Artificial Neural Networks for Prediction and Improvement of Efficiency and Exhaust Temperature in a CNG/Diesel Dual Fuel Engine
Publish place: 4th International Conference and Exhibition on CNG
Publish Year: 1390
نوع سند: مقاله کنفرانسی
زبان: English
View: 2,592
This Paper With 10 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
CNGCONF04_001
تاریخ نمایه سازی: 19 تیر 1390
Abstract:
During the last few years a great deal of effort has been made for the reduction of pollutant emissions from direct injection diesel engines. Various solutions have been proposed, one of which is the use of gaseous fuels as a supplement for liquid diesel fuel. However, the combustion process in a dual fuel engine tends to display a complex combination of features of both compression and spark ignition engine operation. Therefore, the objective of this work is to investigate the ability of an artificial neural network model, using a back propagation learning algorithm, to predict specific fuel consumption, thermal efficiency and exhaust gas temperature of a dual fuel engine for various engine speeds and loads. The model predicted values are compared with corresponding experimental results. The comparison showed that the consistency between experimental and neural network results is achieved by a mean absolute relative error less than 2%.
Keywords:
Neural networks- CNG/Diesel engine , Dual Fuel Engine (DFE) , Specific fuel consumption , Thermal efficiency , Exhaust gas temperature
Authors
M Sadr Musavi
Computer Dept, Azad University
N Mahdinejad
Mechanical Engineering Dept, Azad University
A Moallemi
Electrical Engineering Dept, Azad University
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :