{"data":{"id":"10.5281/zenodo.20407863","type":"dois","attributes":{"doi":"10.5281/zenodo.20407863","prefix":"10.5281","suffix":"zenodo.20407863","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Kichou, Sofiane","nameType":"Personal","givenName":"Sofiane","familyName":"Kichou","affiliation":["Czech Technical University in Prague"],"nameIdentifiers":[{"nameIdentifier":"0000-0003-4122-5823","nameIdentifierScheme":"ORCID"}]},{"name":"Bouzek, Karel","nameType":"Personal","givenName":"Karel","familyName":"Bouzek","affiliation":["University of Chemistry and Technology"],"nameIdentifiers":[{"nameIdentifier":"0000-0002-0394-0634","nameIdentifierScheme":"ORCID"}]},{"name":"Paušová, Šárka","nameType":"Personal","givenName":"Šárka","familyName":"Paušová","affiliation":["University of Chemistry and Technology"],"nameIdentifiers":[{"nameIdentifier":"0000-0003-2494-1510","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"Dataset of \"A Physics-guided, Environmentally Compensated, Intelligent and Noise-Resilient Framework to Multi-Class Fault Detection and Diagnosis in Photovoltaic Systems Including Shunt and Series Resistances Degradation\""}],"publisher":"Zenodo","container":{},"publicationYear":2025,"subjects":[{"subject":"VZ6"},{"subject":"VA6.1"},{"subject":"CVUT/VUT"},{"subject":"214 021/214 022"},{"subject":"Photovoltaic fault diagnosis"},{"subject":"Physics-guided"},{"subject":"machine learning"},{"subject":"Series and shunt resistance faults"},{"subject":"Bayesian optimization"},{"subject":"Noise robustness."}],"contributors":[{"name":"Kichou, Sofiane","nameType":"Personal","givenName":"Sofiane","familyName":"Kichou","affiliation":["Czech Technical University in Prague"],"contributorType":"ContactPerson","nameIdentifiers":[{"nameIdentifier":"0000-0003-4122-5823","nameIdentifierScheme":"ORCID"}]}],"dates":[{"date":"2025-05-29","dateType":"Issued"},{"date":"2025-05-29","dateType":"Submitted","dateInformation":"Sent to peer review process"}],"language":"en","types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[{"relationType":"HasVersion","relatedIdentifier":"10.5281/zenodo.20407864","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":"Version 1","rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"In photovoltaic (PV) systems, intrinsic fault signatures are often masked by measurements and environmental variability, making reliable fault detection and diagnosis particularly challenging. To address this issue, this paper proposes a physics-guided Machine Learning framework that combines PV system modeling and data-driven intelligence to enhance classification performance. In order to replicate realistic behavior, reproduce degradation-related faults, and generate a physically consistent dataset of defective modules using the equivalent-circuit parameter changes, specifically the series resistance (Rs) and shunt resistance (Rsh), a complete PV model using Simulink was developed. Building on this foundation, Environmentally Compensated Features were incorporated to enhance class separability and mitigate sensitivity to environmental variations.\nA three-stage, physics-guided framework for PV fault detection and diagnosis is proposed. First, synthetic data are generated using physical models. Second, faults are detected using an AdaBoost ensemble, with hyperparameters tuned via Bayesian optimization for binary classification. Third, faults are diagnosed using a nonlinear Support Vector Machine (SVM), which is also optimized via Bayesian search, while LASSO (Least Absolute Shrinkage and Selection Operator)- based feature selection reduces dimensionality for the multi-classification task. To ensure unbiased performance assessment and prevent data leakage, models are evaluated using nested cross-validation. Results indicate improved separability of fault signatures and reliable classification of six fault categories, including degradation-related faults such as Rs and Rsh deviations that are typically difficult for purely data-driven methods. The detection model attains 99.74% accuracy, 99.78% balanced accuracy, and an F1 score of 0.997. The diagnosis model achieves 99.68% accuracy and an F1 score of 0.9967 across six classes. A robustness analysis under additive Gaussian noise further confirms the proposed models' stability. Overall, the framework provides a robust, physically guided solution for PV fault detection and diagnosis under dynamic conditions.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[{"awardTitle":"The Energy Conversion and Storage","funderName":"Ministry of Education Youth and Sports","awardNumber":"CZ.02.01.01/00/22_008/0004617","funderIdentifier":"10.13039/501100001823","funderIdentifierType":"Crossref Funder ID"}],"xml":"<?xml version="1.0" encoding="UTF-8"?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4/metadata.xsd">
  <identifier identifierType="DOI">10.5281/ZENODO.20407863</identifier>
  <creators>
    <creator>
      <creatorName nameType="Personal">Kichou, Sofiane</creatorName>
      <givenName>Sofiane</givenName>
      <familyName>Kichou</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="">0000-0003-4122-5823</nameIdentifier>
      <affiliation>Czech Technical University in Prague</affiliation>
    </creator>
    <creator>
      <creatorName nameType="Personal">Bouzek, Karel</creatorName>
      <givenName>Karel</givenName>
      <familyName>Bouzek</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="">0000-0002-0394-0634</nameIdentifier>
