Prediksi Nilai Oktan Bahan Bakar Bensin Menggunakan Deret Sensor Gas Dan Kolom Kromatografi

Zulfahmi, Syarofan (2024) Prediksi Nilai Oktan Bahan Bakar Bensin Menggunakan Deret Sensor Gas Dan Kolom Kromatografi. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6022212016-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB) | Request a copy

Abstract

Bensin merupakan produk dari minyak bumi yang termasuk dalam jenis energi tak terbarukan yang merupakan salah satu bahan bakar mesin pembakaran dalam. Harga bensin komersial dibedakan berdasarkan nilai oktanya. Nilai oktan menjelaskan kemampuan bensin dalam menahan kompresi mesin tanpa adanya knocking. Semakin tinggi angka oktan maka bensin semakin tahan terhadap kompresi mesin. Biasanya, oktan pengukuran jumlah dilakukan dengan menggunakan standar American Society of Testing and Materials (ASTM). Namun cara ini memerlukan waktu pengujian yang lama dan dilakukan oleh operator bersertifikat. Penelitian ini mengembangkan sistem untuk mengklasifikasikan angka oktan suatu produk bahan bakar bensin. Sistem ini terdiri dari kolom partisi dan sensor gas untuk membentuk pola tertentu pada setiap angka oktan. Algoritma jaringan saraf digunakan untuk mengklasifikasikan pola yang dihasilkan oleh sensor gas. Hasil percobaan menunjukkan bahwa susunan sensor gas dapat memberikan pola tertentu pada setiap jenis bensin dengan angka oktan penelitian yang berbeda-beda yaitu 90, 92, dan 98. Algoritma jaringan syaraf tiruan dapat membedakan setiap jenis bensin dengan akurasi sebesar 83,33%
=====================================================================================================================================
Gasoline is a product from petroleum which is included in a type of non-renewable energy which is one of the fuels for internal combustion engines. Commercial gasoline prices are differentiated based on octa value. Octane value explains the ability of gasoline to withstand engine compression without knocking. The higher the octane number, the more resistant the gasoline to engine compression. Typically, octane number measurements are performed using American Society of Testing and Materials (ASTM) standards. However, this method requires a long testing time and is carried out by a certified operator. This research develops a system for classifying the octane number of a gasoline fuel product. This system consists of a partition column and a gas sensor to form a certain pattern for each octane number. Neural network algorithms are used to classify patterns produced by gas sensors. The experimental results show that the gas sensor arrangement can provide a certain pattern for each type of gasoline with different research octane numbers, namely 90, 92, and 98. The artificial neural network algorithm can differentiate each type of gasoline with an accuracy of 83.33%

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Energi, Sensor Gas, Jaringan Syaraf Tiruan , Nilai Oktan, Kolom Partisi; energy, gas sensor, neural network, octane number, partition column
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7871.674 Detectors. Sensors 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 Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis
Depositing User:	Syarofan Zulfahmi
Date Deposited:	26 Jul 2024 04:22
Last Modified:	26 Jul 2024 04:22
URI:	http://repository.its.ac.id/id/eprint/109425

Actions (login required)

View Item