Ryan Mackey

General Purpose Data-Driven System Monitoring for Space Operations

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 (IMS) is a data-driven system health monitoring software tool that has been successfully applied to several aerospace applications. IMS 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 IMS space operations applications include International Space Station flight control, satellite 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 IMS data-driven technique as related to several Integrated Systems Health Management (ISHM) elements. Thematically, the projects listed will be used as case studies. The maturation of IMS 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 IMS can be used to complement a suite of other ISHM tools, providing initial fault detection support for diagnosis and recovery.

BEAM: technology for autonomous self-analysis

BEAM (Beacon-based Exception Analysis for Multimissions) is an end-to-end method of data analysis intended for real-time fault detection and characterization. It provides a generic system analysis capability for potential application to deep space probes and other highly automated systems. This paper describes in brief the architecture, application, and operating theory of BEAM. BEAM provides a generalized formalism for diagnostics and prognostics in virtually any instrumented system. Consideration is given to all standard forms of data, both time-varying (sensor or extracted feature) quantities and discrete measurements, embedded physical and symbolic models, and communication with other autonomy-enabling components such as planners and schedulers. This approach can be adapted to on-board or ground-based implementations with no change to the basic operating theory. The approach is illustrated with an overview of application types, past validations, and ongoing efforts.

Anomaly detector fusion processing for advanced military aircraft

Automated Prognostics and Health Management (PHM) is a requirement for advanced military aircraft. PHM is the key to achieving true condition-based maintenance. PHM processing strategies include modules for the processing of known nominal and fault conditions. However in real operations there will also occur faults and other off-nominal operations that were never anticipated nor ever encountered before. We call these events anomalies. Missing the presence of an anomaly could potentially be catastrophic with the loss of the pilot and aircraft. Several different anomaly detectors (ADs) have been developed for advanced military aircraft to solve this problem. Fusion of these ADs can significantly reduce false alarms while at the same time substantially improving detection performance. Fusion is a way of approaching the goal of perfect detection with zero false alarms. We have developed a neural net approach for performing AD fusion. Presented is a description of that technique and the application to military aircraft subsystem data.

Generalized cross-signal anomaly detection on aircraft hydraulic system

This paper outlines the mathematical foundation for a general method of anomaly detection from time-correlated sensor data. This method is a component of BEAM, but as an individual algorithm is capable of fault detection and partial classification. The method is applicable to a broad class of problems and is designed to respond to any departure from normal operation, including faults or events that lie outside the training envelope. We will also consider training of the detector and interface to a larger diagnostic system. Lastly we examine a brief illustration taken from aircraft testing that demonstrates the power and versatility of this method.

Guiding Technology Deployment Decisions using a Quantitative Requirements Analysis Technique

Successful and convincing operation of a prototype, deployed in a real setting, is a key step in advancement of many a new technology from research laboratory to real-world use. Often, however, such a deployment must be interjected into a pre-existing context of ongoing activities, established designs and standard practices. That context can pose a number of obstacles, which if unaddressed can preclude success. Careful selection of what demonstration opportunities to pursue, and determination of how best to pursue them, are therefore crucial. A study was conducted to select and plan for deployment of prototypes of integrated system health management (ISHM) software on NASA spacecraft. The study itself utilized our seasoned technology maturation assessment process, based on a quantitative requirements analysis technique. However, this process is typically applied to scrutinize a single technology application at once. In this case there were a number of candidate deployment opportunities. Since it would have been tedious and time-consuming to consider each of them one-by-one, we adapted our assessment process to accommodate their simultaneous consideration. We relate our experience in doing this - the shortcuts we took, the similarities we exploited, and the workarounds we adopted to complete this study in a timely yet effective manner.

FRACSAT: Automated design synthesis for future space architectures

This paper describes the algorithmic basis and development of FRACSAT (FRACtionated Spacecraft Architecture Toolkit), a new approach to conceptual design, cost-benefit analysis, and detailed trade studies for space systems. It provides an automated capability for exploration of candidate spacecraft architectures, leading users to near-optimal solutions with respect to user-defined requirements, risks, and program uncertainties. FRACSAT utilizes a sophisticated planning algorithm (PlanVisioner) to perform a quasi-exhaustive search for candidate architectures, constructing candidates from an extensible model-based representation of space system components and functions. These candidates are then evaluated with emphasis on the business case, computing the expected design utility and system costs as well as risk, presenting the user with a greatly reduced selection of candidates. The user may further refine the search according to cost or benefit uncertainty, adaptability, or other performance metrics as needed.

Model-based approach to rover health assessment for increased productivity

This paper presents an analysis tool useful for assessing diagnostic performance of a model-based fault management (FM) system. The FM system called MONSID is designed to provide off-nominal state detection and identification capabilities that are key components to assessing spacecraft state awareness. The analysis tool can be applied to MONSID models to predict MONSIDs diagnostic performance for various sensor suite configurations and model topologies. The underlying algorithms of the diagnostic resolution analysis tool are discussed. The tool is applied to a MONSID model of a robot power subsystem to illustrate how MONSIDs ability to distinguish among potentially faulty components is affected by the number of sensors and their placement (injection points) in the model. The tool can be utilized for FM design early in the program by supporting sensor suite selection. In the operations phase, it can be used to reduce the amount of onboard processing required by the MONSID engine in the fault identification process.

Measures of product design adaptability for changing requirements

Abstract Adaptability can have many different definitions: reliability, robustness, survivability, and changeability (adaptability to requirements change). In this research, we focused entirely on the last type. We discuss two alternative approaches to requirements change adaptability. One is the valuation approach that is based on utility and cost of design changes in response to modified requirements. The valuation approach is theoretically sound because it is based on utility and decision theory, but it may be difficult to use in the real world. The second approach is based on examining product architecture characteristics that facilitate changes that include modularity, hierarchy, interfaces, performance sensitivity, and design margins. This approach is heuristic in nature but more practical to use. If calibrated, it could serve as a surrogate for real adaptability. These measures were incorporated in a software tool for exploring alternative configurations of fractionated space satellite systems.

AUTONOMOUS CONTROL OF UNINHABITED AIR VEHICLES

The research covered in this paper for the autonomous control of Uninhabited Air Vehicles (UAVs) is to develop and demonstrate an innovative systems approach to total air vehicle management. This enables and is the first step in the development of robust and capable UAVs. This approach is on the cutting edge of vehicle management research and development. It combines traditional approaches to systems design with advanced artificial intelligence systems for monitoring and plan management. These are based on technologies developed for autonomous space exploration. This effort combines research conducted at the Lockheed Martin Aeronautics Company, the Jet Propulsion Laboratory, and the General Electric Corporate Research and Development Center.