Search NASA⌕ Search

SEARCH · Search NASA

Results for “failure detection”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Anomaly Detection in Seismic Data with Deep Learning: Application for Instrument Failure Detection and Forecasting

Seismic data quality assessment (QA) is the first and one of the most important steps before conducting any further data analysis. Traditional methods involve checking various metrics, such as spike detection and power spectral density, by setting strict thresholds or comparing data against synthetic benchmarks. However, these approaches often rely on pre-existing knowledge and assumptions about data anomalies, leading to potential misclassification of unusual cases. Here, in this study, we propose a deep autoencoder model, an unsupervised learning approach that evaluates data quality without making assumptions about normal and anomalous data, which can be used to identify deviations in recorded data that may indicate nascent instrument failure. We test the model with the U.S. International Monitoring System (IMS) seismic stations and demonstrate the capability of detecting anomalies on a monthly scale. This could prompt station operators to examine potential problems early, allowing sufficient time for instrument maintenance to prevent data outages. In addition, we use a new manually selected testing dataset to compare our model performance against two supervised machine learning (ML) approaches and a standard QA package, as baseline models. When applied to the dataset containing known data anomalies, performance of the supervised and unsupervised ML approaches is similar, with an accuracy of 88.1% for our model compared to ∼90% for the supervised ML approach and 78.2% for the standard QA package. Our model outperforms the baseline models when applied to new stations, where new types of data anomalies can be station-specific and not included in the training dataset. Finally, we show model transferability by training the model with data from the Global Seismograph Network only and applying it to the IMS network data. The results suggest that our model is generalizable and can be applied to new stations with good accuracy.

Lin, Jiun-Ting [Lawrence Livermore National Labora↗
DOE OSTI2024

Systems, methods, and devices for failure detection of one or more energy storage devices

An energy storage device management system can include a management portion for charging/discharging an energy storage device and an ultrasound interrogation portion for passing ultrasound energy through the energy storage device during charge/discharge cycles. A memory stores a stream of capture data instances derived from ultrasound energy exiting the energy storage device and baseline ultrasound data instances corresponding with the energy storage device during normal charging/discharging thereof. A processor can compare each capture data instance with the baseline ultrasound data and detect abnormal operating states of the energy storage device. A warning system can issue a notification when abnormal operating states are detected.

Kowalski, Jeffrey A.↗
DOE OSTI2026

High-Sensitivity DNA Aptasensors for Detecting Salivary Biomarker S100A7 in Heart Failure

Early detection of heart failure (HF) is vital for improving patient outcomes, lowering hospital readmission rates, and enabling prompt treatment. We present the first high-affinity DNA aptamer for the salivary HF biomarker S100A7 and its application in highly sensitive, noninvasive diagnostic tests. Iterative truncation of the initial 82-nt aptamer (17–82) produced a 43-nt core (17–43) with a binding affinity of 27 nM, which was further enhanced to 5.5 nM through dimerization. Biochemical and mutational studies confirmed that 17–43 adopts a G-quadruplex structure, which is essential for S100A7 recognition and resistance to enzymatic degradation in human saliva. Incorporating 17–43 into sandwich aptamer-ELISA and hybrid aptamer–antibody ELISA assays allowed detection of recombinant S100A7 in human saliva with limits of detection (LOD) of 7.4 ng mL–1 (0.6 nM) and 29 pg/mL (2.2 pM), respectively-outperforming commercial immunoassays in both sensitivity and dynamic range. The hybrid assay maintained its full performance after 2.5 months of room temperature storage. Additionally, a biolayer interferometry (BLI) sensor with 17–43 quantified S100A7 in patient saliva (n = 3), achieving a LOD of 3.2 ng mL–1 (0.3 nM) with a total assay time of less than 20 min. The aptamer’s stability, high specificity, and versatility across biosensing platforms establish it as a promising tool for noninvasive heart failure diagnostics, laying the groundwork for portable aptamer-based biosensors for multiplexed monitoring of HF biomarkers.

DNA aptamer↗
DOE OSTI2025

Analysis of Warped April Tag Impacts on Detection and Pose Estimation

This report evaluates the impact of geometric deformation on an April Tag, particularly when warped due to attachment on a curved surface, on its detectability and pose estimation performance. A comparative analysis was conducted using a flat April Tag as a control under identical experimental conditions, which involved recording video sequences with varying viewing angles. For detectability, the warped tag exhibited consistent detection failures at viewing angles beyond 40° and complete failures beyond 60°, whereas the flat tag maintained reliable detection across all angles. For pose estimation, measured by pose jitter (variation in rotation and translation), differences between the warped and flat tags were minimal and statistically insignificant, indicating robust performance even for the deformed tag. These findings suggest that while geometric warping reduces an April Tag’s detectability, its pose estimation accuracy remains relatively unaffected under the tested conditions.

