发表机构
Institute for Data Science in Mechanical Engineering (DSME); RWTH Aachen University（机械工程数据科学研究所（DSME）; 亚琛工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有时间序列概念提取方法的局限，提出CENDRe方法，可自动确定概念数量，同时在时域和频域定位概念，在合成基准和真实轴承故障数据上均表现优异。
AI 中文摘要
卷积神经网络（CNN）广泛用于时间序列分类，但其在关键领域的部署需要理解驱动预测的时间和频谱模式。概念提取（CE）方法通过分析模型潜空间内的表示来识别此类模式，但现有时间序列CE方法存在三个局限：仅在时域操作、忽略频率特征，需预先定义概念数量，且生成的定位与模型使用的区域不匹配。我们提出针对CNN的概念提取方法CENDRe以解决这些局限。它首先通过两个阶段对每时间步的潜表示进行聚类来发现概念，其中基于轮廓系数的聚合自动选择概念数量；接着通过存在得分的梯度定位每个概念，该得分将潜表示与其原型对比，生成聚焦于驱动概念区域的掩码。这些梯度通过输入的可微可逆映射（如傅里叶变换）传播，得到相同概念在频域的定位。最后，每个概念获得量化其对每个类贡献的相关性得分。在合成基准上，CENDRe的表示正确性与最先进的CE方法相当，且重要性正确性显著更高；在真实轴承故障数据上，CENDRe提取了驱动模型预测的频带，这些频带位于故障诊断常检查的区域，提供了时域CE方法无法提供的模型评估证据。
英文摘要
Convolutional neural networks (CNNs) are widely used for time-series classification, but their deployment in critical domains requires understanding the temporal and spectral patterns that drive their predictions. Concept extraction (CE) methods identify such patterns by analyzing representations within the models' latent space. However, existing time-series CE methods have three limitations: they operate only in the time domain and overlook frequency features, predefine the number of concepts, and produce localizations misaligned with the regions the model uses. We address these limitations by proposing CENDRe, a concept extraction method for CNNs. It first discovers concepts by clustering per-timestep latent representations in two stages, where silhouette-guided aggregation selects the number of concepts automatically. Then, it localizes each concept through gradients of a presence score that contrasts the latent representations with their prototypes, producing masks that concentrate on the regions driving the concept. These gradients, propagated through a differentiable invertible mapping of the input such as a Fourier transform, yield localizations for the same concepts in the frequency domain. Finally, each concept receives a relevance score that quantifies its contribution to each class. On synthetic benchmarks, CENDRe achieves representation correctness comparable to state-of-the-art CE methods and significantly higher importance correctness. On real bearing-fault data, CENDRe extracts the frequency bands driving the model's predictions, located in regions commonly inspected for fault diagnosis, producing evidence to assess the model that time-domain CE methods cannot.
