Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2512.01149 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915811741925376 |
|---|---|
| author | Dhande, Shaunak Ma, Chutian Saggese, Giacinto Paolo Smith, Paul Taduri, Krishna |
| author_facet | Dhande, Shaunak Ma, Chutian Saggese, Giacinto Paolo Smith, Paul Taduri, Krishna |
| contents | Predictive maintenance in manufacturing environments presents a challenging optimization problem characterized by extreme cost asymmetry, where missed failures incur costs roughly fifty times higher than false alarms. Predictive maintenance in manufacturing environments presents a challenging optimization problem characterized by extreme cost asymmetry, where missed failures incur costs roughly fifty times higher than false alarms. Conventional machine learning approaches typically optimize statistical accuracy metrics that do not reflect this operational reality and cannot reliably distinguish causal relationships from spurious correlations. This study benchmarks eight predictive models, ranging from baseline statistical approaches to Bayesian structural causal methods, on a dataset of 10,000 CNC machines with a 3.3 percent failure prevalence. While ensemble correlation-based models such as Random Forest (L4) achieve the highest raw cost savings (70.8 percent reduction), the Bayesian Structural Causal Model (L7) delivers competitive financial performance (66.4 percent cost reduction) with an inherent ability of failure attribution, which correlation-based models do not readily provide. The model achieves perfect attribution for HDF, PWF, and OSF failure types. These results suggest that causal methods, when combined with domain knowledge and Bayesian inference, offer a potentially favorable trade-off between predictive performance and operational interpretability in predictive maintenance applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_01149 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Benchmark of Causal vs. Correlation AI for Predictive Maintenance Dhande, Shaunak Ma, Chutian Saggese, Giacinto Paolo Smith, Paul Taduri, Krishna Artificial Intelligence Machine Learning Predictive maintenance in manufacturing environments presents a challenging optimization problem characterized by extreme cost asymmetry, where missed failures incur costs roughly fifty times higher than false alarms. Predictive maintenance in manufacturing environments presents a challenging optimization problem characterized by extreme cost asymmetry, where missed failures incur costs roughly fifty times higher than false alarms. Conventional machine learning approaches typically optimize statistical accuracy metrics that do not reflect this operational reality and cannot reliably distinguish causal relationships from spurious correlations. This study benchmarks eight predictive models, ranging from baseline statistical approaches to Bayesian structural causal methods, on a dataset of 10,000 CNC machines with a 3.3 percent failure prevalence. While ensemble correlation-based models such as Random Forest (L4) achieve the highest raw cost savings (70.8 percent reduction), the Bayesian Structural Causal Model (L7) delivers competitive financial performance (66.4 percent cost reduction) with an inherent ability of failure attribution, which correlation-based models do not readily provide. The model achieves perfect attribution for HDF, PWF, and OSF failure types. These results suggest that causal methods, when combined with domain knowledge and Bayesian inference, offer a potentially favorable trade-off between predictive performance and operational interpretability in predictive maintenance applications. |
| title | A Benchmark of Causal vs. Correlation AI for Predictive Maintenance |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2512.01149 |