One of the most prominent technical challenges to effective deployment of health management systems is the vast difference in user objectives with respect to engineering development. In this paper, a detailed survey on the objectives of different users of health management systems is presented. These user objectives are then mapped to the metrics typically encountered in the development and testing of two main systems health management functions: diagnosis and prognosis. Using this mapping, the gaps between user goals and the metrics associated with diagnostics and prognostics are identified and presented with a collection of lessons learned from previous studies that include both industrial and military aerospace applications.

The use of Echo State Networks (ESNs) for the prediction of the Remaining Useful Life (RUL) of industrial components, i.e. the time left before the equipment will stop fulfilling its functions, is attractive because of their capability of handling the system dynamic behavior, the measurement noise, and the stochasticity of the degradation process. In particular, in this paper we originally resort to an ensemble of ESNs, for enhancing the performances of individual ESNs and providing also an estimation of the uncertainty affecting the RUL prediction. The main methodological novelties in our use of ESNs for RUL prediction are: i) the use of the individual ESN memory capacity within the dynamic procedure for aggregating of the ESNs outcomes; ii) the use of an additional ESN for estimating the RUL uncertainty, within the Mean Variance Estimation (MVE) approach. With these novelties, the developed approach outperforms a static ensemble and a standard MVE approach for uncertainty estimation in tests performed on a synthetic and two industrial datasets.

Among the various data-driven approaches used for RUL prediction, Recurrent Neural Networks (RNNs) have certain prima facie advantages over other approaches because the connections between internal nodes form directed cycles, thus creating internal states which enables the network to encapsulate dynamic temporal behavior and also to properly handle the noise affecting the collected signals. However, the application of traditional RNNs is limited by the difficulty of optimizing their numerous internal parameters and the significant computational effort associated with the training process. In this work, we explore the use of the Echo State Network (ESN), a relatively new type of Recurrent Neural Network (RNN). One of the main advantages of ESN is the training procedure, which is based on a simple linear regression. Unlike traditional RNNs, ESNs can be trained with fairly little computational effort, while still providing the generalization capability characteristic of RNNs. In this paper, we use Differential Evolution (DE) for the optimization of the ESN architecture for RUL prediction of a turbofan engine working under variable operating conditions. A procedure for pre-processing of the monitored signals and for identification of the onset of acceleration of degradation (i.e., the so-called elbow point in the degradation trend) will be shown. The datasets used to validate the approach have been taken from the NASA Ames Prognostics CoE Data Repository. These datasets were generated using a turbofan engine simulator, based on a detailed physical model that allows input variations of health-related parameters under variable operating conditions and records values from some specific sensor measurements. The results obtained on these data confirm the ESN’s capability to provide accurate RUL predictions.

As new operational paradigms and additional aircraft are being introduced into the National Airspace System (NAS), maintaining safety in such a rapidly growing environment becomes more challenging. It is therefore desirable to have an automated framework to provide an overview of the current safety of the airspace at different levels of granularity, as well an understanding of how the state of the safety will evolve into the future given the anticipated flight plans, weather forecast, predicted health of assets in the airspace, and so on. Towards this end, as part of our earlier work, we formulated the Real-Time Safety Monitoring (RTSM) framework for monitoring and predicting the state of safety and to predict unsafe events. In our previous work, the RTSM framework was demonstrated in simulation on three different constructed scenarios. In this paper, we further develop the framework and demonstrate it on real flight data from multiple data sources. Specifically, the flight data is obtained through the Shadow Mode Assessment using Realistic Technologies for the National Airspace System (SMART-NAS) Testbed that serves as a central point of collection, integration, and access of information from these different data sources. By testing and evaluating using real-world scenarios, we may accelerate the acceptance of the RTSM framework towards deployment. In this paper we demonstrate the framework's capability to not only estimate the state of safety in the NAS, but predict the time and location of unsafe events such as a loss of separation between two aircraft, or an aircraft encountering convective weather. The experimental results highlight the capability of the approach, and the kind of information that can be provided to operators to improve their situational awareness in the context of safety.

To gain the situational awareness necessary for informed decision making regarding avoidance of airspace hazards, each operator must consolidate operations-relevant information from disparate sources and apply extensive domain knowledge to correctly interpret not just the current state of the NAS but forecast its (combined) evolution over the duration of the operation. This time- and workload-intensive process is periodically repeated throughout the operation so that changes can be managed in a timely manner.The imprecision, inaccuracies, inconsistency, and incompleteness of the incoming data further challenges the process. To facilitate informed decision making, this paper presents a model-based framework for the textitautomated real-time monitoring and prediction of possible effects of airspace hazards on the safety of the National Airspace System (NAS). First, hazards to flight are identified and transformed into sms, that is, quantities of interest that could be evaluated based on available data and are predictive of an unsafe event. The sms and associated thresholds that specify when an event transitions from emphsafe to emphunsafe are combined with models of airspace operations and aircraft dynamics. The framework can include any hazard to flight that can be modeled quantitatively. Models can be detailed and complex, or they can be considerably simplifed, as appropriate to the application. Real-time NAS safety monitoring and prediction begins with an estimate of the state of the NAS using the dynamic models. Given the state estimate and a probability distribution of future inputs to the NAS, we can then predict the evolution of the NAS - the future state - and the occurrence of hazards and unsafe events. The entire probability distribution of airspace sms is computed, not just point estimates, without significant assumptions regarding the distribution type andor parameters. We demonstrate our overall approach through a simulated scenario in which we predict the occurrence of some unsafe events and show how these predictions evolve in time as flight operations progress. Predictions accounting for common sources of uncertainty are included and it is shown how the predictions improve in time, become more confident, and change dynamically as new information is made available to the prediction algorithm.

