Detection and Diagnosis of Centrifugal Pump Bearing Faults Based on the Envelope Analysis of Airborne Sound Signals

Daraz, Alsadak; Alabied, Samir; Smith, Alexander Thomas T.; Gu, Fengshou; Ball, Andrew

doi:10.23919/iconac.2018.8749053

Cited by 11 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A range of factors can contribute to premature bearing failure, including lubrication failure, excessive temperature and improper installation. 1,2 Approaches to the fault detection and diagnosis of bearings exist based on a variety of measured parameters, including lubricant wear debris, 3 temperature, 4 acoustic emission, 5,6 airborne acoustics 7 and vibration. 8 Of these different methods, vibration-based approaches remain the most extensively employed in condition monitoring of bearings, and they have been proven to be both efficient and effective in the detection, diagnosis and location of defects in rolling bearings.…”

Section: Introductionmentioning

confidence: 99%

A phase linearisation–based modulation signal bispectrum for analysing cyclostationary bearing signals

et al. 2020

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

Bearings are used as the most important load-carrying transmission components in various machines, thus subjecting to a number of faults including wear, fatigue pitting, cracks and so on. Fault detection and diagnosis of bearings can effectively prevent the machine from such typical failures and subsequent consequences. The faults in bearings can lead to the vibration signals that exhibit cyclostationary characteristics due to the inevitably random phase noise (or slippage between bearing components). In this article, a phase linearisation–based modulation signal bispectrum is proposed to tune up the cyclostationary bearing signal into a periodic waveform by linearizing the instantaneous phase of the narrow frequency band signals. In this way, the signal becomes more deterministic and modulation signal bispectrum can be effectively applied to suppression noise and obtain accurate and robust diagnosis results. As a result, this fault detector can achieve high performance in characterising the nonstationary bearing vibration signals and hence diagnose the bearing faults even in the case of extremely low signal-to-noise ratio (<−20 dB), which is benchmarked by the method of conventional modulation signal bispectrum in both simulation and experiment studies.

show abstract

Section: Introductionmentioning

confidence: 99%

A phase linearisation–based modulation signal bispectrum for analysing cyclostationary bearing signals

et al. 2020

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such techniques are performed on monitored signals. The most common monitored signals are vibration, sound, temperature, flow rate, currents, and acoustic emission [4,5]. Data-driven fault diagnosis includes several stages: feature extraction, feature selection, and fault classification [6].…”

Section: Introductionmentioning

confidence: 99%

Improved Mel Frequency Cepstral Coefficients for Compressors and Pumps Fault Diagnosis with Deep Learning Models

Cabrera,

Medina,

Cerrada

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Compressors and pumps are machines frequently used in petroleum and chemical industries for fluid transportation through flow systems to keep industrial processes running permanently. As their failure can produce costly disruption, developing fault detection and diagnosis tools is essential for accurately detecting and diagnosing faults. This research proposes a bi-dimensional representation of the vibration signal corresponding to the Mel Frequency Cepstral Coefficients (MFCC) and their first two derivatives as features. The pseudo-periodic nature of the fault signature in rotating machines is exploited to put forward an efficient and accurate patch-wise fault classification method. This approach enables the classification of 13 combined types of faults in a multi-stage centrifugal pump and 17 faults in a reciprocating compressor. Classification is performed using the Long Short-Term Memory (LSTM) network, the bidirectional Long Short-Term Memory (BiLSTM) neural network, and the Convolutional Neural Network (CNN). Accurate classification over 99% is attained, showing that the proposed feature extraction procedure correctly classifies a large set of faults simultaneously appearing in such rotating machines.

show abstract

“…Induction motors have high efficiency, simple construction, low price, and easy maintenance [2]. However, the motors do not operate normally continuously because they have an aging period due to long-term use [3]. Bearings and eccentricity may suffer mechanical damage and the stator and rotor may sufferer electrical damage [4].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Outer Race Bearing Damage by Calculation of Sound Signal Frequency Based on the FFT Method

Karyatanti

Noersena

Purnomo

et al. 2023

Int. j. eng. technol. innov.

View full text Add to dashboard Cite

This study aims to identify the outer race bearing needed to protect an induction motor from severe damage. Faults are diagnosed using a non-invasive technique through the sound signal from an induction motor. The diagnosis aims to assess the damage to the bearings on the fan or main shaft. Moreover, this study discusses the type of damage, loading variations, and the diagnostic accuracy with the damage to the outer race bearing placed on the fan or main shaft rotor. The disturbance detection approach is used to analyze the sound spectrum to identify the harmonic components near the disturbance frequency. The damage frequency characteristics are also calculated to determine the sound spectrum peak value. The results show that the detection is slightly affected by the damage severity and the incorrect placement of the bearings on the rotor shaft. The lowest detection accuracy in testing the outer race bearing damage on the fan shaft is 91.66%. However, the accuracy percentage is 100% with the outer race bearing damage on the main shaft.

show abstract

Detection and Diagnosis of Centrifugal Pump Bearing Faults Based on the Envelope Analysis of Airborne Sound Signals

Cited by 11 publications

References 14 publications

A phase linearisation–based modulation signal bispectrum for analysing cyclostationary bearing signals

A phase linearisation–based modulation signal bispectrum for analysing cyclostationary bearing signals

Improved Mel Frequency Cepstral Coefficients for Compressors and Pumps Fault Diagnosis with Deep Learning Models

Analysis of Outer Race Bearing Damage by Calculation of Sound Signal Frequency Based on the FFT Method

Contact Info

Product

Resources

About