Elektrikli araçta menzil artırıcı motor uygulaması ve enerji yönetiminin sinirsel ağlar ile tahmin edilmesi
Date
2023-02-14
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Bursa Uludağ Üniversitesi
Abstract
Bu çalışmada, menzil artırıcı donanımlar ile elektrikli bir aracın desteklenmesi ve aracın performans özelliklerinin tahmin edilmesidir. Menzil artırıcı çalışma sistematiğini oluşturabilmek için, içten yanmalı motor, jeneratör ve batarya şarj durumunun başlıca parametreler olarak girdi sağlayacağı düşünülerek simülasyon modelleri oluşturularak analizler yapılmış ve sinirsel ağlar kullanılarak içten yanmalı motorun çalışma stratejisi belirlenmesi için tahminlere dayalı bir yaklaşım uygulanmıştır. İçten yanmalı motorun gürültü ve titreşim seviyesinin ölçülmesi sonucunda motorun çalışacağı sınır şartlar belirlenmiştir. Menzil artırıcı güç ünitesinin hafif ticari araç üzerine entegrasyonu, tasarımsal ve fiziksel olarak gerçekleştirilerek, son durumda deneysel yakıt tüketimi testleri gerçekleştirildi. Hafif ticari aracın ve içten yanmalı motorun teknik özelliklerinin simülasyon modele aktarılması ile değişken şartlara bağlı olarak yakıt tüketimi değerleri belirlendi. Tezin amacı, hafif ticari bir elektrikli araç için ek güç ünitesi uygulamasını ve araç entegrasyonunun sağlanması ile sinir ağı tabanlı bir model kullanarak enerji yönetiminin tahmininin menzil artırıcı motor için yakıt tüketimini azaltmak üzere farklı yükleme koşullarına göre çalışma stratejisini uyarlayarak elde edilmesidir.
In this study, the energy management strategy based on fuel economy is presented to achieve a further range enlargement of the range extender light commercial vehicle. Estimation of energy management strategy is carried out using neural networks based surrogate model for range extended vehicle based on fuel economy under various conditions. The surrogate based optimization plays an essential role in the optimization processes, especially when the optimization model is established based on complex problems with uncertainties in data sets due to various conditions. Neural networks have advantages in creating surrogate based models in case of complex problems with uncertainties in data sets to evaluate the process and estimate the outputs. This study discusses additional power unit application and vehicle integration for a light commercial electric vehicle. It provides preliminary design work and techniques for identifying NVH problems in particular. SIMULINK and neural network based surrogate models are established, and the changeable parameters of the vehicle, such as mass, battery/fuel-tank capacity, internal combustion engine power and electric motor power units are simulated at different dynamic and static conditions to determine energy management strategy for range extended vehicle based on fuel economy under various conditions. It is seen that APU parameters and energy management strategy significantly affect the fuel consumption of REX. The results show that the estimation and optimization of energy management using a neural network based surrogate model can be achieved by adapting the operating strategy according to different loading conditions to reduce fuel consumption for REX.
In this study, the energy management strategy based on fuel economy is presented to achieve a further range enlargement of the range extender light commercial vehicle. Estimation of energy management strategy is carried out using neural networks based surrogate model for range extended vehicle based on fuel economy under various conditions. The surrogate based optimization plays an essential role in the optimization processes, especially when the optimization model is established based on complex problems with uncertainties in data sets due to various conditions. Neural networks have advantages in creating surrogate based models in case of complex problems with uncertainties in data sets to evaluate the process and estimate the outputs. This study discusses additional power unit application and vehicle integration for a light commercial electric vehicle. It provides preliminary design work and techniques for identifying NVH problems in particular. SIMULINK and neural network based surrogate models are established, and the changeable parameters of the vehicle, such as mass, battery/fuel-tank capacity, internal combustion engine power and electric motor power units are simulated at different dynamic and static conditions to determine energy management strategy for range extended vehicle based on fuel economy under various conditions. It is seen that APU parameters and energy management strategy significantly affect the fuel consumption of REX. The results show that the estimation and optimization of energy management using a neural network based surrogate model can be achieved by adapting the operating strategy according to different loading conditions to reduce fuel consumption for REX.
Description
Keywords
Menzil artırıcı sistem, Sinir ağları, 1 boyutlu analiz, Emisyon seviyeleri, Range extended vehicle, Energy management, Fuel economy, Neural networks, Surrogate model
Citation
Türker, E. (2023). Elektrikli araçta menzil artırıcı motor uygulaması ve enerji yönetiminin sinirsel ağlar ile tahmin edilmesi. Yayınlanmamış doktora tezi. Bursa Uludağ Üniversitesi Fen Bilimleri Enstitüsü.