Parametric optimization of Archimedes screw turbine by response surface methodology and artificial neural networks
<p>This study investigates the performance optimisation of the Archimedes Screw Turbine (AST) to enhance power output, focusing on the key parameters of flow rate and inclination angle. Utilising response surface methodology (RSM) through a central composite design (CCD) and artificial neural...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Academy Publishing Center
2024-10-01
|
| Series: | Renewable Energy and Sustainable Development |
| Subjects: | |
| Online Access: | http://apc.aast.edu/ojs/index.php/RESD/article/view/1008 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | <p>This study investigates the performance optimisation of the Archimedes Screw Turbine (AST) to enhance power output, focusing on the key parameters of flow rate and inclination angle. Utilising response surface methodology (RSM) through a central composite design (CCD) and artificial neural networks (ANN), the research explores the predictive accuracy of these methods for optimal power generation. The experimental work was carried out with two parameters: flow rate (5-15 lps) and inclination angle (15º-40º). The optimized power output predicted by the RSM and ANN models was 204.16 watts at 14.58 lps and 36.23º, while the ANN predicted 187.24 watts at a flow rate of 13.82 lps and inclination angle 34.15º, respectively. The correlation coefficients (R²) for the ANN and RSM models were 0.9842 and 0.9718, respectively, revealing a significant quadratic regression for both models. Comparative analysis indicates that ANN offers better predictive accuracy than RSM, suggesting a more reliable approach for optimising AST performance.</p><p> </p><p><strong>Received: 12 September 2024 </strong></p><p><strong>Accepted: 08 October 2024 </strong></p><p><strong>Published: 15 October 2024</strong></p> |
|---|---|
| ISSN: | 2356-8518 2356-8569 |