Turbulent flow is a complex and vital phenomenon in fluid dynamics, as it is the most common type of flow in both natural and artificial systems. Traditional methods of studying turbulent flow, such as computational fluid dynamics and experiments, have limitations such as high computational costs, experiment costs, and restricted problem scales and sizes. Recently, artificial intelligence has provided a new avenue for examining turbulent flow, which can help improve our understanding of its flow features and physics in various applications. Strained turbulent flow, which occurs in the presence of gravity in situations such as combustion chambers and shear flow, is one such case. This study proposes a novel data-driven transformer model to predict the velocity field of turbulent flow, building on the success of this deep sequential learning technique in areas such as language translation and music. The present study applied this model to experimental work by Hassanian et al., who studied distorted turbulent flow with a specific range of Taylor microscale Reynolds numbers 100<Reλ<120. The flow underwent a vertical mean strain rate of 8 s−1 in the presence of gravity. The Lagrangian particle tracking technique recorded every tracer particle's velocity field and displacement. Using this dataset, the transformer model was trained with different ratios of data and used to predict the velocity of the following period. The model's predictions significantly matched the experimental test data, with a mean absolute error of 0.002–0.003 and an R2 score of 0.98. Furthermore, the model demonstrated its ability to maintain high predictive performance with less training data, showcasing its potential to predict future turbulent flow velocity with fewer computational resources. To assess the model, it has been compared to the long short-term memory and gated recurrent units model. High-performance computing machines, such as JUWELS-DevelBOOSTER at the Juelich Supercomputing Center, were used to train and run the model for inference.

The subject of this study presents an employed method in deep learning to create a model and predict the following period of turbulent flow velocity. The applied data in this study are extracted datasets from simulated turbulent flow in the laboratory with the Taylor microscale Reynolds numbers in the range of 90 < $R_{\lambda }$< 110. The flow has been seeded with tracer particles. The turbulent intensity of the flow is created and controlled by eight impellers placed in a turbulence facility. The flow deformation has been conducted via two circular flat plates moving toward each other in the center of the tank. The Lagrangian particle-tracking method has been applied to measure the flow features. The data have been processed to extract the flow properties. Since the dataset is sequential, it is used to train long short-term memory and gated recurrent unit model. The parallel computing machine DEEP-DAM module from Juelich supercomputer center has been applied to accelerate the model. The predicted output was assessed and validated by the rest of the data from the experiment for the following period. The results from this approach display accurate prediction outcomes that could be developed further for more extensive data documentation and used to assist in similar applications. The mean average error and R² score range from 0.001–0.002 and 0.9839–0.9873, respectively, for both models with two distinct training data ratios. Using GPUs increases the LSTM performance speed more than applications with no GPUs.

This study proposes a computational model to define the wind velocity of the environment on the photovoltaic (PV) module via heat transfer concepts. The effect of the wind velocity and PV module is mostly considered a cooling effect. However, cooling and controlling the PV module temperature leads to the capability to optimize the PV module efficiency. The present study applied a nominal operating cell temperature (NOCT) condition of the PV module as a reference condition to determine the wind velocity and PV module temperature. The obtained model has been examined in contrast to the experimental heat transfer equation and outdoor PV module performance. The results display a remarkable matching of the model with experiments. The model’s novelty defines the PV module temperature in relation to the wind speed, PV module size, and various ambient temperatures that were not included in previous studies. The suggested model could be used in PV module test specification and provide analytical evaluation.

This paper evaluates the photovoltaic (PV) module operating temperature’s relation to efficiency via a numerical heat transfer model. The literature reports that higher PV module operating temperatures impact PV module efficiency. There are dozens of explicit and implicit equations used to determine the PV module operating temperature. However, they are not universal, and for each application, it is necessary to insert a correction coefficient based on the environment and boundary conditions. Using a numerical method covering a more comprehensive range of PV module operation conditions to estimate a global equation, this study considers the solar radiation flux, Gt, solar ray direction with respect to the ground level, γ, convective heat transfer coefficient, h, tilt angle, β, ambient temperature, Ta, PV power output, Ppv, PV panel efficiency, η, and environmental properties. The results match the extant empirical work and related literature. PV module efficiency is found to have a linear relationship to the PV module operating temperature via a numerical heat transfer model corresponding to the well-known PV module. It specifies that heat transfer convection changes with PV module tilt angle, causing PV module operating temperature effects. It also represents the PV module operating temperature variations with ambient temperature and solar flux, like those reported in the literature.

In this study, recorded empirical data were applied with a practical approach to investigate the optimal tilt angle of the flat plate collectors facing south for a long period in Tehran, Iran. The data included 20 years of recorded average total radiation on the horizontal plane in Tehran’s meteorological station. Based on the previous studies, the annual optimum tilt angle for Tehran was estimated at 33 degrees annually; however, this estimation does not focus on the energy absorption and effectiveness of changing the tilt angle monthly, seasonally, and bi-annually via measured data. This paper aims to explain this distinction between various radiation receptions with different tilt angle adjustments. This study shows that annual solar cumulative radiation energy gained via a monthly tilt angle can be approximately 7% higher than that achieved with an annual tilt angle setup. Additionally, the seasonal and bi-annual tilt angles have about 6% more annual cumulative radiation absorption than the annual tilt angle setup. Moreover, with consideration of similar monthly received radiation, the results illustrate that the radiation gained with a monthly tilt angle set up was 20% greater in the summer months than an annual tilt angle adjustment.

This study aimed to simulate straining turbulent flow empirically, having direct similarities with vast naturally occurring flows and engineering applications. The flow was generated in 100<Re_λ<500 and seeded with passive and inertial particles. Lagrangian particle tracking and particle image velocimetry were employed to extract the dynamics of particle statistics and flow features, respectively. The studies for axisymmetric straining turbulent flow reported that the strain rate, flow geometry, and gravity affect particle statistics. To practically investigate mentioned effects in the literature, we present the behavior of both passive and inertial particles from the novel experiment conducted on initially homogeneous turbulence undergoing a sudden axisymmetric expansion. We represent the result with two different mean strains and Reynolds-Taylor microscales. However, this study, in contrast to the previous studies, considers the fields of inertial particles in the presence of gravity. The result discloses that the novel designed and conducted experiments simulated the flow satisfactorily. Then the particle behavior in such flow showed the effectiveness of the flow distortion on particle dynamics such as velocity root mean square (RMS) and Reynolds-stress. Straining turbulence flow is subject to many industrial applications and physics studies, such as stagnation points, external flow around an airfoil, internal flow in changeable cross-section pipe, expansion in the engine mixing chamber, and leading edge erosion. This study's conclusion could apply constructively to these areas.