This study investigates the use of deep learning algorithms to predict the discharge coefficient (Cd) of contaminated multi-hole orifice flow meters with circular opening. Datasets (MHO1 and MHO2) were obtained from computational fluid dynamic simulations for two circular multi-hole orifice flow meters of different geometries. To evaluate the performance and generalization capabilities of different models, three distinct scenarios, each involving different dataset configurations and normalization techniques were designed. For each scenario, three deep learning models (feedforward neural networks, convolutional neural network, and recurrent neural network) were implemented and evaluated based on their performance metrics, including mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and the coefficient of determination (R2). For all three scenarios eight models for each neural network model were developed (FFNN – four models, CNN – two models, RNN – two models). The same structure of models was used across all scenarios to ensure consistency in the evaluation process. Key input parameters include geometrical and flow variables such as β – parameter, contamination thickness, radial distance, Reynolds number, and orifice diameters. Results demonstrate the effectiveness of deep learning in accurately predicting discharge coefficient for different contamination conditions and different geometries. This study showed that deep learning models can be used for prediction of discharge coefficients for multi-hole orifice flow meters of similar geometry, based on data obtained from one orifice flow meter for different contamination parameters.

- The influence of multi-hole orifice flow meter geometry parameters on the parameters of Newtonian fluid through multi-hole orifice meters was investigated using computational fluid dynamics as well as the effect of contamination in front of the MHO flow meter. The air flow was steady, three-dimensional, and turbulent. Analysed Newtonian fluid was air and physical properties that were considered were density and dynamic viscosity. The numerical method was finite volume method, and standard k-ε turbulence model was used for turbulence modelling. Multi-hole orifice meter with thre e different β parameters 0.5 5, 0.6 and 0.7, was observed and Reynold’s number was 10 5 . The pressure drop and discharge coefficient were analysed. Numerical simulations were performed using commercial software the STAR-CCM+ 2019.2. It was found that increase in 𝛽𝛽 parameter results with the decrease in pressure drop and increase in discharge coefficient. Also, it was found that that the influence of 𝛽𝛽 parameter is much higher when analyzing pressure drop rather than discharge coefficient values. Numerical simulations were also performed to investigate the effect of contaminations in front of the MHO plate with 𝛽𝛽 = 0.5, on the discharge coefficients. It was found that as the contamination angle is increased the discharge coefficient tends to increase.

Drying of textiles in industrial facilities represents an energy-intensive process where a large number of measures for energy and production cost savings can be introduced. Typical measures include the introduction of energy management, waste-heat recovery, process optimization and so on. Drying is a complex process with coupled heat and mass transfer between the heated air and humid textile, where parameters such as the air flow rate, air velocity and its flow regime and textile velocity and water content represent significant influential factors. The distribution of air temperature and density inside the drying section of an industrial stenter frame is analyzed in detail using three-dimensional numerical simulation, where the textile is modeled as a porous medium to analyze moisture diffusion within the textile. Heated air is introduced into a chamber by inlet nozzles and removed by exit nozzles, the distribution of which is based on actual machine configuration. A humid textile is introduced into a section, where temperature and density distribution within the textile are calculated for selected time periods. During the simulation in the Fluent program, models of specific component transport, multiphase air flow, turbulent flow, porosity and evaporation were used. The results represent a valuable data set that provides an in-depth insight into the drying process in the industrial stenter machine.

The heat transfer performances of ionic liquids [C4mpyrr][NTf2] and ionanofluids with Al2O3 nanoparticles under a laminar flow regime, and with constant heat flux on the tube wall is numerically modeled and analyzed for three values of initial/inlet temperature and for two Reynolds numbers. Heat transfer characteristics were considered by analyzing the temperature distribution along the upper wall, as well as by analyzing the Nusselt number and heat transfer coefficient. The results obtained numerically were validated using Shah’s equation for ionic liquid. Thermophysical properties were temperature-dependent, and obtained by curve-fitting the experimental values of the thermophysical properties. Furthermore, the same set of results was calculated for the ionic liquid and ionanofluids with constant thermophysical properties. It is concluded that the assumption that thermophysical properties are constant has a significant influence on the heat transfer performance parameters of both ionic liquid and ionanofluids, and therefore such assumptions should not be made in research.