Reliability-as-a-Service for bearing risk assessment investigated with advanced mathematical models
Bibliographic record
Abstract
As a key player in bearing service life, the lubricant chemistry has a profound effect on bearing reliability. To increase the reliability of bearings, an Industrial Analytics solution is proposed for proactive condition monitoring and this is delivered via a Reliability-as-a-Serviceapplication. The performance predictions of bearings rely on customized algorithms with the main focus on digitalizing lubricant chemistry; the principles behind these processes are outlined in this study. Subsequently, independent testing is performed to confirm the ability of the presented Industrial Analytics solution for such predictions. By deciphering the chemical compounds of lubricants and characteristics of the interface, the Industrial Analytics solution delivers a precise bearing reliability assessment a priori to predict service life of the operation. Bearing tests have shown that the classification system of this Industrial Analytics solution is able to predict 12 out of 13 bearing failures (92%). The described approach provides a proactive bearing risk classification that allows the operator to take immediate action in reducing the failure potential during smooth operation - preventing any potential damage from occurring. For this purpose, a mathematical model is introduced that derives a set of classification rules for oil lubricants, based on linear binary classifiers (support vector machines) that are applied to the chemical compound’s mixture data.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".