Tag
This paper evaluates SelF-Rocket for multi-class fault diagnosis in electrical and mechanical systems, introducing a multivariate extension and comparing it with ROCKET-based methods on benchmark datasets.
This paper introduces an optimized fuzzy logic approach combined with the IEEE Key Gas Method for diagnosing power transformer faults using dissolved gas analysis, achieving up to 98.6% accuracy in experimental validation.
This paper introduces Spectral Aliasing Pretext (SAP), a self-supervised learning method for fault diagnosis in rotating machinery. By deliberately undersampling vibration signals and training a Transformer to reconstruct the original spectrum, SAP learns discriminative frequency-domain representations that achieve strong classification performance with limited labeled data.
DBA-Bench is a production-fidelity benchmark for evaluating LLM-based database agents, featuring 106 scenarios across seven domains with outcome-first evaluation and controlled reproducibility. The best automated baseline achieves only 17.9% Safe Pass compared to 93.4% for human DBAs.
The paper presents BearingNAS, a hardware-aware neural architecture search framework that designs intelligent fault diagnosis systems for bearings, targeting microcontrollers and sensor processing units with extremely limited memory (4-8 KiB RAM, 16-32 KiB Flash) while running entirely on a laptop CPU and achieving 99.50% diagnostic accuracy.
This paper demonstrates that naive train/test splitting on sliding-window sequences can severely inflate or deflate performance metrics in multi-task learning for predictive maintenance, and proposes a leakage-robust evaluation protocol.
Presents Onnes, a physics-grounded multi-agent LLM simulator for cryogenic fault diagnosis in quantum computing infrastructure. With curated few-shot demonstrations and self-consistency voting, a zero-shot LLM agent panel achieves 0.990 fault-classification accuracy, matching a supervised classifier without parameter updates.
This paper proposes a reinforcement learning-driven adaptive sim-to-real alignment method for vibration-based bearing health monitoring, addressing data scarcity and heterogeneous fault-type gaps via proximal policy optimization.
Proposes a lightweight neural architecture search performed directly on the deployment device for near-sensor computing, validated on sEMG sign language and fault diagnosis datasets, achieving improved accuracy and reduced RAM occupancy.
Proposes RGNet, a neural network architecture based on renormalization group theory for hierarchical coarse-graining of feature space to address class imbalance and noise in fault diagnosis. Experimental results on the AI4I dataset show RGNet provides interpretable and competitive performance.
The paper proposes a reliable fault diagnosis method using a belief rule base with robustness analysis, addressing sensor reliability issues, and validates the approach on WD615 diesel engine and bearing datasets.