Prognostics has taken center stage in Condition Based Maintenance (CBM) where it is desired to estimate Remaining Useful Life (RUL) of a system so that remedial measures may be taken in advance to avoid catastrophic events or unwanted downtimes. Validation of such predictions is an important but difficult proposition and a lack of appropriate evaluation methods renders prognostics meaningless. Evaluation methods currently used in the research community are not standardized and in many cases do not sufficiently assess key performance aspects expected out of a prognostics algorithm. In this paper we introduce several new evaluation metrics tailored for prognostics and show that they can effectively evaluate various algorithms as compared to other conventional metrics. Four prognostic algorithms, Relevance Vector Machine (RVM), Gaussian Process Regression (GPR), Artificial Neural Network (ANN), and Polynomial Regression (PR), are compared. These algorithms vary in complexity and their ability to manage uncertainty around predicted estimates. Results show that the new metrics rank these algorithms in a different manner; depending on the requirements and constraints suitable metrics may be chosen. Beyond these results, this paper offers ideas about how metrics suitable to prognostics may be designed so that the evaluation procedure can be standardized.

Prognostics is an engineering discipline that focuses on estimation of the health state of a component and the prediction of its remaining useful life (RUL) before failure. Health state estimation is based on actual conditions and it is fundamental for the prediction of RUL under anticipated future usage. Failure of electronic devices is of great concern as future aircraft will see an increase of electronics to drive and control safety-critical equipment throughout the aircraft. Therefore, development of prognostics solutions for electronics is of key importance. This paper presents an accelerated aging system for gate-controlled power transistors. This system allows for the understanding of the effects of failure mechanisms, and the identification of leading indicators of failure which are essential in the development of physics-based degradation models and RUL prediction. In particular, this system isolates electrical overstress from thermal overstress. Also, this system allows for a precise control of internal temperatures, enabling the exploration of intrinsic failure mechanisms not related to the device packaging. By controlling the temperature within safe operation levels of the device, accelerated aging is induced by electrical overstress only, avoiding the generation of thermal cycles. The temperature is controlled by active thermal-electric units. Several electrical and thermal signals are measured in-situ and recorded for further analysis in the identification of leading indicators of failures. This system, therefore, provides a unique capability in the exploration of different failure mechanisms and the identification of precursors of failure that can be used to provide a health management solution for electronic devices.

It is an inescapable truth that no matter how well a system is designed it will degrade, and if degrading parts are not repaired or replaced the system will fail. Avoiding the expense and safety risks associated with system failures is certainly a top priority in many systems; however, there is also a strong motivation not to be overly cautious in the design and maintenance of systems, due to the expense of maintenance and the undesirable sacrifices in performance and cost effectiveness incurred when systems are over designed for safety. This paper describes an analytical process that starts with the derivation of an expression to evaluate the desirability of future control outcomes, and eventually produces control routines that use uncertain prognostic information to optimize derived risk metrics. A case study on the design of fault-adaptive control for a skid-steered robot will illustrate some of the fundamental challenges of prognostics-based control design.

Prognostics is an emerging concept in condition basedmaintenance(CBM)ofcriticalsystems.Alongwith developing the fundamentals of being able to confidently predict Remaining Useful Life (RUL), the technology calls for fielded applications as it inches towards maturation. This requires a stringent performance evaluation so that the significance of the concept can be fully exploited. Currently, prognostics concepts lack standard definitions and suffer from ambiguous and inconsistent interpretations. This lack of standards is in part due to the varied end-user requirements for different applications, time scales, available information, domain dynamics, etc. to name a few issues. Instead, the research community has used a variety of metrics based largely on convenience with respect to their respective requirements. Very little attention has been focused on establishing a common ground to compare different efforts. This paper surveys the metrics that are already used for prognostics in a variety of domains including medicine, nuclear, automotive, aerospace, and electronics. It also considers other domains that involve prediction-related tasks, such as weather and finance. Differences and similarities between these domains and health maintenancehave been analyzed to help understand what performance evaluation methods may or may not be borrowed. Further, these metrics have been categorized in several ways that may be useful in deciding upon a suitable subset for a specific application. Some important prognostic concepts have been defined using a notational framework that enables interpretation of different metrics coherently. Last, but not the least, a list of metrics has been suggested to assess critical aspects of RUL predictions before they are fielded in real applications.

