Article Preview
TopKey Contributions
The main contributions of this proposed system are as follows:
- 1)
To provide a better value for renewable energy products supported by transportation to DMVs, avoiding the impact of fossil fuel consumption and electric vehicles.
- 2)
To create pollution-free transportation, and to increase the usage of vehicles by making use of the power generated from the rear axle of the vehicle to run the vehicle effectively.
- 3)
To create an optimized system using semantic techniques based on deep neural networks to achieve enhanced customer efficiency in choosing the preferred fuel type or self-charging mode in dual-mode vehicles.
TopFossil fuels have a greater impact on the environment than renewable energy. Concerns have been voiced regarding an 87% surge in carbon dioxide emissions resulting from the combustion of fossil fuels like coal, natural gas, and oil. The impact of rising carbon dioxide levels on the world's climate includes climate change and respiratory problems in humans. Atarod et al. (2021) identified the rapid growth of greenhouse gas emissions and related problems as the main features of the fossil fuel-based economy. Hosseinzadeh et al. (2019) stress the need to focus on the use of bioenergy to replace carbon dioxide. Manikandan et al. (2021) proposed an electric wheel design technology to recover lost power and move the vehicle with electric devices, and their test results show the performance of the self-charging car.
According to Gargi Pancholi.,Yadav et al (2017), the needs and preferences of supercapacitors are driven in parallel with batteries. The results show the performance of battery-powered vehicles as well as hybrid vehicles based on batteries and supercapacitors. Gangavarapu et al. (2021) proposed a solar cell and battery that can be operated simultaneously. Experimental results show that the performance differences of DC-DC converters for solar electric vehicles are widening. Paul Banda et al. (2021) proposed a case study for power estimation for an electric vehicle, and their results show the basis of CNN's adaptive learning model. Liu et al. (2021) proposed neural network-based electrical control in hybrid electric vehicle, and their results demonstrate competitive fuel economy and state-of-the-art battery.
Today, electric cars are an irreversible change. Huo and Meckl (2022) proposed energy management in electronic networks, and their results show the validity of total greenhouse gas emissions and government prices using the dynamic data program. Maino et al. (2021) proposed a method to predict carbon dioxide emissions from hybrid electric vehicles based on deep neural networks, and their findings indicate that the simulation method achieves a classification efficiency exceeding 91% and an average regression error below 1%. Adel Oubelaid et al. (2022) proposed a torque distribution to maximize the power of hybrid electric vehicles, and their results showed that the conversion rate dropped from 69% to zero. Adel Oubelaid et al. (2022) suggested a fuzzy power management system tailored for a battery-supercapacitor electric vehicle, and the results of their study show that the fuzzy power control strategy improves speed and torque control; they also proposed a power control scheme to detect the occurrence of electric vehicle faults, and the results show that the difference between power and speed is minimal (2022). Federico et al. (2023) proposed a power management system based on neural networks in hybrid electric vehicles, and the results of their study show that CO2 emissions are reduced and fuel economy is increased. Olov Holmer Lars Eriksson (2017) suggested a method to concurrently decrease fuel consumption and NOx emissions in hybrid vehicles, and the outcomes demonstrated a 3.8% reduction in fuel consumption compared to non-hybrid vehicles.