SEARCH · Engineering Papers
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.
A system and method which partitions a parameter estimation model, a fault detection model, and a fault classification model for a process surveillance scheme into two or more coordinated submodels together providing improved diagnostic decision making for at least one determined operating mode of an asset.
Not Available
Classification of power system event data is a growing need, particularly where non-protective relaying-based sensors are used to monitor grid performance. Given the high burden of obtaining event data with appropriate labeling, an unsupervised approach is highly valuable. This approach enables using event data without labeling, which is far easier to obtain. This paper presents an unsupervised learning method to classify and label transients observed in the distribution grid. A Convolutional Variational Autoencoder (CVAE) was developed for this purpose. We demonstrate the efficacy of our approach using the transient data generated from the simulations. The simulation data is used to train the CVAE that identifies different faults as different clusters in the latent space. The clusters are then used as the foundation model to categorize the real-world data.
We survey how AI/ML is being deployed across Jefferson Lab's experimental and accelerator programs. In EPSCI, Hydra applies computer vision to automate real-time data-quality monitoring across all four experimental halls, replacing manual inspection of hundreds to thousands of histograms per shift. AIEC (AI Experiment Controls) uses ML to stabilize drift chamber gains and is now part of standard CEBAF production running, while AI Optimized Polarization (AIOP) targets autonomous control of polarized targets and photon beam angular alignment. In CASA, cavity fault classification models identify faulted cavities and trip types from waveform data with ~85% and ~78% agreement to labeled data, respectively, and are deployed in production; a separate effort applies LLMs and hybrid search to make the CEBAF operations logbook AI-ready. QCD-focused work includes transformer- and GAN-based generative models for particle-level event simulation, with distributed GAN training scaling studies on Polaris. Additional efforts span ML-on-FPGA for the EIC and a new Data Science Department coordinating anomaly detection, uncertainty quantification, and HPC-scalable ML lab-wide. Collectively, these projects illustrate AI's growing role in improving efficiency across JLab's nuclear physics mission.
In this paper, we propose a learning-based method utilizing the Soft Actor-Critic (SAC) algorithm to train a binary Support Vector Machine (SVM) classifier. This classifier is designed to identify valid input spaces in high-dimensional, highly constrained systems while minimizing the total runtime of offline simulations. The simulations adapt their runtime based on the likelihood that a given training input will be informative to the classifier. Furthermore, we introduce a method for using the trained SAC model to predict whether a desired system input is likely to violate constraints, along with a technique to adjust the input as necessary. Additionally, we explore the potential of this model to detect faults or adversarial attacks within the system. The effectiveness of our approach is demonstrated through various simulations of challenging classification problems and a constrained quadrotor model.
This paper introduces an extended taxonomy of faults specific to hybrid quantum-classical systems, addressing the unique challenges that arise from integrating quantum accelerators into high-performance computing (HPC) infrastructures. Building on the foundational fault classification by Avizienis et al., we incorporate fault types unique to quantum computing-such as qubit decoherence, spontaneous gate errors, and photon loss-alongside traditional and human-induced faults including development errors, operational mistakes, and malicious attacks. Our taxonomy classifies faults by their origin (natural vs. human-made), intent (accidental, deliberate non-malicious, or malicious), system boundaries (internal vs. external), and persistence (transient to permanent). We also explore how different architectural integration patterns-ranging from tight coupling to loose on-premise and cloud-based configurations-shape the manifestation and propagation of faults. These scenarios are analyzed in terms of timing mismatches, interface inconsistencies, and security threats such as data tampering and denial-of-service attacks. Through this fault-centric lens, we aim to support the co-design of dependable quantum-classical systems and highlight the critical role that integration strategies play in ensuring reproducibility, resilience, and security across hybrid computing platforms.
More than 81% of the annual capacity of utility-scale photovoltaic (PV) power plants in the U.S. use single-axis trackers (SATs) due to SATs delivering 4% in capacity factor on average over fixed-array systems. However, SATs are subject to faults, such as software misconfigurations and mechanical failures, resulting in suboptimal tracking. If left undetected, the overall power yield of the PV power plant is reduced significantly. Minimizing downtime and ensuring efficient operation of SATs requires robust detection and diagnosis mechanisms for SAT faults. We present a machine learning framework for implementing real-time SAT fault detection and classification. Our implementation of the proposed framework reliably identifies measurements taken from a test PV system undergoing emulated SAT faults relative to state-of-the-art algorithms and produces nearly zero false positives on our testing days. Code and data are available at https://pvpmc.sandia.gov/tools.
