Accurate modeling is an important aspect for a reliable design, control and optimization of proton exchange membrane (PEM) fuel cell. The mathematical model of PEM fuel cell involves a set of non-linear equations and is considered as multi-variate, multi-modal and non-linear optimization problem having seven unidentified parameters. This paper proposes a new hybrid approach based on weIghted meaN oF vectOrs and Nelder-Mead (INFONM) method for PEM fuel cell parameter extraction. An optimization problem is framed and a sum of squared error (SSE) based objective function is formulated between estimated and experimental voltages. The effectiveness of the developed approach is evaluated on four available benchmark fuel cell data sheets such as NedStack PS6, BCS 500 W, 250 W and Ballard Mark V fuel cell stacks. A fair comparison is presented with well-established algorithms as well as existing literature work to demonstrate the superiority of INFONM. The results reveal that hybrid approach produces better outcomes in terms of accuracy, reliability and effectiveness as compared to other algorithms. Also, the good closeness between the estimated and experimental polarization curves proves that hybrid approach accurately determines unknown parameters. The obtained value of SSE for NedStack PS6, BCS 500 W, 250 W and Ballard Mark V PEM fuel cell stacks are 1.242, 0.0111, 0.317, and 0.619 respectively whereas, the maximum values of percentage voltage deviations are -1.076%, 0.458%, 1.688%, and 2.69% respectively. Furthermore, statistical indices such as mean, minimum, standard deviation, and maximum value of SSE for hybrid approach indicate a least value among all other algorithms which elucidates hybrid approach as more robust and efficient. Additionally, the convergence curves, box plot study and non-parametric test further validate the robustness and reliability of INFONM in identifying unknown parameters of PEM fuel cell. Moreover, a sensitivity analysis considering SOBOL indicators is also presented to provide an illustration of influence of variation in extracted parameters on PEM fuel cell model.

The high penetration of renewables into the active distribution network (ADN) brings voltage deviation and difficulties to the optimal power flow (OPF) problem. The optimal operation of the distribution grid aims to efficiently manage the flow of electricity from sources to end-users, ensuring a resilient and sustainable grid. To perform the optimal operation, OPF plays a pivotal role in solving a complex optimization problem due to the system’s operational constraints and the provided OPF solutions. Implementing traditional OPF algorithms can be challenging for large-scale networks with complex topologies and constraints. The most recent advancement in learning-based models has shifted the paradigm towards data-driven approaches. This paper proposes a high-fidelity graph attention networks (GAT) model that leverages the attention mechanism and graph convolution feature mapping property to learn neighbor informative node representations for OPF solutions.We validated the proposed model on the IEEE-33, 69, and modified 123-bus power distribution networks. The proposed GAT model outperformed the state-of-the-art MPGCN and DNN models, achieving improvement of 86.33% and 62.71%, respectively, under 60% DG penetration condition. The robustness assessment of DNN, MPGCN, and GAT models are also compared in all three test cases. The GAT model exhibited less variability in its median error 0.22, 0.21, and 0.038, respectively, in each case. For computational efficiency analysis, the GAT model was processed on an IEEE-123 bus with 13,810 samples in 782 seconds, which remains within the steady-state OPF calculation time limit of 15 minutes (900 seconds). The proposed GAT model showcases its effectiveness and promises results for addressing the OPF problem in the distribution network, as evidenced by performance evaluation metrics.

The principal reason for why electric vehicles are required to serve as an alternative to the more widespread gasoline and petroleum-based vehicles used in modern times is due to the use of an environmentally conscious means of transportation or to circumvent the tumultuous economic dealings of the compressed natural gas and petroleum industries. There is a growing daily need for large, high-voltage e-mobilities, mostly driven by anticipated advancements in electric vehicle technology. Consequently, all of the various components of these vehicles must be able to be accommodated within a limited and compact space. The battery is an essential component in e-mobility. The insulation, health monitoring, and problem diagnostics of lithium-ion (Li-ion) batteries are of utmost importance in ensuring these vehicles’ safety and efficient functioning. Real-time and fast insulation detection techniques are required to ensure safety in high-voltage (HV) vehicles and to avoid insulation failure. This paper used the Recursive-Least-Squares (RLS) algorithm because it is computationally efficient for building the insulation detection system. Based on the RLS technique, we proposed field programmable gate array (FPGA)-based algorithms and implemented them using VHDL coding. The FPGA is very fast at detection, and the error is lower. We validated the FPGA results with MATLAB simulation results from the existing literature, and the errors are much less when using FPGAs. An experimental hardware platform was also created to validate the proposed FPGA technique with various motor and resistive loadings on electric vehicles (EVs).

