AI 中文总结
针对安全关键型机械系统中AI诊断的验证问题，提出诊断证据网络DENet，将输出扩展为结构化证据记录，包括分类、预测特征频率等，能检测误分类，还通过约束语言模型减少无根据声明率，提升诊断可靠性。
AI 中文摘要
在安全关键型机械系统中，基于人工智能的诊断的可靠部署取决于验证，即预测能否在付诸行动之前对照物理现实进行检查。当前的智能故障诊断器在两个方面未达此标准。其标准输出是带有softmax置信度分数的类别标签，无法对照独立的物理知识进行检查；生成式语言模型在维护报告中的使用增加了第二个风险，即虚假内容进入决策所依据的报告。本文以轴承故障诊断为测试平台，从输出端解决这两个问题。提出的诊断证据网络（DENet）是一个与编码器无关的多任务框架，将输出扩展为结构化证据记录：分类、可与由轴承几何形状和轴速度确定的理论值进行比较的预测特征频率，以及可在原始波形上检查的瞬态脉冲的时间定位。在四个编码器和三个公共数据集上，这种证据不会带来统计学上显著的精度成本，在频谱估计在结构上不适用的1024点段上，频率误差约为6Hz。预测频率与理论频率之间的偏差构成了一个无标签、推理时的验证信号，它能检测误分类，AUROC值分别为0.970和0.871，并且在高置信度区域仍然具有判别力，而基于置信度的检测器在此区域是盲目的。最后，一个经过QLoRA调整的语言模型被约束为只翻译而不生成诊断内容，将无根据声明率从10 - 12%降至2%，并消除了虚构数量。
英文摘要
Integrating multi-level information, from physical models through data-driven diagnostics to natural language reasoning, into verifiable decision chains is a growing need in intelligent manufacturing. In bearing fault diagnosis, taken here as a representative testbed, the standard output is a class label and a confidence score derived from the classifier's own distribution, offering limited means of comparison against independent physical knowledge. Meanwhile, language models increasingly used for maintenance communication may introduce unsupported content. This work addresses both limitations from the output side. The proposed Diagnostic Evidence Network (DENet) is an encoder-agnostic multi-task framework that extends the output to a structured evidence record: the classification, a predicted characteristic frequency comparable against the theoretical value determined by bearing geometry and shaft speed, and a temporal localization of transient impulses inspectable on the raw waveform. Across four encoders and three public datasets, this evidence incurs no statistically significant accuracy cost, with a frequency error of about 6 Hz on 1,024-point segments. The deviation between predicted and theoretical frequency constitutes a label-free, inference-time validation signal. It detects misclassifications with AUROC of 0.970 and 0.871, and retains separation within the high-confidence subset. Finally, a QLoRA-adapted language model renders DENet's evidence into traceable maintenance reports without contributing diagnostic decisions, reducing unsupported-claim rates from 10-12% to 2% with no fabricated quantities observed.
