FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285091162> ?p ?o ?g. }

• W4285091162 endingPage "5085" @default.
• W4285091162 startingPage "5085" @default.
• W4285091162 abstract "Classification machine learning models require high-quality labeled datasets for training. Among the most useful datasets for photovoltaic array fault detection and diagnosis are module or string current-voltage (IV) curves. Unfortunately, such datasets are rarely collected due to the cost of high fidelity monitoring, and the data that is available is generally not ideal, often consisting of unbalanced classes, noisy data due to environmental conditions, and few samples. In this paper, we propose an alternate approach that utilizes physics-based simulations of string-level IV curves as a fully synthetic training corpus that is independent of the test dataset. In our example, the training corpus consists of baseline (no fault), partial soiling, and cell crack system modes. The training corpus is used to train a 1D convolutional neural network (CNN) for failure classification. The approach is validated by comparing the model’s ability to classify failures detected on a real, measured IV curve testing corpus obtained from laboratory and field experiments. Results obtained using a fully synthetic training dataset achieve identical accuracy to those obtained with use of a measured training dataset. When evaluating the measured data’s test split, a 100% accuracy was found both when using simulations or measured data as the training corpus. When evaluating all of the measured data, a 96% accuracy was found when using a fully synthetic training dataset. The use of physics-based modeling results as a training corpus for failure detection and classification has many advantages for implementation as each PV system is configured differently, and it would be nearly impossible to train using labeled measured data." @default.
• W4285091162 created "2022-07-14" @default.
• W4285091162 creator A5008536450 @default.
• W4285091162 creator A5023923197 @default.
• W4285091162 creator A5036653771 @default.
• W4285091162 creator A5087506938 @default.
• W4285091162 date "2022-07-12" @default.
• W4285091162 modified "2023-10-05" @default.
• W4285091162 title "Physics-Based Method for Generating Fully Synthetic IV Curve Training Datasets for Machine Learning Classification of PV Failures" @default.
• W4285091162 cites W1515333057 @default.
• W4285091162 cites W1967163241 @default.
• W4285091162 cites W2274867803 @default.
• W4285091162 cites W2280977705 @default.
• W4285091162 cites W2519548899 @default.
• W4285091162 cites W2525912335 @default.
• W4285091162 cites W2574657229 @default.
• W4285091162 cites W2582823158 @default.
• W4285091162 cites W2754764275 @default.
• W4285091162 cites W2767142322 @default.
• W4285091162 cites W2791324218 @default.
• W4285091162 cites W2795975941 @default.
• W4285091162 cites W2889814654 @default.
• W4285091162 cites W2895159086 @default.
• W4285091162 cites W2895777600 @default.
• W4285091162 cites W2902214734 @default.
• W4285091162 cites W2912100457 @default.
• W4285091162 cites W2924092017 @default.
• W4285091162 cites W2947207459 @default.
• W4285091162 cites W2955168996 @default.
• W4285091162 cites W2964482767 @default.
• W4285091162 cites W2995283502 @default.
• W4285091162 cites W3004602362 @default.
• W4285091162 cites W3008241461 @default.
• W4285091162 cites W3011781975 @default.
• W4285091162 cites W3012182407 @default.
• W4285091162 cites W3014582166 @default.
• W4285091162 cites W3036050535 @default.
• W4285091162 cites W3075254871 @default.
• W4285091162 cites W3081831675 @default.
• W4285091162 cites W3083460526 @default.
• W4285091162 cites W3094790588 @default.
• W4285091162 cites W3118674140 @default.
• W4285091162 cites W3118755289 @default.
• W4285091162 cites W3119875471 @default.
• W4285091162 cites W3125741799 @default.
• W4285091162 cites W3134768369 @default.
• W4285091162 cites W3165219381 @default.
• W4285091162 cites W3191214549 @default.
• W4285091162 cites W3198470964 @default.
• W4285091162 cites W4249517230 @default.
• W4285091162 doi "https://doi.org/10.3390/en15145085" @default.
• W4285091162 hasPublicationYear "2022" @default.
• W4285091162 type Work @default.
• W4285091162 citedByCount "2" @default.
• W4285091162 countsByYear W42850911622022 @default.
• W4285091162 crossrefType "journal-article" @default.
• W4285091162 hasAuthorship W4285091162A5008536450 @default.
• W4285091162 hasAuthorship W4285091162A5023923197 @default.
• W4285091162 hasAuthorship W4285091162A5036653771 @default.
• W4285091162 hasAuthorship W4285091162A5087506938 @default.
• W4285091162 hasBestOaLocation W42850911621 @default.
• W4285091162 hasConcept C119857082 @default.
• W4285091162 hasConcept C121332964 @default.
• W4285091162 hasConcept C124101348 @default.
• W4285091162 hasConcept C127313418 @default.
• W4285091162 hasConcept C153180895 @default.
• W4285091162 hasConcept C153294291 @default.
• W4285091162 hasConcept C154945302 @default.
• W4285091162 hasConcept C157486923 @default.
• W4285091162 hasConcept C165205528 @default.
• W4285091162 hasConcept C16910744 @default.
• W4285091162 hasConcept C175551986 @default.
• W4285091162 hasConcept C199360897 @default.
• W4285091162 hasConcept C202444582 @default.
• W4285091162 hasConcept C2776459999 @default.
• W4285091162 hasConcept C2777211547 @default.
• W4285091162 hasConcept C33923547 @default.
• W4285091162 hasConcept C37914503 @default.
• W4285091162 hasConcept C41008148 @default.
• W4285091162 hasConcept C50644808 @default.
• W4285091162 hasConcept C51632099 @default.
• W4285091162 hasConcept C76155785 @default.
• W4285091162 hasConcept C81363708 @default.
• W4285091162 hasConcept C9652623 @default.
• W4285091162 hasConceptScore W4285091162C119857082 @default.
• W4285091162 hasConceptScore W4285091162C121332964 @default.
• W4285091162 hasConceptScore W4285091162C124101348 @default.
• W4285091162 hasConceptScore W4285091162C127313418 @default.
• W4285091162 hasConceptScore W4285091162C153180895 @default.
• W4285091162 hasConceptScore W4285091162C153294291 @default.
• W4285091162 hasConceptScore W4285091162C154945302 @default.
• W4285091162 hasConceptScore W4285091162C157486923 @default.
• W4285091162 hasConceptScore W4285091162C165205528 @default.
• W4285091162 hasConceptScore W4285091162C16910744 @default.
• W4285091162 hasConceptScore W4285091162C175551986 @default.
• W4285091162 hasConceptScore W4285091162C199360897 @default.
• W4285091162 hasConceptScore W4285091162C202444582 @default.
• W4285091162 hasConceptScore W4285091162C2776459999 @default.

• next