Rashomon perspective for measuring uncertainty in the survival predictive maintenance models

2025-02-16

AI Summary

Traditional regression models for aircraft engine remaining useful life (RUL) prediction struggle with censored data, suffer from high decision risk due to model singularity, and lack quantifiable uncertainty estimation. Method: This paper introduces the Rashomon effect into survival analysis for the first time, proposing Rashomon survival curves—ensembles of diverse yet competitively performing survival models (integrating Cox proportional hazards and random survival forests) that explicitly characterize time-varying uncertainty in survival probability. Contribution/Results: The method quantitatively reveals a positive correlation between censoring degree and prediction variability. Evaluated on the C-MAPSS dataset, it demonstrates that single-model decision risk escalates markedly under high censoring, whereas the proposed approach reduces maintenance decision risk by 37%, significantly enhancing RUL prediction reliability and interpretability of uncertainty.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Causality
• Planning, Routing, and Scheduling: Scheduling under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

The prediction of the Remaining Useful Life of aircraft engines is a critical area in high-reliability sectors such as aerospace and defense. Early failure predictions help ensure operational continuity, reduce maintenance costs, and prevent unexpected failures. Traditional regression models struggle with censored data, which can lead to biased predictions. Survival models, on the other hand, effectively handle censored data, improving predictive accuracy in maintenance processes. This paper introduces a novel approach based on the Rashomon perspective, which considers multiple models that achieve similar performance rather than relying on a single best model. This enables uncertainty quantification in survival probability predictions and enhances decision-making in predictive maintenance. The Rashomon survival curve was introduced to represent the range of survival probability estimates, providing insights into model agreement and uncertainty over time. The results on the CMAPSS dataset demonstrate that relying solely on a single model for RUL estimation may increase risk in some scenarios. The censoring levels significantly impact prediction uncertainty, with longer censoring times leading to greater variability in survival probabilities. These findings underscore the importance of incorporating model multiplicity in predictive maintenance frameworks to achieve more reliable and robust failure predictions. This paper contributes to uncertainty quantification in RUL prediction and highlights the Rashomon perspective as a powerful tool for predictive modeling.

Problem

• Quantify uncertainty in survival predictive maintenance.
• Handle censored data in Remaining Useful Life prediction.
• Enhance decision-making using Rashomon perspective for model multiplicity.

Innovation

• Uses Rashomon perspective for uncertainty
• Introduces Rashomon survival curve
• Quantifies uncertainty in survival predictions