发表机构
Istanbul Bilgi University; Beştepe Koleji（伊斯坦布尔比尔基大学; 贝什泰佩学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究将优化目标作为设计变量，通过多目标超参数优化（NSGA-II 与熵-CRITIC 加权）在 C-MAPSS 和 BackBlaze 基准上校准 RUL 预测的时效性，显著减少方向性不平衡，并揭示架构性能的配置依赖性。
AI 中文摘要
在预测性维护中，过早和过晚的剩余使用寿命（RUL）预测误差会带来不对称的后果，然而超参数优化通常针对单一准确度指标，该指标对两个方向的误差同等对待。本研究将优化目标本身视为设计变量。在三种机制下评估了五种架构（MLP、LSTM、XGBoost、TCN 和 Transformer）：$R^2$ 的单目标最大化、NASA 评分函数的单目标最小化，以及联合优化这两个标准的的多目标公式。多目标搜索采用带熵-CRITIC 加权进行帕累托选择的 NSGA-II。在 NASA C-MAPSS 涡扇发动机和 BackBlaze 硬盘驱动器基准上评估了七十五种模型-数据集-策略组合。在 C-MAPSS 上，所有策略均实现了相当的准确度（$R^2 \approx 0.89$），然而多目标优化将方向性不平衡减少了约 33%，改善了早期与晚期预测的校准。模型排名被证明依赖于配置，较简单的架构经常优于更深的时间模型。在 BackBlaze 上，目标从互补转变为冲突，产生了发散的熵-CRITIC 权重和显著的泛化差距（最佳 $R^2 \approx 0.34$）。这些结果表明，优化目标实质上塑造了预测行为，并且多目标搜索为校准 RUL 建模中的预测时效性提供了一种实用机制。
英文摘要
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.
