UI - Skripsi Membership :: Back

UI - Skripsi Membership :: Back

Implementasi Reinforcement Learning berbasis Algoritma Deep Deterministic Policy Gradient (DDPG) untuk Pengendalian Ketinggian Air pada Sistem Coupled Tank = Implementation of Reinforcement Learning Based on Deep Deterministic Policy Gradient (TD3) Algorithm for Water Level Control in Coupled Tank System

Nur Fadilah Yuliandini; Prawito Prajitno, supervisor; Djati Handoko, examiner; Surya Darma, examiner (Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Indonesia, 2023)

 Abstract

Sistem Coupled tank umum digunakan pada bidang industri otomatis, salah satu pengendalian yang umum terjadi pada coupled tank adalah pengendalian ketinggian air. Sistem pengendalian tersebut bertujuan untuk menjaga ketinggian air yang berada pada tangki. Penelitian ini melakukan simulasi pengendalian ketinggian air pada coupled tank dengan menerapkan Reinforcement Learning (RL) dengan algoritma Deep Deterministic Policy Gradient (DDPG). Proses simulasi tersebut dilakukan menggunakan simulink pada MATLAB. Algoritma DDPG melalui serangkaian training sebelum diimplementasikan pada sistem coupled tank. Kemudian pengujian algoritma DDPG dilakukan dengan memvariasikan nilai set point dari ketinggian air dan sistem diberikan gangguan berupa bertambahnya flow in dari control valve lain. Performa dari algorima DDPG dalam sistem pengendalian dilihat dari beberapa parameter seperti overshoot, rise time, settling time, dan steady state error. Hasil yang diperoleh pada penelitian ini bahwa algoritma DDPG memperoleh nilai settling time terbesar sebesar 109 detik, nilai steady state error terbesar sebesar 0.067%. Algoritma DDPG juga mampu mengatasi gangguan dengan waktu terbesar sebesar 97 detik untuk membuat sistem kembali stabil.

The Coupled Tank system is commonly used in the field of industrial automation, and one of the common controls implemented in this system is water level control. The purpose of this study is to simulate water level control in a coupled tank using Reinforcement Learning (RL) with the Deep Deterministic Policy Gradient (DDPG) algorithm. The simulation process is performed using Simulink in MATLAB. The DDPG algorithm undergoes a series of training sessions before being implemented in the coupled tank system. Subsequently, the DDPG algorithm is tested by varying the set point values of the water level and introducing disturbances in the form of increased flow from another control valve. The performance of the DDPG algorithm in the control system is evaluated based on parameters such as overshoot, rise time, settling time, and steady-state error. The results obtained in this study show that the DDPG algorithm achieves a maximum settling time of 109 seconds and a maximum steady-state error of 0.067%. The DDPG algorithm is also capable of overcoming disturbances, with the longest recovery time of 97 seconds to restore system stability.

 Digital Files: 1

Shelf
 S-Nur Fadilah Yuliandini.pdf :: Download

LOGIN required

 Metadata

Collection Type : UI - Skripsi Membership
Call Number : S-pdf
Main entry-Personal name :
Additional entry-Personal name :
Additional entry-Corporate name :
Study Program :
Subject :
Publishing : Depok: Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Indonesia, 2023
Cataloguing Source LIbUI ind rda
Content Type text
Media Type computer
Carrier Type online resource
Physical Description xii, 49 pages : illustration + appendix
Concise Text
Holding Institution Universitas Indonesia
Location Perpustakaan UI
  • Availability
  • Review
  • Cover
Call Number Barcode Number Availability
S-pdf 14-24-87816580 TERSEDIA
Review:
No review available for this collection: 9999920527737
Cover