为传感器诊断管道搜索提供可审计的候选者命运记录框架
Candidate-Fate Accounting for Transparent Sensor Diagnostic Pipeline Search
- 记录每个候选管道的命运，包括无效、剪枝、缓存等状态
- 在三个轴承数据集上发现30至41个被传统报告忽略的候选者
- 适合关注自动化诊断可解释性与完整性的研究者
工业传感器诊断依赖预处理、表征和分类流水线，自动化流水线搜索可降低人工设计成本。然而，现有自动化机器/深度学习（AutoML/AutoDL）报告通常仅保留已拟合的试验、得分和优胜者，遗漏了无效、剪枝、跳过、缓存或未拟合的候选者。这限制了评审者对信号约束、预算使用及未评估合法替代方案的核查能力。为此，我们提出候选者命运会计（candidate-fate accounting），一种针对诊断搜索轨迹的候选级审计框架。它将每个观测到的候选者作为可审计证据：哈希合并重复观测，合法性检查标记无效候选者，分配合理性解释预算决策，封闭命运账本为每个候选者分配唯一终态命运。在三个轴承诊断数据集上的实验表明，该框架能检测无效候选者，并识别出30–41个被仅保留拟合试验的报告遗漏的候选者；封闭命运记录验证了候选者的完整会计，同时保持具有竞争力的诊断性能。代码已公开于 https://github.com/XXIE999/candidate-fate-accounting。
原文摘要 · Abstract (English)
Industrial sensor diagnostics relies on preprocessing, representation, and classification pipelines, making automated pipeline search useful for reducing manual design cost. However, existing automated machine/deep learning (AutoML/AutoDL) reports typically retain only fitted trials, scores, and winners, omitting generated candidates that are invalid, pruned, skipped, cached, or unfitted. This omission limits reviewers' ability to check signal constraints, budget use, and unevaluated legal alternatives. To address this, we propose candidate-fate accounting, a candidate-level audit framework for diagnostic search traces. It records each observed candidate as auditable evidence: hashes merge repeated observations, legality checks flag invalid candidates, allocation rationales explain budget decisions, and a closed fate ledger assigns one terminal fate to each candidate. Experiments on three bearing-diagnostic datasets show that the framework detects invalid candidates and identifies 30--41 candidates omitted by fitted-trial-only reports, with closed fate records verifying complete candidate accounting while maintaining competitive diagnostic performance. The code is available at https://github.com/XXIE999/candidate-fate-accounting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。