42 ENGINEERING↗
DOE OSTI2024

Analyzing Potential Failures and Effects in a Pilot-Scale Biomass Preprocessing Facility for Improved Reliability

This study demonstrates a failure identification methodology applied to a preprocessing facility generating conversion-ready feedstocks from biomass meeting conversion process critical quality attribute (CQA) specifications. Failure Modes and Effects Analysis (FMEA) was used as an industrially relevant risk analysis approach to evaluate a logging residue preprocessing system to prepare feedstock for pyrolysis conversion. Risk evaluations considered both system-level and operation unit-level assessments considering process efficiency, product quality, cost, sustainability, and safety. Key outputs included estimations of semi-quantitative risk scores for each failure, identification of the failure impacts, identification of failure causes associated with material attributes and process parameters, ranking success rates of failure detection methods, and speculation of potential mitigation strategies for decreasing failure risk scores. Results showed that deviations from moisture specifications had cascading consequences for other CQAs along with process safety implications. Failures linked to fixed carbon specifications carried the highest risk scores for product quality and process efficiency impacts. As increased throughput can be inversely related to meeting product quality specifications; achieving throughput and other material-based CQAs simultaneously will likely require system optimization or prioritization based on system economics. Ultimately, this work successfully demonstrates FMEA as a risk analysis approach for other bioenergy process systems.

09 BIOMASS FUELS↗
DOE OSTI2026

Electronic Trap-State Modulation in Sm-Doped SnO 2 Nanofibers Enables Ultrasensitive Hydrogen Sensing

The demand for sub-ppm hydrogen (H 2 ) sensing is growing across emerging applications such as environmental monitoring, breath-based disease diagnostics, and early-stage battery failure detection. However, achieving reliable ppb-level detection with chemiresistive metal oxide sensors remains challenging. At trace gas concentrations, resistance modulation is often insufficient, particularly in the absence of noble metal catalysts. Here, we report samarium-doped tin dioxide (Sm-SnO 2 ) nanofibers in which electronic trap-state modulation is exploited to enable ultrasensitive hydrogen sensing. The 2 at% Sm-doped SnO 2 nanofibers exhibited markedly enhanced H 2 sensitivity, achieving clear detection down to 25 ppb H 2 at 200 °C, with a theoretical limit of detection of 4.5 ppb, placing this material among the most sensitive noble-metal-free SnO 2 -based H 2 sensors reported to date. Mechanistic investigations through X-ray photoelectron spectroscopy and electron energy loss spectroscopy revealed that Sm 3+ doping introduces deep trap states associated with charge-compensating defect complexes. These states reduce free carrier density, increase baseline resistance, and enable trap-assisted charge release during H 2 exposure, thereby amplifying the sensing response. Trap-state engineering via rare-earth doping, exemplified by Sm-SnO 2 , provides an effective pathway for achieving ppb-level hydrogen detection in noble-metal-free chemiresistive sensors.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Detecting Process Equipment Failures Using Acoustic Data and Machine Learning

Nuclear power plant (NPP) process equipment such as fans, motors, valves, and pumps generate frequent or continuous noise, and deviations from the normal operational sounds made by this equipment can indicate potential issues. These deviations can be identified via automated acoustic anomaly detection, which involves using acoustic sensors (i.e., microphones) alongside detection algorithms to continuously monitor for changes in acoustic signatures. This task is made challenging by the substantial background noise that exists, such as operators opening and closing doors, manipulating valves, and conversing—in addition to typical plant noises. In collaboration with a nuclear power utility partner, this effort assessed the efficacy of acoustic anomaly detection when using a specific acoustic sensor that compresses data into a fixed set of features that are transferable over a standard Internet of Things communication protocol, thereby improving usability but potentially degrading detection performance. Two methods of performing automated acoustic anomaly detection were evaluated: one-class support vector machine (OC-SVM) and isolation forest (iForest). To enable the use of high-quality acoustic data encompassing both normal and anomalous conditions, the study utilized the publicly available Malfunctioning Industrial Machine Investigation and Inspection dataset, which includes real measured acoustic sensor data for a range of equipment types, model numbers, and signal-to-noise ratios (SNRs), along with a benchmark set of detection results. Using this dataset, the methods were tested and then compared against the benchmark results. The results indicated that although the specific acoustic sensor did not enable as rich a feature set extraction, the proposed methods with the limited feature set performed just as well. This provides solid justification for both the methods and the use of the proposed acoustic sensor.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗
DOE OSTI2026

