SACM - United States of America
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9668
Browse
4 results
Search Results
Item Restricted HYBRID MACHINE LEARNING APPROACHES FOR SOC AND RUL ESTIMATION IN BATTERY MANAGEMENT SYSTEMS(Oakland University, 2024) Hawsawi, Tarik Abdullah; Zohdy, MohamedWith the fast development of electric vehicles (EVs), new technologies are needed to manage batteries more efficiently to optimize performance and more profound and longer battery use. A significant problem that must be solved successfully is accurate estimation of the State-of-Charge (SoC) to avoid fully discharging a battery. It shortens battery life and prolongs the time it takes to charge the battery. This dissertation introduces a new approach that uses Edge Computing and real-time predictive analytics to assess the status of EV batteries and send alerts when necessary, thus facilitating energy efficiency. The Edge Impulse platform is used to predict the Remain Useable Life RUL of batteries with enhanced accuracy using EON-Tuner and DSP processing blocks, enhancing computational capability and making it feasible for edge devices. Since traditional SoC estimations include tools like Kalman filters and Extended Kalman filters, which are effective but have a considerable drawback in estimating the SoC with changing battery parameters, this study proposes a multi-variable optimization method. The method enhances performance prediction after key parameters are iteratively adjusted, thus resolving the emergence hypotheses of most existing techniques. The system was designed and tested on Jupyter Notebook, and performance indicators of accuracy, MSE, and efficiency further validated the design. This study helps ensure proper energy use and long battery life for e-vehicles, which promotes clean energy use.7 0Item Embargo Optimized Dynamic Electric Vehicles Charging in Smart Cities(University of Maryland Baltimore County, 2024-11-22) Alaskar, Shorooq Sulaiman; Younis, MohamedRecent technological advances have fueled interest in the development of smart cities where the convenience and health of inhabitants are core objectives. Increased automation and reduced green gas emission are prime means for achieving these objectives. No wonder that there is a major push for the adoption of electrical vehicles. Yet, the deployment of electric vehicles (EVs) is slow-paced. One of the primary obstacles hindering the widespread adoption of EVs is range anxiety, which refers to the fear that an EV will not have sufficient battery charge to reach its destination or a nearby charging station. Additionally, long charging times pose a significant barrier, as recharging an EV battery can take considerably longer compared to refueling a conventional gasoline vehicle, making it less convenient for users. Furthermore, the scarcity of charging infrastructure capable of handling a large number of EVs exacerbates these concerns, deterring potential buyers due to worries about accessibility and convenience. Most of the existing charging techniques require EVs to remain stationary while being charged. Wireless charging has emerged as a viable solution that mitigates such a shortcoming by enabling dynamic EV-to-EV charging. It can also expand the driving range of automobiles if the battery can be continuously charged while the vehicle is in motion, hence extending the traveled distance. EV-to-EV charging provides drivers with greater temporal and spatial flexibility, specifically in densely populated urban regions, while aiding in the reduction of energy consumption. It can also mitigate the burden of the grid during peak loads and optimize power usage during off-peak hours. EV-to-EV charging not only adds convenience to drivers, but it enables a new business model as well, where mobile suppliers may sell their energy to EVs on the road. This dissertation addresses the challenge of the dynamic charging and routing of EVs in smart cities. We first present RIMEC, a Routing for Increased Mobile Energy Charging algorithm that determines an optimized EV travel route for utilizing the Mobile Energy Disseminator (MEDs) in order to maximize the potential energy that can be harvested while minimizing the impact on travel time. Second, we introduce an EV-to-EV charging framework for energy suppliers. The framework opts to maximize the profit, while considering battery degradation and the overhead cost. The optimization is modeled as a time-space network and a dynamic programming-based solution strategy is pursued to optimally pair and route the energy supplier (ES) and requester (ER). Specifically, ES is incentivized to rendezvous ERs at encounter nodes to dispense the requested energy through platooning. The complexity of the problem arises from nonstationary consumers and service supply, which make monitoring and synchronizing the movement of ES and ER spatiotemporally challenging. Third, we tackle the problem of dynamic EV-to-EV charging that aims to maximize the supplier's profitability within a specific timeframe, taking into account overhead costs. Finally, we address the multi-supplier, multi-requester routing problem. We formulate the optimization problem mathematically as a mixed-integer program and develop a local search based-heuristic algorithm. Our objective is to optimize system-level metrics, including profitability and throughput. The simulation results validate the effectiveness of our proposed approach, demonstrating significant improvements in maximizing overall profit while minimizing energy consumption, travel time, and distance for requesters.29 0Item Restricted DATA-DRIVEN EV CHARGING INFRASTRUCTURE PLANNING: ADAPTIVE SIMULATION AND STRATEGIC DEPLOYMENT IN VIRGINIA(Geroge Mason University, 2024-04-29) Zaylaee, Mohammed; Ji, WenyingAbstract The rapid adoption of electric vehicles (EVs) necessitates innovative approaches to manage and optimize the deployment of EV charging infrastructure. This scholarly paper integrates two complementary studies focusing on the dynamic modeling of EV charging behaviors and the strategic evaluation of charging station coverage in Virginia. The first part of the thesis employs advanced spatial analysis techniques to assess the current network of public EV charging stations in Virginia. Using a comprehensive dataset from Virginia Clean Cities, this analysis identifies regions with insufficient charging facilities, particularly in areas exhibiting high growth potential in the EV market. Techniques such as buffer and coverage analysis are utilized to map and visualize the distribution and capacity of existing infrastructure, thereby pinpointing areas where expansion is most needed. This spatial investigation highlights underserved areas by comparing infrastructure against critical benchmarks, facilitating targeted policy actions to bridge infrastructure gaps. The second part introduces a novel adaptive simulation framework that enhances traditional models by incorporating Bayesian inference with (MCMC). Together, these studies provide a comprehensive approach to understanding and improving the EV charging infrastructure. By combining detailed spatial analysis with adaptive simulation techniques, this scholarly paper offers actionable insights that can drive the sustainable growth of the EV market through more informed decision-making and strategic deployment of resources.191 0Item Restricted EXPLORING SUCESS FACTORS OF ADOPTING ADVANCED MANUFACTURING TECHNOLOGY FOR ELECTRICAL VEHICLES INDUSTRY IN SAUDI ARABIA APPLYING THE TECHNOLOGY ACCEPTANCE MODEL (TAM)(Al Fatais, Abdullah, 2023) Al Fatais, Abdullah Mohammed; Korwowski, WaldemarBased on the Technology Acceptance Model (TAM), the study explores the success factors of adopting Advanced Manufacturing Technology (AMT) for the Electrical Vehicles (EVs) industry in Saudi Arabia. The study assesses the impact of eight factors on AMT adoption and implementation success. The dimensions include Training & Education, Planning, Management, Technology, Business, Economic, Policies & Regulations, and Social. The study analyzes the sample including people with careers related to advanced manufacturing in Saudi Arabia, either in the public sector, private sector, industrial sector, and academia. Furthermore, an online questionnaire was used to collect data from the participants. Additionally, a Systematic Literature Review (SLR) was conducted to analyze the existing literature in addition to the utilization of TAM for data analysis. This study aims to evaluate the readiness of the Saudi industrial sector to adopt EVs manufacturing technologies. Moreover, this study is expected to use a reasonable sample size for analysis purposes which can result in solid conclusions and practical recommendations.19 0