An Adaptive Neuro-Fuzzy Model-Based Algorithm for Fault Detection in PV Systems
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This article presents an intelligent algorithm-based fault detection scheme to improve the reliability and sustainability of a photovoltaic (PV) system. The PV systems are extremely susceptible to power grid transients and their operation may suffer drastically during faults located within the solar arrays, power electronics, and the inverter. Thus, it is significantly important to develop an intelligent mechanism to detect any type of fault or abnormalities at the shortest possible time and provide security for the solar system. In order to accomplish that, an adaptive neuro-fuzzy inference system (ANFIS) is developed to distinguish between normal, and faulty operation of a grid-connected PV system. A large dataset from real-time laboratory experiment using TBD125x125-36-P PV module, which includes the current, and voltage characteristic of PV is extracted, preprocessed and used in the training of the machine learning algorithm. The performance of the proposed intelligent fault detection scheme is also compared with other popular machine learning algorithms, where ANFIS have demonstrated outstanding results, with accuracy rate of 95.4%. Furthermore, the proposed technique is significantly more robust, straightforward, and requires less implementation time compared to other machine learning techniques such as, K nearest neighbor, decision tree, Naïve Bayes, Ensemble, linear discriminant analysis, support vector machine, and finally neural network. Thus, the developed ANFIS based intelligent technique will enhance the reliability of the PV system through minimizing the maintenance cost, saving time and energy.
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.
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 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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 it