Optimization of fuel consumption and emissions in diesel engines by using of artificial neural network and ant colony algorithm with intake VVT and fuel injection approach
Author(s):
Abstract:
In this paper, by using of the experimental results and numerical simulation with AVL FIRE software and using of artificial neural network, NOx and soot emissions and fuel consumption of a diesel engine was modeled, that input variables of modeling are, air intake temperature, mass fuel injected, fuel injection timing, injection duration, engine speed and IVC timing. Then by using of ant colony optimization algorithm and based on the obtained models for outputs, values of NOx and soot emissions and fuel consumption has been optimized. For this purpose, by using of experimental data and numerical simulation, the arranging for modeling of performance and output was provided by the ANN.
Artificial neural network with Levenberg-Marquardt training algorithm and using of the experimental and numerical data was applied for modeling and training of relationship between these parameters and this method was applied as a predictive method of ant colony algorithm to find the optimal values and used as a subroutine. Then the design variables that optimized the objective functions were obtained. The results show a fast convergence and good response times and optimizing the control parameters of the ant colony algorithm compared with other metaheuristic algorithms. Due to the rapid and significant convergence of output parameters, combination of artificial neural network (ANN) and ant colony optimization (ACO) can be used as an effective method in intelligent control systems for diesel engines to reduce emissions and fuel consumption.
Artificial neural network with Levenberg-Marquardt training algorithm and using of the experimental and numerical data was applied for modeling and training of relationship between these parameters and this method was applied as a predictive method of ant colony algorithm to find the optimal values and used as a subroutine. Then the design variables that optimized the objective functions were obtained. The results show a fast convergence and good response times and optimizing the control parameters of the ant colony algorithm compared with other metaheuristic algorithms. Due to the rapid and significant convergence of output parameters, combination of artificial neural network (ANN) and ant colony optimization (ACO) can be used as an effective method in intelligent control systems for diesel engines to reduce emissions and fuel consumption.
Keywords:
Optimization , ANN , Ant colony algorithm , NOx , Soot
Language:
Persian
Published:
Journal of Engine Research, Volume:12 Issue: 43, 2016
Pages:
13 to 30
magiran.com/p1628723
دانلود و مطالعه متن این مقاله با یکی از روشهای زیر امکان پذیر است:
اشتراک شخصی
با عضویت و پرداخت آنلاین حق اشتراک یکساله به مبلغ 1,390,000ريال میتوانید 70 عنوان مطلب دانلود کنید!
اشتراک سازمانی
به کتابخانه دانشگاه یا محل کار خود پیشنهاد کنید تا اشتراک سازمانی این پایگاه را برای دسترسی نامحدود همه کاربران به متن مطالب تهیه نمایند!
توجه!
- حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران میشود.
- پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانههای چاپی و دیجیتال را به کاربر نمیدهد.
In order to view content subscription is required
Personal subscription
Subscribe magiran.com for 70 € euros via PayPal and download 70 articles during a year.
Organization subscription
Please contact us to subscribe your university or library for unlimited access!