![Institutional Repository [SANDBOX]](images/dias.logo.png "Institutional Repository [SANDBOX]"){kind=logo}
Institutional Repository [SANDBOX]
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/CE4B95F0-7DC0-4D90-9538-796AE6575E15 | ||
| Year | 2020 | ||
| Type of Item | Diploma Work | ||
| License |
|
||
| Bibliographic Citation | Georgios Iliakis, "Fault detection of photovoltaic systems using machine learning techniques", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2020 https://doi.org/10.26233/heallink.tuc.87037 | ||
| Appears in Collections |
The purpose of this project is the development of an algorithm, which is able to detect faults in the operation of Photovoltaic Systems. It is obvious that, like in every system, photovoltaic systems have specific conditions in order to function properly. When those conditions are not satisfied, we can claim with certainty that the normal function of the system has been affected. For the purposes of this research, a photovoltaic system consisting of photovoltaic panels connected inseries and parallel, was simulated in the Matlab/Simulink environment. In order to decide if the system operates properly, the software that was developed relies mainly on machine learning techniques. More specifically, it uses stored data, which correspond to normal or not states of function, it compares them with the current state of the system, and decides accordingly if there is an error in the operation of the Photovoltaic system or not. The software can be described asflexible, because with small adjustments it is able to operate for several different connections of photovoltaic panels. When it comes to the performance of the algorithm, it can be described as very effective, since the software which was developed is in most cases able to detect the state of the Photovoltaic system correctly.
Copyright © DIAS 2013