Prognostics has received considerable attention recently as an emerging sub-discipline within SHM. Prognosis is here strictly defined as “predicting the time at which a component will no longer perform its intended function”. Loss of function is often times the time at which a component fails. The predicted time to that point becomes then the remaining useful life (RUL). For prognostics to be effective, it must be performed well before deviations from normal performance propagate to a critical effect. This enables a failure preclusion or prevention function to repair or replace the offending components, or if the components cannot be repaired, to retire the system (or vehicle) before the critical failure occurs. Therefore, prognosis has the promise to provide critical information to system operators that will enable safer operation and more cost-efficient use. To that end, Department of Defense (DoD), NASA, and industry have been investigating this technology for use in their vehicle health management solutions. Dedicated prognostic algorithms (in conjunction with failure detection and fault isolation algorithms) must be developed that are capable of operating in an autonomous and real-time vehicle health management system software architecture that is possibly distributed in nature. This envisioned prognostic and health management system will be realized in a vehicle-level reasoner that must have visibility and insight into the results of local diagnostic and prognostic technologies implemented at the LRU and subsystem levels. Accomplishing this effectively requires an integrated suite of prognostic technologies that compute failure effect propagation through diverse subsystems and that can capture interactions that occur in these subsystems. In this chapter a generic set of selected prognostic algorithm approaches is presented and an overview of the required vehicle-level reasoning architecture needed to integrate the prognostic information across systems is provided.

Prognostics and Health Management (PHM) principles have considerable promise to change the game of lifecycle cost of engineering systems at high safety levels by providing a reliable estimate of future system states. This estimate is a key for planning and decision making in an operational setting. While technology solutions have made considerable advances, the tie-in into the systems engineering process is lagging behind, which delays fielding of PHM-enabled systems. The derivation of specifications from high level requirements for algorithm performance to ensure quality predictions is not well developed. From an engineering perspective some key parameters driving the requirements for prognostics performance include: (1) maximum allowable Probability of Failure (PoF) of the prognostic system to bound the risk of losing an asset, (2) tolerable limits on proactive maintenance to minimize missed opportunity of asset usage, (3) lead time to specify the amount of advanced warning needed for actionable decisions, and (4) required confidence to specify when prognosis is sufficiently good to be used. This paper takes a systems engineering view towards the requirements specification process and presents a method for the flowdown process. A case study based on an electric Unmanned Aerial Vehicle (e-UAV) scenario demonstrates how top level requirements for performance, cost, and safety flow down to the health management level and specify quantitative requirements for prognostic algorithm performance.

**Abstract** Prognostics solutions for mission critical systems require a comprehensive methodology for proactively detecting and isolating failures, recommending and guiding condition-based maintenance actions, and estimating in real time the remaining useful life of critical components and associated subsystems. A major challenge has been to extend the benefits of prognostics to include computer servers and other electronic components. The key enabler for prognostics capabilities is monitoring time series signals relating to the health of executing components and subsystems. Time series signals are processed in real time using pattern recognition for proactive anomaly detection and for remaining useful life estimation. Examples will be presented of the use of pattern recognition techniques for early detection of a number of mechanisms that are known to cause failures in electronic systems, including: environmental issues; software aging; degraded or failed sensors; degradation of hardware components; degradation of mechanical, electronic, and optical interconnects. Prognostics pattern classification is helping to substantially increase component reliability margins and system availability goals while reducing costly sources of "no trouble found" events that have become a significant warranty-cost issue. **Bios** Aleksey Urmanov is a research scientist at Sun Microsystems. He earned his doctoral degree in Nuclear Engineering at the University of Tennessee in 2002. Dr. Urmanov's research activities are centered around his interest in pattern recognition, statistical learning theory and ill-posed problems in engineering. His most recent activities at Sun focus on developing health monitoring and prognostics methods for EP-enabled computer servers. He is a founder and an Editor of the Journal of Pattern Recognition Research. Anton Bougaev holds a M.S. and a Ph.D. degrees in Nuclear Engineering from Purdue University. Before joining Sun Microsystems Inc. in 2007, he was a lecturer in Nuclear Engineering Department and a member of Applied Intelligent Systems Laboratory (AISL), of Purdue University, West Lafayette, USA. Dr. Bougaev is a founder and the Editor-in-Chief of the Journal of Pattern Recognition Research. His current focus is in reliability physics with emphasis on complex system analysis and the physics of failures which are based on the data driven pattern recognition techniques.

