KNT-artificial neural network model for flux prediction of ultrafiltration membrane producing drinking water

2004 ◽  
Vol 50 (8) ◽  
pp. 103-110 ◽  
Author(s):  
H.K. Oh ◽  
M.J. Yu ◽  
E.M. Gwon ◽  
J.Y. Koo ◽  
S.G. Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Correlation Coefficient ◽  
Network Model ◽  
Operating Conditions ◽  
Transmembrane Pressure ◽  
Feed Water ◽  
Permeate Flux ◽  
Artificial Neural

This paper describes the prediction of flux behavior in an ultrafiltration (UF) membrane system using a Kalman neuro training (KNT) network model. The experimental data was obtained from operating a pilot plant of hollow fiber UF membrane with groundwater for 7 months. The network was trained using operating conditions such as inlet pressure, filtration duration, and feed water quality parameters including turbidity, temperature and UV254. Pre-processing of raw data allowed the normalized input data to be used in sigmoid activation functions. A neural network architecture was structured by modifying the number of hidden layers, neurons and learning iterations. The structure of KNT-neural network with 3 layers and 5 neurons allowed a good prediction of permeate flux by 0.997 of correlation coefficient during the learning phase. Also the validity of the designed model was evaluated with other experimental data not used during the training phase and nonlinear flux behavior was accurately estimated with 0.999 of correlation coefficient and a lower error of prediction in the testing phase. This good flux prediction can provide preliminary criteria in membrane design and set up the proper cleaning cycle in membrane operation. The KNT-artificial neural network is also expected to predict the variation of transmembrane pressure during filtration cycles and can be applied to automation and control of full scale treatment plants.

Nonlinear auto-regressive neural network for mathematical modelling of an airship using experimental data

2018 ◽  
Vol 233 (7) ◽  
pp. 2549-2569
Author(s):  
Farrukh Mazhar ◽  
Mohammad A Choudhry ◽  
Muhammad Shehryar
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Flight Test ◽  
Aerial Vehicle ◽  
Auto Regressive ◽  
Artificial Neural ◽  
Trained Neural Network

Autonomous flight of an aerial vehicle requires a sufficiently accurate mathematical model, which can capture system dynamics in the presence of external disturbances. Artificial neural network is known for ideal in capturing systems behaviour, where little knowledge about vehicle dynamics is available. In this paper, we explored this potential of artificial neural network for characterizing nonlinear dynamics of an unmanned airship. The flight experimentation data for an outdoor experimental airship are acquired through a series of pre-determined flight tests. The experimental data are subjected to a class of dynamic recurrent neural network model dubbed as nonlinear auto-regressive model with exogenous inputs for training. Sufficiently trained neural network model captured and demonstrated the longitudinal dynamics of the airship satisfactorily. We also demonstrated the usefulness of proposed technique for Lotte airship, wherein the performance of proposed model is validated and analysed for the Lotte airship flight test data.

Artificial Neural Network Applied to Predicting the Surface Tension of Acoustically Levitated Droplets of Supercooling Nanofluids

NANO ◽  
2021 ◽  
pp. 2150108
Author(s):  
Baohui Wu ◽  
Yudong LIU ◽  
Dengshi Wang ◽  
Nan Jiang ◽  
Jie Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Surface Tension ◽  
Artificial Neural Network ◽  
Graphene Oxide ◽  
Network Model ◽  
Neural Network Model ◽  
Artificial Neural Network Model ◽  
Deionized Water ◽  
Artificial Neural

Droplet oscillation method is a noncontact experimental approach, which can be used to measure the surface tension of acoustically levitated droplet. In this paper, we obtained huge amounts of experimental data of deionized water and water-based graphene oxide nanofluids within the temperature range of [Formula: see text]8.2–[Formula: see text]C. Based on the experimental data, we analyzed the influence of droplet’s deformation and frequency shift phenomenon on the surface tension of levitated droplet. Eight parameters that strongly correlate with surface tension were found and used as input neurons of artificial neural network model to predict the surface tension of supercooling graphene oxide nanofluids. The experimental data of nonsupercooling graphene oxide nanofluids were used as training set to optimize artificial neural network model, and that of deionized water were served as validation set, which was used to verify the predictive ability of artificial neural network model. The root mean square error of the optimized artificial neural network model to validation set is only 0.2558[Formula: see text]mN/m, and the prediction values of the surface tension of supercooling deionized water were in good agreement with the theoretical values calculated by Vargaftik equation, which indicates that artificial neural network model can deal well with the complex nonlinear relationship. Afterwards, we successfully predicted the surface tension of supercooling nanofluids by means of the optimized artificial neural network model and obviously reduced the dispersion and deviation caused by droplet deformation and other problems during oscillation process.