      <affiliation>University of Chemistry and Technology</affiliation>
    </creator>
    <creator>
      <creatorName nameType="Personal">Paušová, Šárka</creatorName>
      <givenName>Šárka</givenName>
      <familyName>Paušová</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="">0000-0003-2494-1510</nameIdentifier>
      <affiliation>University of Chemistry and Technology</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Dataset of "A Physics-guided, Environmentally Compensated, Intelligent and Noise-Resilient Framework to Multi-Class Fault Detection and Diagnosis in Photovoltaic Systems Including Shunt and Series Resistances Degradation"</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2025</publicationYear>
  <resourceType resourceTypeGeneral="Dataset"/>
  <subjects>
    <subject>VZ6</subject>
    <subject>VA6.1</subject>
    <subject>CVUT/VUT</subject>
    <subject>214 021/214 022</subject>
    <subject>Photovoltaic fault diagnosis</subject>
    <subject>Physics-guided</subject>
    <subject>machine learning</subject>
    <subject>Series and shunt resistance faults</subject>
    <subject>Bayesian optimization</subject>
    <subject>Noise robustness.</subject>
  </subjects>
  <contributors>
    <contributor contributorType="ContactPerson">
      <contributorName nameType="Personal">Kichou, Sofiane</contributorName>
      <givenName>Sofiane</givenName>
      <familyName>Kichou</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="">0000-0003-4122-5823</nameIdentifier>
      <affiliation>Czech Technical University in Prague</affiliation>
    </contributor>
  </contributors>
  <dates>
    <date dateType="Issued">2025-05-29</date>
    <date dateType="Submitted" dateInformation="Sent to peer review process">2025-05-29</date>
  </dates>
  <language>en</language>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="HasVersion">10.5281/zenodo.20407864</relatedIdentifier>
  </relatedIdentifiers>
  <sizes/>
  <formats/>
  <version>Version 1</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode" rightsIdentifier="cc-by-4.0" rightsIdentifierScheme="SPDX" schemeURI="https://spdx.org/licenses/">Creative Commons Attribution 4.0 International</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">In photovoltaic (PV) systems, intrinsic fault signatures are often masked by measurements and environmental variability, making reliable fault detection and diagnosis particularly challenging. To address this issue, this paper proposes a physics-guided Machine Learning framework that combines PV system modeling and data-driven intelligence to enhance classification performance. In order to replicate realistic behavior, reproduce degradation-related faults, and generate a physically consistent dataset of defective modules using the equivalent-circuit parameter changes, specifically the series resistance (Rs) and shunt resistance (Rsh), a complete PV model using Simulink was developed. Building on this foundation, Environmentally Compensated Features were incorporated to enhance class separability and mitigate sensitivity to environmental variations.
A three-stage, physics-guided framework for PV fault detection and diagnosis is proposed. First, synthetic data are generated using physical models. Second, faults are detected using an AdaBoost ensemble, with hyperparameters tuned via Bayesian optimization for binary classification. Third, faults are diagnosed using a nonlinear Support Vector Machine (SVM), which is also optimized via Bayesian search, while LASSO (Least Absolute Shrinkage and Selection Operator)- based feature selection reduces dimensionality for the multi-classification task. To ensure unbiased performance assessment and prevent data leakage, models are evaluated using nested cross-validation. Results indicate improved separability of fault signatures and reliable classification of six fault categories, including degradation-related faults such as Rs and Rsh deviations that are typically difficult for purely data-driven methods. The detection model attains 99.74% accuracy, 99.78% balanced accuracy, and an F1 score of 0.997. The diagnosis model achieves 99.68% accuracy and an F1 score of 0.9967 across six classes. A robustness analysis under additive Gaussian noise further confirms the proposed models' stability. Overall, the framework provides a robust, physically guided solution for PV fault detection and diagnosis under dynamic conditions.</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>Ministry of Education Youth and Sports</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100001823</funderIdentifier>
      <awardNumber>CZ.02.01.01/00/22_008/0004617</awardNumber>
      <awardTitle>The Energy Conversion and Storage</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
","url":"https://zenodo.org/doi/10.5281/zenodo.20407863","contentUrl":null,"metadataVersion":1,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":2,"versionOfCount":1,"created":"2026-05-27T08:37:00.000Z","registered":"2026-05-27T08:37:00.000Z","published":"2025","updated":"2026-09-07T00:56:29.000Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}},"provider":{"data":{"id":"cern","type":"providers"}},"media":{"data":{"id":"10.5281/zenodo.20407863","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[{"id":"10.5281/zenodo.20407864","type":"dois"},{"id":"10.5281/zenodo.20407863","type":"dois"}]},"versionOf":{"data":[{"id":"10.5281/zenodo.20407863","type":"dois"}]}}}}