Search NASA⌕ Search

SEARCH · Search NASA

Results for “Predictive Maintenance”

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
DOE OSTI2024

Software stewardship and advancement of a high-performance computing scientific application: QMCPACK

Here, we provide an overview of the software engineering efforts and their impact in QMCPACK, a production-level ab-initio Quantum Monte Carlo open-source code targeting high-performance computing (HPC) systems. Aspects included are: (i) strategic expansion of continuous integration (CI) targeting CPUs, using GitHub Actions own runners, and NVIDIA and AMD GPUs used in pre-exascale systems, (ii) incremental reduction of memory leaks using sanitizers, (iii) incorporation of Docker containers for CI and reproducibility, and (iv) refactoring efforts to improve maintainability, testing coverage, and memory lifetime management. We quantify the value of these improvements by providing metrics to illustrate the shift towards a predictive, rather than reactive, maintenance approach. Our goal, in documenting the impact of these efforts on QMCPACK, is to contribute to the body of knowledge on the importance of research software engineering (RSE) for the stewardship and advancement of community HPC codes to enable scientific discovery at scale.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1992

Fuzzy logic and neural network technologies

Applications of fuzzy logic technologies in NASA projects are reviewed to examine their advantages in the development of neural networks for aerospace and commercial expert systems and control. Examples of fuzzy-logic applications include a 6-DOF spacecraft controller, collision-avoidance systems, and reinforcement-learning techniques. The commercial applications examined include a fuzzy autofocusing system, an air conditioning system, and an automobile transmission application. The practical use of fuzzy logic is set in the theoretical context of artificial neural systems (ANSs) to give the background for an overview of ANS research programs at NASA. The research and application programs include the Network Execution and Training Simulator and faster training algorithms such as the Difference Optimized Training Scheme. The networks are well suited for pattern-recognition applications such as predicting sunspots, controlling posture maintenance, and conducting adaptive diagnoses.

Villarreal, James A.↗
NASA NTRS1994

The 4-D approach to visual control of autonomous systems

Development of a 4-D approach to dynamic machine vision is described. Core elements of this method are spatio-temporal models oriented towards objects and laws of perspective projection in a foward mode. Integration of multi-sensory measurement data was achieved through spatio-temporal models as invariants for object recognition. Situation assessment and long term predictions were allowed through maintenance of a symbolic 4-D image of processes involving objects. Behavioral capabilities were easily realized by state feedback and feed-foward control.

Dickmanns, Ernst D.↗
NASA NTRS1998

The Implications of Reduced Ground Reaction Forces During Space Flight for Bone Strains

The specific mechanisms regulating bone mass are not known, but most investigators agree that bone maintenance is largely dependent upon mechanical demand and the resultant local bone strains. During space flight, bone loss such as that reported by LeBlanc et al. may result from failure to effectively load the skeleton and generate sufficient localized bone strains. In microgravity, a gravity replacement system can be used to tether an exercising subject to a treadmill. It follows that the ability to prevent bone loss is critically dependent upon the external ground reaction forces (GRFs) and skeletal loads imparted by the tethering system. To our knowledge, the loads during orbital flight have been measured only once (on STS 81). Based on these data and data from ground based experiments, it appears likely that interventions designed to prevent bone loss in micro-gravity generate GRFs substantially less than body weight. It is unknown to what degree reductions in external GRFs will affect internal bone strain and thus the bone maintenance response. To better predict the efficacy of treadmill exercise in micro-gravity we used a unique cadaver model to measure localized bone strains under conditions representative of those that might be produced by a gravity replacement system in space.

