Analisis Vibrasi Untuk Klasifikasi Kerusakan Motor Di Pt Petrokimia Gresik Menggunakan Fast Fourier Transform Dan Neural Network

Priatama, Nirma (2014) Analisis Vibrasi Untuk Klasifikasi Kerusakan Motor Di Pt Petrokimia Gresik Menggunakan Fast Fourier Transform Dan Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2210100159_Undergraduate_Thesis.pdf Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Pada studi ini data vibrasi motor dari PT Petrokimia Gresik dianalisis untuk diklasifikasikan jenis kerusakan motor yang terjadi menggunakan Fast Fourier Transform (FFT) dan neural network. Data sinyal vibrasi motor diubah ke dalam domain frekuensi menggunakan FFT, sehingga didapat data amplitudo spektrum vibrasi tiap jenis kerusakan yang dijadikan sebagai input neural network. Neural network digunakan untuk mengklasifikasikan jenis kerusakan motor ke dalam lima kondisi, yaitu normal, unbalance, misalignment, looseness, dan kerusakan anti-friction bearing. Neural network yang dirancang diuji dengan 10 data vibrasi motor dengan jenis kerusakan yang berbeda. Tingkat ketepatan neural network dalam mengklasifikasikan jenis kerusakan mencapai 100%.
============================================================================================================================
On this study, motors vibration data from PT Petrokimia Gresik are analyzed to classify the type of motor fault that occured using Fast Fourier Transform (FFT) and neural network. Motors vibration data are transformed into frequency domain using FFT to obtain vibration spectra’s amplitudo data that are used as neural network input. Neural network is used to classify the type of motor fault into five conditions, they are unbalance, misalignment, looseness, and anti-friction bearing fault. The designed neural network is tested using 10 motors vibration data with different fault types. Accuracy level of the neural network to classify the fault types reaches 100%.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	analisis vibrasi, fast fourier transform, neural network, klasifikasi kerusakan motor. vibration analysis, fast fourier transform, neural network, motor fault classification.
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK2681.B47 Electric motors, Direct current.
Divisions:	Faculty of Industrial Technology > Electrical Engineering > 20201-(S1) Undergraduate Thesis
Depositing User:	Eko Sulistiono
Date Deposited:	18 Sep 2025 08:15
Last Modified:	18 Sep 2025 08:15
URI:	http://repository.its.ac.id/id/eprint/128307

Actions (login required)

View Item