Innovative web system for condition-based maintenance of generators
Bibliographic record
Abstract
A novel integrated diagnostic system has been developed at IREQ, the research institute of Hydro-Quebec, over the last eight years. The goal of this project was to build an integrated methodology for generator diagnostics using the results from on-site measurement tools, which would help the utility to make the transition from time-based maintenance to condition-based maintenance. The system makes use of information technology (Internet) to provide a new, modern and efficient way to produce a continuous classification of the condition of all generators of a fleet along with individual diagnostics for any unit at any time. The system computes actual measurements provided by plant personnel who transfer data files to a centralized server. The application calculates simple condition indexes from each of six on-line/off-line diagnostic tools and from visual inspections, and aggregates the results into a comprehensive global diagnostic for the selected generator. Plant and generator selection is done via a user-friendly interface displaying a simple rating of the results for every tool. The algorithm underlying the system generates a global diagnostic for any combination of tools, regardless of their number and selection. However, the level of confidence of the diagnostic will increase with the number of tools used for the diagnostic. In addition to the simplified integrated condition index values of all generators and the individual index for each tool, specialists can access and display the complete data for every measurement series. Each tool, some commercial, others developed at Hydro-Quebec, was selected based on its ability to characterize specific complementary aspects of the generator. Since the system was developed with an expandable modular approach, it will be possible in the future to add new diagnostic tools, not yet considered in the current version, without affecting the logic of the system. Hydro-Quebec has recently implemented this new system and is already noting improvement in maintenance practices. The ready availability of centralized, simplified information makes it possible for generator specialists and managers alike to assess the condition of any generator in a few minutes. Thanks to this new diagnostic system, technical and management staff can now work together with common information and in real time to optimize maintenance intervention on generators showing degradation. Thus, it is possible to plan any corrective action more effectively or request additional testing when doubts remain about active degradation mechanisms. At the same time, efforts in diagnosis and maintenance could be optimized by reducing the number of measurement campaigns for the vast majority of generators that are in good condition as revealed by their condition indexes.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.021 | 0.013 |
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".