In this paper, an energy-management strategy based on fuel economy is presented to achieve a further range increase for range-extended light commercial vehicles. Estimation of the energy-management strategy was carried out using a neural-network-based surrogate model for an range-extended vehicle. Surrogate-based optimization plays an important role in optimization problems, which are based on complex structures with uncertainties in data sets due to various conditions. Neural networks have advantages in creating surrogate-based models in cases of complex problems with uncertainties in data sets to evaluate the process and estimate the outputs. This study discusses additional power-unit applications 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 in different dynamic and static conditions to determine an energy-management strategy for a range-extended vehicle based on fuel economy under various conditions. It was seen that APU parameters and an energy-management strategy significantly affected the fuel consumption of REX. A neural-network-based surrogate-model approach gave high-precision results in predicting the operating strategy according to different loading conditions to reduce fuel consumption. In some cases, it can be required to determine the fuel consumption results in various conditions with the variables, which may be out-of-boundary conditions. It was seen that the proposed neural-network-model also offers higher prediction ability in cases of unexpected results in data sets of various conditions compared to regression analysis. The results show that 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. This study presents an approach for future new vehicle projects by transforming a prototype light commercial electric vehicle to REX. The proposed approach was developed to design the most efficient range-extended vehicle by changing all variables without costly computations and time-consuming analysis. It is possible to generate variable data sets and to have reference knowledge for future vehicle projects.

In this study, a module consisting of 30 pouch-type lithium-ion batteries with Lithium Iron Phosphate (LFP) chemistry, known for its lower flammability, was modeled along with its cooling system in a one-dimensional framework. The modeling was conducted using Matlab Simulink and Simscape Battery. The temperature variations and heat generation rates of the battery system were analyzed at different discharge rates. A liquid cooling system, designed to cool the battery module from below, was developed. The cooling performance was examined by selecting a laminar flow regime at lower Reynolds numbers, which were assumed to result in lower pumping losses. In the analyses performed at different Reynolds numbers and with varying numbers of cooling plate channels, it was observed that as the Reynolds number increased, both the heat transfer rate and coolant flow velocity increased, leading to a reduction in battery temperature values but an increase in pressure values.

In this study, prevention of fracture in vibration fatigue testing of automotive alternator heatsink blocks was investigated using an artificial neural network. Automotive components such as alternator heatsink blocks are subjected to high cyclic vibration fatigue loads throughout their lifespan, which can lead to the formation and propagation of fatigue cracks and ultimately component failure. The basic parameters affecting the resonant frequency of the heatsink blocks, including geometry and loading conditions, are determined. Data-driven decision making provides advanced predictive insights to analyze data for prediction and decisions using artificial intelligence approaches. An efficient artificial neural network model was defined to predict the resonance frequency in the vibration fatigue test. While the artificial neural network was trained to establish a functional relationship between the parameters and the resonance frequency, regression analysis was used to develop a predictive model to detect the resonance frequency of the heatsinks. The proposed approach aims to provide a comprehensive framework for preventing fracture problems in vibration fatigue tests of automotive alternator heatsinks and ultimately contribute to the reliable design and performance of these critical components. While the artificial neural network approach achieved high classification accuracy in predicting the new natural frequency, the regression model was also able to make accurate predictions. The results of this study showed that the time spent on design and simulation can be significantly reduced in preventing breakage problems that may occur before dynamic tests such as vibration tests of alternator components.