Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays
Automatic detection of solar array faults reduces maintenance costs and increases efficiency. In this paper, we address the problem of fault detection, localization, and classification in utility-scale photovoltaic (PV) arrays using machine learning methods. More specifically, we develop a series of...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9525102/ |
| _version_ | 1819118487503634432 |
|---|---|
| author | Sunil Rao Gowtham Muniraju Cihan Tepedelenlioglu Devarajan Srinivasan Govindasamy Tamizhmani Andreas Spanias |
| author_facet | Sunil Rao Gowtham Muniraju Cihan Tepedelenlioglu Devarajan Srinivasan Govindasamy Tamizhmani Andreas Spanias |
| author_sort | Sunil Rao |
| collection | DOAJ |
| description | Automatic detection of solar array faults reduces maintenance costs and increases efficiency. In this paper, we address the problem of fault detection, localization, and classification in utility-scale photovoltaic (PV) arrays using machine learning methods. More specifically, we develop a series of customized neural networks for detection and classification of solar array faults. We evaluate fault detection and classification using metrics such as accuracy, confusion matrices, and the Risk Priority Number (RPN). We examine and assess the use of customized neural networks with dropout regularizers. We develop and evaluate neural network pruning strategies and illustrate the trade-off between fault classification model accuracy and algorithm complexity. Our approach promises to elevate the performance and robustness of PV arrays and compares favorably against existing methods. |
| first_indexed | 2024-12-22T05:49:40Z |
| format | Article |
| id | doaj.art-3b9eea62698b4393aebbdd33bb9fb112 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T05:49:40Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3b9eea62698b4393aebbdd33bb9fb1122022-12-21T18:36:54ZengIEEEIEEE Access2169-35362021-01-01912003412004210.1109/ACCESS.2021.31086849525102Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic ArraysSunil Rao0https://orcid.org/0000-0002-8151-5174Gowtham Muniraju1https://orcid.org/0000-0003-0532-2896Cihan Tepedelenlioglu2https://orcid.org/0000-0002-9180-1158Devarajan Srinivasan3https://orcid.org/0000-0003-1675-3288Govindasamy Tamizhmani4Andreas Spanias5https://orcid.org/0000-0003-0306-9348SenSIP Center, School of ECEE, Arizona State University, Tempe, AZ, USASenSIP Center, School of ECEE, Arizona State University, Tempe, AZ, USASenSIP Center, School of ECEE, Arizona State University, Tempe, AZ, USAPoundra, LLC, Tempe, AZ, USAPhotovoltaic Reliability Laboratory, Arizona State University, Mesa, AZ, USASenSIP Center, School of ECEE, Arizona State University, Tempe, AZ, USAAutomatic detection of solar array faults reduces maintenance costs and increases efficiency. In this paper, we address the problem of fault detection, localization, and classification in utility-scale photovoltaic (PV) arrays using machine learning methods. More specifically, we develop a series of customized neural networks for detection and classification of solar array faults. We evaluate fault detection and classification using metrics such as accuracy, confusion matrices, and the Risk Priority Number (RPN). We examine and assess the use of customized neural networks with dropout regularizers. We develop and evaluate neural network pruning strategies and illustrate the trade-off between fault classification model accuracy and algorithm complexity. Our approach promises to elevate the performance and robustness of PV arrays and compares favorably against existing methods.https://ieeexplore.ieee.org/document/9525102/Dropout neural networksmachine learningphotovoltaic panel fault detectionpruned neural networkssolar array fault classification |
| spellingShingle | Sunil Rao Gowtham Muniraju Cihan Tepedelenlioglu Devarajan Srinivasan Govindasamy Tamizhmani Andreas Spanias Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays IEEE Access Dropout neural networks machine learning photovoltaic panel fault detection pruned neural networks solar array fault classification |
| title | Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays |
| title_full | Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays |
| title_fullStr | Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays |
| title_full_unstemmed | Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays |
| title_short | Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays |
| title_sort | dropout and pruned neural networks for fault classification in photovoltaic arrays |
| topic | Dropout neural networks machine learning photovoltaic panel fault detection pruned neural networks solar array fault classification |
| url | https://ieeexplore.ieee.org/document/9525102/ |
| work_keys_str_mv | AT sunilrao dropoutandprunedneuralnetworksforfaultclassificationinphotovoltaicarrays AT gowthammuniraju dropoutandprunedneuralnetworksforfaultclassificationinphotovoltaicarrays AT cihantepedelenlioglu dropoutandprunedneuralnetworksforfaultclassificationinphotovoltaicarrays AT devarajansrinivasan dropoutandprunedneuralnetworksforfaultclassificationinphotovoltaicarrays AT govindasamytamizhmani dropoutandprunedneuralnetworksforfaultclassificationinphotovoltaicarrays AT andreasspanias dropoutandprunedneuralnetworksforfaultclassificationinphotovoltaicarrays |