Using Committee Neural Network for Prediction of Pressure Drop in Two-Phase Microchannels
Numerous studies have proposed to correlate experimental results, however there are still significant errors in those predictions. In this study, an artificial neural network (ANN) is considered for a two-phase flow pressure drop in microchannels incorporating four neural network structures: multila...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/15/5384 |
| _version_ | 1827711645310255104 |
|---|---|
| author | Arman Haghighi Mostafa Safdari Shadloo Akbar Maleki Mohammad Yaghoub Abdollahzadeh Jamalabadi |
| author_facet | Arman Haghighi Mostafa Safdari Shadloo Akbar Maleki Mohammad Yaghoub Abdollahzadeh Jamalabadi |
| author_sort | Arman Haghighi |
| collection | DOAJ |
| description | Numerous studies have proposed to correlate experimental results, however there are still significant errors in those predictions. In this study, an artificial neural network (ANN) is considered for a two-phase flow pressure drop in microchannels incorporating four neural network structures: multilayer perceptron (MLP), radial basis function (RBF), general regression (GR), and cascade feedforward (CF). The pressure drop predication by ANN uses six inputs (hydraulic diameter of channel, critical temperature of fluid, critical pressure of fluid, acentric factor of fluid, mass flux, and quality of vapor). According to the experimental data, for each network an optimal number of neurons in the hidden layer is considered in the range 10–11. A committee neural network (CNN) is fabricated through the genetic algorithm to improve the accuracy of the predictions. Ultimately, the genetic algorithm designates a weight to each ANN model, which represents the relative contribution of each ANN in the pressure drop predicting process for a two-phase flow within a microchannel. The assessment based on the statistical indexes reveals that the results are not similar for all models; the absolute average relative deviation percent for MLP, CF, GR, and CNN were obtained to be equal to 10.89, 10.65, 7.63, and 5.79, respectively. The CNN approach is demonstrated to be superior to many ANN techniques, even with simple linearity in the model. |
| first_indexed | 2024-03-10T17:59:01Z |
| format | Article |
| id | doaj.art-e93151e1026a41909524fcb8da1e46e7 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T17:59:01Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e93151e1026a41909524fcb8da1e46e72023-11-20T09:03:27ZengMDPI AGApplied Sciences2076-34172020-08-011015538410.3390/app10155384Using Committee Neural Network for Prediction of Pressure Drop in Two-Phase MicrochannelsArman Haghighi0Mostafa Safdari Shadloo1Akbar Maleki2Mohammad Yaghoub Abdollahzadeh Jamalabadi3Institute of Research and Development, Duy Tan University, Da Nang 550000, VietnamCORIA-CNRS (UMR6614), Normandie Universty, INSA of Rouen, 76000 Rouen, FranceFaculty of Mechanical Engineering, Shahrood University of Technology, Shahrood 3619995161, IranDepartment for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City 700000, VietnamNumerous studies have proposed to correlate experimental results, however there are still significant errors in those predictions. In this study, an artificial neural network (ANN) is considered for a two-phase flow pressure drop in microchannels incorporating four neural network structures: multilayer perceptron (MLP), radial basis function (RBF), general regression (GR), and cascade feedforward (CF). The pressure drop predication by ANN uses six inputs (hydraulic diameter of channel, critical temperature of fluid, critical pressure of fluid, acentric factor of fluid, mass flux, and quality of vapor). According to the experimental data, for each network an optimal number of neurons in the hidden layer is considered in the range 10–11. A committee neural network (CNN) is fabricated through the genetic algorithm to improve the accuracy of the predictions. Ultimately, the genetic algorithm designates a weight to each ANN model, which represents the relative contribution of each ANN in the pressure drop predicting process for a two-phase flow within a microchannel. The assessment based on the statistical indexes reveals that the results are not similar for all models; the absolute average relative deviation percent for MLP, CF, GR, and CNN were obtained to be equal to 10.89, 10.65, 7.63, and 5.79, respectively. The CNN approach is demonstrated to be superior to many ANN techniques, even with simple linearity in the model.https://www.mdpi.com/2076-3417/10/15/5384two-phase flowmicrochannelintelligence approachespressure drop |
| spellingShingle | Arman Haghighi Mostafa Safdari Shadloo Akbar Maleki Mohammad Yaghoub Abdollahzadeh Jamalabadi Using Committee Neural Network for Prediction of Pressure Drop in Two-Phase Microchannels Applied Sciences two-phase flow microchannel intelligence approaches pressure drop |
| title | Using Committee Neural Network for Prediction of Pressure Drop in Two-Phase Microchannels |
| title_full | Using Committee Neural Network for Prediction of Pressure Drop in Two-Phase Microchannels |
| title_fullStr | Using Committee Neural Network for Prediction of Pressure Drop in Two-Phase Microchannels |
| title_full_unstemmed | Using Committee Neural Network for Prediction of Pressure Drop in Two-Phase Microchannels |
| title_short | Using Committee Neural Network for Prediction of Pressure Drop in Two-Phase Microchannels |
| title_sort | using committee neural network for prediction of pressure drop in two phase microchannels |
| topic | two-phase flow microchannel intelligence approaches pressure drop |
| url | https://www.mdpi.com/2076-3417/10/15/5384 |
| work_keys_str_mv | AT armanhaghighi usingcommitteeneuralnetworkforpredictionofpressuredropintwophasemicrochannels AT mostafasafdarishadloo usingcommitteeneuralnetworkforpredictionofpressuredropintwophasemicrochannels AT akbarmaleki usingcommitteeneuralnetworkforpredictionofpressuredropintwophasemicrochannels AT mohammadyaghoubabdollahzadehjamalabadi usingcommitteeneuralnetworkforpredictionofpressuredropintwophasemicrochannels |