Exploring Rolling Element Bearing Data Collection and Algorithm Hyperparameters for Machine Learning-Based Fault Diagnosis
Bibliographic record
Abstract
This paper explores rolling element bearing data collection and hyperparameter tuning for machine learning-based fault diagnosis to aid in the development of modern condition monitoring systems. The integration of industrial internet of things (IIoT) products and cloud databases has led to an increased interest in utilizing artificial intelligence (AI) models, including artificial neural networks (ANNs) and convolutional neural networks (CNNs), to diagnose machine faults. However, the development of AI methodologies in smart monitoring is hindered by a lack of publicly available industry data, as well as limitations involved in the collection and storage of large high-dimensional datasets. Combining machine learning (ML) methods, such as traditional learning (TL), deep learning (DL), and bearing signature theory, will allow for a better understanding of data collection and hyperparameter tuning. Moreover, considering how high-dimensional datasets for rolling element bearing fault diagnosis affect ML algorithms has yet to be explored in the literature, providing little robustness for analysis. Concerns around the way data has been collected and used historically for both TL and DL are raised. Therefore, recommendations for data collection specifically suited to TL and DL methods for rolling element bearing fault diagnosis are proposed by analyzing existing lab-based datasets. The recommendations proposed combine knowledge of these methodologies to aid in selecting an appropriate sampling rate, as well as the ideal number of samples, stride, duration of each sample, and resolution for rolling element bearing fault diagnosis. The goal is to increase efficiency and reduce setup and collection time when selecting the design parameters for creating new rolling element bearing datasets. To achieve this, the study applied a structured approach with the use of multiple datasets to determine a threshold accuracy of 95% for fault diagnosis. Furthermore, the results of this study will help IIoT companies re-evaluate the constraints imposed by the limited data storage and transmission of their devices when used for ML. This paper will also help improve the efficiency and effectiveness of AI methodologies in smart monitoring systems by establishing data collection recommendations. This work will hopefully motivate the vast collection of open-access data that can be used by researchers to further develop ML-based methods for rolling element fault diagnosis.
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 | 0.005 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".