调参能显著提升生存森林模型预测设备故障时间的准确性。
On the Tunability of Random Survival Forests Model for Predictive Maintenance
- 提出三层评估框架，量化超参数对生存模型的影响。
- 调参后C指数平均提升0.0547，Brier评分降低0.0199。
- ntree和mtry最易优化，nodesize在10-30间表现稳定。
本文研究随机生存森林（RSF）模型在预测性维护中的可调性，该场景下准确估计故障时间至关重要。尽管RSF因灵活性和对删失数据的处理能力被广泛使用，但其性能对超参数配置敏感。然而，系统性评估仍有限，尤其在预测性维护中。我们提出一个三层框架：(1) 模型级指标衡量调参带来的整体性能提升；(2) 超参数级指标评估各参数贡献；(3) 识别最优调参区间。基于生存分析指标——区分度用C-index，校准度用Brier score——在四个CMAPSS数据子集上进行实验，模拟航空发动机退化过程。结果显示，调参一致提升性能：平均C-index提高0.0547，Brier score降低0.0199，且在所有子集上均成立。ntree与mtry具有最高平均可调性，nodesize在10至30范围内持续改善；而splitrule平均呈现负可调性，说明不当调参反而降低性能。研究强调了生存模型调参的实际意义，并为实际应用中优化RSF提供可行指导。
原文摘要 · Abstract (English)
This paper investigates the tunability of the Random Survival Forest (RSF) model in predictive maintenance, where accurate time-to-failure estimation is crucial. Although RSF is widely used due to its flexibility and ability to handle censored data, its performance is sensitive to hyperparameter configurations. However, systematic evaluations of RSF tunability remain limited, especially in predictive maintenance contexts. We introduce a three-level framework to quantify tunability: (1) a model-level metric measuring overall performance gain from tuning, (2) a hyperparameter-level metric assessing individual contributions, and (3) identification of optimal tuning ranges. These metrics are evaluated across multiple datasets using survival-specific criteria: the C-index for discrimination and the Brier score for calibration. Experiments on four CMAPSS dataset subsets, simulating aircraft engine degradation, reveal that hyperparameter tuning consistently improves model performance. On average, the C-index increased by 0.0547, while the Brier score decreased by 0.0199. These gains were consistent across all subsets. Moreover, ntree and mtry showed the highest average tunability, while nodesize offered stable improvements within the range of 10 to 30. In contrast, splitrule demonstrated negative tunability on average, indicating that improper tuning may reduce model performance. Our findings emphasize the practical importance of hyperparameter tuning in survival models and provide actionable insights for optimizing RSF in real-world predictive maintenance applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。