Deep‐learning–based method for faults classification of PV system
Abstract The installation of photovoltaic (PV) system, as a renewable energy source, has significantly increased. Therefore, fast and efficient fault detection and diagnosis technique is highly needed to prevent unpredicted power interruptions. This is obtained in this study in the following steps....
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | IET Renewable Power Generation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rpg2.12016 |
| _version_ | 1797894181296799744 |
|---|---|
| author | Sayed A. Zaki Honglu Zhu Mohammed Al Fakih Ahmed Rabee Sayed Jianxi Yao |
| author_facet | Sayed A. Zaki Honglu Zhu Mohammed Al Fakih Ahmed Rabee Sayed Jianxi Yao |
| author_sort | Sayed A. Zaki |
| collection | DOAJ |
| description | Abstract The installation of photovoltaic (PV) system, as a renewable energy source, has significantly increased. Therefore, fast and efficient fault detection and diagnosis technique is highly needed to prevent unpredicted power interruptions. This is obtained in this study in the following steps. First, an efficient meta‐heuristic algorithm is proposed for extracting the optimal five parameters of the PV model in order to assist the MATLAB simulation model. It is used due to its simplicity and high efficiency in building the PV array simulation. Second, a new PV system deep‐learning convolutional neural network (CNN) fault classification method is presented for the advantage of automatic feature extraction, which reduces the computational burden and increases the high classification capability. Finally, for the practical and theoretical validation of the employed CNN model, normal and six fault cases are selected based on different atmospheric conditions. At same time, three electrical indicators are analysed and accordingly chosen as inputs to the proposed classification model. Moreover, the proposed model is compared with other machine‐learning models. |
| first_indexed | 2024-04-10T07:05:55Z |
| format | Article |
| id | doaj.art-36075b42f566409ba283504259eab643 |
| institution | Directory Open Access Journal |
| issn | 1752-1416 1752-1424 |
| language | English |
| last_indexed | 2024-04-10T07:05:55Z |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Renewable Power Generation |
| spelling | doaj.art-36075b42f566409ba283504259eab6432023-02-27T08:21:53ZengWileyIET Renewable Power Generation1752-14161752-14242021-01-0115119320510.1049/rpg2.12016Deep‐learning–based method for faults classification of PV systemSayed A. Zaki0Honglu Zhu1Mohammed Al Fakih2Ahmed Rabee Sayed3Jianxi Yao4School of New Energy North China Electric Power University Beijing ChinaSchool of New Energy North China Electric Power University Beijing ChinaSchool of New Energy North China Electric Power University Beijing ChinaSchool of New Energy North China Electric Power University Beijing ChinaSchool of New Energy North China Electric Power University Beijing ChinaAbstract The installation of photovoltaic (PV) system, as a renewable energy source, has significantly increased. Therefore, fast and efficient fault detection and diagnosis technique is highly needed to prevent unpredicted power interruptions. This is obtained in this study in the following steps. First, an efficient meta‐heuristic algorithm is proposed for extracting the optimal five parameters of the PV model in order to assist the MATLAB simulation model. It is used due to its simplicity and high efficiency in building the PV array simulation. Second, a new PV system deep‐learning convolutional neural network (CNN) fault classification method is presented for the advantage of automatic feature extraction, which reduces the computational burden and increases the high classification capability. Finally, for the practical and theoretical validation of the employed CNN model, normal and six fault cases are selected based on different atmospheric conditions. At same time, three electrical indicators are analysed and accordingly chosen as inputs to the proposed classification model. Moreover, the proposed model is compared with other machine‐learning models.https://doi.org/10.1049/rpg2.12016Solar power stations and photovoltaic power systemsOptimisation techniquesData handling techniquesOptimisation techniquesPower engineering computingNeural nets |
| spellingShingle | Sayed A. Zaki Honglu Zhu Mohammed Al Fakih Ahmed Rabee Sayed Jianxi Yao Deep‐learning–based method for faults classification of PV system IET Renewable Power Generation Solar power stations and photovoltaic power systems Optimisation techniques Data handling techniques Optimisation techniques Power engineering computing Neural nets |
| title | Deep‐learning–based method for faults classification of PV system |
| title_full | Deep‐learning–based method for faults classification of PV system |
| title_fullStr | Deep‐learning–based method for faults classification of PV system |
| title_full_unstemmed | Deep‐learning–based method for faults classification of PV system |
| title_short | Deep‐learning–based method for faults classification of PV system |
| title_sort | deep learning based method for faults classification of pv system |
| topic | Solar power stations and photovoltaic power systems Optimisation techniques Data handling techniques Optimisation techniques Power engineering computing Neural nets |
| url | https://doi.org/10.1049/rpg2.12016 |
| work_keys_str_mv | AT sayedazaki deeplearningbasedmethodforfaultsclassificationofpvsystem AT hongluzhu deeplearningbasedmethodforfaultsclassificationofpvsystem AT mohammedalfakih deeplearningbasedmethodforfaultsclassificationofpvsystem AT ahmedrabeesayed deeplearningbasedmethodforfaultsclassificationofpvsystem AT jianxiyao deeplearningbasedmethodforfaultsclassificationofpvsystem |