RTU Research Information System
Latviešu English

Publikācija: Application of Artificial Neural Networks for Detection of Developing Faults in Solar Combisystems

Publication Type Full-text conference paper published in other conference proceedings
Funding for basic activity Unknown
Defending: ,
Publication language English (en)
Title in original language Application of Artificial Neural Networks for Detection of Developing Faults in Solar Combisystems
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 diagnosis
Abstract A solar combisystem represents a unit, which combines solar collectors and an auxiliary heater, to cover both the space heating and domestic hot water loads. Despite perceived simplicity of solar collectors, failures can occur during the operation. Thus the objective of the paper is to present the development of fault detection system for solar combisystems. The developed ANN has 3 layers: an input, intermediate or hidden and output. For the input and output layers the historical data about the fault-free operation parameters from the experimental solar combisystem is feed to the ANN. The fault detection tool presented within the research can be used to increase the reliability of performance for solar combisystems. The fault detection tool can be used for both: owners of solar combisystems and research facilities. The remote monitoring of the system is possible with the neural networks.
Reference Timma, L., Blumberga, D. Application of Artificial Neural Networks for Detection of Developing Faults in Solar Combisystems. In: 8th Conference on Sustainable Development of Energy, Water and Environmental Systems: Conference Proceedings, Croatia, Dubrovnik, 22-27 September, 2013. Zagreb: 2013, pp.1-12. ISSN 1847-7178.
ID 16413