Hydrological flow rate estimation using artificial neural networks: Model development and potential applications

2016 ◽  
Vol 291 ◽  
pp. 373-385 ◽  
Author(s):  
Srđan Kostić ◽  
Milan Stojković ◽  
Stevan Prohaska
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Flow Rate ◽  
Model Development ◽  
Rate Estimation ◽  
Potential Applications ◽  
Artificial Neural

scholarly journals Application of Phase Change Material and Artificial Neural Networks for Smoothing of Heat Flux Fluctuations

Energies ◽  
2021 ◽  
Vol 14 (12) ◽  
pp. 3531
Author(s):  
Tomasz Tietze ◽  
Piotr Szulc ◽  
Daniel Smykowski ◽  
Andrzej Sitka ◽  
Romuald Redzicki
Keyword(s):  
Neural Networks ◽  
Heat Flux ◽  
Artificial Neural Networks ◽  
Phase Change ◽  
Mass Flow Rate ◽  
Phase Change Material ◽  
Flow Rate ◽  
Smoothing Effect ◽  
Artificial Neural ◽  
Change Material

The paper presents an innovative method for smoothing fluctuations of heat flux, using the thermal energy storage unit (TES Unit) with phase change material and Artificial Neural Networks (ANN) control. The research was carried out on a pilot large-scale installation, of which the main component was the TES Unit with a heat capacity of 500 MJ. The main challenge was to smooth the heat flux fluctuations, resulting from variable heat source operation. For this purpose, a molten salt phase change material was used, for which melting occurs at nearly constant temperature. To enhance the smoothing effect, a classical control system based on PID controllers was supported by ANN. The TES Unit was supplied with steam at a constant temperature and variable mass flow rate, while a discharging side was cooled with water at constant mass flow rate. It was indicated that the operation of the TES Unit in the phase change temperature range allows to smooth the heat flux fluctuations by 56%. The tests have also shown that the application of artificial neural networks increases the smoothing effect by 84%.

scholarly journals The evaluation on artificial neural networks (ANN) and multiple linear regressions (MLR) models over particulate matter (PM10) variability during haze and non-haze episodes: A decade case study

2019 ◽  
Vol 15 (2) ◽  
pp. 164-172 ◽  
Author(s):  
Ku Mohd Kalkausar Ku Yusof ◽  
Azman Azid ◽  
Muhamad Shirwan Abdullah Sani ◽  
Mohd Saiful Samsudin ◽  
Siti Noor Syuhada Muhammad Amin ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Particulate Matter ◽  
Meteorological Factors ◽  
Model Development ◽  
Eastern Region ◽  
Multiple Linear Regressions ◽  
Artificial Neural ◽  
Linear Regressions

The comprehensives of particulate matter studies are needed in predicting future haze occurrences in Malaysia. This paper presents the application of Artificial Neural Networks (ANN) and Multiple Linear Regressions (MLR) coupled with sensitivity analysis (SA) in order to recognize the pollutant relationship status over particulate matter (PM10) in eastern region. Eight monitoring studies were used, involving 14 input parameters as independent variables including meteorological factors. In order to investigate the efficiency of ANN and MLR performance, two different weather circumstances were selected; haze and non-haze. The performance evaluation was characterized into two steps. Firstly, two models were developed based on ANN and MLR which denoted as full model, with all parameters (14 variables) were used as the input. SA was used as additional feature to rank the most contributed parameter to PM10 variations in both situations. Next, the model development was evaluated based on selected model, where only significant variables were selected as input. Three mathematical indices were introduced (R2, RMSE and SSE) to compare on both techniques. From the findings, ANN performed better in full and selected model, with both models were completely showed a significant result during hazy and non-hazy. On top of that, UVb and carbon monoxide were both variables that mutually predicted by ANN and MLR during hazy and non-hazy days, respectively. The precise predictions were required in helping any related agency to emphasize on pollutant that essentially contributed to PM10 variations, especially during haze period.

