Automatic fault classification of photovoltaic strings based on an in situ IV characterization system and a Gaussian process algorithm

Jones, C. Birk; Martínez‐Ramón, Manel; Smith, Ryan; Carmignani, Craig; Lavrovа, Olga; Robinson, Charles; Stein, Joshua S.

doi:10.1109/pvsc.2016.7749915

Cited by 13 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results show that calculating parameters based on domain knowledge allows for more stable and accurate results. If stringlevel control field measurements are not available to calculate δ I , control IV curves can be generated through either a diode model or Gaussian process regression [29], [30].…”

Section: Resultsmentioning

confidence: 99%

Neural Network-Based Classification of String-Level IV Curves From Physically-Induced Failures of Photovoltaic Modules

et al. 2020

View full text Add to dashboard Cite

Accurate diagnosis of failures is critical for meeting photovoltaic (PV) performance objectives and avoiding safety concerns. This analysis focuses on the classification of field-collected string-level current-voltage (IV) curves representing baseline, partial soiling, and cracked failure modes. Specifically, multiple neural network-based architectures (including convolutional and long short-term memory) are evaluated using domain-informed parameters across different portions of the IV curve and a range of irradiance thresholds. The analysis identified two models that were able to accurately classify the relatively small dataset (~400 samples) at a high accuracy (99%+). Findings also indicate optimal irradiance thresholds and opportunities for improvements in classification activities by focusing on portions of the IV curve. Such advancements are critical for expanding accurate classification of PV faults, especially for those with low power loss (e.g., cracked cells) or visibly similar IV curve profiles.

show abstract

Section: Resultsmentioning

confidence: 99%

Neural Network-Based Classification of String-Level IV Curves From Physically-Induced Failures of Photovoltaic Modules

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Module-level in-situ I-V testers have been used for system monitoring [120], degradation analysis [112], and real-time fault detection [121]. Techniques have also been established for in-situ measurements at the array level, which have been used for automatic fault detection [122]. The rise of wireless sensors have enabled these measurements to be conducted in a more scalable way, as compared to wired sensors [123].…”

Section: Outdoor Characterization Applicationsmentioning

confidence: 99%

Measuring outdoor I–V characteristics of PV modules and systems

et al. 2022

View full text Add to dashboard Cite

The cumulative installed capacity of photovoltaics has passed 1 TW, of which about two-thirds were only installed in the past five years. Many of these new installations incorporate novel module and cell designs that have not yet been subjected to long-term in-field characterization. Indoor accelerated stress testing has historically been a valuable methodology to identify fault mechanisms, estimate degradation rates, and to ensure the safety and normal operation of modules in the field. Still, these methodologies deliver an incomplete image of the exact stress mechanisms that photovoltaic systems are subject to outdoors, which vary with location, time of day, and time of year. In this work we review different outdoor methods to measure current-voltage characteristics of photovoltaic systems, discuss how the environmental conditions impact those characteristics, and examine alternative methodologies for acquiring light and pseudo current-voltage characteristics more applicable to larger scale installations. This review also provides an insight into methods useful for real-time monitoring and degradation analysis at the module and string level.

show abstract

Analysis and design of a robust controller for a grid-connected photovoltaic power plant

Nagaraja

Kumar

Raju

2018

International Journal of Ambient Energy

View full text Add to dashboard Cite

Automatic fault classification of photovoltaic strings based on an in situ IV characterization system and a Gaussian process algorithm

Cited by 13 publications

References 9 publications

Neural Network-Based Classification of String-Level IV Curves From Physically-Induced Failures of Photovoltaic Modules

Neural Network-Based Classification of String-Level IV Curves From Physically-Induced Failures of Photovoltaic Modules

Measuring outdoor I–V characteristics of PV modules and systems

Analysis and design of a robust controller for a grid-connected photovoltaic power plant

Contact Info

Product

Resources

About