The Optical Plume Anomaly Detection (OPAD) system is under development to predict engine anomalies and engine parameters of the Space Shuttle's Main Engine (SSME). The anomaly detection is based on abnormal metal concentrations in the optical spectrum of the rocket plume. Such abnormalities could be indicative of engine corrosion or other malfunctions. Here, we focus on the second task of the OPAD system, namely the prediction of engine parameters such as rated power level (RPL) and mixture ratio (MR). Because of the high dimensionality of the spectrum, we developed a linear algorithm to resolve the optical spectrum of the exhaust plume into a number of separate components, each with a different physical interpretation. These components are used to predict the metal concentrations and engine parameters for online support of ground-level testing of the SSME. Currently, these predictions are labor intensive and cannot be done online. We predict RPL using neural networks and give preliminary results.

Over the last several years researchers at NASA Glenn and Ames Research Centers have developed a real-time fault detection and isolation system for propulsion subsystems of future space vehicles. The Propulsion IVHM Technology Experiment (PITEX), as it is called follows the model-based diagnostic methodology and employs Livingstone, developed at NASA Ames, as its reasoning engine. The system has been tested on flight-like hardware through a series of nominal and fault scenarios. These scenarios have been developed using a highly detailed simulation of the X-34 flight demonstrator main propulsion system and include realistic failures involving valves, regulators, microswitches, and sensors. This paper focuses on one of the recent research and development efforts under PITEX – to provide more complete transient region coverage. It describes the development of the transient monitors, the corresponding modeling methodology, and the interface software responsible for coordinating the flow of information between the quantitative monitors and the qualitative, discrete representation in Livingstone.

Several different unsupervised anomaly detection algorithms have been applied to Space Shuttle Main Engine (SSME) data to serve the purpose of developing a comprehensive suite of Integrated Systems Health Management (ISHM) tools. As the theoretical bases for these methods vary considerably, it is reasonable to conjecture that the resulting anomalies detected by them may differ quite significantly as well. As such, it would be useful to apply a common metric with which to compare the results. However, for such a quantitative analysis to be statistically significant, a sufficient number of examples of both nominally categorized and anomalous data must be available. Due to the lack of sufficient examples of anomalous data, use of any statistics that rely upon a statistically significant sample of anomalous data is infeasible. Therefore, the main focus of this paper will be to compare actual examples of anomalies detected by the algorithms via the sensors in which they appear, as well the times at which they appear. We find that there is enough overlap in detection of the anomalies among all of the different algorithms tested in order for them to corroborate the severity of these anomalies. In certain cases, the severity of these anomalies is supported by their categorization as failures by experts, with realistic physical explanations. For those anomalies that can not be corroborated by at least one other method, this overlap says less about the severity of the anomaly, and more about their technical nuances, which will also be discussed.

Modern space propulsion and exploration system designs are becoming increasingly sophisticated and complex. Determining the health state of these systems using traditional methods is becoming more difficult as the number of sensors and component interactions grows. Data-driven monitoring techniques have been developed to address these issues by analyzing system operations data to automatically characterize normal system behavior. The Inductive Monitoring System is a data-driven system health monitoring software tool that has been successfully applied to several aerospace applications. Inductive Monitoring System uses a data mining technique called clustering to analyze archived system data and characterize normal interactions between parameters. This characterization, or model, of nominal operation is stored in a knowledge base that can be used for real-time system monitoring or for analysis of archived events. Ongoing and developing Inductive Monitoring System space operations applications include International Space Station flight control, spacecraft vehicle system health management, launch vehicle ground operations, and fleet supportability. As a common thread of discussion this paper will employ the evolution of the Inductive Monitoring System data-driven technique as related to several Integrated Systems Health Management elements. Thematically, the projects listed will be used as case studies. The maturation of Inductive Monitoring System via projects where it has been deployed or is currently being integrated to aid in fault detection will be described. The paper will also explain how Inductive Monitoring System can be used to complement a suite of other Integrated System Health Management tools, providing initial fault detection support for diagnosis and recovery.

