Applied Data Analytics Approach for Defect Root Causes Analysis in Manufacturing: The Case of Multi-Product Assembly Lines
Bibliographic record
Abstract
Multi-product assembly lines are commonly used for their flexibility in mass-customized production, but their complexity makes identifying the root causes of defects difficult. This research addresses the limitations of traditional methods for analyzing the root causes of defects in this context. It introduces a four-step methodology for preparing data and conducting descriptive analysis of defect root causes. Product families are created by segmenting production data from the company's information systems using AHC algorithms or company knowledge. Defect rates are then calculated for each product group and the transitions between product sequences. Finally, a CART decision tree is used to generate rules that lead to defective clusters. These rules are used for descriptive analysis of defect root causes and are seen as improvement opportunities for multi-product assembly lines. The methodology was applied to two case studies using real production data. This led to the identification and validation of the root causes of defects by the partner companies. Nevertheless, limitations must be taken into account, e.g., the reliance on expert judgment for the identification of root causes, the sensitivity of the data used, and the necessity of regenerating the decision tree for each new analysis.
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 | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.008 | 0.007 |
| Science and technology studies | 0.001 | 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 | 0.000 |
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".