Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “fault prognostics”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS2015

Real-Time Model-Based Leak-Through Detection within Cryogenic Flow Systems

The timely detection of leaks within cryogenic fuel replenishment systems is of significant importance to operators on account of the safety and economic impacts associated with material loss and operational inefficiencies. Associated loss in control of pressure also effects the stability and ability to control the phase of cryogenic fluids during replenishment operations. Current research dedicated to providing Prognostics and Health Management (PHM) coverage of such cryogenic replenishment systems has focused on the detection of leaks to atmosphere involving relatively simple model-based diagnostic approaches that, while effective, are unable to isolate the fault to specific piping system components. The authors have extended this research to focus on the detection of leaks through closed valves that are intended to isolate sections of the piping system from the flow and pressurization of cryogenic fluids. The described approach employs model-based detection of leak-through conditions based on correlations of pressure changes across isolation valves and attempts to isolate the faults to specific valves. Implementation of this capability is enabled by knowledge and information embedded in the domain model of the system. The approach has been used effectively to detect such leak-through faults during cryogenic operational testing at the Cryogenic Testbed at NASA's Kennedy Space Center.

Walker, M.↗
NASA NTRSDate not supplied

A Case Study on the Challenges and Opportunities for the Deployment of PHM Capabilities in Existing Engineering Systems

The field of Prognostics and Health Management (PHM) of engineering systems has experienced considerable growth over the last decade. From benefits associated with faster and more powerful hardware in the form of wireless sensors, edge devices, and general computing capabilities (GPU’s and cloud computing), to development of powerful algorithms for anomaly detection and remaining useful life (RUL) estimation, the number of engineering systems featuring advanced diagnostics and prognostics capabilities continues to grow at an increasingly faster pace. However, the deployment of PHM capabilities as part of the upgrade of existing engineering systems presents multiple challenges to the PHM practitioner charged with retrofitting such systems. Issues include a lack of specific instrumentation needed to capture the signals of interest; insufficient data and sampling rates required for fault detection and diagnosis, and for detection of failure/degradation indicators; and difficulties in the identification of a system’s nominal behavior as a result of age induced degradation. Today’s PHM practitioner must be able to quickly identify and assess these types of issues to effectively evaluate and select the optimal PHM strategies required to achieve the desired results. This paper presents results from the preliminary evaluation of the High-Pressure Gas Facility (HPGF) infrastructure at NASA’s Stennis Space Center in Hancock County, Mississippi. This evaluation is part of a feasibility study conducted prior to the deployment of prognostics and diagnostics capabilities in the pumps skids of the liquid nitrogen (LN2) system of the HPGF.

Condition Based Maintenance↗
NASA NTRS2014

Integrated Diagnostics and Prognostics for the Electrical Power System of a Planetary Rover

For electric vehicles, technology for monitoring, diagnosis, and prognosis of the electrical power system (EPS) becomes essential for safe and efficient operation. To this end, we develop a general system-level integrated diagnosis and prognosis framework, which detects, isolates, and identifies EPS faults, and predicts when the EPS will fail to deliver sufficient power. The approach takes advantage of recent work in structural model decomposition in order to distribute the global diagnosis and prognosis problems into local subproblems that can be solved in parallel, thus enabling implementation on distributed computational platforms. The framework is applied to the EPS of a planetary rover testbed, and is demonstrated using data from field experiments.

Daigle, Matthew↗
DOE OSTI2026

Gearbox bearing crack growth prognostics and uncertainty quantification with physics-informed machine learning

