A Data Mining Approach for Forecasting Machine Related Disruptions
Bibliographic record
Abstract
SUMMARY & CONCLUSIONSProduction disruptions in high-tech mass production companies producing many parts every single minute will lead to considerable economic impact and affect manufacturing efficiency. The root causes of disruptions are classified into three categories: human-related, machine-related, and material related. Using different management, hiring, and training strategies, companies are generally successful in reducing human-related and material related disruptions. However, machine-related disruptions (MRDs) are still occurring even in companies employing a solid maintenance program.The MRDs pose random pauses of various durations in a production. Forecasting the characteristics of such pauses (downtimes) can assist in real-time manufacturing process adjustment and real-time rescheduling of a production. This study aims at utilizing available recorded MRDs for forecasting time to forthcoming MRD and its duration. Our general approach is to evaluate the performance of different data mining-based learning techniques for predicting both the duration and time to forthcoming MRDs and determining the outperforming approach. We consider a smart factory located in the northern part of Toronto great area active in the field of thermoplastic injection molding of various components. We use the historical data on the MRDs recorded from 2013 to 2019 to conduct the investigation. In this study, a set of different classifiers, including rule-based, function-based, tree-based, and lazy, are implemented for forecasting each of the duration and time to forthcoming MRD. The part ID, machine ID, mold age, and the ordinal number of the forthcoming MRD are considered as the input attributes of the developed data mining-based classifiers.In order to determine how effectively the data mining-based methods perform, we calculate different performance criteria, including the Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Bias, Correlation Coefficient (CC), and R2. The overall accuracy rate for some tree-based algorithms is significant (CC exceeded 0.92 and MAE<0.06). It shows the capabilities of data mining-based approaches in forecasting the durations and times to MRDs. The obtained trained models are accurate enough to be coupled with stochastic optimization algorithms for real-time manufacturing process adjustment and rescheduling when an MDR takes place.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 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".