Peterman, Marc M.↗
NASA NTRS2015

Comparison of Spares Logistics Analysis Techniques for Long Duration Human Spaceflight

As the durations and distances involved in human exploration missions increase, the logistics associated with the repair and maintenance becomes more challenging. Whereas the operation of the International Space Station (ISS) depends upon regular resupply from the Earth, this paradigm may not be feasible for future missions. Longer mission durations result in higher probabilities of component failures as well as higher uncertainty regarding which components may fail, and longer distances from Earth increase the cost of resupply as well as the speed at which the crew can abort to Earth in the event of an emergency. As such, mission development efforts must take into account the logistics requirements associated with maintenance and spares. Accurate prediction of the spare parts demand for a given mission plan and how that demand changes as a result of changes to the system architecture enables full consideration of the lifecycle cost associated with different options. In this paper, we utilize a range of analysis techniques - Monte Carlo, semi-Markov, binomial, and heuristic - to examine the relationship between the mass of spares and probability of loss of function related to the Carbon Dioxide Removal System (CRS) for a notional, simplified mission profile. The Exploration Maintainability Analysis Tool (EMAT), developed at NASA Langley Research Center, is utilized for the Monte Carlo analysis. We discuss the implications of these results and the features and drawbacks of each method. In particular, we identify the limitations of heuristic methods for logistics analysis, and the additional insights provided by more in-depth techniques. We discuss the potential impact of system complexity on each technique, as well as their respective abilities to examine dynamic events. This work is the first step in an effort that will quantitatively examine how well these techniques handle increasingly more complex systems by gradually expanding the system boundary.

Owens, Andrew↗
DOE OSTI2025

Pavement condition and climatic data in southeast Texas: A dataset for evaluating flood impacts on pavement performance

Effective pavement maintenance is essential for economic stability, optimal network performance, and roadway safety. Achieving this requires thorough evaluation of pavement conditions, including structural integrity, surface roughness, and distress characteristics. Pavement performance indicators play a critical role in influencing vehicle safety and ride quality. Recent advances have emphasized the use of data-driven modeling to anticipate pavement behavior, with the goal of optimizing resource allocation and refining Maintenance and Rehabilitation (M&R) strategies through accurate condition assessment. A foundational requirement for these modeling efforts is the availability of standardized, high-quality datasets that can support robust and reproducible infrastructure analysis. This data article presents a comprehensive dataset assembled to facilitate pavement performance prediction, with a geographic focus on Southeast Texas, particularly the flood-vulnerable area of Beaumont. The dataset encompasses pavement and traffic attributes, meteorological records, flood simulation outputs, ground deformation measurements, and topographic indices, enabling detailed examination of both load-associated and non-load-associated degradation mechanisms. Data preprocessing was performed using ArcGIS Pro, Microsoft Excel, and Python to ensure consistency and usability in data-driven modeling applications, including machine learning workflows. Key contributions of this dataset include its utility in analyzing the climatic and environmental factors affecting pavement conditions, identifying critical predictive features, and enabling in-depth correlation analysis across diverse variables. By filling existing gaps in input variable selection resources, this dataset supports the development of predictive tools for estimating future maintenance demand and enhancing the resilience of pavement networks in flood-impacted areas. The resource highlights the importance of standardized datasets for advancing pavement management practices and provides a robust foundation for ongoing infrastructure performance modeling.

42 ENGINEERING↗
NASA NTRSDate not supplied

Assessment of Crew Time for Maintenance and Repairs Activities for Lunar Surface Missions