Microgrids are now a common practice in distribution systems to increase resilience and reliability. However, microgrid protection remains a critical challenge, considering its requirement to operate in both grid connected and islanded, and the variability in fault characteristics under each mode of operation. This paper presents unbalanced power (S unb ) based fault detection algorithm, which considers local voltage and current unbalances to determine faults in the system. S unb is a computationally efficient fault detection algorithm that is suitable for implementation in the programmable logic of entry level protective relays. In addition, the difference in current and voltage unbalance (D n ) is used to determine the fault type. The proposed method demonstrates high sensitivity and selectivity for line-to-ground (LG), line-to-line (LL), and double line-to-ground (LLG) faults, representing the most common faults in distribution systems. It also allows relay coordination with upstream and downstream protection devices in both island and grid connected operation, while preserving grading margins. The same pickup and time multiplier settings of a particular relay for both modes of operation eliminates the need for adaptive settings, which rely on communication networks. Validation was performed with a hardware-in-the-loop (HIL) setup using Typhoon HIL real time simulator interfaced with three entry-level, SEL 751 relays. Results confirmed the algorithm’s ability to discriminate fault conditions, and determine the fault type under both operating modes, maintain fast detection times, and ensure proper protection coordination.
No abstract available
Power system protection devices have transitioned over the past few decades from mechanical to analog devices, then to solid state and finally digital. Relays and their associated critical network of equipment have significantly increased in complexity. Even internally, relays have gained significant intricacy, with relatively simple overcurrent or differential functions now being assisted by a myriad of other functions. This is necessary as the grid becomes more complex, but it brings increased difficulty in monitoring and upkeep. Misoperation caused by accidental improper relay settings or deliberate malicious actions is a constant challenge faced by all utilities. These improper settings can be difficult to identify and may require exhaustive post-mortem analysis, typically after a major outage event has already occurred. A mechanism is needed for monitoring the behavior of protection systems to validate that their performance falls within expectations. Relays that fail to isolate a fault or trip when there is no system disturbance can be flagged for settings review in situations where this behavior may not have been noticed due to manual restoration or backup protection operations. This work presents a concept for a machine learning (ML) system capable of validating the performance of protection systems by identifying fault events and characterizing protection system responses based solely on available current and voltage measurements. As a first step in its development, an experimental dataset is generated, and a random forest model is implemented with high accuracy in distinguishing four power system scenarios.
As power system protection devices continue the widespread transition from analog to digital, they become increasingly intricate. The internal functions and communication between critical grid components must now be significantly more complex to keep up with the demands of the modern smart grid. This brings increased difficulty in maintenance and monitoring, making it harder to identify potential misoperation, power anomalies, and cyber threats. Such issues are often only pinpointed after an exhaustive and costly post-mortem analysis, when a major outage or damage has already occurred. A solution is needed for validating protection systems as they operate, independently evaluating grid state and confirming whether the protection system is behaving accordingly. As opposed to incident response, this acts as a constant verification mechanism that raises a flag when subtler issues are noticed, catching them earlier and preventing larger incidents. This work presents the implementation of such a system, expanding on the prototype developed by the authors in a previous paper. This is accomplished with a machine learning (ML) system capable of validating the performance of protection systems by classifying anomalous events and characterizing protection system responses based solely on available current and voltage measurements. Additionally, this system is contextualized within a larger, modular Master State awareness Overseer (MSO) framework, responsible for monitoring, analyzing, and managing an electric grid.
Automated fault detection is an increasingly important problem in aircraft maintenance and operation. Standard methods of fault detection assume the availability of either data produced during all possible faulty operation modes or a clearly-defined means to determine whether the data provide a reasonable match to known examples of proper operation. In the domain of fault detection in aircraft, identifying all possible faulty and proper operating modes is clearly impossible. We envision a system for online fault detection in aircraft, one part of which is a classifier that predicts the maneuver being performed by the aircraft as a function of vibration data and other available data. To develop such a system, we use flight data collected under a controlled test environment, subject to many sources of variability. We explain where our classifier fits into the envisioned fault detection system as well as experiments showing the promise of this classification subsystem.
This work is an extension of a recently developed software tool called MILD (Multi-level Immune Learning Detection), which implements a negative selection algorithm for anomaly and fault detection that is inspired by the human immune system. The immunity-based approach can detect a broad spectrum of known and unforeseen faults. We extend MILD by applying a neural network classifier to identify the pattern of fault detectors that are activated during fault detection. Consequently, MILD now performs fault detection and identification of the system under investigation. This paper describes the application of MILD to detect and classify faults of a generic transport aircraft augmented with an intelligent flight controller. The intelligent control architecture is designed to accommodate faults without the need to explicitly identify them. Adding knowledge about the existence and type of a fault will improve the handling qualities of a degraded aircraft and impact tactical and strategic maneuvering decisions. In addition, providing fault information to the pilot is important for maintaining situational awareness so that he can avoid performing an action that might lead to unexpected behavior - e.g., an action that exceeds the remaining control authority of the damaged aircraft. We discuss the detection and classification results of simulated failures of the aircraft's control system and show that MILD is effective at determining the problem with low false alarm and misclassification rates.
