Impact of Combining RGB and Grayscale Images on Hotspot Detection in Solar Panels Using Inception Resnet V2 Architecture
Bibliographic record
Abstract
Solar panels are a technology that converts solar energy into electricity through the photovoltaic effect.This photovoltaic technology is packaged into solar modules consisting of many solar cells arranged in series or parallel.Damage to these panels can be identified by detecting hotspots using a thermal camera.Hotspots can be classified into three categories of damage: No Damage, Minor Damage, and Severe Damage.This study applies the Inception ResNet V2 architecture from deep learning to automatically classify the level of damage based on thermal images.The novelty of this research is its implementation for real time monitoring of a structured array of 20 solar panels (54 panel), enabling early detection and reporting of damage conditions.The model includes several architectural enhancements such as Average Pooling, Flatten, and ReLU layers.Training was conducted using three different datasets: RGB, grayscale, and a combination of both.The RGB dataset achieved the highest accuracy at 98.62 percent, followed by the combined dataset at 98.44 percent, and the grayscale dataset at 96.93 percent.These high accuracy results demonstrate that the proposed system can effectively support preventive maintenance of solar panels.Specifically, the system is applicable for operational use at PT PLN Nusantara Power UP Cirata to improve reliability, reduce power loss, and enhance the overall efficiency of solar energy generation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".