Implementation of Digital Twin and Deep Learning for Process Monitoring: Case Study in Injection Molding Manufacturing
Bibliographic record
Abstract
This study explores the implementation of artificial intelligence for process monitoring within smart factories, particularly under the Factory 4.0 paradigm.It proposes an approach centered on a data-centric model for digital twins, enhanced by the application of deep learning methodologies utilizing LSTM models to forecast the melt cushion parameter-a crucial indicator of process stability in injection molding.The methodical framework unfolds in stages, beginning with the proposition of the digital twin architecture, followed by the deployment of LSTM networks trained on historical datasets.Following training, the model integrates smoothly into the digital twin ecosystem to provide predictive analytics and decision-making support.In the experimental phase, a hybrid strategy is adopted, combining edge and cloud computing for data acquisition and simulation.Core elements of the methodology include architecture validation, establishment of communication protocols, creation of offline model conditions, integration of the digital twin without disruption, and utilization of edge computing for real-time predictive analysis during simulations.This approach offers a comprehensive solution to the challenges of process monitoring in smart factories, facilitating enhanced operational efficiency and performance optimization.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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".