NASA is currently evaluating different methods to predict how much time crewmembers will spend conducting repair and maintenance activities on future space missions. As mission scope and spacecraft architectures change, it will be necessary to understand how crew repair and maintenance timelines are impacted by mission operations and technology changes. Past work has been done using historical ISS data to accurately predict crew habitation and operation timelines, resulting in the development of NASA’s Exploration Crew Time Model (ECTM). However, understanding crew maintenance and repair requirements has posed a unique challenge due to the complexity of available datasets, the probabilistic nature of sub-system failures, and the impacts of reliability growth on failure rates. This paper presents a methodology to collect and condition empirical repair and maintenance time data from available data sets, to extrapolate from that data to estimate projected maintenance and repair times for a lunar Surface Habitat, and to assess how uncertainty in repair time could impact utilization time on the lunar surface. NASA International Space Station (ISS) maintenance and crew time data are logged into two central databases, the Maintenance Data Collection (MDC) and the Operations Planning Timeline Integration System (OPTimIS) respectively. Separately, each of these two datasets capture only portions of the complete set of data required to generate an accurate assessment of crew time spent on maintenance activities at a sub-system level. MDC provides a detailed catalog of failure events and an overview of the failure’s required maintenance and OPTimIS provides a description of crew activities and crew time durations dedicated to maintenance. To create a more useful crew time estimate for maintenance timelines, the authors developed a methodology to capture relevant data from each set and combine and utilize that data by linking crew time requirements to specific components. The authors compare the failure logs in the MDC to crew activity logs pulled from OPTimIS and then process the data to estimate required repair times for each failure event. Data is also classified by the outcome of each repair event, whether the failed component was replaced or whether it was repaired in place. The entire maintenance activity dataset is then categorized based on the class of failed component to allow for a statistically significant sample size for each class and to provide accurate crew time estimates for any components lacking relevant data. This resultant component repair time data can be used in the future to generate Mean Time To Repair (MTTR) estimates and confidence intervals for each class of component based on a probabilistic distribution of documented maintenance events. These improved MTTR values can then be applied to candidate element sub-system architectures, along with component Mean Time Between Failure (MTBF) data to generate distributions for potential required system crew repair time estimates for a given mission. Repair time distributions can then be used to develop more accurate crew schedules and to assess potential available utilization time.

Crew Time↗
NASA NTRSDate not supplied

Assessment of Crew Time for Maintenance and Repair Activities for Lunar Surface Missions

NASA is currently evaluating different methods to predict how much time crewmembers will spend conducting repair and maintenance activities on future space missions. As mission scope and spacecraft architectures change, understanding how crew repair and maintenance timelines are impacted by mission operations and technology changes is vital for future mission planning. Past work has been done using historical International Space Station (ISS) data to accurately predict crew habitation and operation timelines, resulting in the development of NASA’s Exploration Crew Time Model (ECTM). However, understanding crew maintenance and repair requirements has posed a unique challenge due to the complexity of available datasets, the probabilistic nature of sub-system failures, and the impacts of reliability growth on failure rates. This paper presents a methodology to collect and condition empirical repair and maintenance time data from available datasets, to extrapolate from that data to estimate projected maintenance and repair times for a lunar Surface Habitat (SH), and to assess how uncertainty in repair time could impact utilization time on the lunar surface. NASA ISS maintenance and crew time data are logged into two central databases: the Maintenance Data Collection (MDC) and the Operations Planning Timeline Integration System (OPTimIS). Separately, each of these two datasets capture only portions of the complete set of data required to generate an accurate assessment of crew time spent on maintenance activities at a sub-system level. To create a more useful crew time estimate for maintenance timelines, the authors developed a methodology to capture relevant data from each set and combine and utilize that data by linking crew time requirements to specific components. The authors compare the failure logs in the MDC to crew activity logs pulled from OPTimIS and then process the data to estimate required repair time for each failure and repair event. The entire maintenance activity dataset is then categorized based on the class of failed component to ensure a significant sample size for each class and accurate crew time estimates for any components lacking relevant data. This resultant component repair time data can be used in the future to generate Mean Time to Repair (MTTR) estimates and confidence intervals for each class of component based on a probabilistic distribution of documented maintenance events. These improved MTTR values can then be applied to candidate element sub-system architectures, along with component Mean Time Between Failure (MTBF) data to generate distributions for potential required system crew repair time estimates for a given mission. The authors applied these modeling methods to a case study of a crewed mission to the planned SH and produced expected corrective maintenance crew time distributions. The results produced an expected corrective maintenance crew time at over 24 hours per mission, and a maintenance crew time distribution that reflects the importance of planning for sufficient maintenance requirements each mission. Repair time distributions can then be used to develop more accurate crew schedules and to assess potential available utilization time.