Receiver Operator Characteristic (ROC) curves are commonly applied as metrics for quantifying the performance of binary fault detection systems. An ROC curve provides a visual representation of a detection system s True Positive Rate versus False Positive Rate sensitivity as the detection threshold is varied. The area under the curve provides a measure of fault detection performance independent of the applied detection threshold. While the standard ROC curve is well suited for quantifying binary fault detection performance, it is not suitable for quantifying the classification performance of multi-fault classification problems. Furthermore, it does not provide a measure of diagnostic latency. To address these shortcomings, a novel three-dimensional receiver operator characteristic (3D ROC) surface metric has been developed. This is done by generating and applying two separate curves: the standard ROC curve reflecting fault detection performance, and a second curve reflecting fault classification performance. A third dimension, diagnostic latency, is added giving rise to 3D ROC surfaces. Applying numerical integration techniques, the volumes under and between the surfaces are calculated to produce metrics of the diagnostic system s detection and classification performance. This paper will describe the 3D ROC surface metric in detail, and present an example of its application for quantifying the performance of aircraft engine gas path diagnostic methods. Metric limitations and potential enhancements are also discussed
Power system protection devices have transitioned over the past few decades from mechanical to analog devices, then to solid state and finally digital. Relays and their associated critical network of equipment have significantly increased in complexity. Even internally, relays have gained significant intricacy, with relatively simple overcurrent or differential functions now being assisted by a myriad of other functions. This is necessary as the grid becomes more complex, but it brings increased difficulty in monitoring and upkeep. Misoperation caused by improper relay settings or malicious actions is a constant challenge faced by all utilities. These improper settings can be difficult to identify and may require exhaustive post-mortem analysis, typically after a major outage event has already occurred. A mechanism is needed for monitoring the behavior of protection systems to validate that they act and perform as expected. This work presents a concept for a machine learning (ML) system capable of validating the performance of protection systems by classifying anomalous events and characterizing protection system responses based solely on available current and voltage measurements. As a first step in its development, an experimental dataset is generated, and a random forest model is implemented with high accuracy in distinguishing four power system scenarios.
Automated fault detection is an increasingly important problem in aircraft maintenance and operation. Standard methods of fault detection assume the availability of either data produced during all possible faulty operation modes or a clearly-defined means to determine whether the data is a reasonable match to known examples of proper operation. In our domain of fault detection in aircraft, the first assumption is unreasonable and the second is difficult to determine. We envision a system for online fault detection in aircraft, one part of which is a classifier that predicts the maneuver being performed by the aircraft as a function of vibration data and other available data. We explain where this subsystem fits into our envisioned fault detection system as well its experiments showing the promise of this classification subsystem.
Automated fault detection is an increasingly important problem in aircraft maintenance and operation. Standard methods of fault detection assume the availability of either data produced during all possible faulty operation modes or a clearly-defined means to determine whether the data provide a reasonable match to known examples of proper operation. In the domain of fault detection in aircraft, the first assumption is unreasonable and the second is difficult to determine. We envision a system for online fault detection in aircraft, one part of which is a classifier that predicts the maneuver being performed by the aircraft as a function of vibration data and other available data. To develop such a system, we use flight data collected under a controlled test environment, subject to many sources of variability. We explain where our classifier fits into the envisioned fault detection system as well as experiments showing the promise of this classification subsystem.
This paper presents analytical techniques for aiding system designers in making aircraft engine health management sensor selection decisions. The presented techniques, which are based on linear estimation and probability theory, are tailored for gas turbine engine performance estimation and gas path fault diagnostics applications. They enable quantification of the performance estimation and diagnostic accuracy offered by different candidate sensor suites. For performance estimation, sensor selection metrics are presented for two types of estimators including a Kalman filter and a maximum a posteriori estimator. For each type of performance estimator, sensor selection is based on minimizing the theoretical sum of squared estimation errors in health parameters representing performance deterioration in the major rotating modules of the engine. For gas path fault diagnostics, the sensor selection metric is set up to maximize correct classification rate for a diagnostic strategy that performs fault classification by identifying the fault type that most closely matches the observed measurement signature in a weighted least squares sense. Results from the application of the sensor selection metrics to a linear engine model are presented and discussed. Given a baseline sensor suite and a candidate list of optional sensors, an exhaustive search is performed to determine the optimal sensor suites for performance estimation and fault diagnostics. For any given sensor suite, Monte Carlo simulation results are found to exhibit good agreement with theoretical predictions of estimation and diagnostic accuracies.