A Centralized Federated Learning Algorithm based Multi classification Predictive Maintenance in Industrial Internet of Things System
Bibliographic record
Abstract
Predictive maintenance (PdM) is essential for maintaining sustained operation for Industry 4.0 systems.Using artificial intelligence is crucial when PdM is required.However, there are several difficulties because of growing requirements for secure learning when uploading and downloading data in cloud servers.This led to the use of a training algorithm that preserves the privacy and security of the dataset.This work proposed a Federated Learning (FL) algorithm in PdM emphasizing its benefits in terms of quicker training time, lower latency, low power consumption, and, mainly, more security and privacy.The proposed system uses FL with deep neural network (DNN) model for both client and global models.Three client systems are represented by three AC motors equipped with different sensors, such as temperature, vibration, and current, which have been interfaced with Raspberry Pi through the I2C communication protocol.The weight values for the models are uploaded and downloaded between the local model and the global model in the cloud server using the MQTT Internet of Things (IoT) protocol.Results show good training performance metrics enhancement for the FL algorithm over the local model training without FL, where the accuracy has been increased from (0.9915) to (0.9983) in FL while the loss is decreased from (0.0232) to (0.0104) in FL.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".