Machine learning is used for extraction of valuable information from data thus helping in exploration of hidden patterns, leading to learning models that can be used for prediction. In the domain of autonomous vehicles machine learning techniques have been applied in several areas, vehicle platooning being one of them. Vehicle platooning is a vital feature of automated highways which provides the key benefits of fuel economy, road safety and environmental protection coupled with safe road transportation. However, high computational cost associated with the numerical simulation of vehicle aerodynamics makes the Computational Fluid Dynamics (CFD) study of vehicle platoon prohibitively expensive and complex. Machine learning, with its high predictive power, has emerged as a promising compliment to CFD studies of external aerodynamics. This paper presents estimation error based performance comparison of five different supervised learning algorithms: Support Vector Regression, Polynomial Regression, Linear Regression and two different models of Neural Networks for prediction of aerodynamic drag coefficient corresponding to each vehicle in a two, three and four vehicle platoon configurations based on the drag coefficients provided by experimental study at different inter-vehicle distances. Predicted drag coefficients are then juxtaposed with CFD data from numerical simulations to evaluate closeness to experimental drag coefficients. Results reveal that polynomial regression model best fits the aerodynamics with 0.0223 estimation error. To the best of our knowledge no machine learning based methods have been applied before for modeling aerodynamic drag on vehicle platoon.
The ever-growing road congestion and safety hazards induced by conventional highways has inspired the development of automated highways which provides four key benefits: fuel economy, environmental protection, road safety and smooth traffic flow. Vehicle platooning is a vital component of automated highways which contributes directly to these four benefits with its sequence of closely spaced leader-follower vehicle configuration by taking advantage of the ‘slip-stream’ effect to minimize the aerodynamic drag. Exploratory studies into platooning parameters, vehicle spacing, speeds and number of vehicles, have proven to be prohibitive expensive both computationally and experimentally due to the complexity of tests and the large number of test cases. In recent years, OpenFOAM® an independently developed, supported and documented open-source toolbox has gained popularity by offering a lower cost alternative to leading commercial CFD products. This paper summarizes the results from a computational study of autonomous vehicle platoons and the capability of OpenFOAM® to substitute leading commercial CFD solutions currently used to support vehicle aerodynamic development. This study investigates the aerodynamic characteristics of a 4-SUV platoon at inter-vehicle distances ranging from 0.25 to 1 SUV length at a constant speed of 23 m/s. Trends of the predicted aerodynamic drag coefficients (Cd) are then compared against experimental data from published literature as well as the results obtained from a leading commercial CFD package.
A numerical simulation was developed for a PV-Hydrogen Electrolyzes system. The system is simply consisted of a PV that feeds Hydrogen electrolyzes cell by electric power. The system was successfully installed and experimentally tested. Each system component was numerically modeled and the governing equations were solved as a steady solution for each time step. The simulation was running along the simulation period of time. TRNSYS 15 program was used to establish the simulation. The simulation results are verified with the corresponding measured data for the same system geometry and under the weather conditions of Egypt. It is found that the simulated Hydrogen flow rate approximately agrees with that produced experimentally where the maximum Hydrogen generation is about 43 ml/min. The difference between the measured and predicted H 2 flow rate during the day hours is about 4 %. The daily overall efficiency of the system is ranged from 2.8 to 4.2 % in both simulated and experimental data. The overall efficiency of the system along the year is approximately between 2.45 to 2.75 % and that is according to the total solar radiation incident and the amount of electric power delivered to the Hydrogen cell with the amount of hydrogen produced as well as the total hydrogen produced annually was 41407931.97 liters. The simulation program is approximately validated and can be used for the predication of the considered system performance.
Wider acceptance of project-based learning (PjBL) in the tertiary education industry has been obstructed by its resource-intensive nature. This paper introduces a transdisciplinary variant of PjBL for undergraduate engineering students through a multidisciplinary complex engineering problem requiring the design and fabrication of a hydraulic robot arm. The robotics-inspired transdisciplinary PjBL variant was first evaluated through student feedback using the Chi-square hypothesis test, which, at Chi-square (4, N = 101) = 129.12; p < 0.05, revealed a statistically significant difference in the proportion of the student feedback in favor of the PjBL for sustainability of transdisciplinary project-based learning. Furthermore, the students’ PjBL and PbBL scores were subjected to the Mann–Whitney U test which concluded the effectiveness of PjBL against PbBL with statistical significance, U(N = 101) = 192.00, z = −11.826, p < 0.05. The results indicate that the novel transdisciplinary project-based learning (PjBL) approach develops students’ practical engineering knowledge spanning multiple disciplines, thereby resulting in a sustainable concept of project-based learning.
In this work, an electrolyze system is considered to produce Hydrogen (H 2) using photovoltaic (PV) panels. The system was experimentally installed and tested under the weather conditions of Cairo. Many PV modules with different specifications of current and voltage were tested for individual loads. One of PV modules that have the maximum current with minimum voltage can produce the highest amount of Hydrogen. In addition, the parameters of (KOH) concentration in water and the apart-distance between the electrodes were studied. The apart-distance of 5 cm between the electrodes was found as optimized distance that produces more H 2 quantity. Moreover, a H 2-cell of 20×15×13 cm 3 has higher H 2 production than the size of 6×6×24 cm 3 , 24×6×24 cm 3 and 24×24×24 cm 3 cells. It is obtained that the optimal system that considers the above efficient conditions must have a PV module with high current and small voltage.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.