Bibliographic record
Abstract
Manufacturers are experiencing ever greater pressures to meet a multitude of business demands: boost production rate, increase yield, improve quality and reduce operating costs, etc. One important measure of success is the ability of automated manufacturing processes to run fault free for extended periods of time. When faults do occur, they must be detected, diagnosed and corrected quickly. High speed automated assembly machines typically employ many different types of sensors to monitor machine health and feedback faults (both cautionary and reactionary) to a central controller for review by a technician or engineer. This paper describes progress with a project whose goal is to examine the effectiveness and feasibility of using machine vision to detect ‘visually cued’ machine faults in high speed automation equipment. Machine vision is commonly used in manufacturing to perform a ‘process’ role such as part quality inspection. Machine vision systems use cameras to capture images of parts in a manufacturing process. Computer software packages use custom algorithms to analyze these images, and determine the quality (or even presence) of the part based on physical characteristics including part geometry and colour. If machine vision were successfully applied as a fault monitoring system, it could effectively reduce the amount of sensors needed to monitor the machine’s operation, as a single camera could monitor several locations where known faults occur. The intent is to not only reduce the amount of sensors required to effectively monitor a machine, but to make the machine ‘smarter’ by enriching the data used for fault detection.
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 | 0.004 |
| 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 | 0.001 |
| 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".