This paper introduces the extreme theory of functional connections (X-TFC), a physics-informed machine learning algorithm, and tailors it to estimate the remaining useful life (RUL) of wind turbine gearbox bearings experiencing fatigue crack growth. Unlike purely data-driven methods, X-TFC embeds a physics model, based on Head's theory in this work, into its training objective. The core of X-TFC is a random-projection single-layer neural network trained via an extreme learning machine, which requires only limited damage progression data and solves for output weights with a least-squares optimization algorithm. A composite loss function balances the network's fit to observed degradation data against the residuals of the governing crack growth differential equation, ensuring the learned damage trajectory remains physically plausible. When applied to a vibration-based health-index (HI) dataset measured during the growth of a crack on the inner ring of a high-speed bearing in a wind turbine gearbox (Bechhoefer and Dubé, 2020), X-TFC achieves near-zero prediction bias. Even when trained on only the first 10 %–20 % of the damage progression data, with sufficient physics weighting its predictions remain monotonic and smooth, delivering high prognosability and trendability. To quantify the epistemic uncertainty, we employ a Monte Carlo ensemble of independently initialized X-TFC models trained on noise-perturbed data, which yields confidence intervals around each RUL estimate and captures both model-parameter and epistemic uncertainty. In addition to a vibration-based HI, we demonstrate that the proposed framework can be directly applied to a supervisory control and data acquisition (SCADA) data-based HI (Eftekhari Milani et al., 2026) measured during similar wind turbine gearbox bearing crack faults, preserving its accuracy and interpretability. This extension shows the versatility of our approach, which is applicable to bearings of multiple gearbox manufacturers, models, and ratings using only SCADA data. By integrating domain knowledge with machine learning, X-TFC offers a rapid, reliable tool for crack prognostics. Its adaptability to other bearing failure modes, such as pitch bearing ring cracks, positions X-TFC as a powerful enabler of data-driven, physics-informed asset management in the wind energy sector and beyond.

17 WIND ENERGY↗
NASA NTRS2005

Hybrid Bearing Prognostic Test Rig

The NASA Glenn Research Center has developed a new Hybrid Bearing Prognostic Test Rig to evaluate the performance of sensors and algorithms in predicting failures of rolling element bearings for aeronautics and space applications. The failure progression of both conventional and hybrid (ceramic rolling elements, metal races) bearings can be tested from fault initiation to total failure. The effects of different lubricants on bearing life can also be evaluated. Test conditions monitored and recorded during the test include load, oil temperature, vibration, and oil debris. New diagnostic research instrumentation will also be evaluated for hybrid bearing damage detection. This paper summarizes the capabilities of this new test rig.

Dempsey, Paula J.↗
NASA NTRS2011

Lightning Pin Injection Test: MOSFETS in "ON" State

The test objective was to evaluate MOSFETs for induced fault modes caused by pin-injecting a standard lightning waveform into them while operating. Lightning Pin-Injection testing was performed at NASA LaRC. Subsequent fault-mode and aging studies were performed by NASA ARC researchers using the Aging and Characterization Platform for semiconductor components. This report documents the test process and results, to provide a basis for subsequent lightning tests. The ultimate IVHM goal is to apply prognostic and health management algorithms using the features extracted during aging to allow calculation of expected remaining useful life. A survey of damage assessment techniques based upon inspection is provided, and includes data for optical microscope and X-ray inspection. Preliminary damage assessments based upon electrical parameters are also provided.

Ely, Jay J.↗
NASA NTRS2007

Hybrid Modeling Improves Health and Performance Monitoring

Scientific Monitoring Inc. was awarded a Phase I Small Business Innovation Research (SBIR) project by NASA's Dryden Flight Research Center to create a new, simplified health-monitoring approach for flight vehicles and flight equipment. The project developed a hybrid physical model concept that provided a structured approach to simplifying complex design models for use in health monitoring, allowing the output or performance of the equipment to be compared to what the design models predicted, so that deterioration or impending failure could be detected before there would be an impact on the equipment's operational capability. Based on the original modeling technology, Scientific Monitoring released I-Trend, a commercial health- and performance-monitoring software product named for its intelligent trending, diagnostics, and prognostics capabilities, as part of the company's complete ICEMS (Intelligent Condition-based Equipment Management System) suite of monitoring and advanced alerting software. I-Trend uses the hybrid physical model to better characterize the nature of health or performance alarms that result in "no fault found" false alarms. Additionally, the use of physical principles helps I-Trend identify problems sooner. I-Trend technology is currently in use in several commercial aviation programs, and the U.S. Air Force recently tapped Scientific Monitoring to develop next-generation engine health-management software for monitoring its fleet of jet engines. Scientific Monitoring has continued the original NASA work, this time under a Phase III SBIR contract with a joint NASA-Pratt & Whitney aviation security program on propulsion-controlled aircraft under missile-damaged aircraft conditions.

