Acoustic emission, cylinder pressure and vibration: a multisensor approach to robust fault diagnosis

Sharkey, Amanda J. C.; Chandroth, Gopinath Odayammadath; Sharkey, Noel

doi:10.1109/ijcnn.2000.859400

Cited by 29 publications

(19 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the study, sources of environmental noise were investigated and the noise level was deteriorated by using signal processing techniques for the diesel engines subsequently. Sharkey et al (2000) used cylinder pressure and vibration signal to verify the robust faults in the engine fault diagnosis. Modgil et al (2004) conducted the diagnostics of vibration for the engine test cells.…”

Section: Introductionmentioning

confidence: 99%

An Analysis of Sound for Fault Engine

Chomphan¹

2014

American Journal of Applied Sciences

View full text Add to dashboard Cite

Various types of faults of the gasoline engine may result in similar symptoms. Sound analysis of engine has been conducted to diagnose the engine faults. This study presents a study of sound analysis of the normal engine and the engine with three different fault conditions. The gasoline engine was our target of this study. The engine sound has been recorded by using a microphone at the engine room for three directions. Three conditions of engine faults including the engine that is not smooth while idling, the engine that goes missing while idling and the engine that has no power are simulated. In the signal processing of the sound, we use five signal features including fundamental frequency, long term spectrum, energy, long term cestrum and zero crossing rate. Thereafter, the important differences between normal engine and the fault engines are concluded. These proposed signal features can be used to discriminate all three conditions and the engine with normal condition effectively.

show abstract

Section: Introductionmentioning

confidence: 99%

An Analysis of Sound for Fault Engine

Chomphan¹

2014

American Journal of Applied Sciences

View full text Add to dashboard Cite

show abstract

“…If the quality of data from each sensor is such that it is sufficient for the classification task (as opposed to poorer quality data where some form of sensor fusion is required before classification becomes possible), then an ensemble can be created from nets each trained on data from a separate sensor (see for instance [14], and the first case study described below). A related approach is to subject the data to different forms of preprocessing; for example, in [16], when three different preprocessing methods (domain expertise, principle component analysis, and wavelet decomposition) were applied to vibration data from an engine, and the resulting nets were combined to form effective ensembles.…”

Section: Methods Of Ensemble Creationmentioning

confidence: 99%

The “Test and Select” Approach to Ensemble Combination

Sharkey

Gerecke

et al. 2000

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The performance of neural nets can be improved through the use of ensembles of redundant nets. In this paper, some of the available methods of ensemble creation are reviewed and the "test and select" methodolology for ensemble creation is considered. This approach involves testing potential ensemble combinations on a validation set, and selecting the best performing ensemble on this basis, which is then tested on a final test set. The application of this methodology, and of ensembles in general, is explored further in two case studies. The first case study is of fault diagnosis in a diesel engine, and relies on ensembles of nets trained from three different data sources. The second case study is of robot localisation, using an evidence-shifting method based on the output of trained SOMs. In both studies, improved results are obtained as a result of combining nets to form ensembles.

show abstract

“…The maximum level J could be 17. However, by a trial and error approach with using different types of wavelets including, Daubechies wavelets and Symlets wavelets families, it has found that Symlets of order 9 wavelet at level J=4 is sufficient so as to enhance the AE signal to show the friction effects in that the viscous friction exhibit higher amplitudes in the middle of the each stroke, which has been investigated in [5,6,23] about friction effects between piston ring and cylinder liner. In general, the continuous characteristics of the AE signals indicated by the viscous friction agree with the piston velocity profile and load variation.…”

Section: A Wmra Analysismentioning

confidence: 99%

“…References [4] and [5] investigated the suitability of acoustic emission (AE) technique for the condition monitoring of diesel engine valve faults. Sharkey et al [6] developed an engine fault diagnosis approach for combustion process using acoustic emission sensors. These researches indicate that the obvious bursts of AE events are caused by valve impacts and combustion.…”

Section: Introductionmentioning

confidence: 99%

Characterisation of acoustic emissions for the frictional effect in engines using wavelets based multi-resolution analysis

Wei

Wang

et al. 2015

2015 21st International Conference on Automation and Computing (ICAC)

View full text Add to dashboard Cite

Abstract-The friction between piston ring-cylinder liner is a major cause of energy losses in internal combustion engines. However, no experimental method is available to measure and analyze the fictional behavior. This paper focuses on the investigation of using acoustic emission (AE) to characterize the friction online. To separate the effect relating to friction sources, wavelets multi-resolution analysis is used to suppress interfering AE events due to valve impacts and combustion progress. Then a wavelet envelope indicator is developed to highlight AE contents from friction induced AE contents. The results show that the AE contents in the middle strokes correlate closely with viscous friction process as their amplitudes exhibit a continuous profile similar to piston speed. Furthermore, the AE envelope indicator proposed can distinguish the differences between two types of lubrication oils, showing superior performance of AE based online lubrication diagnosis.

show abstract

Acoustic emission, cylinder pressure and vibration: a multisensor approach to robust fault diagnosis

Cited by 29 publications

References 2 publications

An Analysis of Sound for Fault Engine

An Analysis of Sound for Fault Engine

The “Test and Select” Approach to Ensemble Combination

Characterisation of acoustic emissions for the frictional effect in engines using wavelets based multi-resolution analysis

Contact Info

Product

Resources

About