# A Comparative Study of RQA-Guided Attention Mechanisms with LSTM Autoencoder for Bearing Anomaly Detection

## TL;DR

This paper introduces a new attention mechanism for detecting anomalies in rotating machinery by incorporating nonlinear dynamics, improving detection accuracy and robustness in noisy environments.

## Contribution

The novel contribution is integrating recurrence quantification analysis into LSTM autoencoder attention mechanisms for unsupervised anomaly detection.

## Key findings

- RQAA outperforms conventional models with up to 99.85% F1-score and 99.00% AUC on bearing vibration datasets.
- The framework shows superior robustness in low signal-to-noise ratio scenarios.
- Explicit dynamical guidance improves anomaly separability and reduces false alarms in early-stage fault detection.

## Abstract

Accurate anomaly detection in rotating machinery under noisy conditions remains challenging in Prognostics and Health Management (PHM). Existing deep learning autoencoders and attention mechanisms rely primarily on data-driven similarity measures and fail to explicitly incorporate nonlinear dynamical characteristics of degradation. In this study, we propose a Recurrence Quantification Analysis-Aware Attention (RQAA) framework that systematically injects chaos-theoretic descriptors into the attention mechanism of LSTM-based autoencoders for unsupervised anomaly detection. Specifically, RQA metrics including recurrence rate, determinism, laminarity, entropy, and trapping time are computed at the window level and embedded into the query-key-value attention scoring to guide the model toward dynamically informative temporal patterns. Three attention variants are developed to investigate different fusion strategies between learned representations and RQA-driven structural cues. The proposed framework is evaluated on three widely used bearing vibration datasets, which are IMS, CWRU, and HUST. Experimental results demonstrate that RQAA consistently outperforms conventional LSTM autoencoders and classical attention-based models, achieving up to 99.85% F1-score and 99.00% AUC while exhibiting superior robustness in low signal-to-noise scenarios. Further analysis reveals that explicit dynamical guidance enhances anomaly separability and reduces false alarms, particularly in early-stage fault detection. These findings indicate that integrating nonlinear dynamical information directly into attention scoring offers a principled and effective pathway for advancing unsupervised anomaly detection in rotating machinery and safety-critical industrial systems.