Sensors

Anomaly detection plays a crucial role in various domains, including but not limited to cybersecurity, space science, finance, and healthcare. However, the lack of standardized benchmark datasets hinders the comparative evaluation of anomaly detection algorithms. In this work, we address this gap by presenting a curated collection of preprocessed datasets for spacecraft anomalies sourced from multiple sources. These datasets cover a diverse range of anomalies and real-world scenarios for the spacecrafts.

The dataset consists of experimental data collected in an anechoic tank, with a specific setup involving single-source transmission and reception by a 6-element circular array with a radius of 0.046 meters. The transmitted signals include common wideband signals used in underwater positioning and communication, such as chirps, single-carrier QPSK, multi-tone signals, and OFDM signals. The transmitter and receiver are located at the same depth, and the receiving array rotates 360 degrees with 30-degree intervals.

Recent semiconductor devices have embraced structural modifications, including vertical stacking, to overcome the limitations of miniaturization. Particularly, memory devices have seen improvements through the transition to 3D stack structures. To address the challenges of etching high aspect ratio contact holes, the Bosch process, which alternates between deposition of a passivation layer on the pattern wall to prevent sidewall etching and etching steps, has been utilized.

New capabilities involving sensors, data collection, and data analysis have enabled innovations in how engineered systems are monitored and maintained. Whereas each new evolution of maintenance philosophies has relied upon the current technological state, this research examines potential future capabilities in the field of prognostics and health management (PHM). PHM algorithms for predicting the estimated time to failure for a system are based on sensor data, physical models, or a combination of both.