Deteksi Kavitasi Berbasis Getaran Pada Pompa Sentrifugal Menggunakan Principal Component Analysis (PCA)

Berli Paripurna Kamiel, Ikhsan Aprima Kausar

Abstract


A centrifugal pump is one type of pumps that widely used in industries. Its mechanism which creates pressure changes may cause cavitation. Cavitation phenomenon that is not properly maintained may results fatal breakdown leading to high economic losses. Therefore, research is needed to find and develop a method that can detect early cavitation phenomena and identify it at several levels as well. This paper presents a method that can detect cavitation by monitoring the vibrations level of the pump based on statistical analysis of time domain and Principal Component Analysis (PCA). Vibration data is collected, trained and tested for each cavitation level. Training data is normalized and trained for each cavitation level using PCA which produces data loading matrix. The loading matrix is then multiplied by the testing data which gives a score matrix used to classify cavitation level of the centrifugal pump. The result shows that the method of domain-based PCA is successful in transforming the original data of 7 statistical parameters to 7 principal components (PC) with maximum variant. Three PCs gives 93.68% variants which can clearly identify and classify the differences between normal, early, intermediate and fully developed cavitation in the centrifugal pumps.


Keywords


statistical parameters, cavitation, centrifugal pumps, Principal Component Analysis, vibration signals.

Full Text:

PDF

References


Al Hashmi, S.A. (2009). Statistical Analysis of Vibration Signals for Cavitation Detection. IEEE Symposium on Industrial Electronics and Application (pp.78 ‒ 82). Kuala Lumpur, Malaysia.

Al Tobi, M.A.S., & Al Sabari, M.H.J. (2016). Cavitation Detection of Centrifugal Pump Using Time-Domain Method. International Journal Of Engineering Research and General Science, 4 (5), 161-167.

Johnson, R.R., & Wichern, D.A. (2007) Applied Multivariate Statistical Analysis. Pearson Prentice Hall.

Kamiel, B.P. (2015). Vibration-Based Multi-Fault Diagnosis for Centrifugal Pumps. ( Doctoral thesis, Curtin University, Perth, Australia).

Li, W., Shi, T., Liao, G., & Yang, S. (2003). Feature Extraction and Classification of Gear Faults Using Principal Component Analysis. Journal of Quality in Maintenance Engineering, 9(2), 132-143.

Luo, Y., Zhixiang, X., Sun, H., Yuan, S., & Yuan, J. (2015). Research on Statistical Characteristics of Vibration in Centrifugal Pump. Advances in Mechanical Engineering, 7(11).

Pirra, M., Gandino, M., Torri, A., Garibaldi, L., & Machorro-Lopez, J.M. (2011). PCA Algorithm for Detection, Localisation and Evolution of Damages in Gearbox Bearings. Journal of Physics: Conference Series, 305(1).

Pratama, M.S.B. (2017). Metode Deteksi Fenomena Kavitasi Pompa Sentrifugal Berbasis Domain Waktu Dan Domain Frekuensi Sinyal Getaran. (Skripsi, Universitas Muhammadiyah Yogyakarta, Yogyakarta, Indonesia).

Ramadhan, R.S. (2017). Pengaruh Kecepatan Operasi Pompa Sentrifugal Terhadap Sensitifitas Metode Deteksi Fenomena Kavitasi Berbasis Parameter Statistik Domain Waktu. (Skripsi, Universitas Muhammadiyah Yogyakarta, Yogyakarta, Indonesia)

Sakthivel, N.R., Sugumaran, V., & Babudevasenapati, S. (2010). Vibration Based Fault Diagnosis of Monoblock Centrifugal Pump Using Decision Tree. Expert Systems with Applications, 37(6), 4040-4049.

Santosa B. (2007). Data Mining (Teori dan Aplikasi). Graha Ilmu, Yogyakarta.

Sukardi, I. A., Isranuri, I., & Lubis, Z. (2012). Studi Awal Kajian Bubble Pada Pompa Sentrifugal Yang Diukur dengan Sinyal Vibrasi. Jurnal Dinamis, I(11), 1-13.

Sularso (1993). Pompa dan Kompresor. Pradnya Paramita, Jakarta.

Susantyo (2013). Ekstraksi Fitur Untuk Pengenalan Wajah Pada Ras Mongoloid Menggunakan Principal Component Analysis (PCA). (Skripsi, Universitas Dian Nuswantoro, Semarang, Indonesia).

Al-Thobiani, F. (2011). The Non-intrusive Detection of Incipient Cavitation in Centrifugal Pumps. (Doctoral thesis, University of Huddersfield, England).




DOI: https://doi.org/10.18196/st.212219

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Editorial Office :

SEMESTA TEKNIKA

Faculty of Engineering, Universitas Muhammadiyah Yogyakarta.

Jln. Brawijaya Tamantirto Kasihan Bantul 55183 Indonesia

Telp:(62)274-387656, Fax.:(62)274-387656, WA: 085729357100

Email: semesta_teknika@umy.ac.id

Website: http://http://journal.umy.ac.id/index.php/st

Creative Commons License

Semesta Teknika is licensed under a Creative Commons Attribution 4.0 International License.