A battery pack consisting of standard cylindrical 18650 lithium-ion cells has been chosen for small satellite missions based on previous flight heritage and compliance with NASA battery safety requirements. However, for batteries that transit through the International Space Station (ISS), additional certification tests are required for individual cells as well as the battery packs. In this manuscript, we discuss the development of generalized testbeds for testing and certifying different types of batteries critical to small satellite missions. Test procedures developed and executed for this certification effort include: a detailed physical inspection before and after experiments; electrical cycling characterization at the cell and pack levels; battery-pack overcharge, over-discharge, external short testing; battery-pack vacuum leak and vibration testing. The overall goals of these certification procedures are to conform to requirements set forth by the agency and identify unique safety hazards. The testbeds, procedures, and experimental results are discussed for batteries chosen for small satellite missions to be launched from the ISS.

The international diagnostic competitions provide a set of diagnostic benchmarks to evaluate diagnostic algorithms. This article describes a common diagnostic framework used to evaluate these algorithms. These competitions, started in 2009, have significantly helped shape subsequent diagnostic algorithms.

As part of an effort to monitor electricity usage by plug loads in a new high performance office building, plug load management devices were deployed to enable data collection, analysis, and active control of plug loads. We used a Commercial Off-The-Shelf (COTS) plug load management system to capture relevant data for two different types of multi-function devices (MFDs) in the facility, one of which was tested for use with different power settings. This enabled a quantitative analysis to assess impacts on energy consumption. It was found that a projected 65% reduction in annual energy consumption would result by using a newer, Energy Star compliant model of MFD, and an additional projected 39% reduction in annual energy consumption would result by subsequently changing the time-to-sleep for that MFD. It was also found that it may be beneficial to apply automated analysis with anomaly detection algorithms to detect problems with MFD performance, such as a failure to go to sleep mode or variations in sleep power draw. Furthermore, we observed that energy savings realized by using plug load management devices to de-energize (unplug) MFDs during non-business hours depends on the sleep power draw and time-to-sleep setting. For the MFDs in this study with settings established per the maintenance contract (which were different than factory default values), turning the device off at night and then on in the morning used more energy than leaving it on in sleep mode due to the start-up behavior and excessive time-to-sleep setting of four hours. From this and other assessments, we offer these recommendations to building occupants: reduce MFD time-to-sleep, encourage employees to use the power save button, and apply automated analysis to detect problems with device performance.

Electrical plug loads comprise an increasingly larger share of building energy consumption as improvements have been made to Heating, Ventilation, and Air Conditioning (HVAC) and lighting systems. It is anticipated that plug loads will account for a significant portion of the energy consumption of Sustainability Base, a recently constructed high-performance office building at NASA Ames Research Center. Consequently, monitoring plug loads will be critical to achieve energy efficient operations. In this paper we describe the development of a knowledge-based system to analyze data collected from a plug load management system that allows for metering and control of individual loads. Since Sustainability Base was not yet occupied at the time of this investigation, the study was conducted in another building on the Ames campus to prototype the system. The paper focuses on the knowledge engineering and verification of a modular software system that promotes efficient use of office building plug loads. The knowledgebased system generates summary usage reports and alerts building personnel of malfunctioning equipment and unexpected plug load consumption. The system is planned to be applied to Sustainability Base and is expected to identify malfunctioning loads and reduce building energy consumption.

NASA Ames Research Center’s Sustainability Base is a new 50,000 sq. ft. LEED Platinum office building. Plug loads are expected to account for a significant portion of the overall energy consumption. This is because building design choices have resulted in greatly reduced energy demand from Heating, Ventilation, and Air Conditioning (HVAC) and lighting systems, which are major contributors to energy consumption in traditional buildings. In anticipation of the importance of plug loads in Sustainability Base, a pilot study was conducted to collect data from a variety of plug loads. A number of cases of anomalous or unhealthy behavior were observed including schedule-based rule failures, time-to-standby errors, changed loads, and inter-channel anomalies. These issues prevent effective plug load management; therefore, they are important to promptly identify and correct. The Inductive Monitoring System (IMS) data mining algorithm was chosen to identify errors. This paper details how an automated data analysis program was created, tested and implemented using IMS. This program will be applied to Sustainability Base to maintain effective plug load management system performance, identify malfunctioning equipment, and reduce building energy consumption.

