HOME
Full Articles List
Search by Author
Title: THE PREDICTION AND OPTIMIZATION OF ALTERNATIVE FUEL CONSUMPTION IN VEHICLES USING ARTIFICIAL NEURAL NETWORKS WITH THE AIM OF REDUCING ATMOSPHERIC POLLUTION
BibTex 
Open this article in the author's DB |
|
THE PREDICTION AND OPTIMIZATION OF ALTERNATIVE FUEL CONSUMPTION IN VEHICLES USING ARTIFICIAL NEURAL NETWORKS WITH THE AIM OF REDUCING ATMOSPHERIC POLLUTION
|
|
|
|
|
|
|
|
||
|
|
10.5593/sgem2024/4.1
|
|
|
|
1314-2704
|
|
|
|
||
|
|
English
|
|
|
|
24
|
|
|
|
4.1
|
|
|
|
• Prof. DSc. Oleksandr Trofymchuk, UKRAINE
• Prof. Dr. hab. oec. Baiba Rivza, LATVIA |
|
|
|
||
|
|
The purpose of this work is to explore the potential for predicting and improving the fuel efficiency of vehicles with thermal engines, especially in the context of reducing exhaust gas emissions that contribute to environmental pollution. With rising fuel costs, consumers need to make informed decisions about the fuel consumption and environmental impact of purchasing vehicles with internal combustion engines. To achieve this goal, the researchers utilized artificial intelligence and created a model using neural networks, drawing on data from vehicle manufacturers that incorporated various factors such as engine power, maximum torque, vehicle weight, engine cylinder volume, and the number of cylinders. The aim of this approach was to optimize fuel consumption for such vehicles. The study involved predicting and optimizing fuel consumption through the selection and fine-tuning of neural network architecture based on the data being analyzed. This included establishing the connections between input and output data, training the network to minimize errors, and validating the model to ensure high generalization. Various neural networks with 1, 2, or 3 layers were examined, taking into account the number of learning cycles, the sensitivity of input data, and the overall importance of each factor in order to minimize prediction errors. The findings of the study indicate that the construction parameters of vehicles significantly impact both fuel consumption and environmental pollution. The application of this fuel consumption prediction and optimization method could lead to the increased use of thermal engine vehicles that are chosen based on practical utility and transportation needs, while also helping to reduce pollution.
|
|
|
||
|
||
|
|
conference
|
|
|
|
||
|
|
||
|
|
Proceedings of 24th International Multidisciplinary Scientific GeoConference SGEM 2024
|
|
|
|
24th International Multidisciplinary Scientific GeoConference SGEM 2024, 1 - 7 July, 2024
|
|
|
|
Proceedings Paper
|
|
|
|
STEF92 Technology
|
|
|
|
First click on Radio Buttons above - Scopus or Clarivate format
|
|
|
|
SWS Scholarly Society; Acad Sci Czech Republ; Latvian Acad Sci; Polish Acad Sci; Russian Acad Sci; Serbian Acad Sci and Arts; Natl Acad Sci Ukraine; Natl Acad Sci Armenia; Sci Council Japan; European Acad Sci, Arts and Letters; Acad Fine Arts Zagreb Croatia; Croatian Acad Sci and Arts; Acad Sci Moldova; Montenegrin Acad Sci and Arts; Georgian Acad Sci; Acad Fine Arts and Design Bratislava; Russian Acad Arts; Turkish Acad Sci.
|
|
|
|
459-466
|
|
|
|
1 - 7 July, 2024
|
|
|
|
website
|
|
|
|
|
|
|
|
9773
|
|
|
|
neural network, air pollution, optimization, fuel.
|
|
Download PDF