Ekstraksi Parameter Statistik Domain Waktu dan Domain Frekuensi untuk Mendeteksi Kavitasi pada Pompa Sentrifugal Berbasis Principal Component Analysis (PCA)


  • Berli Paripurna Kamiel Universitas Muhammadiyah Yogyakarta http://orcid.org/0000-0002-1127-8097
  • Niko Prastomo Universitas Muhammadiyah Yogyakarta
  • Bambang Riyanta Universitas Muhammadiyah Yogyakarta




Centrifugal Pump, Cavitation, Vibration Signal, Time Domain, Frequency Domain, Principal Component Analysis (PCA)


Cavitation phenomenon frequently occurs on the centrifugal pump which may decrease its performance. It may cause a catastrophic failure which leads to a total breakdown of the piping system if the presence of cavitation is not immediately detected and solved. Recently, the popular method used to detect cavitation is based on pattern recognition. The use of pattern recognition technique requires statistical features which are used as input for building the classifier. The extraction of statistical features is usually taken from the vibration signal which consists of time domain and frequency domain. Previous research tends to use the statistical features extracted from the time domain or the frequency domain solely. There is a research gap that can be explored by combining statistical features extracted from both time domain and frequency domain. In this study, Principal Component Analysis (PCA) is used as a feature’s selection and fault classification. PCA linearly transforms statistical features from the original coordinate system into a new coordinate system called principal components (PCs). The first few PCs are a set of selected features which can be used as a classifier. The classifier evaluates and classifies the new set of vibration data then decides whether it falls into normal condition or cavitation category. The vibration signal is taken from the cavitation test-rig under normal condition by opening the valve, level 1 cavitation by opening 75% of valve, level 2 by 50%, and level 3 by 25%. The data is extracted into 7 statistical features from the time domain and 5 from the frequency domain.  Five hundred sets of vibration data are recorded using an accelerometer which was then divided into 400 set for training and 100 set for testing. The study shows that the classifier using statistical features taken from the time domain and frequency domain gives promising results where the clustering effect between normal and cavitation condition is clearly observed.

Author Biography

Berli Paripurna Kamiel, Universitas Muhammadiyah Yogyakarta

Teknik Mesin | Lektor


SULARSO & TAHARA, H., Pompa dan kompresor, 7th ed., Jakarta, Pradnya Paramita, 2000.

MUSYAFA. A. A., SIREGAR. I. H., “Pengaruh Jumlah Sudu Sentrifugal Impeller Terhadap Kapasitas Dan Efisiensi Pompa Sentrifugal†Jurnal Teknik Mesin, v. 3, n. 3, pp. 136-144, 2015.

BRENNEN, E. C., Cavitation and bubble dynamics, 1st ed., California, Cambridge University Press, 2013.

SCHEFFER, C., & GIRDHAR, P., Machinery Vibration Analysis & Predictive Maintenance, 1st ed., Oxford, Newnes, 2004.

KAMIEL, B.P., RAMADHAN, R. S., “Pengaruh Kecepatan Operasi Pompa Sentrifugal Terhadap Sensitifitas Metode Deteksi Fenomena Kavitasi Berbasis Parameter Statistik Domain Waktuâ€, Jurnal Semesta Teknika, v. 20, n. 1, pp. 51-66, May 2017.

LUO, Y., ZHIXIANG, X., SUN, H., YUAN, S., & YUAN, J., “Research on Statistical Characteristics of Vibration in Centrifugal Pumpâ€, Research Center of Fluid Machinery Engineering and Technology, v. 38, n. 1, pp. 49 - 61, 2015.

SYAFUTRA, K., Metode Deteksi Fenomena Kavitasi Pada Pompa Sentrifugal Berbasis Domain Frekuensi Sinyal Getaran (skripsi), Degree S.T., Universitas Muhammadiyah Yogyakarta, Yogyakarta, Indonesia, 2017.

FAROKHZAD, S., “Vibration Based Fault Detection of Centrifugal Pump by Fast Fourier Transform and Adaptive Neuro-Fuzzy Inference Systemâ€, Journal of Mechanical Engineering and Technology, v. 1, Iss. 3, pp. 82-87, Dec. 2013

WANG, F., SUN, J., YAN, D., ZHANG, S., CUI, L., & XU, Y., “A Feature Extraction Method for Fault Classification of Rolling Bearing based on PCAâ€, Journal of Physics, Conf. Ser. 628 012079, 2015.

KAMIEL, B. P., “Impeller Fault Detection for a Centrifugal Pump Using Principal Component Analysis of Time Domain Vibration Features†Degree Ph. D., Department of Mechanical Engineering Curtin University, Perth, Australia, 2015.

SUTIKNO D, SOENOKO R, PRATIKTO P, PUTRA F, CAHYO P., â€Study on Pressure Distribution in the Blade Passage of the Francis Turbineâ€, Jurnal Rekayasa Mesin, v.2, n.2, pp. 154-158, Aug 2011

DELLY, J., (2010), “Pengaruh Temperatur Terhadap Terjadinya Kavitasi Pada Sudu Pompa Sentrifugalâ€, Dinamika Jurnal Ilmiah Teknik Mesin, v. 1, n. 1, pp. 21-28, Nov 2009.

HALLIGAN, G. R., & JAGANNATHAN, S., “PCA-based fault isolation and prognosis with application to pumpâ€, The International Journal of Advanced Manufacturing Technology, 55(5-8), pp. 699–707, 2010.

RAPUR, J. S., & TIWARI, R., “Experimental Time-Domain Vibration-Based Fault Diagnosis of Centrifugal Pumps Using Support Vector Machineâ€, ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering, v. 3, n. 4, pp. 1-35, 2017.

SAKTHIVEL, N. R., SUGUMARAN, V., & BABUDEVASENAPATI, S., “Vibration based fault diagnosis of monoblock centrifugal pump using decision treeâ€, Expert Systems with Applications, v. 37, n. 6, pp. 4040–4049, 2010.