Sistem Condition Based Maintenance Pada Bearing Mesin Conveyor Finish Good Dengan Metode Neural Network Di PT Suntory Garuda Beverage

Arista, Yulfi (2023) Sistem Condition Based Maintenance Pada Bearing Mesin Conveyor Finish Good Dengan Metode Neural Network Di PT Suntory Garuda Beverage. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 10311910000056-Undergraduate_Thesis.pdf] Text
10311910000056-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2025.

Download (11MB) | Request a copy

Abstract

Beban kerja conveyor pada komponen bearing yang ada pada mesin conveyor finish good (CFG) dalam proses distribusi kardus minuman dari line produksi menuju gudang penyimpanan memiliki amplitudo kecepatan getaran yang mencapai 30 mm/s. Getaran disebabkan dari pengaruh conveyor yang mengalami pergeseran shaft. Pergeseran shaft menyebabkan terjadinya kerusakan bearing sehingga menimbulkan downtime. Kejadian downtime yang lama menimbulkan hambatan dalam proses produksi minuman tersebut. Sistem condition based maintenance ini mengimplementasikan klasifikasi kondisi bearing conveyor pada mesin conveyor finish good secara langsung. Klasifikasi kondisi bearing conveyor pada sistem ini menggunakan Neural Network yang merupakan sebuah metode untuk mencari pengaturan weight berdasarkan tingkat error yang diperoleh pada iterasi sebelumnya. Sinyal kecepatan getaran direkam menggunakan sensor akselerometer ADXL345 yang diolah menggunakan Fast Fourier Transform, sehingga didapatkan jenis sinyal kecepatan getaran dalam domain frekuensi rendah maupun frekuensi tinggi. Pada penelitian ini dilakukan 36 kali percobaan untuk menentukan arsitektur Neural Network yang terbaik. Berdasarkan pengujian yang telah dilakukan, arsitektur terbaik menggunakan 10 neuron pada hidden layer, dan menggunakan iterasi sebanyak 50 kali, yang mendapatkan nilai MSE sebesar 0,045. Sistem yang dibuat dapat mengklasifikasikan kondisi bearing conveyor dalam 4 kondisi, yaitu kondisi normal, maintenance (pelumasan), maintenance (misalignment), dan rusak dengan nilai akurasi hingga 100%, sehingga sistem ini dapat dinyatakan baik dan layak untuk digunakan dalam melakukan klasifikasi kondisi bearing conveyor secara langsung.
=================================================================================================================================
The conveyor workload on the bearing components on the finish good (CFG) conveyor machine in the distribution process of beverage cartons from the production line to the storage warehouse has an amplitude of vibration speed that reaches 30 mm/s. Vibration is caused by the influence of the conveyor which is experiencing a shift in the shaft. Shaft shift causes bearing damage causing downtime. Long downtime events cause obstacles in the beverage production process. This condition-based maintenance system implements the condition classification of conveyor bearings on conveyor finish good machines directly. Conveyor bearing condition classification in this system uses a Neural Network which is a method for finding weight settings based on the error rate obtained in the previous iteration. The vibration speed signal is recorded using the ADXL345 accelerometer sensor which is processed using the Fast Fourier Transform, so that the type of vibration speed signal is obtained in the low frequency and high frequency domains. In this research, 36 experiments were carried out to determine the best Neural Network architecture. Based on the tests that have been done, the best architecture uses 10 neurons in the hidden layer, and uses 50 iterations, which gets an MSE value of 0.045. The system created can classify conveyor bearing conditions in 4 conditions, namely normal conditions, maintenance (lubrication), maintenance (misalignment), and damaged with an accuracy value of up to 100%, so that this system can be declared good and feasible to be used in classifying conveyor bearing conditions directly.

Item Type: Thesis (Other)
Uncontrolled Keywords: Bearing Conveyor, Neural Network, Condition Based Maintenance
Subjects: T Technology > TJ Mechanical engineering and machinery > TJ1077 Lubrication and lubricants.
T Technology > TJ Mechanical engineering and machinery > TJ1398 Conveyors
T Technology > TJ Mechanical engineering and machinery > TJ174 Maintenance and repair of machinery
T Technology > TJ Mechanical engineering and machinery > TJ217.6 Predictive Control
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK2785 Electric motors, Induction.
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK3070 Automatic control
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK351 Electric measurements.
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK4055 Electric motor
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5102.9 Signal processing.
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5103.2 Wireless communication systems. Two way wireless communication
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.888 Web sites--Design. Web site development.
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK6565.P3 Panels
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7868.P6 Power supply
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7870.23 Reliability. Failures
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7878 Electronic instruments
T Technology > TS Manufactures > TS195 Packaging
Divisions: Faculty of Vocational > 36304-Automation Electronic Engineering
Depositing User: YULFI ARISTA
Date Deposited: 14 Nov 2023 06:49
Last Modified: 14 Nov 2023 06:49
URI: http://repository.its.ac.id/id/eprint/103863

Actions (login required)

View Item View Item