A NEW NON‐TUNED SELF‐ADAPTIVE MACHINE‐LEARNING APPROACH FOR SIMULATING THE DISCHARGE COEFFICIENT OF LABYRINTH WEIRS. (13th March 2020)
- Record Type:
- Journal Article
- Title:
- A NEW NON‐TUNED SELF‐ADAPTIVE MACHINE‐LEARNING APPROACH FOR SIMULATING THE DISCHARGE COEFFICIENT OF LABYRINTH WEIRS. (13th March 2020)
- Main Title:
- A NEW NON‐TUNED SELF‐ADAPTIVE MACHINE‐LEARNING APPROACH FOR SIMULATING THE DISCHARGE COEFFICIENT OF LABYRINTH WEIRS
- Authors:
- Norouzi, Payam
Rajabi, Ahmad
Izadbakhsh, Mohammad Ali
Shabanlou, Saeid
Yosefvand, Fariborz
Yaghoubi, Behrouz - Abstract:
- Abstract: In this study, the labyrinth weir discharge coefficient was simulated using the self‐adaptive extreme learning machine (SAELM) artificial intelligence model in two cases: normal orientation labyrinth weirs (NLWs) and inverted orientation labyrinth weirs (ILWs). First, the most optimized neuron of the hidden layer was computed. The number of hidden layer neurons was calculated as 30. Also, by analysing the results of different activation functions, it was concluded that the sigmoid activation function has higher accuracy than the others. Next, the superior model was identified by conducting a sensitivity analysis. The model approximated the discharge coefficient of labyrinth weirs with reasonable accuracy. For example, the R 2, scatter index and Nash–Sutcliffe efficiency coefficient for the best model were estimated as 0.966, 0.034 and 0.964, respectively. In addition, the ratio of the total head above the weir to the height of the weir crest ( H T / P ) and the ratio of length of apex geometry to width of a single cycle ( A / w ) were identified as the most effective parameters. Furthermore, the uncertainty analysis results indicated that the superior model had an overestimated performance. Then, a relationship was proposed in terms of all input variables for the superior model. © 2020 John Wiley & Sons, Ltd. Résumé: Dans l'étude, le coefficient de décharge des déversoirs à labyrinthe a été simulé à l'aide du modèle d'intelligence artificielle 'self‐adaptiveAbstract: In this study, the labyrinth weir discharge coefficient was simulated using the self‐adaptive extreme learning machine (SAELM) artificial intelligence model in two cases: normal orientation labyrinth weirs (NLWs) and inverted orientation labyrinth weirs (ILWs). First, the most optimized neuron of the hidden layer was computed. The number of hidden layer neurons was calculated as 30. Also, by analysing the results of different activation functions, it was concluded that the sigmoid activation function has higher accuracy than the others. Next, the superior model was identified by conducting a sensitivity analysis. The model approximated the discharge coefficient of labyrinth weirs with reasonable accuracy. For example, the R 2, scatter index and Nash–Sutcliffe efficiency coefficient for the best model were estimated as 0.966, 0.034 and 0.964, respectively. In addition, the ratio of the total head above the weir to the height of the weir crest ( H T / P ) and the ratio of length of apex geometry to width of a single cycle ( A / w ) were identified as the most effective parameters. Furthermore, the uncertainty analysis results indicated that the superior model had an overestimated performance. Then, a relationship was proposed in terms of all input variables for the superior model. © 2020 John Wiley & Sons, Ltd. Résumé: Dans l'étude, le coefficient de décharge des déversoirs à labyrinthe a été simulé à l'aide du modèle d'intelligence artificielle 'self‐adaptive extreme learning machine' (SAELM) dans les deux cas, y compris les déversoirs à labyrinthe d'orientation normale (NLW) et les déversoirs à labyrinthe d'orientation inversée (ILW). Tout d'abord, le neurone le plus optimisé de la couche cachée a été calculé. Le nombre de neurones de la couche cachée a été calculé à 30. De plus, en analysant les résultats de différentes fonctions d'activation, il a été conclu que la fonction d'activation sigmoïde a une précision plus élevée que d'autres. Après cela, le modèle supérieur a été identifié en effectuant une analyse de sensibilité. Le modèle a approximé le coefficient de décharge des déversoirs à labyrinthe avec une précision raisonnable. Par exemple, le R 2, l'indice de dispersion et le coefficient d'efficacité de Nash Sutcliffe pour le meilleur modèle ont été estimés à 0.966, 0.034 et 0.964, respectivement. De plus, le rapport de la hauteur totale au‐dessus du déversoir à la hauteur de la crête du déversoir ( HT / P ) et le rapport de la longueur de la géométrie du sommet à la largeur d'un cycle unique ( A / w ) ont été identifiés comme les paramètres les plus efficaces. Par ailleurs, les résultats de l'analyse d'incertitude ont indiqué que le modèle supérieur avait une performance surestimée. Après cela, une relation a été proposée à partir de toutes les variables d'entrée pour le modèle supérieur. © 2020 John Wiley & Sons, Ltd. … (more)
- Is Part Of:
- Irrigation and drainage. Volume 69:Number 3(2020)
- Journal:
- Irrigation and drainage
- Issue:
- Volume 69:Number 3(2020)
- Issue Display:
- Volume 69, Issue 3 (2020)
- Year:
- 2020
- Volume:
- 69
- Issue:
- 3
- Issue Sort Value:
- 2020-0069-0003-0000
- Page Start:
- 398
- Page End:
- 416
- Publication Date:
- 2020-03-13
- Subjects:
- discharge coefficient -- labyrinth weir -- partial derivative sensitivity analysis -- self‐adaptive extreme learning machine -- sensitivity analysis -- uncertainty analysis
coefficient de débit -- déversoir à labyrinthe -- analyse de sensibilité aux dérivées partielles -- machine d'apprentissage extrême auto‐adaptative -- analyse de sensibilité -- analyse d'incertitude
Irrigation engineering -- Periodicals
Drainage -- Periodicals
Flood control -- Periodicals
Sustainable agriculture -- Periodicals
627.52 - Journal URLs:
- http://onlinelibrary.wiley.com/ ↗
- DOI:
- 10.1002/ird.2423 ↗
- Languages:
- English
- ISSNs:
- 1531-0353
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 4580.946000
British Library DSC - BLDSS-3PM
British Library STI - ELD Digital store - Ingest File:
- 13361.xml