Energy Modeling of a Solar Dish/Stirling by Artificial Intelligence Approach
No Thumbnail Available
Access rights
openAccess
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
2019-11
Major/Subject
Mcode
Degree programme
Language
en
Pages
20
Series
Energy Conversion & Management, articlenumber 112021
Abstract
Solar energy is a renewable energy resources that is available across the world. A solar dish/Stirling system means a parabolic dish concentrator and a Stirling engine combined to generate mechanical and/or electrical output power. In this system, the input energy of Stirling engine is provided by sunlight as a source of heat. This study presents the effect of different variables on the power generation and efficiency of the system. In addition, artificial intelligence approach is employed to model a solar dish/Stirling system. For this target, a huge dataset was provided by considering a wide range of input variables. The intelligent methods are group method of data handling (GMDH) type neural network, adaptive neuro-fuzzy inference system (ANFIS) and multilayer perceptron (MLP) neural network (ANN). The MLP and ANFIS are optimized with particle swarm optimization (PSO) and genetic algorithm (GA). The intelligent methods are trained with inputs and targets. The considered input parameters are the ratio of focal point to dish diameter, hour of day, solar radiation, geometric concentration factor and working gas specific constant. The power generation, global efficiency, heat used to run the Stirling cycle, hot Stirling chamber temperature and engine speed are selected to be the targets. The results depict that the intelligent methods operate successfully for energy modeling of the solar dish/Stirling system and the statistical indicators illustrate that the ANFIS-PSO method performs better than the other developed methods.Description
Keywords
Adaptive neuro-fuzzy inference system, Artificial neural network, Energy modeling, Genetic algorithm, Particle swarm optimization, Solar dish/Stirling system
Other note
Citation
Khosravi, A, Syri, S, Garcia Pabon, J J, R. Sandoval, O, Castro Caetano, B & H. Barrientos, M 2019, ' Energy Modeling of a Solar Dish/Stirling by Artificial Intelligence Approach ', Energy Conversion & Management . https://doi.org/10.1016/j.enconman.2019.112021