Crew Time↗
DOE OSTI2025

A Practical Comparison of Data-Driven Prognostics Methods for Energy Systems

This study explores data-driven prognostics for nuclear power plant (NPP) condensers, focusing on tube fouling. We utilized the Asherah nuclear power plant simulator (ANS) to compare four methods: Random Forest (RF), Support Vector Regressor (SVR), Fully Connected Neural Network (FCNN), and Long Short-Term Memory Neural Network (LSTM). By simulating various fouling scenarios in the ANS, we generated data with different degradation rates under transient operations. The models were trained and tested on these data, with performance evaluated visually and numerically including uncertainty assessment. The LSTM model excelled, exhibiting minimal prediction noise and the most accurate remaining useful life estimates across all degradation levels. Its ability to capture long-term dependencies and produce cleaner outputs makes it a strong candidate, although accurate training data across the entire component lifespan are crucial. The RF model emerged as a robust alternative, providing reliable predictions with high confidence. The FCNN and SVR models, while less effective overall, showed potential under specific conditions. FCNN offers a less complex alternative to LSTM and might benefit from larger datasets. SVR excels in precision when the quality of the training data is high. Furthermore, this study highlights the operational benefits of advanced prognostics in the energy sector and emphasizes the need for further research in NPP condenser health management through real-life experiments.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
NASA NTRS1995

Application of Different Statistical Techniques in Integrated Logistics Support of the International Space Station Alpha

The process to predict the values of the maintenance time dependent variable parameters such as mean time between failures (MTBF) over time must be one that will not in turn introduce uncontrolled deviation in the results of the ILS analysis such as life cycle cost spares calculation, etc. A minor deviation in the values of the maintenance time dependent variable parameters such as MTBF over time will have a significant impact on the logistics resources demands, International Space Station availability, and maintenance support costs. It is the objective of this report to identify the magnitude of the expected enhancement in the accuracy of the results for the International Space Station reliability and maintainability data packages by providing examples. These examples partially portray the necessary information hy evaluating the impact of the said enhancements on the life cycle cost and the availability of the International Space Station.

Sepehry-Fard, F.↗
NASA NTRS2024

Integrated Simulations of the Sabatier and Carbon Vapor Deposition Reactor to Understand Its Impacts to Operations and Performance

The carbon vapor deposition (CVD) reactor is a technology developed by Honeywell Aerospace to convert methane, at high temperatures, into hydrogen and solid carbon. This element is coupled with a Sabatier reactor to support a closed-loop environmental control and life support system with the aim of achieving nearly complete oxygen recovery (> 95%). Initial open-loop, brassboard CVD reactor tests and simulations have shown the CVD’s ability to achieve moderately high methane conversion and high hydrogen selectivity. However, in an integrated system, additional deficiencies are expected due to recycling of unreacted or extraneous species from the Sabatier reactor (e.g., carbon dioxide, hydrogen, water) and CVD reactor (e.g., hydrocarbons, methane, etc.). Sabatier and CVD reactor models were integrated and simulated to predict potential impacts to individual reactors’ and the overall system’s performance. The simulations showed that increasing the recycle of the CVD effluent hydrogen combined with decreasing the system inlet hydrogen flow rate (i.e., drawing a stoichiometric flow rate from an electrolyzer) can lead to an oxygen recovery of > 95%. However, system integration comes at a detriment to the individual reactors. The simulations show the initial conversion from the integrated system (Sabatier = 87% and CVD = 59%) to be lower than the standalone systems (Sabatier = 91% and CVD = 69%). Furthermore, transient simulations show substrate densification, leading to worsening methane conversion coupled with increasing acetylene production, which is commensurate with soot formation. Simulations predict a shortening of the maintenance interval (i.e., time until CVD methane conversion drops below 50%) in the integrated system, which would increase the consumable substrate mass. These analyses highlight the importance of long-duration, integrated tests to corroborate these findings as well as suggest potential modifications (e.g., intermediate gas separations) to improve performance.

