Artificial Intelligence Techniques for Industrial Predictive Maintenance: A Systematic Review of Recent Advances
Bibliographic record
Abstract
Modern industrial operations are under growing pressure to maximize asset performance, reduce expensive downtime, and improve safety.Exploiting progress in sensor technology and data analytics, Predictive Maintenance (PdM) presents a forward-looking maintenance strategy, moving past conventional reactive or scheduled approaches.This review explores the innovative use of Artificial Intelligence (AI), encompassing Machine Learning (ML) and Deep Learning (DL), to significantly boost PdM efficiency.Drawing upon a methodical analysis of 29 peer-reviewed articles from the last decade, this review consolidates the current landscape, major trends, obstacles, and future outlook regarding the deployment of AI methods for industrial Predictive Maintenance.The analysis indicates a significant tendency towards utilizing DL techniques for sophisticated tasks such as Remaining Useful Life (RUL) estimation and anomaly identification.Developing fields include employing Deep Reinforcement Learning (DRL) for optimal maintenance scheduling, methods for explainability (XAI) for fostering trust, and the convergence of PdM with data-driven production planning and emerging Digital Twins.Despite substantial advancements, significant hurdles remain concerning data quality and accessibility, model interpretability, scalability, system integration, and cybersecurity.This review offers a thorough, holistic overview for researchers and industry professionals, underscoring the game-changing possibilities of AI within PdM and pinpointing key domains that warrant deeper exploration.
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) | 0.002 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".