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.

Aviation safety systems have undergone dramatic changes over the past fifty years. If you take a look at the early technology in this area, you'll see that there was a lot of work done in the area of so-called 'built-in-testing' (BIT) which essentially tests connectivity between different components. Technology has moved forward very far since that time. With the massive storage systems and advanced sensors and other communications systems, we are now able to capture and store vast quantities of health and control related data. This data is usually stored off-line for future analysis. In many cases, we also have an abundance of human-written text reports that relate to known safety issues. A key problem is to 'look' across all these data sources in order to find precursors to safety events. Although humans do look at many aspects of the data, it is difficult, if not impossible for them to integrate all the information available in a meaningful way. Other industries face this glut of data in their own way. Businesses have invested heavily in business intelligence products based on data mining that are designed to convert data into actionable information to maximize their profits or other metrics. The IVHM project is investing in data mining technologies to help sift through these massive data sets to uncover actionable information from a safety perspective. I've attached a presentation that Irv Statler and I gave at NASA HQ on this subject during an Aeronautics Technical Seminar. A video of the talk is also included. It's about 90 minutes long, so grab some popcorn. :)

The purpose of this project is to extend current ground-based Human Reliability Analysis (HRA) techniques to a long-duration, space-based tool to more effectively predict the risk associated with human actions on long-duration missions.  By doing so, the agency will be able to focus resources on the risk drivers, such as specific training, conditioning, procedures, exercising, etc. for these future missions.  NASA uses Probabilistic Risk Assessments (PRAs) to assess the probability of Loss of Crew (LOC) and Loss of Mission (LOM).  PRAs take into account multiple contributing factors and their interactions, such as how the crew, software, and hardware work together to achieve mission objectives.  HRA is used to assess the human contribution to risk in PRAs.  Current HRA techniques were developed for ground applications using Earth based human reliability data to estimate human error probability.  These ground-based HRA techniques have been shown to be a reasonable tool for short-duration space missions, such as Space Shuttle and lunar fly-bys.  However, longer-duration beyond Earth orbit missions, such as asteroid and Mars missions, will require crews to be in space for 400 to 900 days with periods of extended autonomy and self-sufficiency.  Current indications show higher risk due to fatigue, physiological effects due to extended low gravity environments, and others, which may impact HRA predictions by affecting the crew’s cognitive abilities, as well as their physiology, and yield a higher probability for LOC and LOM (e.g. early return).  PRAs will need to account for these effects in order to provide management, designers, and the crew our best estimate of risk.

With the funding of this IR&D project over the next three years, Safety & Mission Assurance (S&MA) will collaborate with Human Health & Performance (HH&P) to establish what is currently used to assess human reliability for human space programs, identify human performance factors that may be sensitive to long duration space flight, collect available historical data, and update current tools to account for performance shaping factors believed to be important to such missions.  JSC’s Human System Integration (HSI) initiative is a work in progress to better understand how the crew, software, and hardware work together and ensure that HSI is accounted for in future space mission designs.