Source record↗
NASA NTRSDate not supplied

In-Time Safety Assessment & Risk Prediction for Unmanned Aerial Systems

One of the critical challenges in emerging autonomous systems is timely mitigation of hazards encountered during operation which may not be known or accounted for at the time of design. Efficient execution of unmanned systems therefore demands a paradigm shift from scheduled periodic maintenance to predictive risk analysis that includes condition-based-monitoring, real-time reliability assessment and hazard mitigation. Particularly, the state-of-health parameters needs to be computed at the component level, unit level as well as the integrated system level. While in the former two levels, the physics of health propagation may be based on underlying electro-mechanical properties, system level prognostics often relies on data-driven models. Further, uncertainty from model, measurements and input sources should be accurately quantified to generate meaningful prediction results that can be fed into reliable decision making processes. Finally, the expected risk and time to failure has to be computed based on the current state-of-health of the overall system. This talk presents a conceptual design of such an in-time safety assurance approach for unmanned aerial vehicles (UAV) operating at low altitudes near and over populated areas. Typical in-flight hazard incidents include unplanned detour, proximity to obstacles, mid-flight component faults, limited battery life and poor quality of GPS measurements. Safety assessment therefore comprises trajectory generation and re-plan, battery RUL computation, distributed fault diagnostics and uncertainty management of predicted trajectory based on GPS measurement noise. The entire monitoring framework will be demonstrated on simulated as well as real UAV flight experiments conducted at the NASA Langley Research Center. This tutorial will therefore guide the audience through a step-by-step tracking of an autonomous system with focus on in-time risk prediction in the presence of unforeseen hazards and uncertain environment.

diagnostics↗
DOE OSTI2022

Advanced Reactor Control and Operations (ARCO): A University Research Facility for Developing Optimized Digital Control Rooms

The Advanced Reactor Control and Operations (ARCO) facility was constructed in January 2018 to serve as a test bed for advanced reactor control rooms and operator support systems. Since then, it has supported human-machine interface user experience research, fault detection and mitigation technology development, control room concept of operations development, and remote operations research. ARCO serves as the control room for the Compact Integral Effects Test (CIET) facility, which replicates the primary-side flow paths and thermal-hydraulic behavior of a fluoride-salt-cooled high-temperature reactor (FHR) using simulant fluids and scaling principles. New reactor designs feature different operating conditions and scenarios than those in existing reactors. ARCO supports the research and development of digital tools for operator communications, intuitive real-time data analysis, online health monitoring and prognostics, and control room cybersecurity. By integrating these different technologies, ARCO acts as a prototypical control system to iteratively develop methods and tools of operation in advanced small modular nuclear reactors. This paper describes the features of and challenges to operating advanced small modular reactors underlying the design basis for ARCO and its operator support systems.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
NASA NTRSDate not supplied

Enabling in-time Prognostics with Surrogate Modeling through Physics-enhanced Dynamic Mode Decomposition Method

Computational models provide essential quantitative tools for assessing and predicting the health and performance of physical systems. However, high-fidelity models are rarely used in real-time operations or large optimization loops, due to their time-intensive nature. A common approach to improving computational efficiency of prognosis is to employ surrogate models. Such models can significantly decrease computation time for some accuracy loss. In this context, use of Dynamic Mode Decomposition (DMD) is proposed to generate surrogate models for lithium-ion (Li-ion) battery discharge. DMD has been suggested and used successfully in the area of fluid dynamics for over a decade, but it has not been applied to the PHM domain, where far-ahead prediction of nonlinear behavior is crucial to propagate faults or predict Remaining Useful Life (RUL). For Li-ion battery health management, the standard application of DMD using only the observable quantities of interest was unable to capture the nonlinear discharge of batteries exhibited in lab testing. The Koopman theory, however, provides a mechanism to tradeoff low dimensional nonlinear models with high-dimensional linear ones in a DMD framework, by augmenting nonlinear state variables into the system representation. In this way, DMD allows for configurable simulation accuracy dependent on the dimensionality of the Koopman operator. For battery health management, we augmented the observable variables with the hidden states of a higher-fidelity physics model to build the DMD surrogate. In comparison to a high-fidelity model, the surrogate improved computational efficiency with only a minimal loss of accuracy, and enabled long-term prognostics horizons. A generalized method for this was implemented in the prog models python package.

