Fault Diagnosis Based on Machine Learning for the High Frequency Link of a Grid-Tied Photovoltaic Converter for a Wide Range of Irradiance Conditions
The objective of this work is to select a Machine Learning Technique (MLT) to develop a fault diagnosis scheme for the power switching devices of the High Frequency link (HF link) in a grid-tied Photovoltaic (PV) system, without increasing the total number of sensors, and being capable to operate on...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9606924/ |
| _version_ | 1818427809807204352 |
|---|---|
| author | Yuniel Leon-Ruiz Mario Gonzalez-Garcia Ricardo Alvarez-Salas Juan Cuevas-Tello Victor Cardenas |
| author_facet | Yuniel Leon-Ruiz Mario Gonzalez-Garcia Ricardo Alvarez-Salas Juan Cuevas-Tello Victor Cardenas |
| author_sort | Yuniel Leon-Ruiz |
| collection | DOAJ |
| description | The objective of this work is to select a Machine Learning Technique (MLT) to develop a fault diagnosis scheme for the power switching devices of the High Frequency link (HF link) in a grid-tied Photovoltaic (PV) system, without increasing the total number of sensors, and being capable to operate online. Artificial Neural Network (ANN), Support Vector Machine (SVM), Probabilistic Neural Network (PNN) and Naive Bayes (NB) algorithms are considered to solve the problem of fault classification. These four MLTs are compared using the specificity and sensitivity indexes. The inputs of the models are obtained from the mean value of the signals given by the Discrete Wavelet Transform (DWT) of the dc link voltage and the power extracted from the PV panels. Support vector machine algorithm is chosen as the most suitable classifier to diagnose single and simultaneous open circuit faults with lower computational effort. Simulation and real-time hardware-based experimental tests demonstrate that the MLTs are suitable and reliable to diagnose open circuit faults in a wide range of irradiance levels, ranging from 200 W/m<sup>2</sup> to 1000 W/m<sup>2</sup>, even under 6 % and 12 % measurement errors, without increasing the overall system cost. |
| first_indexed | 2024-12-14T14:51:38Z |
| format | Article |
| id | doaj.art-92bcd048bbb1438eb82ee41b2c6b3d6a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T14:51:38Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-92bcd048bbb1438eb82ee41b2c6b3d6a2022-12-21T22:57:08ZengIEEEIEEE Access2169-35362021-01-01915120915122010.1109/ACCESS.2021.31267069606924Fault Diagnosis Based on Machine Learning for the High Frequency Link of a Grid-Tied Photovoltaic Converter for a Wide Range of Irradiance ConditionsYuniel Leon-Ruiz0Mario Gonzalez-Garcia1https://orcid.org/0000-0003-4653-4895Ricardo Alvarez-Salas2https://orcid.org/0000-0002-7646-0260Juan Cuevas-Tello3https://orcid.org/0000-0002-7566-0412Victor Cardenas4Engineering Department, Autonomous University of San Luis Potosi (UASLP), San Luis Potosi, MexicoEngineering Department, CONACyT, Autonomous University of San Luis Potosi (UASLP), San Luis Potosi, MexicoEngineering Department, Autonomous University of San Luis Potosi (UASLP), San Luis Potosi, MexicoEngineering Department, Autonomous University of San Luis Potosi (UASLP), San Luis Potosi, MexicoEngineering Department, Autonomous University of San Luis Potosi (UASLP), San Luis Potosi, MexicoThe objective of this work is to select a Machine Learning Technique (MLT) to develop a fault diagnosis scheme for the power switching devices of the High Frequency link (HF link) in a grid-tied Photovoltaic (PV) system, without increasing the total number of sensors, and being capable to operate online. Artificial Neural Network (ANN), Support Vector Machine (SVM), Probabilistic Neural Network (PNN) and Naive Bayes (NB) algorithms are considered to solve the problem of fault classification. These four MLTs are compared using the specificity and sensitivity indexes. The inputs of the models are obtained from the mean value of the signals given by the Discrete Wavelet Transform (DWT) of the dc link voltage and the power extracted from the PV panels. Support vector machine algorithm is chosen as the most suitable classifier to diagnose single and simultaneous open circuit faults with lower computational effort. Simulation and real-time hardware-based experimental tests demonstrate that the MLTs are suitable and reliable to diagnose open circuit faults in a wide range of irradiance levels, ranging from 200 W/m<sup>2</sup> to 1000 W/m<sup>2</sup>, even under 6 % and 12 % measurement errors, without increasing the overall system cost.https://ieeexplore.ieee.org/document/9606924/Fault diagnosishigh frequency linkmachine learningphotovoltaic systems |
| spellingShingle | Yuniel Leon-Ruiz Mario Gonzalez-Garcia Ricardo Alvarez-Salas Juan Cuevas-Tello Victor Cardenas Fault Diagnosis Based on Machine Learning for the High Frequency Link of a Grid-Tied Photovoltaic Converter for a Wide Range of Irradiance Conditions IEEE Access Fault diagnosis high frequency link machine learning photovoltaic systems |
| title | Fault Diagnosis Based on Machine Learning for the High Frequency Link of a Grid-Tied Photovoltaic Converter for a Wide Range of Irradiance Conditions |
| title_full | Fault Diagnosis Based on Machine Learning for the High Frequency Link of a Grid-Tied Photovoltaic Converter for a Wide Range of Irradiance Conditions |
| title_fullStr | Fault Diagnosis Based on Machine Learning for the High Frequency Link of a Grid-Tied Photovoltaic Converter for a Wide Range of Irradiance Conditions |
| title_full_unstemmed | Fault Diagnosis Based on Machine Learning for the High Frequency Link of a Grid-Tied Photovoltaic Converter for a Wide Range of Irradiance Conditions |
| title_short | Fault Diagnosis Based on Machine Learning for the High Frequency Link of a Grid-Tied Photovoltaic Converter for a Wide Range of Irradiance Conditions |
| title_sort | fault diagnosis based on machine learning for the high frequency link of a grid tied photovoltaic converter for a wide range of irradiance conditions |
| topic | Fault diagnosis high frequency link machine learning photovoltaic systems |
| url | https://ieeexplore.ieee.org/document/9606924/ |
| work_keys_str_mv | AT yunielleonruiz faultdiagnosisbasedonmachinelearningforthehighfrequencylinkofagridtiedphotovoltaicconverterforawiderangeofirradianceconditions AT mariogonzalezgarcia faultdiagnosisbasedonmachinelearningforthehighfrequencylinkofagridtiedphotovoltaicconverterforawiderangeofirradianceconditions AT ricardoalvarezsalas faultdiagnosisbasedonmachinelearningforthehighfrequencylinkofagridtiedphotovoltaicconverterforawiderangeofirradianceconditions AT juancuevastello faultdiagnosisbasedonmachinelearningforthehighfrequencylinkofagridtiedphotovoltaicconverterforawiderangeofirradianceconditions AT victorcardenas faultdiagnosisbasedonmachinelearningforthehighfrequencylinkofagridtiedphotovoltaicconverterforawiderangeofirradianceconditions |