NASA researchers recently demonstrated successful real-time fault detection and isolation of a virtual reusable launch vehicle main propulsion system. Using a detailed simulation of a vehicle propulsion system to produce synthesized sensor readings, the NASA team demonstrated that advanced diagnostic algorithms, running on flight-like computers, can, in real time, successfully diagnose the presence and cause of faults. This demonstration was conducted as part of the NASA Propulsion IVHM Technology Experiment, or PITEX.

Title: 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.

The loading of spacecraft propellants is a complex, risky operation. Therefore, diagnostic solutions are neces- sary to quickly identify when a fault occurs, so that recov- ery actions can be taken or an abort procedure can be initi- ated. Model-based diagnosis solutions, established using an in-depth analysis and understanding of the underlying physi- cal processes, offer the advanced capability to quickly detect and isolate faults, identify their severity, and predict their ef- fects on system performance. We develop a physics-based model of a cryogenic propellant loading system, which de- scribes the complex dynamics of liquid hydrogen filling from a storage tank to an external vehicle tank, as well as the in- fluence of different faults on this process. The model takes into account the main physical processes such as highly non- equilibrium condensation and evaporation of the hydrogen vapor, pressurization, and also the dynamics of liquid hydro- gen and vapor flows inside the system in the presence of he- lium gas. Since the model incorporates multiple faults in the system, it provides a suitable framework for model-based di- agnostics and prognostics algorithms. Using this model, we analyze the effects of faults on the system, derive symbolic fault signatures for the purposes of fault isolation, and per- form fault identification using a particle filter approach. We demonstrate the detection, isolation, and identification of a number of faults using simulation-based experiments.

Electrical power systems play a critical role in spacecraft and aircraft, and they exhibit a rich variety of failure modes. This paper discusses electrical power system fault diagnosis by means of probabilistic techniques. Specically, we discuss our development of a diagnostic capability for an electrical power system testbed, ADAPT, located at NASA Ames. We emphasize how we have tackled two challenges, regarding modelling and real-time performance, often encountered when developing diagnostic applications. We carefully discuss our Bayesian network modeling approach for electrical power systems. To achieve real-time performance, we build on recent theoretically well-founded developments that compile a Bayesian network into an arithmetic circuit. Arithmetic circuits have low footprint and are optimized for embedded, real-time systems such as spacecraft and aircraft. We discuss our probabilistic diagnostic models developed for ADAPT along with successful experimental results.

Prior to the launch of STS-119 NASA had completed a study of an issue in the flow control valve (FCV) in the Main Propulsion System of the Space Shuttle using an adaptive learning method known as Virtual Sensors. Virtual Sensors are a class of algorithms that estimate the value of a time series given other potentially nonlinearly correlated sensor readings. In the case presented here, the Virtual Sensors algorithm is based on an ensemble learning approach and takes sensor readings and control signals as input to estimate the pressure in a subsystem of the Main Propulsion System. Our results indicate that this method can detect faults in the FCV at the time when they occur. We use the standard deviation of the predictions of the ensemble as a measure of uncertainty in the estimate. This uncertainty estimate was crucial to understanding the nature and magnitude of transient characteristics during startup of the engine. This paper overviews the Virtual Sensors algorithm and discusses results on a comprehensive set of Shuttle missions and also discusses the architecture necessary for deploying such algorithms in a real-time, closed-loop system or a human-in-the-loop monitoring system. These results were presented at a Flight Readiness Review of the Space Shuttle in early 2009.

This paper provides a review of three different advanced machine learning algorithms for anomaly detection in continuous data streams from a ground-test firing of a subscale Solid Rocket Motor (SRM). This study compares Orca, one-class support vector machines, and the Inductive Monitoring System (IMS) for anomaly detection on the data streams. We measure the performance of the algorithm with respect to the detection horizon for situations where fault information is available. These algorithms have been also studied by the present authors (and other co-authors) as applied to liquid propulsion systems. The trade space will be explored between these algorithms for both types of propulsion systems.