A Data-Driven Predictive Maintenance Approach for Industry 4.0 Using LSTM with Cross-Validation and the IDAIC Framework
Bibliographic record
Abstract
In the current context of intense competition, industrial maintenance plays a crucial role in ensuring the performance and resilience of companies.It ensures the continuous availability of equipment, which is essential to avoid unplanned downtime that can lead to significant economic losses.Moreover, maintenance improves production quality by reducing failures and manufacturing defects, and by optimizing the costs associated with maintenance interventions.Predictive maintenance, which is a fundamental part of Industry 4.0, allows for anticipating failures before they occur by leveraging real-time data to predict malfunctions and plan the necessary actions.This not only reduces unplanned downtime but also lowers the overall cost of repairs and equipment replacements.However, data acquisition and processing present major challenges for data science project managers, as they require appropriate frameworks and approaches tailored to each problem and context.This study proposes an innovative solution with a predictive maintenance model developed using the industrial data analysis improvement cycle (IDAIC) approach, specifically designed for industrial maintenance projects.By using a deep learning algorithm, long short-term memory (LSTM), and techniques such as early stopping, the model was applied to the data of a plastic injection molding machine and achieved impressive results.With an R² of 96% and an MSE of 99%, it presents itself as a powerful decision-support tool for industrial maintenance.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".