Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Fault Types01:18

Fault Types

When analyzing a single line-to-ground fault from phase A to ground at a three-phase bus, it is important to consider the fault impedance. This impedance is zero for a bolted fault, equal to the arc impedance for an arcing fault, and represents the total fault impedance for a transmission-line insulator flashover. To derive sequence and phase currents, fault conditions are translated from the phase domain to the sequence domain.
For line-to-line faults occurring between phases B and C, the...
Differential Leveling01:12

Differential Leveling

Differential leveling is a precise method in surveying used to determine the elevation difference between two points. Its primary goal is to establish accurate vertical measurements to create level surfaces or grade lines critical for designing and constructing infrastructures such as roads, bridges, and buildings.The procedure for differential leveling begins with setting up and leveling the instrument at a point where the benchmark can be seen. The level rod is held on the benchmark (BM), and...
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

MRI findings in individuals with temporomandibular disorders.

Cranio : the journal of craniomandibular practice·2026
Same author

Non-Volatile Metabolic Reprogramming and Sensory Evolution of Anhua Qianliang Tea During Long-Term Storage.

Foods (Basel, Switzerland)·2026
Same author

Bleeding Risk Associated with Novel Oral Anticoagulants in Critically Ill Patients: A Scoping Review.

Journal of visualized experiments : JoVE·2026
Same author

Plasma proteomics predicts pathological complete response and reveals LIF as a potential mediator of resistance to neoadjuvant immunochemotherapy in resectable NSCLC.

Journal for immunotherapy of cancer·2026
Same author

Spatially Decoupled Capture-Conversion Architectures for Photocatalytic Uranium Extraction from Dilute Wastewater.

Journal of the American Chemical Society·2026
Same author

Aroma evolution of Anhua Qianliang tea across different storage years: Machine learning-assisted discrimination of storage stages and screening of marker volatile compounds.

Food chemistry: X·2026

Related Experiment Videos

GMD-YOLO: A Dual-Modality Framework with Multi-Scale Enhancement and Adaptive Fusion for PV Fault Detection.

Zhichao Lin1,2, Xiuling Wang1,2, Yuyang Guo1,2

  • 1College of Information Engineering, Inner Mongolia University of Technology, Hohhot 010080, China.

Sensors (Basel, Switzerland)
|June 12, 2026
PubMed
Summary

This study introduces a dual-modality visible-infrared fusion framework for photovoltaic (PV) module fault detection. The new method enhances accuracy and efficiency in identifying PV module defects, improving safety and power generation.

Keywords:
Shape-IoUYOLO11dual-modality detectionobject detectionphotovoltaic modulesvisible–infrared fusion

Related Experiment Videos

Area of Science:

  • Renewable Energy Systems
  • Artificial Intelligence
  • Computer Vision

Background:

  • Photovoltaic (PV) module faults like hotspots and short circuits reduce efficiency and safety.
  • Current inspection methods struggle with varying illumination and weak thermal signals.
  • Deep learning models often overlook the combined benefits of visible and infrared imaging.

Purpose of the Study:

  • To develop a robust dual-modality fusion framework for intelligent PV module fault detection.
  • To improve the accuracy and efficiency of identifying diverse PV module faults.
  • To address limitations of single-modality and existing deep learning approaches.

Main Methods:

  • Proposed a visible-infrared fusion framework based on YOLOv11.
  • Integrated multi-scale pyramid pooling (MSPPD), gradient-aware fusion (GAFusion), and dynamic convolution (Detect-DEhead).
  • Utilized gradient-aware feature interaction for enhanced cross-modal consistency and Shape-IoU loss for localization accuracy.

Main Results:

  • Improved mean average precision (mAP)@0.5 from 86.7% to 88.4%.
  • Reduced model parameters, computational cost (GFLOPs), and size (MB).
  • Achieved significant gains in precision (2.2%), recall (1.6%–2.7%), and mAP@0.5 on the FLIR Thermal dataset.

Conclusions:

  • The dual-modality fusion framework offers an effective balance between accuracy and efficiency for PV module inspection.
  • The proposed GAFusion and Detect-DEhead modules enhance fault detection capabilities.
  • This approach advances intelligent inspection systems for renewable energy infrastructure.