Penurunan konsumsi bahan bakar sepeda motor sistem injeksi menggunakan metode optimasi artificial neural network dengan algoritma back-propagation

Paridawati, Paridawati and SINAGA , Nazaruddin (2015) Penurunan konsumsi bahan bakar sepeda motor sistem injeksi menggunakan metode optimasi artificial neural network dengan algoritma back-propagation. In: Prosiding Seminar Nasional Perkembangan Riset dan Teknologi di Bidang Industri ke 21, 1 June 2015, Yogya,Indonesia.

[img]
Preview
PDF - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

4Mb

Abstract

Nowadays the modern automobile engine is equipped with Engine map in the electronic control unit (ECU). Engine map serve as guidelines for determining both the fuel injection and ignition timing of an engine. Engine map is typically used to optimize engine performance, fuel efficiency and emission reduction. Engine map created by the vehicle manufacturer, usually optimized by considering multiple criteria and objectives. With increasing lifespan of the vehicle and also the presence of criteria and different optimization objectives, the engine map shall adjusted, or even re-optimizing according to the conditions of vehicle user. The present study is intended to seek the more optimum engine map which is more suitable to the condition current in Indonesia with the main goal of improving its efficiency. This research, first of all will be take the current of data using an engine scanner on the engine control unit (ECU) to determine engine map current (existing). The next step is to optimum remap by using Artifcial Neural Network (ANN) that can improve the efficiency. ANN optimization results are then applied as new maps. A new map will be implemented into the ECU and tested. The results were then analyzed and compared between value optimization using ANN with the value of the original Engine map (default vehicle manufacturer). Conclution this research that engine map optimization results are expected to be able to reduce the level of fuel consumption. The best engine map III have error (MSE)=0,06 and R=0,99 and the results of fuel consumption have efisiensy 14%, higher were compared to standar engine map.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:Efficiency, engine map, optimization, Artificial Neural Network
Subjects:T Technology > TJ Mechanical engineering and machinery
Divisions:Faculty of Engineering > Department of Mechanical Engineering
Faculty of Engineering > Department of Mechanical Engineering
ID Code:75838
Deposited By:Mr Nazaruddin Sinaga
Deposited On:27 Aug 2019 10:32
Last Modified:27 Aug 2019 10:32

Repository Staff Only: item control page