Machine learning-based dynamic production planning and control in unreliable manufacturing systems with supply disruptions
Bibliographic record
Abstract
This paper addresses a production planning and control problem within failure-prone manufacturing systems disrupted by irregular raw material supply. It introduces a machine learning-based approach that supports dynamic and responsive decision-making for integrated production and replenishment control policies, minimising expected long-term total costs under stochastic conditions. Our approach enables continuous adjustments to production rates, as well as replenishment order size and triggers, in response to system states and delivery lead time variations. By integrating machine learning techniques, experimental design, and simulation modelling, we assess the impact of control policies parameters and raw material delivery lead times on total costs. The optimised machine learning model then dynamically adjusts these parameters, defining a hedging point production policy combined with an economic order quantity-type replenishment strategy. Numerical experiments show that the dynamic control policies resulting from our approach reduces costs by up to 15% compared to semi-dynamic policies and up to 25% compared to static policies, particularly in environments with high delivery lead time variability. This highlights significant gains in resilience and economic performance over existing approaches. Additionally, our approach can be applied in production environments affected by supply uncertainties, enabling continuous inventory and production adjustments based on observed system conditions.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 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".