Anomaly Detection for Electro-Hydrostatic Actuators using LSTM Autoencoder
Researchers have developed a new anomaly detection framework for electro-hydrostatic actuators (EHAs) using an LSTM autoencoder. This method is designed to address the challenges of processing large volumes of high-frequency sensor data in aerospace and industrial systems. The LSTM autoencoder demonstrated high accuracy, precision, and recall in detecting sensor anomalies across various fault-injection scenarios, significantly outperforming traditional methods. AI
IMPACT This research could enhance the safety and reliability of critical aerospace and industrial systems by enabling more accurate and efficient anomaly detection.