Knowledge-Intensive Diagnostics Using Case-Based Reasoning and Synthetic Case Generation
Bibliographic record
Abstract
Due to commercial pressures, North-American printed circuit-board assembly manufacturers have had to reposition themselves in the more difficult market segment of lower volume, higher complexity products, also called high-mix, low-volume (HMLV). The high per-unit costs of these products justify substantial diagnosis and repair efforts when defects are detected in production. Although automated diagnostics is desirable, the low production volumes impose severe limits on available data. We propose a novel approach based on knowledge modeling and case-based reasoning for automated diagnosis of assembled printed circuit boards in an HMLV production environment. Our hybrid approach can overcome the knowledge-acquisition bottleneck even in a data-poor environment. The proposed approach does not require contributions from product designers or experts and is designed to operate using only information available during manufacturing. Our test results show that our diagnostic system can detect, locate and classify all single faults and multiple faults affecting up to three neighboring nodes with a better success rate than the reference commercial tool. Moreover, case base data, including board layout information and user feedback from previous repairs, is used to feed a recommender system to provide repair suggestions. A production and repair data simulator is described and used to evaluate the recommender system’s effectiveness.
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 | 0.003 | 0.014 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".