Global warming and an impending energy problem have compelled nations to become greener and cleaner. Worldwide, interest in electric vehicles (EVs) is growing as a result of rising gasoline prices and environmental concerns. The need for electrical components and cabling networks is expanding along with the demand for electrified vehicles. The complexity of vehicle electrical, electronics, and control circuits is also rising. There are many wire and cable performance issues in modern e-mobility, including limited space, vibration, high-temperature variation, unfriendly fluids, and rising data transmission requirements. Thus, it is important to study and evaluate the thermal and electrical stresses in the electric vehicles cabling network to avoid insulation failure, which causes fire accidents in the electric components of EVs. An EV's entire electrical system gets hotter, and insulation strength is affected by both temperature and the electrical field. The insulation system is one of the most important components in any electrified vehicle. From a design and protection perspective, the computation of electric potential distribution and electric field within and around the cables of electric vehicles is very important. The strong non-linear dependency of the electrical conductivity of the insulation material on prevailing electrical stress and temperature makes the field problem not only coupled but also non-linear. Finite Difference Numerical (FDM) is used for non-linear field computation. In this paper, different electric vehicle cabling network layouts were studied and listed the challenges. Chosen the high voltage cables of electric vehicles from the cabling network and numerically computed the conductivity, temperature, and electrical fields of cable.

The demand for pollution-free transportation is increasing daily worldwide due to increasing concerns about global warming, greenhouse gas emissions, and the depletion of fossil fuels. In e-mobility, electric vehicles (EVs) have received massive popularity due to their performances and efficiencies compared with IC engine vehicles in recent decades. Cables play an essential role in delivering electric power to the different electrical components system from the battery source of vehicles. Electrical insulation is the backbone of the power cable, and its state is usually used to reflect the healthy condition of this cable and any electrical networks. Deterioration of the cable during normal operation is a major concern. Usually, electric cables receive less maintenance as compared to other electrical components in EVs. Due to the many stresses, the cable insulation must constantly withstand better connectivity between different parts in e-mobility. In the analytical method, the solution obtains known elementary functions by integrating a partial differential equation better to understand the variation of thermal and electrical stresses. This paper studied the high voltage cabling network of electric vehicles and the analytical method used for computing conductivity, temperature, and electrical stress distribution in electric vehicle cabling networks by including the higher vehicle ambient temperatures. The thermal and electrical stress maximizes at the conductors' surface and gradually reduces the function of the radial distance.

An accurate and efficient approach is required to identify the unknown parameters of solid oxide fuel cell (SOFC) mathematical model for a robust design of any energy system considering SOFC. This research study proposes a modified fire hawk algorithm (MFHA) to determine the values of SOFC model parameters. The performance evaluation of MFHA is tested on two case studies. Firstly, the performance of MFHA is tested on commercially available cylindrical cell developed by Siemens at four temperatures. Results reveal that the least value of sum of squared error (SSE) is 1.04E−05, 2.30E−05, 1.03E−05, and 1.60E−05 at 1073 K, 1173 K, 1213 K, and 1273 K respectively. Results obtained using MFHA have been compared with original fire hawk algorithm (FHA) and other well established and recent algorithms. Secondly, MFHA is implemented for estimating unknown parameters of a 5 kW dynamic tabular stack of 96 cells at various pressures and temperatures. The obtained value of SSE at different temperatures of 873 K, 923 K, 973 K, 1023 K and 1073 K is 1.18E−03, 6.12E−03, 2.21E−02, 5.18E−02, and 6.00E−02, respectively whereas, SSE at different pressures of 1 atm, 2 atm, 3 atm, 4 atm, and 5 atm is 6.05E−02, 6.11E−02, 5.53E−02, 5.11E−02, and 6.64E−02 respectively.