Air Revitalization↗
NASA NTRS2015

Advanced Ground Systems Maintenance Prognostics Project

The project implements prognostics capabilities to predict when a component system or subsystem will no longer meet desired functional or performance criteria, called the end of life. The capability also provides an assessment of the remaining useful life of a hardware component. The project enables the delivery of system health advisories to ground system operators. This project will use modeling techniques and algorithms to assess components' health andpredict remaining life for such components. The prognostics capability being developed will beused:during the design phase and during pre/post operations to conduct planning and analysis ofsystem design, maintenance & logistics plans, and system/mission operations plansduring real-time operations to monitor changes to components' health and assess their impacton operations.This capability will be interfaced to Ground Operations' command and control system as a part ofthe AGSM project to help assure system availability and mission success. The initial modelingeffort for this capability will be developed for Liquid Oxygen ground loading applications.

Prognostics↗
NASA NTRS2011

Prognostics for Ground Support Systems: Case Study on Pneumatic Valves

Prognostics technologies determine the health (or damage) state of a component or sub-system, and make end of life (EOL) and remaining useful life (RUL) predictions. Such information enables system operators to make informed maintenance decisions and streamline operational and mission-level activities. We develop a model-based prognostics methodology for pneumatic valves used in ground support equipment for cryogenic propellant loading operations. These valves are used to control the flow of propellant, so failures may have a significant impact on launch availability. Therefore, correctly predicting when valves will fail enables timely maintenance that avoids launch delays and aborts. The approach utilizes mathematical models describing the underlying physics of valve degradation, and, employing the particle filtering algorithm for joint state-parameter estimation, determines the health state of the valve and the rate of damage progression, from which EOL and RUL predictions are made. We develop a prototype user interface for valve prognostics, and demonstrate the prognostics approach using historical pneumatic valve data from the Space Shuttle refueling system.

Daigle, Matthew↗
NASA NTRS1993

Modelling early failures in Space Station Freedom

A major problem encountered in planning for Space Station Freedom is the amount of maintenance that will be required. To predict the failure rates of components and systems aboard Space Station Freedom, the logical approach is to use data obtained from previously flown spacecraft. In order to determine the mechanisms that are driving the failures, models can be proposed, and then checked to see if they adequately fit the observed failure data obtained from a large variety of satellites. For this particular study, failure data and truncation times were available for satellites launched between 1976 and 1984; no data past 1984 was available. The study was limited to electrical subsystems and assemblies, which were studied to determine if they followed a model resulting from a mixture of exponential distributions.

Navard, Sharon E.↗
NASA NTRS2021

Aircraft Engine Run-to-Failure Dataset Under Real Flight Conditions for Prognostics and Diagnostics

A key enabler of intelligent maintenance systems is the ability to predict the remaining useful lifetime (RUL) of its components, i.e., prognostics. The development of data-driven prognostics models requires datasets with run-to-failure trajectories. However, large representative run-to-failure datasets are often unavailable in real applications because failures are rare in many safety-critical systems. To foster the development of prognostics methods, we develop a new realistic dataset of run-to-failure trajectories for a fleet of aircraft engines under real flight conditions. The dataset was generated with the Commercial Modular Aero-Propulsion System Simulation (CMAPSS) model developed at NASA. The damage propagation modelling used in this dataset builds on the modelling strategy from previous work and incorporates two new levels of fidelity. First, it considers real flight conditions as recorded on board of a commercial jet. Second, it extends the degradation modelling by relating the degradation process to its operation history. This dataset also provides the health respectively fault class. Therefore, besides its applicability to prognostics problems, the dataset can be used for fault diagnostics.

