Rancang Bangun Sistem Fault Tolerant Discrete Control Pada Pengendalian Speed Sensorless Motor DC Berbeban Menggunakan Machine Learning

Athari, Mohamad Vikry (2024) Rancang Bangun Sistem Fault Tolerant Discrete Control Pada Pengendalian Speed Sensorless Motor DC Berbeban Menggunakan Machine Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5009201124-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB) | Request a copy

Abstract

Penelitian ini bertujuan untuk merancang sistem fault tolerant discrete control (FTDC) untuk pengendalian kecepatan pada motor DC berbeban secara sensorless menggunakan machine learning. Sistem FTDC ini dirancang untuk mengatasi perubahan beban dan kesalahan sensor. Metode kontrol yang digunakan dalam penelitian ini adalah state feedback control untuk pengendalian kecepatan motor DC dengan extended state observer (ESO) untuk estimasi kecepatan, arus, dan sinyal kesalahan dari motor DC. Algoritma machine learning yang digunakan adalah decision tree untuk klasifikasi jenis kesalahan. Hasil penelitian menunjukkan bahwa sistem FTDC yang dirancang mampu mencapai performa yang memuaskan. State feedback control menghasilkan rise time 3.984s, settling time 10.820s, overshoot 4.151%, dan error steady state 2.146%. ESO dengan Mean Absolute Percentage Error (MAPE) masing-masing sebesar 4.9117% dan 1.0358%. Sistem FTDC mampu mengembalikan operasi plant ke setpoint ketika diberikan kesalahan sensor arus sebesar 10 A. Sistem FTDC belum mampu mengakomodasi penambahan torsi beban yang terjadi sebab nilai beban yang kecil. FTDC dapat menjaga kestabilan sistem untuk kesalahan sensor. Parameter respon untuk sistem FTDC ketika diberikan kesalahan sensor arus adalah settling time, overshoot, dan error steady state berturut turut adalah 4.2s, 0.090%, dan 0.050% untuk kesalahan sensor arus 1A.
=================================================================================================================================
This research aims to design a fault tolerant discrete control (FTDC) system for sensorless speed control of loaded DC motors using machine learning. This FTDC system is designed to overcome load changes and sensor errors. The control method used in this research is state feedback control for DC motor speed control with an extended state observer (ESO) for estimating speed, current and error signals from the DC motor. The machine learning algorithm used is a decision tree for classifying error types. The research results show that the designed FTDC system is able to achieve satisfactory performance. State feedback control resulting rise time 3,984s settling time 10,820s, overshoot 4,151%, and steady state error 2,146%. ESO with Mean Absolute Percentage Error (MAPE) of 4.912% and 1.036% respectively. The FTDC system is able to return plant operations to set point when a current sensor error of 10 A is given. The FTDC system is not able to accommodate the additional load torque that occurs due to the small load value. FTDC can maintain system stability for sensor errors. The response parameters for the FTDC system when a current sensor error is given are setting time, overshoot, and steady state error, respectively, 4.2s, 0.090%, and 0.050% for a 1A current sensor error.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Decision Tree, Fault Tolerant Discrete Control, Motor DC, Observer State Feedback, Speed Sensorless, DC Motor
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK2681.B47 Electric motors, Direct current. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK3070 Automatic control T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK4055 Electric motor T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7878 Electronic instruments T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7882.P3 Pattern recognition systems
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User:	Mohamad Vikry Athari
Date Deposited:	29 Jul 2024 02:15
Last Modified:	29 Jul 2024 02:15
URI:	http://repository.its.ac.id/id/eprint/109256

Actions (login required)

View Item