Using Artificial Neural Networks in the Reactor Safety Research

2008 ◽  
Author(s):  
Alexander Kratzsch ◽  
Wolfgang Ka¨stner ◽  
Rainer Hampel
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Heat Dissipation ◽  
Model Development ◽  
Reactor Core ◽  
Differential Pressure ◽  
Reactor Safety ◽  
Safety Research ◽  
Artificial Neural ◽  
Residual Heat

The paper deals with the creation of a differential pressure model with artificial neural networks (ANN). Particular, model development and verification tests are considered. One of the main features in reactor safety research is the safe heat dissipation from the reactor core and the reactor containment of light-water reactors. In the case of loss of coolant accident (LOCA) the possibility of the entry of isolation material into the reactor containment and the building sump of the reactor containment and into the associated systems to the residual heat exhaust is a serious problem. This can lead to a handicap of the system functions. To ensure the residual heat exhaust it is necessary the emergency cooling systems to put in operation which transport the water from the sump to the condensation chamber and directly to the reactor pressure vessel. A high allocation of the sieves with fractionated isolation material, in the sump can lead to a blockage of the strainers, inadmissibly increase of differential pressure, build-up at the sieves and to malfunctioning pumps. Hence, the scaling and retention of fractionated isolation material in the building sump of the reactor containment must be estimated. This allows the potential plant status in case of incidents to be assessed. The differential pressure is the essential parameter for the assessment of allocation of the strainers. For modelling we use artificial neural networks. To build up the ANN, the available experimental data are used to train the ANN.

Artificial Neural Networks Modeling of Electrospun Polyurethane Nanofibers from Chloroform/Methanol Solution

2016 ◽  
Vol 41 ◽  
pp. 18-30 ◽  
Author(s):  
Saman Firoozi ◽  
Amir Amani ◽  
Mohammad Ali Derakhshan ◽  
Hossein Ghanbari
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Polymer Solution ◽  
Flow Rate ◽  
Applied Voltage ◽  
Polymer Concentration ◽  
Electrospun Nanofibers ◽  
Dominant Factor ◽  
Artificial Neural ◽  
Chloroform Methanol

In this study, electrospun nanofibers of polyurethane were prepared utilizing a new solvent system made of chloroform/methanol. Also, we planned to assess effects of four important parameters on diameter of electrospun polyurethane nanofibers using Artificial Neural Networks (ANNs). The parameters investigated included flow rate of syringe pump, distance of spinneret to collector, applied voltage and concentration of polymer solution. Diameter of obtained electrospun nanofibers was measured using scanning electron microscopy (SEM). Results showed that flow rate and distance had reverse relation with fiber diameter, while applied voltage and concentration of polymer solution directly affected the diameter. Also, polymer concentration was shown to be the dominant factor here.

scholarly journals Comparative Evaluation of Artificial Neural Networks and Data Analysis in Predicting Liposomes’ Size in a Periodic Disturbance Micromixer

2021 ◽  
Vol 4 (1) ◽  
pp. 42
Author(s):  
Ixchel Ocampo ◽  
Rubén R. Lopéz ◽  
Vahée Nerguizian ◽  
Ion Stiharu ◽  
Sergio Camacho León
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Data Analysis ◽  
Flow Rate ◽  
Periodic Disturbance ◽  
Analysis Techniques ◽  
Relevant Variables ◽  
Total Data ◽  
Liposome Size ◽  
Artificial Neural

Artificial Neural Networks (ANN) and Data analysis are powerful tools used for supporting decision-making. They have been employed in diverse fields and one of them is nanotechnology used, for example, in predicting particles size. Liposomes are nanoparticles used in different biomedical applications that can be produced in Dean Forces-based Periodic Disturbance Micromixers (PDM). In this work, ANN and data analysis techniques are used to build a liposome size prediction model by using the most relevant variables in a PDM, i.e., Flow Rate Radio (FRR) and Total Flow Rate (TFR). The ANN was designed in MATLAB and fed data from 60 experiments, which were 70% training, 15% validation and 15% testing. For data analysis, regression analysis was used. The model was evaluated; it showed 98.147% of regression number for training and 97.247% in total data compared with 78.89% regression number obtained by data analysis. These results demonstrate that liposomes’ size can be better predicted by ANN with just FRR and TFR as inputs, compared with data analysis techniques when the temperature, solvents, and concentrations are kept constant.

Sign in / Sign up

Export Citation Format

Share Document