Appliance Anomaly Detection as NILM Extention
Bibliographic record
Abstract
The demand for and use of residential electrical appliances has increased rapidly in recent years, as people seek a more comfortable life. Consequently, the number of faults and anomalies within these appliances has grown, resulting in a considerable amount of energy waste. Artificial Intelligence (AI) tools have shown promising results in appliance fault identification. However, most existing methods require the installation of individual sensors for each appliance, which is expensive and complicated. Additionally, these approaches are limited to a few numbers of appliances and fault types and often require manual intervention to set up rules with calculated threshold values for fault identification, which limits their expansion and generalization capability. Non-Intrusive Load Monitoring (NILM) is an approach that monitors individual appliance energy consumption non-intrusively without installing individual sensors at the appliance level. This study proposes a NILM-based hierarchical faulty identification model that addresses many of the existing limitations. The proposed low load hierarchical NILM based model can easily expand for new appliances and faults without requiring manual rule settings. The solution has been developed on a modular basis using a convolutional neural network (CNN) that works in plug-and-play mode. The results have revealed unbiased performance of the model with minimal computational overheads.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| 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 | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".