A Novel Convolutional Neural Network-Based Approach for Fault Classification in Photovoltaic Arrays
Fault diagnosis in photovoltaic (PV) arrays is essential in enhancing power output as well as the useful life span of a PV system. Severe faults such as Partial Shading (PS) and high impedance faults, low location mismatch, and the presence of Maximum Power Point Tracking (MPPT) make fault detection...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9018018/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825207025792974848 |
|---|---|
| author | Farkhanda Aziz Azhar Ul Haq Shahzor Ahmad Yousef Mahmoud Marium Jalal Usman Ali |
| author_facet | Farkhanda Aziz Azhar Ul Haq Shahzor Ahmad Yousef Mahmoud Marium Jalal Usman Ali |
| author_sort | Farkhanda Aziz |
| collection | DOAJ |
| description | Fault diagnosis in photovoltaic (PV) arrays is essential in enhancing power output as well as the useful life span of a PV system. Severe faults such as Partial Shading (PS) and high impedance faults, low location mismatch, and the presence of Maximum Power Point Tracking (MPPT) make fault detection challenging in harsh environmental conditions. In this regard, there have been several attempts made by various researchers to identify PV array faults. However, most of the previous work has focused on fault detection and classification in only a few faulty scenarios. This paper presents a novel approach that utilizes deep two-dimensional (2-D) Convolutional Neural Networks (CNN) to extract features from 2-D scalograms generated from PV system data in order to effectively detect and classify PV system faults. An in-depth quantitative evaluation of the proposed approach is presented and compared with previous classification methods for PV array faults – both classical machine learning based and deep learning based. Unlike contemporary work, five different faulty cases (including faults in PS – on which no work has been done before in the machine learning domain) have been considered in our study, along with the incorporation of MPPT. We generate a consistent dataset over which to compare ours and previous approaches, to make for the first (to the best of our knowledge) comprehensive and meaningful comparative evaluation of fault diagnosis. It is observed that the proposed method involving fine-tuned pre-trained CNN outperforms existing techniques, achieving a high fault detection accuracy of 73.53%. Our study also highlights the importance of representative and discriminative features to classify faults (as opposed to the use of raw data), especially in the noisy scenario, where our method achieves the best performance of 70.45%. We believe that our work will serve to guide future research in PV system fault diagnosis. |
| format | Article |
| id | doaj-art-77946559540545fdbe35be6da4b92ff1 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-77946559540545fdbe35be6da4b92ff12025-02-07T00:00:46ZengIEEEIEEE Access2169-35362020-01-018418894190410.1109/ACCESS.2020.29771169018018A Novel Convolutional Neural Network-Based Approach for Fault Classification in Photovoltaic ArraysFarkhanda Aziz0https://orcid.org/0000-0002-3232-913XAzhar Ul Haq1https://orcid.org/0000-0003-1036-9613Shahzor Ahmad2https://orcid.org/0000-0002-4319-5851Yousef Mahmoud3https://orcid.org/0000-0002-4243-7273Marium Jalal4https://orcid.org/0000-0002-8217-6637Usman Ali5https://orcid.org/0000-0001-6113-6735Department of Electrical Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology (NUST), Islamabad, PakistanDepartment of Electrical Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology (NUST), Islamabad, PakistanDepartment of Electrical Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology (NUST), Islamabad, PakistanDepartment of Electrical and Computer Engineering, Worcester Polytechnic Institute (WPI), Worcester, MA, USADepartment of Electronic Engineering, Fatima Jinnah Women University, Rawalpindi, PakistanDepartment of Electrical Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology (NUST), Islamabad, PakistanFault diagnosis in photovoltaic (PV) arrays is essential in enhancing power output as well as the useful life span of a PV system. Severe faults such as Partial Shading (PS) and high impedance faults, low location mismatch, and the presence of Maximum Power Point Tracking (MPPT) make fault detection challenging in harsh environmental conditions. In this regard, there have been several attempts made by various researchers to identify PV array faults. However, most of the previous work has focused on fault detection and classification in only a few faulty scenarios. This paper presents a novel approach that utilizes deep two-dimensional (2-D) Convolutional Neural Networks (CNN) to extract features from 2-D scalograms generated from PV system data in order to effectively detect and classify PV system faults. An in-depth quantitative evaluation of the proposed approach is presented and compared with previous classification methods for PV array faults – both classical machine learning based and deep learning based. Unlike contemporary work, five different faulty cases (including faults in PS – on which no work has been done before in the machine learning domain) have been considered in our study, along with the incorporation of MPPT. We generate a consistent dataset over which to compare ours and previous approaches, to make for the first (to the best of our knowledge) comprehensive and meaningful comparative evaluation of fault diagnosis. It is observed that the proposed method involving fine-tuned pre-trained CNN outperforms existing techniques, achieving a high fault detection accuracy of 73.53%. Our study also highlights the importance of representative and discriminative features to classify faults (as opposed to the use of raw data), especially in the noisy scenario, where our method achieves the best performance of 70.45%. We believe that our work will serve to guide future research in PV system fault diagnosis.https://ieeexplore.ieee.org/document/9018018/Photovoltaic arraymaximum power point trackingfault classificationconvolutional neural networkscalogramstransfer learning |
| spellingShingle | Farkhanda Aziz Azhar Ul Haq Shahzor Ahmad Yousef Mahmoud Marium Jalal Usman Ali A Novel Convolutional Neural Network-Based Approach for Fault Classification in Photovoltaic Arrays IEEE Access Photovoltaic array maximum power point tracking fault classification convolutional neural network scalograms transfer learning |
| title | A Novel Convolutional Neural Network-Based Approach for Fault Classification in Photovoltaic Arrays |
| title_full | A Novel Convolutional Neural Network-Based Approach for Fault Classification in Photovoltaic Arrays |
| title_fullStr | A Novel Convolutional Neural Network-Based Approach for Fault Classification in Photovoltaic Arrays |
| title_full_unstemmed | A Novel Convolutional Neural Network-Based Approach for Fault Classification in Photovoltaic Arrays |
| title_short | A Novel Convolutional Neural Network-Based Approach for Fault Classification in Photovoltaic Arrays |
| title_sort | novel convolutional neural network based approach for fault classification in photovoltaic arrays |
| topic | Photovoltaic array maximum power point tracking fault classification convolutional neural network scalograms transfer learning |
| url | https://ieeexplore.ieee.org/document/9018018/ |
| work_keys_str_mv | AT farkhandaaziz anovelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT azharulhaq anovelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT shahzorahmad anovelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT yousefmahmoud anovelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT mariumjalal anovelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT usmanali anovelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT farkhandaaziz novelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT azharulhaq novelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT shahzorahmad novelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT yousefmahmoud novelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT mariumjalal novelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays AT usmanali novelconvolutionalneuralnetworkbasedapproachforfaultclassificationinphotovoltaicarrays |