Maximum Power Point Tracking Dengan Orientasi Arus Riak Berbasis Artificial Neural Network (ANN) Pada Aplikasi Fuel Cell PEMFC (Proton Exchange Membran Cell)

Winarza, Andhika Aryaputra (2022) Maximum Power Point Tracking Dengan Orientasi Arus Riak Berbasis Artificial Neural Network (ANN) Pada Aplikasi Fuel Cell PEMFC (Proton Exchange Membran Cell). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 07111840000009-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2024. Download (4MB) | Request a copy

Abstract

Seiring kemajuan zaman, dunia menghadapi dua masalah yang cukup besar yakni bahan bakar fosil yang menipis dan juga suhu iklim yang meningkat atau global warming. Fuel cell adalah salah satu energi terbarukan yang sangat ramah terhadap lingkungan karena rendah polusi terhadap pollutant, minim suara dan juga mempunyai efisiensi yang cukup tinggi. Dalam upaya pemaksimalan daya dari fuel cell dibutuhkan yang namanya MPPT atau Maximum Power Point Tracking. Maka dari itu pada penelitian ini didesain MPPT dengan metode alternatif yaitu MPPT dengan Orientasi Arus Riak berbasis ANN. MPPT tersebut akan dibandingkan dengan MPPT dengan metode P&O. Dari hasil penelitian yang dilakukan didapatkan efisiensi energi dari orinetasi arus riak berbasis ANN sebesar 99.59% pada pembebanan tanpa inverter dan 99.85% pada pembebanan menggunakan inverter. Sedangkan metode P&O memiliki efisiensi sebesar 99.25% pada pembebanan tanpa inverter dan 99.49% pada pembebanan menggunakan inverter. Untuk dapat mencapai nilai maksimum (time peak) metode orientasi arus riak berbasis ANN lebih cepat 0.1201418 detik dibandingkan dengan metode P&O pada pembebanan tanpa inverter dan 0.121162188 detik lebih cepat dibandingkan dengan metode P&O pada pembebanan menggunakan inverter.
==================================================================================================================================

Along with the progress of the times, the world is facing two major problems, namely the depletion of fossil fuels and also increasing climate temperature or global warming. Fuel cell is a renewable energy that is very friendly to the environment because it is low in pollution to pollutant, minimal noise and also has a fairly high efficiency. In an effort to maximize power from the fuel cell, it is necessary to call it MPPT or Maximum Power Point Tracking. Therefore, in this study, MPPT was designed with an alternative method, namely MPPT with ANN-based Ripple Current Orientation. The MPPT will be compared with the MPPT using the P&O method. From the results of the research conducted, the energy efficiency of the ANN-based ripple current orientation is 99.59% for loading without an inverter and 99.85% for loading using an inverter. While the P&O method has an efficiency of 99.25% for loading without an inverter and 99.49% for loading using an inverter. To be able to reach the maximum value (time peak) the ANN-based ripple current orientation method is 0.1201418 seconds faster than the P&O method for loading without an inverter and 0.121162188 seconds faster than the P&O method for loading using an inverter.

Item Type:	Thesis (Other)
Additional Information:	RSE 621.312 429 Win m-1 2022
Uncontrolled Keywords:	Fuel Cell, MPPT, Orientasi arus riak, Artificial Neural Network (ANN), Buck Converter
Subjects:	Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK6592.A9 Automatic tracking.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20201-(S1) Undergraduate Thesis
Depositing User:	- Davi Wah
Date Deposited:	16 Jul 2024 06:55
Last Modified:	16 Jul 2024 06:55
URI:	http://repository.its.ac.id/id/eprint/108329

Actions (login required)

View Item