DIAGNOSA KERUSAKAN BANTALAN BOLA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE

Muhammad Fathurrohman, R. Lulus Lambang G. H, Didik Djoko Susilo

Abstract

Bearings are the critical part of any rotating machine. The catastrophic failure of the bearing can lead to fatal and harmful to the operation of the machine. Therefore, predictive maintenance based on condition monitoring of bearing is very important. The objective of this research is to apply Support Vector Machine (SVM) method for fault diagnosis of the ball bearing. The research was carried out at the bearing test rig. Four types of ball bearing condition, such as normal, inner race defect, ball defect, and outer race defect were measured of the vibration signals using data acquisition with a sampling frequency of 20 kHz at the constant speed of 1400 RPM. Various features were extracted from vibration signals in time domain, such as RMS, variance, standard deviation, crest factor, shape factor, skewness, kurtosis, log energy entropy and sure entropy. PCA transformation was employed to reduce the dimension of feature extracted data. SVM classification problems were solved using MATLAB 2016a. The results showed that the application of RBF kernel function with the C parameter =1 was the best configuration. The training model accuracy was 98.93% and the testing accuracy of SVM was 97.5%. Finally, the research results show that the SVM classification method can be used to diagnose the fault condition of the ball bearing..

Full Text:

PDF

References

K. Aji, “Deteksi Kerusakan Bantalan Gelinding Pada Pompa Sentrifugal dengan Analisa Sinyal Getaran,” Teknik Mesin Fakultas Teknik Universitas Sebelas Maret, Surakarta, vol. 7, no. 1, 2007.

A. Bilosova dan J. Bilos, “Vibration Diagnostics, Investments in Education Development,” Ostrava, 2012.

BS ISO, ISO 13373-1:2002 “Condition monitoring and diagnostics of machines - Vibration condition monitoring,” British Standard Institution, 2002.

K. K. Chin, “Support Vector Machines applied to Speech Pattern Classification,” MPhil.

Thesis, University of Cambridge, 1998.

H. A. Estilaf dan S. M. J. R. Fatemi, “Bearing Fault Diagnosis of Electrical Machine base on Vibration Signal using Multi-Class Support Vector Machine,” Indian J.Sci.Res., vol. 2, no. 1, pp. 46-53, 2014.

C. W. Hsu dan C. J. Lin, “A comparison of methods for multiclass support vector machines,” IEEE Transactions on Neural Networks, vol. 13, no. 2, pp. 415–425, 2002.

Johnson dan Wichern, “Applied Multivariate Statistical Analysis,” Edisi keenam, Pearson Prentice Hall, 2007.

K. Kappaganthu, C. Nataraj, dan B. Samanta, “Model Based Bearing Fault Detection Using Support Vector Machines,” Annual Conference of the Prognostics and Health Management Society, 2009.

R. K. Mobley, “An Introduction to Predictive Maintenance, Elsevier Science,” Butterworth-Heinemann, 2002.

S. Poyhonen, “Support Vector Machine based Classification in Condition Monitoring of Induction Motors,” Helsinki University of Technology Control Engineering Laboratory,

Report 141, 2004.

D. Rahmanto, “Pengaruh Variasi Putaran terhadap Efektifitas Balancing Poros Fleksibel pada Proses Two-Plane Balancing,” Teknik Mesin Fakultas Teknik Universitas Sebelas Maret, Surakarta, 2007.

A. Ramali, B. Setiono, dan A. Hidayatno, “Identifikasi Kerusakan Mesin Berbasis Sinyal Getaran dengan Metode Fuzzy Logic,” Teknik Elektro Fakultas Teknik Universitas Diponegoro, Semarang, 2012.

K. Sembiring, “Tutorial Support Vector Machine,” Teknik Informatika ITB, Bandung, 2007.

A. Sharma, M. Amarnath, and P. K. Kankar, “Feature Extraction and Fault Severity

Classification in Ball Bearings,” J. of Vibration and Control, vol. 22, no. 1, pp. 1–17, 2014.

N. T. Sitohang, E. Erinofiardi, dan A. F. Suryono, “Analisa Kegagalan Bantalan Skf 6005 pada Carrier Idler di PT. Pelabuhan Indonesia II (Persero) Cabang Bengkulu,” Teknik Mesin Fakultas Teknik Universitas Bengkulu, Bengkulu, 2014.

Suhardjono, “Analisis Sinyal Getaran untuk Menentukan Jenis dan Tingkat Kerusakan Bantalan Bola (Ball Bearing),” Teknik Mesin Institut Teknologi Sepuluh November, Surabaya, 2005.

T. Thelaidjia, A. Moussaoui, dan S. Chenikher, “Feature Extraction and Optimized Support Vector Machine for Severity Fault Diagnosis in Ball Bearing,” Engineering Solid Mechanics, vol. 4, no. 4, pp. 167-176, 2016.

H. H. Ullu, T. Prahasto, dan A. Widodo, “Prognosis Kerusakan Bantalan Gelinding dengan menggunakan Metode Support Vector Regression (SVR),” Masters thesis Diponegoro University, Semarang, 2013.

A. Widodo, “Application of Intelligent System for Machine Fault Diagnosis and Prognosis,” Badan Penerbit Universitas Diponegoro, Semarang, 2019.

A. Winoto, “Prediksi Umur Pahat Dengan Metode Mesin Pendukung (Support Vector Machine),” Teknik Mesin Fakultas Teknik Universitas Sebelas Maret, Surakarta, 2011.

M. L. D. Wong, C. Liu, dan A. K. Nandi, “Classification of Ball Bearing Faults using Entropic Measures,” Proceeding Surveillance 7, Chartres, France, 2014.

DOI: https://doi.org/10.20961/mekanika.v18i1.35041

Refbacks

  • There are currently no refbacks.