Automating Detection and Diagnosis of Faults, Failures, and Underperformance in PV Plants

The project developed hybrid physics-based and machine-learning methods for near-real-time detection of balance-of-system faults (e.g., string, combiner, and tracker outages) in utility-scale Photovoltaic plants, achieving over 50% true positive rates with under 10% false positives and significantly reducing engineering setup time. In the extended phase, the scope expanded to plant-level underperformance analysis and industry benchmarking through the SUPER.epri.com platform. SUPER standardizes data processing and performance metrics across more than 9 GWac and 120+ plants, enabling robust comparisons and insights into loss rates, inverter downtime, and capacity degradation.

14 SOLAR ENERGY↗
DOE OSTI2025

Investigating lab-scaled offshore wind aerodynamic testing failure and developing solutions for early anomaly detections

As offshore wind systems become more complex, the risk of human error or equipment malfunction increases during experimental testing. This study investigates a lab-scale incident involving a 1 : 50 scale 5 MW wind turbine, where a generator failure led to rotor overspeed and a blade–tower strike. To improve early fault detection, we propose a data-driven method based on multivariate long short-term memory (LSTM) models. High-frequency measurements are projected onto principal components, and anomalies are identified using reconstruction error and its time derivative. Two models are trained on different healthy datasets and tested using single- and multi-principal component (1PC and MPC) variations. Results show that combining both error and error derivative improves detection accuracy. The 1PC model detects faults faster, has a higher recall rate, and achieves a 43 % improvement in anomaly detection accuracy, while the MPC model yields higher precision. This approach provides a simple and effective tool for early anomaly detection in lab-scale experiments, helping to reduce the risk of future failures during the testing of new technologies.

17 WIND ENERGY↗
DOE OSTI2025

FIRE: A Failure-Adaptive RL Framework for Edge Computing Migrations

In edge computing, users' service profiles are migrated between edge servers due to user mobility. Reinforcement Learning (RL) frameworks have been proposed to do so, often trained on simulated data. However, existing RL frameworks overlook occasional server failures, which although rare, impact latency-sensitive applications like AR/VR and real- time obstacle detection. These rare failures, being not adequately represented in historical training data, pose a challenge for data-driven RL algorithms. We introduce FIRE, a framework that adapts to rare events by training a RL policy in an edge computing digital twin environment. We propose FIRE-ImRE, an importance sampling-based Q-learning algorithm, which samples rare events proportionally to their impact on the value function. FIRE considers delay, migration, failure, and backup placement costs across individual and shared service profiles. We prove FIRE-ImRE's boundedness and convergence to optimality. Next, we introduce novel deep Q-learning (FIRE-ImDQL) and actor critic (FIRE-ImACRE) versions of our algorithm to enhance scalability. Here, we extend our framework to accommodate users with varying risk tolerances of rare failure events. Through trace-driven experiments, we show that FIRE reduces edge computing costs compared to vanilla RL and the greedy baseline in the event of failures.

Edge computing↗
DOE OSTI2025

A survey on degradation modeling, prognosis, and prognostics-driven maintenance in wind energy systems

Wind energy generation proliferated over the past decades, introducing unique challenges and opportunities for failure prediction, operation and maintenance. Decision-makers are continuously looking into new methods to infer failure mechanisms and behaviors of wind turbine components to detect and intervene in the failures before they happen. Evidently, degradation modeling and prognosis become engaging topics for researchers and practitioners to prevent catastrophic failures. Prognostics-driven approaches predict the time of failure for the components (e.g., predicting remaining useful life), which provides significant insights for scheduling of operations and maintenance activities. Integrating these prognostics-driven insights into wind farm operations and maintenance presents a substantial challenge, demanding careful consideration of numerous factors such as accessibility, crew routing, and spare part logistics. This study provides state-of-the-art review for degradation modeling, prognosis, and prognostics-driven maintenance techniques for wind energy systems. The discussed techniques align with the United Nations' sustainable development goals, in particular Goal 7 (Affordable and Clean Energy), by enhancing effectiveness and sustainability of wind energy operations. This work also showcases open research questions related to degradation modeling, prognosis, and prognostics-driven maintenance.

