Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine
L C Chen, P J Lin, J Zhang, Z C Chen, Y H Lin, L J Wu and S Y Cheng
Institute of Physics (IOP)
Published 2018
Institute of Physics (IOP)
Published 2018
| Publication Date: |
2018-10-31
|
|---|---|
| Publisher: |
Institute of Physics (IOP)
|
| Print ISSN: |
1755-1307
|
| Electronic ISSN: |
1755-1315
|
| Topics: |
Geography
Geosciences
Physics
|
| Published by: |
| _version_ | 1836399076054138880 |
|---|---|
| autor | L C Chen, P J Lin, J Zhang, Z C Chen, Y H Lin, L J Wu and S Y Cheng |
| beschreibung | In order to dig out more typical features of photovoltaic (PV) with multitudinous characteristic parameters, and realize fault diagnosis and classification for PV arrays effectively. A method based on principal component analysis (PCA) has been proposed in this paper. At first, the data set of PV array is processed by PCA and then a transform matrix is produced. Second, the processed data will be classified by supporting vector machine (SVM). Finally, a classification model will be built. Two sets of data, collected from PV simulation system and actual PV array, are adopted to examine this method. The result shows that the method is able to recognize four kinds of states accurately (normal, open circuit, short circuit and partial shadow). Consequently, the fault of PV array can be diagnosed and classified. |
| citation_standardnr | 6350407 |
| datenlieferant | ipn_articles |
| feed_id | 108844 |
| feed_publisher | Institute of Physics (IOP) |
| feed_publisher_url | http://www.iop.org/ |
| insertion_date | 2018-10-31 |
| journaleissn | 1755-1315 |
| journalissn | 1755-1307 |
| publikationsjahr_anzeige | 2018 |
| publikationsjahr_facette | 2018 |
| publikationsjahr_intervall | 7984:2015-2019 |
| publikationsjahr_sort | 2018 |
| publisher | Institute of Physics (IOP) |
| quelle | IOP Conference Series: Earth and Environmental Science |
| relation | http://iopscience.iop.org/1755-1315/188/1/012089 |
| search_space | articles |
| shingle_author_1 | L C Chen, P J Lin, J Zhang, Z C Chen, Y H Lin, L J Wu and S Y Cheng |
| shingle_author_2 | L C Chen, P J Lin, J Zhang, Z C Chen, Y H Lin, L J Wu and S Y Cheng |
| shingle_author_3 | L C Chen, P J Lin, J Zhang, Z C Chen, Y H Lin, L J Wu and S Y Cheng |
| shingle_author_4 | L C Chen, P J Lin, J Zhang, Z C Chen, Y H Lin, L J Wu and S Y Cheng |
| shingle_catch_all_1 | Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine In order to dig out more typical features of photovoltaic (PV) with multitudinous characteristic parameters, and realize fault diagnosis and classification for PV arrays effectively. A method based on principal component analysis (PCA) has been proposed in this paper. At first, the data set of PV array is processed by PCA and then a transform matrix is produced. Second, the processed data will be classified by supporting vector machine (SVM). Finally, a classification model will be built. Two sets of data, collected from PV simulation system and actual PV array, are adopted to examine this method. The result shows that the method is able to recognize four kinds of states accurately (normal, open circuit, short circuit and partial shadow). Consequently, the fault of PV array can be diagnosed and classified. L C Chen, P J Lin, J Zhang, Z C Chen, Y H Lin, L J Wu and S Y Cheng Institute of Physics (IOP) 1755-1307 17551307 1755-1315 17551315 |
| shingle_catch_all_2 | Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine In order to dig out more typical features of photovoltaic (PV) with multitudinous characteristic parameters, and realize fault diagnosis and classification for PV arrays effectively. A method based on principal component analysis (PCA) has been proposed in this paper. At first, the data set of PV array is processed by PCA and then a transform matrix is produced. Second, the processed data will be classified by supporting vector machine (SVM). Finally, a classification model will be built. Two sets of data, collected from PV simulation system and actual PV array, are adopted to examine this method. The result shows that the method is able to recognize four kinds of states accurately (normal, open circuit, short circuit and partial shadow). Consequently, the fault of PV array can be diagnosed and classified. L C Chen, P J Lin, J Zhang, Z C Chen, Y H Lin, L J Wu and S Y Cheng Institute of Physics (IOP) 1755-1307 17551307 1755-1315 17551315 |
| shingle_catch_all_3 | Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine In order to dig out more typical features of photovoltaic (PV) with multitudinous characteristic parameters, and realize fault diagnosis and classification for PV arrays effectively. A method based on principal component analysis (PCA) has been proposed in this paper. At first, the data set of PV array is processed by PCA and then a transform matrix is produced. Second, the processed data will be classified by supporting vector machine (SVM). Finally, a classification model will be built. Two sets of data, collected from PV simulation system and actual PV array, are adopted to examine this method. The result shows that the method is able to recognize four kinds of states accurately (normal, open circuit, short circuit and partial shadow). Consequently, the fault of PV array can be diagnosed and classified. L C Chen, P J Lin, J Zhang, Z C Chen, Y H Lin, L J Wu and S Y Cheng Institute of Physics (IOP) 1755-1307 17551307 1755-1315 17551315 |
| shingle_catch_all_4 | Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine In order to dig out more typical features of photovoltaic (PV) with multitudinous characteristic parameters, and realize fault diagnosis and classification for PV arrays effectively. A method based on principal component analysis (PCA) has been proposed in this paper. At first, the data set of PV array is processed by PCA and then a transform matrix is produced. Second, the processed data will be classified by supporting vector machine (SVM). Finally, a classification model will be built. Two sets of data, collected from PV simulation system and actual PV array, are adopted to examine this method. The result shows that the method is able to recognize four kinds of states accurately (normal, open circuit, short circuit and partial shadow). Consequently, the fault of PV array can be diagnosed and classified. L C Chen, P J Lin, J Zhang, Z C Chen, Y H Lin, L J Wu and S Y Cheng Institute of Physics (IOP) 1755-1307 17551307 1755-1315 17551315 |
| shingle_title_1 | Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine |
| shingle_title_2 | Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine |
| shingle_title_3 | Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine |
| shingle_title_4 | Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine |
| timestamp | 2025-06-30T23:37:13.286Z |
| titel | Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine |
| titel_suche | Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine |
| topic | R TE-TZ U |
| uid | ipn_articles_6350407 |