Using Artificial Neural Network (ANN) for Manipulating Energy Gain of Nansulate Coating

2011 ◽  
Vol 2 (1) ◽  
Author(s):  
Hadi Salehi ◽  
Mosayyeb Amiri ◽  
Morteza Esfandyari
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Energy Gain ◽  
Operating Conditions ◽  
Maximum Relative Error ◽  
Ann Model ◽  
Wide Range ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

In this work, an extensive experimental data of Nansulate coating from NanoTechInc were applied to develop an artificial neural network (ANN) model. The Levenberg–Marquart algorithm has been used in network training to predict and calculate the energy gain and energy saving of Nansulate coating. By comparing the obtained results from ANN model with experimental data, it was observed that there is more qualitative and quantitative agreement between ANN model values and experimental data results. Furthermore, the developed ANN model shows more accurate prediction over a wide range of operating conditions. Also, maximum relative error of 3% was observed by comparison of experimental and ANN simulation results.

scholarly journals Modeling the cooling performance of vortex tube using a genetic algorithm-based artificial neural network

2016 ◽  
Vol 20 (1) ◽  
pp. 53-65 ◽  
Author(s):  
Hassan Pouraria ◽  
Seyed Kia ◽  
Warn-Gyu Park ◽  
Bahman Mehdizadeh
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Vortex Tube ◽  
Temperature Drop ◽  
Cooling Performance ◽  
Artificial Neural

In this study, artificial neural networks (ANNs) have been used to model the effects of four important parameters consist of the ratio of the length to diameter(L/D), the ratio of the cold outlet diameter to the tube diameter(d/D), inlet pressure(P), and cold mass fraction (Y) on the cooling performance of counter flow vortex tube. In this approach, experimental data have been used to train and validate the neural network model with MATLAB software. Also, genetic algorithm (GA) has been used to find the optimal network architecture. In this model, temperature drop at the cold outlet has been considered as the cooling performance of the vortex tube. Based on experimental data, cooling performance of the vortex tube has been predicted by four inlet parameters (L/D, d/D, P, Y). The results of this study indicate that the genetic algorithm-based artificial neural network model is capable of predicting the cooling performance of vortex tube in a wide operating range and with satisfactory precision.

Predicting Nanofiltration Performance during Treatment of Welding Electrode Manufacturing Wastewater, Using Artificial Neural Networks

2014 ◽  
Vol 618 ◽  
pp. 55-59
Author(s):  
H. Alizadeh Golestani
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Cross Flow ◽  
Transmembrane Pressure ◽  
Permeate Flux ◽  
Absolute Deviation ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Set Up ◽  
Welding Electrode

This paper presents artificial neural network (ANN) predictions for a nanofiltration membrane used to treat wastewater of welding electrode manufacturing in a cross flow set up. The main parameters were time, feed flow rate, and transmembrane pressure (TMP). The experimental data were correlated and analyzed using ANN. ANN’s prediction of the permeate flux, turbidity, total dissolved solids (TDS), hardness for various TMPs, and flow rates are discussed. The effects of the training algorithm, neural network architectures, and transfer function on the ANN performance, as reflected by the percentage average absolute deviation, are discussed. A network with one input layer, 50-100 hidden layers, and one output layer is found to be adequate for mapping input–output relationships and providing a good interpolative tool. A good agreement has been obtained between the ANN predictions and the experimental data with a deviation below 2% for all cases considered.

Prediction of Efficient Operating Conditions Inside a Heavy-Duty Natural Gas Spark Ignition Engine Using Artificial Neural Networks

2020 ◽  
Author(s):  
Jinlong Liu ◽  
Christopher Ulishney ◽  
Cosmin E. Dumitrescu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Artificial Neural Network Model ◽  
Fused Silica ◽  
Operating Conditions ◽  
Spark Ignition Engine ◽  
Optical Engine ◽  
Artificial Neural

Abstract Research engines with optical access can assist traditional engine development and optimization by providing first-hand information of in-cylinder combustion process. However, the fragility of the optical engine components (e.g., the see-thru windows are usually made from fused silica) limit the engine operating conditions such as the maximum in-cylinder pressure and pressure rise rate. To make it easier to determine if a particular engine operating condition can be used for optical investigations, a back-propagation artificial neural network model was built to provide the values of pressure-based parameters of interest for engine safety. The training data came from steady-state engine experiments that changed spark timing, mixture equivalence ratio, and engine speed, but using the non-optical configuration of the engine to widen the testing conditions. The comparison between model predictions and experimental data indicated that the well-trained artificial neural network model can provide fast and consistent results, making it an easy-to-use tool for designing future optical engine investigations.

Sign in / Sign up

Export Citation Format

Share Document