Altinpulluk, Nur Banu↗
DOE OSTI2025

Enhanced Component Performance Study: Emergency Diesel Generators 1998-2024

This report presents an enhanced performance evaluation of the emergency power system (EPS) and high-pressure core spray (HPCS) emergency diesel generators (EDGs) at U.S. commercial nuclear power plants. This report evaluates component performance over time using (1) Institute of Nuclear Power Operations (INPO) Industry Reporting and Information System (IRIS) data from 1998 through 2024 and (2) maintenance unavailability performance data from Mitigating Systems Performance Index (MSPI) Basis Document data from 2002 through 2024. The objective is to show estimates of current failure probabilities and rates related to EDGs, trend these data on an annual basis, determine if the current data are consistent with the probability distributions currently recommended for use in Nuclear Regulatory Commission (NRC) probabilistic risk assessments, show how the reliability data differ for different EDG manufacturers and for EDGs with different ratings; and summarize the subcomponents, causes, detection methods, and recovery associated with each EDG failure mode. The EDG failure modes considered are fail to start (FTS), fail to load and run (FTLR), and fail to run after one hour of operation (FTR>1H). Engineering analyses were performed with respect to time-period and failure mode without regard to the actual number of EDGs at each plant. The factors analyzed include subcomponent, failure cause, detection method, recovery, manufacturer, and EDG rating. The following increasing trends were identified for EDGs for the most recent 10-year period: • EPS and HPCS EDG frequency of start demands (demands per reactor year) • EPS and HPCS EDG frequency of FTLR demands • EPS and HPCS EDG frequency of run>1H hours. The following decreasing trends were identified for EDGs for the most recent 10-year period: • EPS EDG FTR>1H failure rate • EPS EDG unreliability • EPS and HPCS EDG frequency of FTR>1H events (failures per reactor year).

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Extending Component Lifetime And Improving Inverter Reliability (ECLAIIR)

Inverter reliability remains one of the most persistent challenges limiting the performance, availability, and economic viability of utility‑scale photovoltaic (PV) plants. Industry data consistently show that inverters account for the highest share of corrective maintenance events and unplanned outages across PV fleets. These failures result in energy losses, increased O&M costs, and reduced confidence in long‑term solar asset performance. Motivated by these challenges, this project—Extending Component Lifetime and Improving Inverter Reliability (ECLAIIR)—was undertaken to systematically investigate inverter degradation and failure mechanisms, develop predictive maintenance capabilities, and establish data‑driven pathways to improve service life and reduce the Levelized Cost of Energy (LCOE) for large‑scale PV systems. The primary goal of the project was to identify pre‑failure signatures in string inverters using both lab‑based accelerated lifetime testing and field‑based data and to develop predictive maintenance algorithms that can anticipate inverter faults before they occur. Through collaboration with inverter testing laboratory, solar PV plant owner, and failure‑analysis experts, the project advanced the technical understanding of inverter reliability. By instrumenting inverters with thermistors, humidity sensors, power‑quality meters, and acoustic sensors, the research established how multiple sensing modalities can reliably detect deviations from normal behavior hours to days before failure. These findings substantially enhance scientific understanding of inverter failure kinetics and provide the PV industry with the most comprehensive cross‑OEM characterization of early‑stage failure indicators reported to date. Technically, the project demonstrated the effectiveness of predictive maintenance by developing and validating the PreDICT (Predictive Diagnostics of PV Inverters Using Condition Monitoring and Trend Analysis) framework—a multi‑layer diagnostic architecture combining peer‑to‑peer analytics, historical trend modeling, and advanced machine‑learning techniques such as the Sequential Conditional Variational Autoencoder (SCVAE). This predictive model achieved more than 90% accuracy in detecting pre‑failure conditions and provided up to four days of lead time before inverter failure in field scenarios. Economically, the project’s LCOE analysis showed that predictive maintenance can reduce lifetime energy losses and minimize corrective maintenance interventions. Modeling indicated that, depending on inverter failure rates and replacement timelines, predictive maintenance can significantly reduce LCOE impacts associated with inverter downtime: from as high as 19.4% under conventional maintenance strategies to 0.1%–10.17% when predictive analytics are adopted. These results confirm that predictive maintenance is both technically feasible and economically advantageous for utilities and plant operators. The project’s findings also have broad public benefit. By improving inverter reliability and reducing downtime, predictive maintenance directly increases electricity generation from existing PV assets. Enhanced reliability lowers operational costs for utilities, which can translate over time into lower energy costs for consumers. Furthermore, the project’s technical publications, conference presentations, and industry workshops ensure that knowledge gained is shared broadly across the solar industry, supporting workforce development and enabling utilities of all sizes to adopt modern asset‑health monitoring practices. The retrofitting case study and service‑life prediction framework further support informed decision‑making for aging PV fleets, helping operators extend system life and reduce electronic waste. In summary, the ECLAIIR project significantly advanced the state of knowledge on inverter degradation, demonstrated the technical and economic value of predictive maintenance, and delivered actionable tools and insights that support more reliable, cost‑effective, and sustainable PV plant operation. The outcomes of this project will continue to inform utility practices, guide inverter design improvements, and strengthen the long‑term performance of solar assets nationwide.