CMAPPS↗
NASA NTRS2018

A Prognostics Framework Development for Swarm Satellite Formations

Prognostics is the science of predicting the failure(s) of a component or a system and understanding how the performance will change in the event of a failure or degradation mechanism. With accurate predictions of possible failures, autonomous mitigative actions can be taken to correct/repair any issues or alert human operators of a failure threshold exceedance requiring condition-based maintenance. Although there is extensive research on failure predictions for a component or a system, there are significantly more opportunities to foray into failure predictions and prognostics for a system of systems such as an airspace consisting of multiple aircraft, a fleet of unmanned aerial vehicles, and a swarm of intelligent satellite systems. Failure prediction and mitigation are particularly important in autonomous systems such as satellite swarm systems that need effective resource management and minimal human interactions. Based on NASA's decadal survey, there is a clear need to prioritize the development of satellite swarm technology for studies of space physics and Earth science. The science community will propose future missions that return in-situ measurements from a 3-D (three-dimensional) volume of space, with relative spacecraft motion and inter-satellite baselines controlled according to the mission objectives. For such multi-spacecraft missions, it is required that ground operations resources do not scale with the number of satellites, thus compromising the swarm or leading to inefficiencies in resource allocation. Swarms of tens or hundreds of small satellites will require autonomy in attitude control, navigation and failure. Although significant research has been conducted in the areas of autonomous formation flying algorithms, less attention has been given to the development of resilient systems robust to failures.The focus of this research paper is the integration of model-based prognostics into the swarm dynamics control and decision-making algorithms. We simulate swarm management strategies for a subsystem failure to demonstrate the importance of failure predictions by comparing two cases: (i) no health information is provided to the system and utilized in the decision-making process and (2) system health information is obtained using prognostics and employed by the control system. One example scenario presented is for the GPS (Global Positioning System) system of an individual satellite to perform off-nominally due to increasing estimated error. In this scenario, the keep-out zone for that satellite would become more conservative, thereby decreasing the risk of collision. This is achieved via tuning the individual artificial repulsive functions assigned to each satellite.This paper is structured as follows. First we provide an overview of current swarm technology development, where we specifically use the term swarm to define multiple satellites flying in formation in similar orbits, with cross-link communication and station-keeping capabilities. Second, we give an introduction to the Swarm Orbital Dynamics Advisor (SODA), a tool that accepts high-level configuration commands and provides the orbital maneuvers required to achieve the prescribed formation configuration. Third, we provide the details of the model-based prognostics algorithm implementation in SODA. Finally, we present different case studies for potential component/subsystem failures and the swarm responses based with and without failure prediction information.

prognostics↗
DOE OSTI2026

Audible Noise Modeling of Hydrogen Release Sonic Hazards in Rail Maintenance Facilities

This study implemented validated literature models to predict audible noise due to pressurized gaseous hydrogen releases through a thermally-activated pressure relief device (TPRD) and attached vent stack. A literature survey discovered limited hydrogen-specific noise prediction models validated by experiments. However, empirical noise prediction models for air flowing through pipes and valves were identified. These empirical models were used to predict noise levels and compared against hydrogen noise data reported in two studies: one experimental study of noise from hydrogen leaking through a pipe and another which modeled hydrogen flowing through a solenoid valve during a fuel cell vehicle refueling. The valve flow model was then applied to predict noise for hydrogen releases through a TPRD. Results show that hydrogen releases through a TPRD can produce harmful noise levels varying from 134 to 150 dB. However, further model validation and additional experimental data are needed to improve prediction confidence and accuracy.

08 HYDROGEN↗
NASA NTRS2014

Advanced Ground Systems Maintenance Prognostics Project

The project implements prognostics capabilities to predict when a component, system or subsystem will no longer meet desired functional or performance criteria, called the "end of life." The capability also provides an assessment of the "remaining useful life" of a hardware component.

Technology Portfolio System↗