Comparative analysis of recent studies on predictive maintenance, energy optimization, and edge AI in manufacturing
| Study | Model/Focus | Key findings | Limitations |
|---|---|---|---|
| Zhang et al. (2023) | Edge AI for predictive maintenance | Improved response time and prediction accuracy | Limited to simulation data |
| Li and Zhao (2022) | Adaptive ML-based maintenance scheduling | Enhanced adaptability and reduced downtime | Focus on ML, not edge deployment |
| Kumar and Singh (2021) | AI for energy optimization in manufacturing | Effective energy consumption reduction using AI | Did not include maintenance as target |
| Wang and Zhang (2019) | Edge computing for predictive maintenance | Low-latency edge solutions improved reliability | General edge use; no energy metrics |
| Ahmed and Khan (2022) | Random Forest for maintenance prediction | High accuracy in predicting equipment behavior | Lacks real-time deployment |
| Chen and Zhao (2020) | DSS for adaptive maintenance in Industry 4.0 | Improved decision processes in maintenance | Theoretical; no field application |
| Lee and Kim (2020) | Energy-aware decision-making systems | Highlighted need for integrating energy metrics | No predictive modeling component |
| Study | Model/Focus | Key findings | Limitations |
|---|---|---|---|
| Edge AI for predictive maintenance | Improved response time and prediction accuracy | Limited to simulation data | |
| Adaptive ML-based maintenance scheduling | Enhanced adaptability and reduced downtime | Focus on ML, not edge deployment | |
| AI for energy optimization in manufacturing | Effective energy consumption reduction using AI | Did not include maintenance as target | |
| Edge computing for predictive maintenance | Low-latency edge solutions improved reliability | General edge use; no energy metrics | |
| Random Forest for maintenance prediction | High accuracy in predicting equipment behavior | Lacks real-time deployment | |
| DSS for adaptive maintenance in Industry 4.0 | Improved decision processes in maintenance | Theoretical; no field application | |
| Energy-aware decision-making systems | Highlighted need for integrating energy metrics | No predictive modeling component |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.