14 SOLAR ENERGY↗
DOE OSTI2025

Ultrasonic Characterization of Lithium Ion Thermal Runaway Conditions for Real-time Ultrasonic Enabled BMS Integration

The demand for energy storage is growing, and lithium-ion batteries are a promising technology to meet this need due to their high power/energy density, high round-trip efficiency, rapid response time, and portability. However, recent catastrophic events caused by thermal runaway have slowed their adoption, highlighting the need for an early warning system for battery failure. In this work, ultrasound is used to detect physical changes in 950 mAh batteries by identifying material property changes independent of voltage and current. [Ultrasound signal features (e.g., time of flight, maximum frequency component) were extracted as the batteries were cycled and subjected to both constant current and constant voltage overcharge and were used to develop two metrics identifying failure: a warning to detect the start of overcharge and an emergency stop (E-stop) to immediately take the battery out of service. The identification method involved locating magnitude differences of several ultrasound features compared to baseline operation considering different currents and temperatures, and the warning/stopping metrics were consistent across all experiments. For an average overcharge time of 140 minutes, the average warning was issued 124 minutes before the failure and the average E-stop was triggered 94 minutes before failure. As a test of using ultrasound for early warning detection, a battery was forced into overcharge and returned to normal cycling conditions based on the previously determined warning metric. Both the voltage profile and the ultrasound measurements returned to their baseline behavior, indicating that ultrasonic detection can not only identify battery failure before a catastrophic event, but can also provide early enough warnings such that overcharges can be detected and corrected quickly enough so the battery does not need to be decommissioned.]

25 ENERGY STORAGE↗
DOE OSTI2026

The future of subsurface monitoring: AEC’s breakthroughs in CCS technology

Carbon capture and storage (CCS) has emerged as a key solution in the fight against climate change. However, for CCS to succeed, it is crucial to ensure that the sequestered CO2 stays safely trapped underground. The U.S. Department of Energy (DOE) has emphasized the need for advancements in subsurface monitoring, measurement, reporting, and verification. Aside from caprock integrity failure, the other primary failure points usually involve defective cement in the casing annulus of wellbores or plugged and abandoned wells. In addition, many energy producers (e.g., oil and gas, geothermal) and storage and disposal operators (e.g., H2 and water) must deal with the same issue. Poorly placed or degraded cement can create pathways for gas or fluid to escape from casing annuli and in plugged and abandoned or orphan wells, posing environmental risks. Yet, a reliable and cost-effective way to monitor cement and well integrity over multiple decades is still unavailable. Traditional geophysical methods like 4D seismic imaging and surface-based electromagnetic monitoring lack the resolution and accuracy for detecting these types of failures (Vasco et al., 2022; Fawad and Mondol, 2021). Wireline logging is expensive to run continuously and is obtrusive to the operation. While fiber optics can potentially be a solution, its bulkiness can significantly compromise the cement's integrity. To address these challenges, the Advanced Energy Consortium (AEC) at The University of Texas at Austin’s Bureau of Economic Geology (the Bureau) has been pioneering research in subsurface monitoring using its portfolio of distributed autonomous microfabricated sensors for harsh subsurface environments since 2008. A class of these microsensors [System on a Chip (SoC)] can be mixed in cement and permanently placed without compromising the cement column; the sensors would then communicate with each other or a data acquisition (DAQ) master node. Another class of the AEC microsensors can be fully autonomous, with rechargeable micro-batteries capable of exceeding 100°C, flash memory, and, currently, a pressure and temperature sensor. They are designed to circulate in mud, geothermal fluids, U-loops, or pipelines. They can log data into memory and are unobtrusive to operations. Our team has been working on a multi-year DOE-funded project (DE-FE0031856)—supported by $2.95M in federal funding and $0.75M in cost-matching from the AEC—to demonstrate SoC sensor utility for CO2 leakage monitoring in CCS applications. This multi-institutional collaboration developed a novel sensing architecture utilizing radiofrequency (RF) microsensors embedded within the cement sheath. These sensors detect CO2 migration and are interrogated via a Smart Casing Collar (SCC).

58 GEOSCIENCES↗