This paper presents a new sensing application to diagnose power semiconductor aging in power drive systems. It has been shown previously that device parasitic characteristics change during the aging process which results in detectable changes in their frequency response. This change is manifested in the current signal at very high frequencies. Therefore, using a wideband AC current sensor, high frequency components of the current can be acquired, providing a way to detect device aging.

NASA Ames Research Center's Sustainability Base is a new 50,000 sq. ft. high-performance office building targeting a LEED Platinum rating. Plug loads are expected to account for a significant portion of overall energy consumption because building design choices resulted in greatly reduced energy demand from Heating, Ventilation, and Air Conditioning (HVAC) and lighting systems, which are typically major contributors to energy consumption in traditional buildings. This paper reports on a pilot study where data from a variety of plug loads were collected in a reference office building to understand usage patterns, to make a preliminary assessment as to the effectiveness of controlling (i.e., turning off and on) selected loads, and to evaluate the utility of the plug load management system chosen for the study. Findings indicate that choosing energy efficient equipment, ensuring that power saving functionality is operating effectively, promoting beneficial occupant energy behavior, and employing plug load controls to turn off equipment when not in use can lead to significant energy savings. These recommendations will be applied to Sustainability Base and further studies of plug load management systems and techniques to reduce plug energy consumption will be pursued.

We present the third implementation of a framework created jointly by NASA Ames Research Center, Palo Alto Research Center, and Delft University of Technology to compare and evaluate diagnosis algorithms (DAs). This year‟s competition, DXC‟11, introduces a software track in addition to the industrial and synthetic tracks of previous competitions. A total of eleven DAs competed in the three tracks. The paper describes the systems, diagnostic problems of the tracks, fault scenarios, evaluation metrics, participating DAs, results and analysis.

A poster for the NASA Aviation Safety Program Annual Technical Meeting. It describes empirical benchmarking on diagnostic algorithms using data from the ADAPT Electrical Power System testbed and a diagnostic software framework.

Solar energy generation has been a mainstay in space applications such as the International Space Station and military and commercial satellites. More recently, solar power has gained a lot of momentum for terrestrial commercial and residential applications as a viable alternative source of energy. In the current work, a low cost impedance measurement system was implemented to measure the complex impedance of solar cells. Some of the cells were then thermally aged, and the impedance changes from baseline were observed. It was noticed that the phase of the complex impedance signal (or alternatively, the imaginary part of the impedance) was different for a few of the cells subjected to aging.1, 2

We present the third implementation of a framework created jointly by NASA Ames Research Center, Palo Alto Research Center, and Delft University of Technology to compare and evaluate diagnosis algorithms (DAs). This year‟s competition, DXC‟11, introduces a software track in addition to the industrial and synthetic tracks of previous competitions. A total of eleven DAs competed in the three tracks. The paper describes the systems, diagnostic problems of the tracks, fault scenarios, evaluation metrics, participating DAs, results and analysis.

A framework to compare and evaluate diagnosis algorithms (DAs) has been created jointly by NASA Ames Research Center, Palo Alto Research Center, and Delft University of Technology. In this paper, we present the second implementation of this framework in a competition called DXC’10. The overall goal of this competition is to evaluate the performance of different diagnostic methods. In order to accurately mimic diagnostic technology use in a real-world context, we have defined diagnostic problems driven by use cases representing different roles of diagnosis results. In the end, the competition pitted seven DAs competing in two diagnostic problems. The paper presents the systems used in DXC’10, a description of faults and data sets used for each diagnostic problem, a listing of participating DAs, the performance metrics and results computed from running the DAs with the framework, and an analysis of the results.

This paper presents a formal computational methodology to explain how the oxide in semiconductors degrades over time and the dependence of oxide degradation on voltage and temperature stresses. The effects of aging are modeled and quantified by modification of the gate-source capacitance value. The model output is validated using experimental results of a thermally aged power semiconductor device.

We present in this paper a case study of the probabilistic approach to model-based diagnosis. Here, the diagnosed system is a real-world electrical power system (EPS), i.e., the Advanced Diagnostic and Prognostic Testbed (ADAPT) located at the NASA Ames Research Center. Our probabilistic approach is formally well founded and based on Bayesian networks (BNs) and arithmetic circuits (ACs). We pay special attention to meeting two of the main challenges often associated with real-world application of model-based diagnosis technologies: model development and real-time reasoning. To address the challenge of model development, we develop a systematic approach to representing EPSs as BNs, supported by an easy-to-use specification language. To address the real-time reasoning challenge, we compile BNs into ACs. AC evaluation (ACE) supports real-time diagnosis by being predictable, fast, and exact. In experiments with the ADAPT BN, which contains 503 discrete nodes and 579 edges and produces accurate results, the time taken to compute the most probable explanation using ACs has a mean of 0.2625 ms and a standard deviation of 0.2028 ms. In comparative experiments, we found that, while the variable elimination and join tree propagation algorithms also perform very well in the ADAPT setting, ACE was an order of magnitude or more faster.