prognostics and health management↗
NASA NTRS2007

Generating Scenarios When Data Are Missing

The Hypothetical Scenario Generator (HSG) is being developed in conjunction with other components of artificial-intelligence systems for automated diagnosis and prognosis of faults in spacecraft, aircraft, and other complex engineering systems. The HSG accepts, as input, possibly incomplete data on the current state of a system (see figure). The HSG models a potential fault scenario as an ordered disjunctive tree of conjunctive consequences, wherein the ordering is based upon the likelihood that a particular conjunctive path will be taken for the given set of inputs. The computation of likelihood is based partly on a numerical ranking of the degree of completeness of data with respect to satisfaction of the antecedent conditions of prognostic rules. The results from the HSG are then used by a model-based artificial- intelligence subsystem to predict realistic scenarios and states.

Mackey, Ryan↗
DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (4th Annual Report)

Nuclear plant sites collect and store large volumes of data collected from various equipment and systems. These datasets typically include plant process parameters, maintenance records, technical logs, online monitoring data, and equipment failure data. The collection of such data affords an opportunity to leverage data-driven machine learning and artificial intelligence technologies to provide diagnostic and prognostic capabilities within the nuclear power industry to reduce operating and maintenance costs. In this way, nuclear energy can become more economically competitive with other energy sources, and premature closures can be avoided. From a maintenance standpoint, savings can be achieved by leveraging machine learning and artificial intelligence technologies to develop data-driven algorithms to better diagnose and predict potential faults within the system. Improved model accuracy can lead to reductions in unnecessary maintenance and more efficient planning of future maintenance, thus lowering the costs associated with parts, labor, and unnecessary planned, forced, or extended outages. From an operations perspective, cost savings can be generated by shifting from route-based monitoring to wireless technologies for online monitoring, and by transitioning from onsite- to cloud-based computing and storage services. Wireless monitoring would reduce the operator manhours required for taking routine measurements, while cloud computing services would generate cost savings by reducing the amount of hardware needing to be purchased and maintained—all while scaling to both computational and storage demands. This report summarizes this project’s effort to shift from costly, labor-intensive preventative maintenance to cheaper predictive maintenance.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRSDate not supplied

Role of PHM in Autonomous Decision-Making: Aerospace applications

There is an increased need for onboard decision-making capabilities in cyber-physical systems be it in energy, automotive, aviation, space, or other industries as they aim for increased efficiency, resiliency, and mission assurance capabilities. Emerging next-gen technologies such as multi-rover planetary missions, distributed satellites, unmanned ground and aerial vehicle operations and smart grid systems rely on in-time risk assessment and autonomous decision-making. One critical piece of the autonomy puzzle is reliable prediction of system behavior under time-varying and potentially uncertain environmental conditions. Further, if agent states change during operation such as initiation of faults or degradation, reliable diagnostic tools need to be investigated. In this tutorial, we will revise approaches that integrates existing physics-based and data-driven models of agents interacting with probability models of the environment and component operation state. Role of existing PHM methodologies as they feed into decision-making under uncertainty will be studied. Balancing critical trade-offs between high-fidelity prognostic models, prediction time-horizons and the computational requirements for in-time cost-effective decision-making will be discussed through the implementation of surrogate models. Finally, the audience will be introduced to a real-time application of in-time trajectory planning of an unmanned aerial system (UAS) based on its PHM assessments under uncertain and varying wind conditions.

decision-making↗
NASA NTRS2014

Demonstration of Prognostics-Enabled Decision Making Algorithms on a Hardware Mobile Robot Test Platform

Prognostics-enabled Decision Making (PDM) is an emerging research area that aims to integrate prognostic health information and knowledge about the future operating conditions into the process of selecting subsequent actions for the system. Previous work developing and testing PDM algorithms has been done in simulation; this paper describes the effort leading to a successful demonstration of PDM algorithms on a hardware mobile robot platform. The hardware platform, based on the K11 planetary rover prototype, was modified to allow injection of selected fault modes related to the rover’s electrical power subsystem. The PDM algorithms were adapted to the hardware platform, including development of a software module framework, a new route planner, and modifications to increase the algorithms’ robustness to sensor noise and system timing issues. A set of test scenarios was chosen to demonstrate the algorithms’ capabilities. The modifications to run with a hardware platform, the test scenarios, and the test results are described in detail. The results show a successful use of PDM algorithms on a hardware test platform to optimize mission planning in the presence of electrical system faults.

