Unsupervised Anomaly Detection for Liquid-Fueled Rocket Propulsion Health Monitoring

Abstract

This article describes the results of applying four unsupervised anomaly detection algorithms to data from two rocket propulsion testbeds. The first testbed uses historical data from the Space Shuttle Main Engine. The second testbed uses data from an experimental rocket engine test stand located at NASA Stennis Space Center. The article describes nine anomalies detected by the four algorithms. The four algorithms use four different definitions of anomalousness. Orca uses a nearest-neighbor approach, defining a point to be an anomaly if its nearest neighbors in the data space are far away from it. The Inductive Monitoring System clusters the training data, and then uses the distance to the nearest cluster as its measure of anomalousness. GritBot learns rules from the training data, and then classifies points as anomalous if they violate these rules. One-class support vector machines map the data into a high-dimensional space in which most of the normal points are on one side of a hyperplane, and then classify points on the other side of the hyperplane as anomalous. Because of these different definitions of anomalousness, different algorithms detect different anomalies. We therefore conclude that it is useful to use multiple algorithms.

Analysis of Flight Data Using Clustering Techniques for Detecting Abnormal Operations

“…(quadratic equations to model time series). Later studies apply data mining techniques to detect data anomalies in aerospace systems [4][5][6][7][8][9]. Some adopts the supervised learning methods [7] such as the Inductive Monitoring System (IMS) software which summarizes the data distributions of typical system behaviors from a pre-sanitized training dataset, which is then compared with real-time operational data to detect abnormal behaviors.…”

Local anomaly detection in hybrid rocket combustion tests

“…A large number of algorithms for anomaly detection exist in the literature (Schwabacher et al 2009). In Sect.…”

Advances in production testing and operational support of new AESA radars

“…For example, data mining methods have successfully been applied in industrial process control [6], fault detection in power plants [7], water supply network analysis [8], faults detection in semiconductor manufacturing process [9], battery state-of-health monitoring [10], diagnosis of growing cracks in gearboxes or turbine engines [11], and even anomaly detection from temperature sensors on the STS 107 Space Shuttle Columbia after disaster [12]. Most frequently encountered methods for system modeling and fault diagnosis include Principal Component Analysis (PCA), Support Vector Machines (SVM), Nearest Neighbors, Clustering, Bayesian Networks, Decision Trees, Neural Networks, Hidden Markov Models (HMM) or combinations of them, sometimes using COTS softwares [13] [14].…”