mechanical faults in induction motors. Acoustic, electric and vibration signals are gathered from motors operating under different loading conditions and health states. The inclusion of the PCA step ensures robustness to varying loading conditions. The obtained results highlight that the proposed method performs better than equivalent single stage or feature-based Bayesian methods.

show abstract

Condition monitoring of distributed systems using two-stage Bayesian inference data fusion

Cited by 46 publications

References 42 publications

Two Stage Data Fusion of Acoustic, Electric and Vibration Signals for Diagnosing Faults in Induction Motors

Two Stage Data Fusion of Acoustic, Electric and Vibration Signals for Diagnosing Faults in Induction Motors

The diagnostic method of rolling bearing in planetary gearbox operating at variable load

A PCA and Two-Stage Bayesian Sensor Fusion Approach for Diagnosing Electrical and Mechanical Faults in Induction Motors

Contact Info

Product

Resources

About