Prognosis↗
NASA NTRS2008

Enhanced Self Tuning On-Board Real-Time Model (eSTORM) for Aircraft Engine Performance Health Tracking

A key technological concept for producing reliable engine diagnostics and prognostics exploits the benefits of fusing sensor data, information, and/or processing algorithms. This report describes the development of a hybrid engine model for a propulsion gas turbine engine, which is the result of fusing two diverse modeling methodologies: a physics-based model approach and an empirical model approach. The report describes the process and methods involved in deriving and implementing a hybrid model configuration for a commercial turbofan engine. Among the intended uses for such a model is to enable real-time, on-board tracking of engine module performance changes and engine parameter synthesis for fault detection and accommodation.

Volponi, Al↗
NASA NTRS1993

The use of multiple models in case-based diagnosis

The work described in this paper has as its goal the integration of a number of reasoning techniques into a unified intelligent information system that will aid flight crews with malfunction diagnosis and prognostication. One of these approaches involves using the extensive archive of information contained in aircraft accident reports along with various models of the aircraft as the basis for case-based reasoning about malfunctions. Case-based reasoning draws conclusions on the basis of similarities between the present situation and prior experience. We maintain that the ability of a CBR program to reason about physical systems is significantly enhanced by the addition to the CBR program of various models. This paper describes the diagnostic concepts implemented in a prototypical case based reasoner that operates in the domain of in-flight fault diagnosis, the various models used in conjunction with the reasoner's CBR component, and results from a preliminary evaluation.

Karamouzis, Stamos T.↗
DOE OSTI2017

Behavior-based approach to misuse detection of a simulated SCADA system - 339

This paper presents the initial findings in applying a behavior-based approach for detection of unauthorized activities in a simulated Supervisory Control and Data Acquisition (SCADA) system. Misuse detection of this type utilizes fault-free system telemetry to develop empirical models that learn normal system behavior. Future monitored telemetry sources that show statistically significant deviations from this learned behavior may indicate an attack or other unwanted actions. The experimental test bed consists of a set of Linux based enterprise servers that were isolated from a larger university research cluster. All servers are connected to a private network and simulate several components and tasks seen in a typical SCADA system. Telemetry sources included kernel statistics, resource usages and internal system hardware measurements. For this study, the Auto Associative Kernel Regression (AAKR) and Auto Associative Multivariate State Estimation Technique (AAMSET) are employed to develop empirical models. Prognostic efficacy of these methods for computer security used several groups of signals taken from available telemetry classes. The Sequential Probability Ratio Test (SPRT) is used along with these models for intrusion detection purposes. The different intrusion types shown include host/network discovery, DoS, brute force login, privilege escalation and malicious exfiltration actions. For this study, all intrusion types tested displayed alterations in the residuals of much of the monitored telemetry and were able to be detected in all signal groups used by both model types. The methods presented can be extended and implemented to industries besides nuclear that use SCADA or business-critical networks. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS2018

Remaining Flying Time Prediction Implementing Battery Prognostics Framework for Electric UAV's

In this paper the problem of building trust in the online safety prediction of an fixed wing small electric unmanned aerial vehicles (e-UAV) for remaining flying time is addressed. A series of flight tests are described to verify the performance of the remaining flying time prediction algorithm. The estimate of remaining flying time is used to activate an alarm when the predicted remaining time falls below a threshold of two minutes. This updates the pilot to transition to the landing sequence of the flight profile. A second alarm is activated when the battery state of charge (SOC) falls below a specified safety limit threshold. This SOC threshold is the point at which the battery energy reserve would no longer safely support enough aborted landing attempts. During the test flights, the motor system is operated with the same predefined timed airspeed profile for each test. To test the robustness of the developed prediction algorithm, partial tests were performed with and remaining were performed without a simulated power train fault. To simulate a partial power train fault in the e-UAV the pilot engages a resistor bank at a specified time during the test flight. The flying time prediction system is agnostic of the pilot's activation of the fault and must adapt to the vehicle's state. The time at which the limit threshold on battery SOC is reached, it is then used to measure the accuracy of the remaining flying time predictions. This is demonstrated through comparing results from two battery models being developed. Accuracy requirements for the alarms are considered and the results discussed.

Kulkarni, Chetan↗