Design of modified structure multi-layer perceptron networks based on decision trees for the prediction of flow parameters in 90° open-channel bends
A modified multi-layer perceptron (MLP) model based on decision trees (DT-MLP) is presented to predict velocity and water free-surface profiles in a 90° open-channel bend. The ability of the new hybrid model to predict the velocity and flow depth in a 90° sharp bend is investigated and compared with...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2016-01-01
|
| Series: | Engineering Applications of Computational Fluid Mechanics |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/19942060.2015.1128358 |
| _version_ | 1811202026196959232 |
|---|---|
| author | Azadeh Gholami Hossein Bonakdari Amir Hossein Zaji Salma Ajeel Fenjan Ali Akbar Akhtari |
| author_facet | Azadeh Gholami Hossein Bonakdari Amir Hossein Zaji Salma Ajeel Fenjan Ali Akbar Akhtari |
| author_sort | Azadeh Gholami |
| collection | DOAJ |
| description | A modified multi-layer perceptron (MLP) model based on decision trees (DT-MLP) is presented to predict velocity and water free-surface profiles in a 90° open-channel bend. The ability of the new hybrid model to predict the velocity and flow depth in a 90° sharp bend is investigated and compared with the abilities of MLP and multiple-linear regression (MLR) models. The MLP and DT-MLP networks are trained and tested using 520 and 506 experimental data measured for velocity and flow depth, respectively, at five different discharge rates of 5, 7.8, 13.6, 19.1 and 25.3 l/s. The MLP and DT-MLP comparison results against MLR reveal that the two artificial neural networks (ANNs) are 84% and 16% more accurate than the MLR model in predicting the velocity and flow depth variables, respectively. According to the results, the root mean square error (RMSE) value of the DT-MLP model decreases by 9% and 7.5% in predicting velocity and flow depth, respectively, compared with the MLP model. It was found that the hybrid decision-tree-based method can significantly improve MLP neural network performance in forecasting velocity and free-surface profiles in a 90° open-channel bend. |
| first_indexed | 2024-04-12T02:33:01Z |
| format | Article |
| id | doaj.art-52b96867fae74ef4838ccb57d700415c |
| institution | Directory Open Access Journal |
| issn | 1994-2060 1997-003X |
| language | English |
| last_indexed | 2024-04-12T02:33:01Z |
| publishDate | 2016-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Engineering Applications of Computational Fluid Mechanics |
| spelling | doaj.art-52b96867fae74ef4838ccb57d700415c2022-12-22T03:51:42ZengTaylor & Francis GroupEngineering Applications of Computational Fluid Mechanics1994-20601997-003X2016-01-0110119320810.1080/19942060.2015.11283581128358Design of modified structure multi-layer perceptron networks based on decision trees for the prediction of flow parameters in 90° open-channel bendsAzadeh Gholami0Hossein Bonakdari1Amir Hossein Zaji2Salma Ajeel Fenjan3Ali Akbar Akhtari4University of RaziUniversity of RaziUniversity of RaziUniversity of RaziUniversity of RaziA modified multi-layer perceptron (MLP) model based on decision trees (DT-MLP) is presented to predict velocity and water free-surface profiles in a 90° open-channel bend. The ability of the new hybrid model to predict the velocity and flow depth in a 90° sharp bend is investigated and compared with the abilities of MLP and multiple-linear regression (MLR) models. The MLP and DT-MLP networks are trained and tested using 520 and 506 experimental data measured for velocity and flow depth, respectively, at five different discharge rates of 5, 7.8, 13.6, 19.1 and 25.3 l/s. The MLP and DT-MLP comparison results against MLR reveal that the two artificial neural networks (ANNs) are 84% and 16% more accurate than the MLR model in predicting the velocity and flow depth variables, respectively. According to the results, the root mean square error (RMSE) value of the DT-MLP model decreases by 9% and 7.5% in predicting velocity and flow depth, respectively, compared with the MLP model. It was found that the hybrid decision-tree-based method can significantly improve MLP neural network performance in forecasting velocity and free-surface profiles in a 90° open-channel bend.http://dx.doi.org/10.1080/19942060.2015.1128358MLP modeldecision treesdepth-averaged velocitywater surfacesharp bendexperimental study |
| spellingShingle | Azadeh Gholami Hossein Bonakdari Amir Hossein Zaji Salma Ajeel Fenjan Ali Akbar Akhtari Design of modified structure multi-layer perceptron networks based on decision trees for the prediction of flow parameters in 90° open-channel bends Engineering Applications of Computational Fluid Mechanics MLP model decision trees depth-averaged velocity water surface sharp bend experimental study |
| title | Design of modified structure multi-layer perceptron networks based on decision trees for the prediction of flow parameters in 90° open-channel bends |
| title_full | Design of modified structure multi-layer perceptron networks based on decision trees for the prediction of flow parameters in 90° open-channel bends |
| title_fullStr | Design of modified structure multi-layer perceptron networks based on decision trees for the prediction of flow parameters in 90° open-channel bends |
| title_full_unstemmed | Design of modified structure multi-layer perceptron networks based on decision trees for the prediction of flow parameters in 90° open-channel bends |
| title_short | Design of modified structure multi-layer perceptron networks based on decision trees for the prediction of flow parameters in 90° open-channel bends |
| title_sort | design of modified structure multi layer perceptron networks based on decision trees for the prediction of flow parameters in 90° open channel bends |
| topic | MLP model decision trees depth-averaged velocity water surface sharp bend experimental study |
| url | http://dx.doi.org/10.1080/19942060.2015.1128358 |
| work_keys_str_mv | AT azadehgholami designofmodifiedstructuremultilayerperceptronnetworksbasedondecisiontreesforthepredictionofflowparametersin90openchannelbends AT hosseinbonakdari designofmodifiedstructuremultilayerperceptronnetworksbasedondecisiontreesforthepredictionofflowparametersin90openchannelbends AT amirhosseinzaji designofmodifiedstructuremultilayerperceptronnetworksbasedondecisiontreesforthepredictionofflowparametersin90openchannelbends AT salmaajeelfenjan designofmodifiedstructuremultilayerperceptronnetworksbasedondecisiontreesforthepredictionofflowparametersin90openchannelbends AT aliakbarakhtari designofmodifiedstructuremultilayerperceptronnetworksbasedondecisiontreesforthepredictionofflowparametersin90openchannelbends |