Saeed Amirkhani; Sh. Nasirivatan; Alibakhsh Kasaeian; Ahmad Hajinezhad · 10.1016/j.renene.2015.04.072 https://doi.org/10.1016/j.renene.2015.04.072
Renewable Energy
ANN and ANFIS models to predict the performance of solar chimney power plants Saeed Amirkhani; Sh. Nasirivatan; Alibakhsh Kasaeian; Ahmad Hajinezhad Neural network (ANN) and adaptive neuro-fuzzy (ANFIS) models are built from three days of measurements on a pilot solar chimney in Zanjan, Iran, to predict chimney inlet air velocity from time, solar radiation and ambient temperature. ANFIS outperforms ANN, reaching a test R2 of about 0.91. Compared with a conventional numerical simulation, it gives accurate predictions at lower computational cost.
Experimental
Machine learning / AI
Numerical / CFD
Solar chimney power plant
2015
Renewable Energy
no
2015-05-21 12:00:00 00003229
ann and anfis models to predict the performance of solar chimney power plants
2015
Renewable Energy
Saeed Amirkhani; Sh. Nasirivatan; Alibakhsh Kasaeian; Ahmad Hajinezhad
10.1016/j.renene.2015.04.072
Summary
Neural network (ANN) and adaptive neuro-fuzzy (ANFIS) models are built from three days of measurements on a pilot solar chimney in Zanjan, Iran, to predict chimney inlet air velocity from time, solar radiation and ambient temperature. ANFIS outperforms ANN, reaching a test R² of about 0.91. Compared with a conventional numerical simulation, it gives accurate predictions at lower computational cost.
Description written by Solar Tower. The original abstract is available from the publisher via the link below.
Open source