RTU Research Information System
Latviešu English

Publikācija: An Algorithm for the Selection of Structure for Artificial Neural Networks. Case Study: Solar Thermal Energy Systems

Publication Type Scientific article indexed in SCOPUS or WOS database
Funding for basic activity Unknown
Defending: ,
Publication language English (en)
Title in original language An Algorithm for the Selection of Structure for Artificial Neural Networks. Case Study: Solar Thermal Energy Systems
Field of research 2. Engineering and technology
Sub-field of research 2.7 Environmental engineering and energetics
Authors Lelde Timma
Dagnija Blumberga
Keywords solar and pellet combisystem; artificial neural networks; fault detection and isolation, sustainable energy systems
Abstract Despite perceived simplicity of solar thermal collectors, failures occur during operation. Therefore fault detection and isolation tools for these systems should be investigated. One of the critical parts for the development of fault detection and isolation is model selection. Within the paper, a specific algorithm for the selection of fault detection and an isolation model is elaborated and presented. The developed algorithm was applied for a solar and pellet combisystem. Through application of the proposed algorithm, a model based approach with recurrent structure of artificial neural networks is chosen for the development of a fault detection and isolation model.
DOI: 10.1016/j.egypro.2015.06.019
Hyperlink: http://www.sciencedirect.com/science/article/pii/S1876610215007092 
Reference Timma, L., Blumberga, D. An Algorithm for the Selection of Structure for Artificial Neural Networks. Case Study: Solar Thermal Energy Systems. Energy Procedia, 2015, Vol.72, pp.135-141. ISSN 1876-6102. Available from: doi:10.1016/j.egypro.2015.06.019
Additional information Citation count:
ID 19820