发表机构
Universidad de Guayaquil; Universidad Bolivariana del Ecuador; Universidad Bernardo O'Higgins（瓜亚基尔大学; 厄瓜多尔玻利瓦尔大学; 贝尔纳多·奥希金斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出基于中智集分解的集成分类方法，通过四个不确定性指标在轴承故障检测中区分错误与模糊预测，并在CWRU和JNU基准上验证，发现预测熵指标有效而决策分歧贡献有限，融合时频域模型可提升不确定性评估。
AI 中文摘要
用于轴承故障检测的机器学习分类器产生标量置信度分数，这些分数将自信的错误与真正模糊的预测混为一谈，且传统的真/假对（F = 1 - T）在构造上代数冗余。我们将随机森林+XGBoost+逻辑回归集成的中智集分解细化为四个指标——T-hat（最高类别证据）、F-hat（最佳竞争者证据）、预测熵I1-hat和决策分歧I2-hat——并在留一条件协议下于两个轴承基准（CWRU和JNU，600-1000 rpm）上进行评估。在CWRU上，修正文件到类别映射错误后，集成在四个保留负载中的三个上达到100.00%的准确率（第四个为92.27%），留下的错误太少而无法进行不确定性分析。在JNU上，保留1000 rpm时，准确率骤降至40.64%，低于多数类基线；逻辑回归（57.91%）的泛化能力远优于树集成。I1-hat显示出与错误超越T-hat/F-hat的稳健关联，而I2-hat贡献甚微；独立逻辑回归置信度优于完整分解，我们如实报告这一边界条件。另外两个结果扩展了这一点：融合同一信号的时域和频域模型并对其Jensen-Shannon散度评分，优于该模型自身的熵（标准分割下AURC 0.29对0.36；更难的单一条件复现下0.54对0.73），这是唯一在CWRU对JNU分布偏移对比中正确移动的指标；且仅在CWRU上，经包络谱正确解调的文献验证轴承故障频率，使用三个可解释特征几乎完美地分离了大多数故障类别（99.57%）。代码、日志和图形已发布以供独立验证。
英文摘要
Machine learning classifiers for bearing fault detection produce scalar confidence scores that conflate confident errors with genuinely ambiguous predictions, and the conventional truth/falsity pair (F = 1 - T) is algebraically redundant by construction. We operationalize a refined neutrosophic decomposition of a Random Forest + XGBoost + Logistic Regression ensemble into four indicators -- T-hat (top-class evidence), F-hat (best-competitor evidence), predictive entropy I1-hat, and decision disagreement I2-hat -- evaluated on two bearing benchmarks (CWRU and JNU, 600-1000 rpm) under a leave-one-condition-out protocol. On CWRU, after correcting a file-to-class mapping error, the ensemble reaches 100.00 percent accuracy on three of four held-out loads (92.27 percent on the fourth), leaving too few errors for uncertainty analysis. On JNU, holding out 1000 rpm, accuracy collapses to 40.64 percent, below a majority-class baseline; Logistic Regression (57.91 percent) generalizes far better than the tree ensembles. I1-hat shows a robust association with error beyond T-hat/F-hat, while I2-hat contributes little; standalone Logistic Regression confidence outperforms the full decomposition, a boundary condition we report honestly. Two further results extend this: fusing a time-domain and a frequency-domain model of the same signal and scoring their Jensen-Shannon divergence beats that model own entropy (AURC 0.29 vs. 0.36 on the standard split; 0.54 vs. 0.73 under a harder single-condition reproduction), the only indicator moving correctly under a CWRU-versus-JNU distributional-shift contrast; and, on CWRU alone, literature-verified bearing fault frequencies, correctly demodulated via the envelope spectrum, separate most fault classes almost perfectly (99.57 percent) using three interpretable features. Code, logs, and figures are released for independent verification.
Comments18 pages, 5 figures
