In the field of fault transfer diagnosis, many approaches only focus on the distribution alignment and knowledge transfer between the source domain and target domain. However, most of these approaches ignore the precondition of whether this transfer task is transferable. Current mainstream transferability discrimination methods heavily depend on expert knowledge and are extremely vulnerable to the noise interference and variations in feature scale. This limits their applicability due to the intelligent requirements and complex industrial environment. To address the challenges mentioned previously, this paper introduces a novel cross-domain similarity measure called maximum subspace transferability discriminant analysis (MSTDA) with zero-label prior knowledge. MSTDA is comprised of a maximum subspace representation and a similarity measurement criterion. During the phase of maximum subspace representation, a new kernel-induced Hilbert space is designed to map the low-dimensional original samples into the high-dimensional space to maximize the separability of different faults and then solve the separable intrinsic fault features. Following that, a novel similarity measurement criterion that is resistant to variations in feature scale is developed. This criterion is based on the orthogonal bases of intrinsic feature subspaces. The mini-batch sampling strategy is used to ensure the timeliness of MSTDA. Finally, the experimental results on three cases, particularly in the actual wind turbine dataset, confirm that the proposed MSTDA outperforms other well-known similarity measure methods in terms of transferability evaluation. The related code can be downloaded from https://qinyi-team.github.io/2024/09/Maximum-subspace-transferability-discriminant-analysis.

中文翻译：

---

最大子空间可传递性判别分析：一种新的风电机组故障传递诊断跨域相似性度量


在故障转移诊断领域，许多方法只关注源域和目标域之间的分布对齐和知识转移。然而，这些方法大多数都忽略了该转移任务是否可转移的前提。目前主流的可转移性判别方法严重依赖于专家知识，并且极易受到噪声干扰和特征尺度变化的影响。由于智能化要求和复杂的工业环境，这限制了它们的适用性。为了解决前面提到的挑战，本文引入了一种新颖的跨域相似性度量，称为具有零标签先验知识的最大子空间可转移性判别分析（MSTDA）。 MSTDA 由最大子空间表示和相似性测量标准组成。在最大子空间表示阶段，设计了新的核诱导希尔伯特空间，将低维原始样本映射到高维空间，最大化不同故障的可分性，进而求解可分离的内在故障特征。随后，开发了一种新颖的相似性测量标准，可以抵抗特征尺度的变化。该标准基于内在特征子空间的正交基。采用小批量抽样策略保证MSTDA的时效性。最后，三种情况下的实验结果，特别是在实际风力涡轮机数据集中，证实了所提出的 MSTDA 在可转移性评估方面优于其他众所周知的相似性度量方法。相关代码可以从https://qinyi-team.github.io/2024/09/Maximum-subspace-transferability-discriminant-analysis下载。