The focus of this work is to computationally obtain an optimized neural network (NN) model to predict battery average Nusselt number (Nuavg) data using four activations functions. The battery Nuavg is highly nonlinear as reported in the literature, which depends mainly on flow velocity, coolant type, heat generation, thermal conductivity, battery length to width ratio, and space between the parallel battery packs. Nuavg is modeled at first using only one hidden layer in the network (NN1). The neurons in NN1 are experimented from 1 to 10 with activation functions: Sigmoidal, Gaussian, Tanh, and Linear functions to get the optimized NN1. Similarly, deep NN (NND) was also analyzed with neurons and activations functions to find an optimized number of hidden layers to predict the Nuavg. RSME (root mean square error) and R-Squared (R2) is accessed to conclude the optimized NN model. From this computational experiment, it is found that NN1 and NND both accurately predict the battery data. Six neurons in the hidden layer for NN1 give the best predictions. Sigmoidal and Gaussian functions have provided the best results for the NN1 model. In NND, the optimized model is obtained at different hidden layers and neurons for each activation function. The Sigmoidal and Gaussian functions outperformed the Tanh and Linear functions in an NN1 model. The linear function, on the other hand, was unable to forecast the battery data adequately. The Gaussian and Linear functions outperformed the other two NN-operated functions in the NND model. Overall, the deep NN (NND) model predicted better than the single-layered NN (NN1) model for each activation function.

Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data

Thermal modelling and characteristic evaluation of electric vehicle battery system

The rapid rise in global oil prices, the scarcity of petroleum sources, and environmental concerns have all created severe issues. As a result of the country’s rapid expansion and financial affluence, Malaysia’s energy consumption has skyrocketed. Biodiesel and solar power are currently two of the most popular alternatives to fossil fuels in Malaysia. These two types of renewable energy sources appear to be viable options because of their abundant availability together with environmental and performance competence to highly polluting and fast depleting fossil fuels. The purpose of adopting renewable technology is to expand the nation’s accessibility to a reliable and secure power supply. The current review article investigates nonconventional energy sources added with nanosized metal particles called as nanomaterials including biodiesel and solar, as well as readily available renewable energy options. Concerning the nation’s energy policy agenda, the sources of energy demand are also investigated. The article evaluates Malaysia’s existing position in renewable energy industries, such as biodiesel and solar, as well as the impact of nanomaterials. This review article discusses biodiesel production, applications, and government policies in Malaysia, as well as biodiesel consumption and recent developments in the bioenergy sector, such as biodiesel property modifications utilizing nanoparticle additions. In addition, the current review study examines the scope of solar energy, different photovoltaic concentrators, types of solar energy harvesting systems, photovoltaic electricity potential in Malaysia, and the experimental setup of solar flat plate collectors (FPC) with nanotechnology.

/pdf/developments-in-nanoparticles-enhanced-biofuels-and-solar-153ia2e9.pdf

Developments in Nanoparticles Enhanced Biofuels and Solar Energy in Malaysian Perspective: A Review of State of the Art


 Due to the increasing demand for energy worldwide, photovoltaic cooling systems have become an important field of research in recent years. The most important factor affecting the performance of a solar PV cell is its operating temperature. For harvesting heat from solar PV systems, phase change material (PCM) is regarded as the most effective material. As a result, this study discusses and describes the effect of using PCM and NanoPCM (NPCM) in cooling PV cells. This research reviews the various feasible hybrid PVT-PCM and PVT-NPCM methods used for cooling PV. The concept focusing on PV cooling technology is discussed where air, water and nanofluid are used as the working medium in combination with PCM and NPCM. It is observed that when high performance heat transfer and improved cooling rate are needed, active cooling methods are favoured, whereas passive cooling methods rely on themselves and don’t require extra power. It is also found that the effectiveness of applying PCM or NPCM for thermal control is heavily influenced by atmospheric air temperatures as well as the precise PCM or NPCM used. It is envisaged that this review will help new researchers better understand the qualities and capabilities of each cooling strategy. They are offered to help investigators quickly identify the basic science that led to the development of the thermal performance system and also improve the overall performance of the PV system.

/pdf/a-comprehensive-review-on-recent-advancements-in-cooling-of-dxi1e6ht.pdf

A comprehensive review on recent advancements in cooling of solar photovoltaic (PV) systems using phase change materials (PCMs)

Machine Learning (ML) and/or Deep Learning (DL) methods can be used to predict fluid flow in porous media, as a suitable replacement for classical numerical approaches. Such data-driven approaches attempt to learn mappings between finite-dimensional Euclidean spaces. A novel neural framework, named Fourier Neural Operator (FNO), has been recently developed to act on infinite-dimensional spaces. A high proportion of the research available on the FNO has focused on problems with large-shape data. Furthermore, most published studies apply the FNO method to existing datasets. This paper applies and evaluates FNO to predict pressure distribution over a small, specified shape-data problem using 1700 Finite Element Method (FEM) generated samples, from heterogeneous permeability fields as the input. Considering FEM-calculated outputs as the true values, the configured FNO model provides superior prediction performance to that of a Convolutional Neural Network (CNN) in terms of statistical error assessment based on the coefficient of determination (R2) and Mean Squared Error (MSE). Sensitivity analysis considering a range of FNO configurations reveals that the most accurate model is obtained using modes=15 and width=100. Graphically, the FNO model precisely follows the observed trend in each porous medium evaluated. There is potential to further improve the FNO’s performance by including physics constraints in its network configuration.

https://www.mdpi.com/1999-4893/16/1/24/pdf?version=1673578308

Fourier Neural Operator for Fluid Flow in Small-Shape 2D Simulated Porous Media Dataset

Parallelization of inhouse develpoed code for numerical computations on heterogeneous computing machine is becoming common. As the numerical solvers and problem complexity are evolving, the parallel computing facilities are also growing. This research study deals with the use of four different schemes to parallelly compute the numerical flow equations based on the finite volume method. The different schemes proposed are applied for parallelization using central processing units and graphical processing units. Open multiprocessing (OpenMP) and compute unified device architecture (CUDA) are the parallel computing tools used for parallelization of the code applying four schemes, viz. red and black successive over-relaxation (RBSOR), wavefront, combined RBSOR and wavefront, and alternate RBSOR and wavefront scheme. The flow analysis is carried out for internal and external flow at different Reynolds numbers on dissimilar machines having their individual computational capability. Speedup obtained and parallel efficiency achieved using the proposed unusual parallelization method are investigated separately. The grid size for both the flow conditions is fixed during the parallel computation performance analysis. The RBSOR scheme provided the maximum speedup in all cases of flow, scheme, and tool used. The wavefront scheme provides the lowest speedup and parallel efficiency. The alternate scheme is better than the wavefront scheme and combined scheme using OpenMP. The speedup achieved and parallel efficiency obtained for the CUDA parallelized code are in the range of 200 × and 70%, respectively, applying the RBSOR scheme.

K. Prashantha

Papers

Parallel finite volume method-based fluid flow computations using OpenMP and CUDA applying different schemes