Driving · 2026-10-20
Motor compound fault diagnosis using an attention-based cross-talk architecture
Wonjun Yi, Wonho Jung, Junho Kim, Rismaya Kumar Mishra, Yong-Hwa Park
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
The authors propose RNDR-TFCA, an attention-based cross-talk architecture for multi-output compound fault diagnosis in motors. It keeps task-specific feature extractors while selectively exchanging features across tasks using time-frequency attention (intra-task) and channel attention via an SE block (inter-task). On a rotor-bearing system, RNDR-TFCA achieves a macro F1 of 0.898, outperforming RNDR and other baselines.
Why it matters
Compound fault diagnosis requires identifying multiple fault components and their severities from the same vibration signal. The paper argues shared-trunk MTL can cause negative transfer because fault components involve different time-frequency regions, and that cross-talk with more selective information exchange can help. RNDR-TFCA targets both intra-task and inter-task feature enhancement within the cross-talk layer.
Method
- Preserve task-specific feature extractors with a residual cross-talk structure while transferring information through cross-talk layers.
- Apply time-frequency attention to each sub-task feature before concatenation to emphasize informative intra-task time-frequency regions.
- After nonlinear fusion, apply channel attention using a squeeze-and-excitation (SE) block to emphasize informative inter-task feature components.
Limitation
The paper does not state a specific limitation.
Abstract (from arXiv)
As physical AI increasingly relies on sensing to understand physical systems, reliable condition monitoring of industrial machinery has become more important. Motors are ubiquitous in industrial systems, and increasing system complexity raises the likelihood of simultaneous faults. Accordingly, compound fault diagnosis that identifies multiple fault components and their severities is increasingly required. Because different fault components jointly affect the same vibration signal, their severity classification can be formulated as related tasks, making multi-task learning (MTL) suitable for exploiting shared information. However, conventional shared-trunk architectures force tasks to share a common representation, potentially causing negative transfer because fault components are characterized by different time-frequency regions. To address this issue, this study proposes a Residual Neural Dimension Reductor with Time-Frequency Channel Attention (RNDR-TFCA), an attention-enhanced cross-talk architecture for multi-output compound fault diagnosis. RNDR-TFCA preserves task-specific feature extractors while selectively exchanging information across tasks. Time-frequency attention emphasizes informative intra-task regions, while channel attention enhances useful inter-task information after nonlinear feature fusion. Experiments on a rotor-bearing system with inner-race fault, outer-race fault, misalignment, and unbalance showed that RNDR-TFCA achieved a macro F1 score of 0.898, outperforming single-task, multi-class, shared-trunk, and cross-talk baselines. Ablation experiments confirmed the benefit of jointly applying both attention mechanisms. RNDR-TFCA required 713 K parameters and 170.42 MMACs, only slightly higher than RNDR. Channel-expanded baselines still underperformed RNDR-TFCA, indicating that the gain was not simply attributable to increased model capacity.
Related papers
- Cross-Domain Joint-Embedding Pretraining For Heterogeneous Industrial Time Series
- End-to-End Learning vs. Modular Architectures: Comparative Insights into Autonomous Driving Systems
- Detecting Silent Action-Interface Mismatch with Calibrated Relational World Models
- What Do Latent Predictive Vehicle Representations Retain? Measuring State, Geometry, and Local Response
- Do VLAs Know They Will Fail? Interpretable Success and Failure Patterns in Physical AI Systems
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-10-19 · Indexed by Pub-AI: 2026-10-20 UTC
Motor compound fault diagnosis using an attention-based cross-talk architecture
Preprint posted: 2026-10-19 · Original record ↗
- arxiv
- 2610.25893
Explicit source versions (1)
- v1 · 2026-10-19
- Preprint available
Source date: 2026-10-19 · First detected: 2026-10-25 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
As physical AI increasingly relies on sensing to understand physical systems, reliable condition monitoring of industrial machinery has become more important. Motors are ubiquitous in industrial systems, and increasing system complexity raises the likelihood of simultaneous faults. Accordingly, compound fault diagnosis that identifies multiple fault components and their severities is increasingly required. Because different fault components jointly affect the same vibration signal, their severity classification can be formulated as related tasks, making multi-task learning (MTL) suitable for exploiting shared information. However, conventional shared-trunk architectures force tasks to share a common representation, potentially causing negative transfer because fault components are characterized by different time-frequency regions. To address this issue, this study proposes a Residual Neural Dimension Reductor with Time-Frequency Channel Attention (RNDR-TFCA), an attention-enhanced cross-talk architecture for multi-output compound fault diagnosis. RNDR-TFCA preserves task-specific feature extractors while selectively exchanging information across tasks. Time-frequency attention emphasizes informative intra-task regions, while channel attention enhances useful inter-task information after nonlinear feature fusion. Experiments on a rotor-bearing system with inner-race fault, outer-race fault, misalignment, and unbalance showed that RNDR-TFCA achieved a macro F1 score of 0.898, outperforming single-task, multi-class, shared-trunk, and cross-talk baselines. Ablation experiments confirmed the benefit of jointly applying both attention mechanisms. RNDR-TFCA required 713 K parameters and 170.42 MMACs, only slightly higher than RNDR. Channel-expanded baselines still underperformed RNDR-TFCA, indicating that the gain was not simply attributable to increased model capacity.
