Tag
The paper proposes an adversarial inverse reinforcement learning framework for machinery fault detection that learns a health reward from normal operational data without requiring fault labels, achieving consistent detection across multiple benchmarks.
This paper presents PASE, a neuro-symbolic framework that uses LLMs to generate structured recovery plans for cloud systems and verifies them via a neural-symbolic world model, achieving over 40% reduction in recovery time.
This paper introduces the Kalman Prototypical Network (KPN), a few-shot learning framework for fault detection in combined-cycle gas turbines. KPN models class prototypes as latent stochastic states to reduce variance and outperforms conventional methods on simulated leak detection tasks.
A benchmark study comparing traditional machine learning methods (Random Forest, XGBoost, SVM, Logistic Regression) against lightweight transformer variants (DistilBERT, TinyBERT, MobileBERT) for on-device fault detection across three public datasets. Traditional ML offers competitive accuracy at far smaller resource footprints, while TinyBERT-4L is the most deployment-friendly transformer.
This paper presents an offline anomaly detection framework using an LSTM autoencoder for Electro-Hydrostatic Actuators (EHAs), achieving an average accuracy of 99.0% and high recall on sensor data, outperforming classical methods.
TPA-AD is a two-stage pseudo anomaly-guided method for bearing time-series anomaly detection that generates pseudo-anomalous windows near normal boundaries using reconstruction models and contrastive learning, then scores anomalies with KNN—without requiring real anomaly samples during training. It is evaluated on bearing fault and degradation datasets, including high-speed train axle-box bearing data.
This paper introduces CAFD, a learning-based approach for DNN fault detection that integrates model-based, distance-based, and a novel concept-based feature called Concept Failure Ratio (CFR) derived from Vision-Language Models. CAFD consistently outperforms state-of-the-art baselines in fault detection rate across multiple datasets and budgets.