🤖 AI Summary
This study addresses the asymmetric cost of early versus late errors in remaining useful life (RUL) prediction for predictive maintenance, where conventional single-objective optimization struggles to balance directional bias. We propose a multi-objective hyperparameter optimization framework that treats the optimization objective itself as a design variable, jointly optimizing R² and the NASA scoring function. The NSGA-II algorithm is combined with an entropy weight–CRITIC method to resolve conflicting objectives, and the approach is systematically evaluated across five architectures: MLP, LSTM, XGBoost, TCN, and Transformer. Experiments on the C-MAPSS dataset demonstrate that the proposed method reduces directional imbalance by 33%. Furthermore, the results reveal that model rankings are highly sensitive to hyperparameter configurations and quantify cross-domain generalization gaps, offering practical insights for reliable RUL estimation.
📝 Abstract
In predictive maintenance, early and late RUL prediction errors carry asymmetric consequences, yet hyperparameter optimization typically targets a single accuracy metric that treats both directions equally. This study treats the optimization objective itself as a design variable. Five architectures (MLP, LSTM, XGBoost, TCN, and Transformer) are evaluated under three regimes: single-objective maximization of $R^2$, single-objective minimization of the NASA scoring function, and a multi-objective formulation that jointly optimizes both criteria. The multi-objective search employs NSGA-II with Entropy-CRITIC weighting for Pareto selection. Seventy-five model-dataset-strategy combinations are assessed on the NASA C-MAPSS turbofan and BackBlaze hard-disk drive benchmarks. On C-MAPSS, all strategies achieve comparable accuracy ($R^2 \approx 0.89$), yet multi-objective optimization reduces directional imbalance by approximately 33%, improving calibration of early versus late predictions. Model rankings prove configuration-dependent, with simpler architectures frequently outperforming deeper temporal models. On BackBlaze, the objectives shift from complementary to conflicting, producing divergent Entropy-CRITIC weights and a substantial generalization gap (best $R^2 \approx 0.34$). These results demonstrate that the optimization objective materially shapes prognostic behavior and that multi-objective search provides a practical mechanism for calibrating prediction timeliness in RUL modeling.