Vibration based fault diagnosis of monoblock centrifugal pump using decision tree

Sakthivel, N. R.; Sugumaran, V.; Babudevasenapati, S.

doi:10.1016/j.eswa.2009.10.002

Cited by 186 publications

(100 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…So to capture cavitation induced high frequency signal, the bandwidth of the vibration spectrum is set as 51200 Hz during signal measuring process, and it is the upper limiting frequency for the presently used accelerometers. The corresponding sampling frequency is 102400 Hz to satisfy Nyquist sampling theorem [18]. To reduce energy leakage of the obtained signals, Hanning window is applied during signal processing [19].…”

Section: V3mentioning

confidence: 99%

Experimental Investigation on Cavitating Flow Induced Vibration Characteristics of a Low Specific Speed Centrifugal Pump

Gao

Guo

Zhang

et al. 2017

Shock and Vibration

View full text Add to dashboard Cite

Cavitating flow developing in the blade channels is detrimental to the stable operation of centrifugal pumps, so it is essential to detect cavitation and avoid the unexpected results. The present paper concentrates on cavitation induced vibration characteristics, and special attention is laid on vibration energy in low frequency band, 10-500 Hz. The correlation between cavitating evolution and the corresponding vibration energy in 10-500 Hz frequency band is discussed through visualization analysis. Results show that the varying trend of vibration energy in low frequency band is unique compared with the high frequency band. With cavitation number decreasing, vibration energy reaches a local maximum at a cavitation number much larger than the 3% head drop point; after that it decreases. The varying trend is closely associated with the corresponding cavitation status. With cavitation number decreasing, cavitation could be divided into four stages. The decreasing of vibration energy, in particular cavitation number range, is caused by the partial compressible cavitation structure. From cavitation induced vibration characteristics, vibration energy rises much earlier than the usual 3% head drop criterion, and it indicates that cavitation could be detected in advance and effectively by means of cavitation induced vibration characteristics.

show abstract

Section: V3mentioning

confidence: 99%

Experimental Investigation on Cavitating Flow Induced Vibration Characteristics of a Low Specific Speed Centrifugal Pump

Gao

Guo

Zhang

et al. 2017

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…Sakthivel et al utilized a decision tree to extract statistical features from vibration measurement and classify these features simultaneously. Outcomes indicated that this method can detect various faults in a monoblock pump with high precision [9]. Muralidharan and Sugurmaran utilized a discrete wavelet transform to extract features from vibration signals, and rough sets to generate rules.…”

Section: Introductionmentioning

confidence: 99%

Cavitation detection in centrifugal pumps using pressure time-domain features

Samanipour¹,

Poshtan²,

Sadeghi³

2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Condition monitoring of centrifugal pumps is vital due to their crucial role in industries. One of the most prevalent faults in pumps is cavitation, which can cause mechanical faults or even failure in the pump. In this paper, an approach is suggested to detect cavitation in a centrifugal pump using time-domain analysis of the pressure signal residual. First, pressure and torque signals are obtained using a model of the electro-pump, and then pressure deviation from the pump performance curve is defined as a residual. The residual time-domain features are extracted and applied as inputs to a self-organizing map (SOM) neural network to classify the system modes. The results indicate that the suggested method is capable of detecting incipient cavitation. Furthermore, the suggested method demonstrates robust performance against disturbance.

show abstract

“…One of the principal tools for diagnosing mechanical faults is vibration-based analysis [1][2][3]. Through the use of processing techniques of vibration signals, it is possible to obtain vital diagnosis information from the signals [4,5].…”

Section: Introductionmentioning

confidence: 99%

The Hybrid Intelligent Method Based on Fuzzy Inference System and Its Application to Fault Diagnosis

Lei¹

2012

Fuzzy Inference System - Theory and Applications

View full text Add to dashboard Cite

Vibration based fault diagnosis of monoblock centrifugal pump using decision tree

Cited by 186 publications

References 21 publications

Experimental Investigation on Cavitating Flow Induced Vibration Characteristics of a Low Specific Speed Centrifugal Pump

Experimental Investigation on Cavitating Flow Induced Vibration Characteristics of a Low Specific Speed Centrifugal Pump

Cavitation detection in centrifugal pumps using pressure time-domain features

The Hybrid Intelligent Method Based on Fuzzy Inference System and Its Application to Fault Diagnosis

Contact Info

Product

Resources

About