SEARCH · Search NASA
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.
This presentation will discuss the following topics: Understanding the benefits of automatic anomaly detection Identifying precursors with algorithms. Overcoming the challenges of data issues in automation.
This chapter will provide a thorough end-to-end description of the process for evaluation of three different data-driven algorithms for anomaly detection to select the best candidate for deployment as part of a suite of IVHM (Integrated Vehicle Health Management) technologies. These algorithms were deemed to be sufficiently mature enough to be considered viable candidates for deployment in support of the maiden launch of Ares I-X, the successor to the Space Shuttle for NASA's Constellation program. Data-driven algorithms are just one of three different types being deployed. The other two types of algorithms being deployed include a "nile-based" expert system, and a "model-based" system. Within these two categories, the deployable candidates have already been selected based upon qualitative factors such as flight heritage. For the rule-based system, SHINE (Spacecraft High-speed Inference Engine) has been selected for deployment, which is a component of BEAM (Beacon-based Exception Analysis for Multimissions), a patented technology developed at NASA's JPL (Jet Propulsion Laboratory) and serves to aid in the management and identification of operational modes. For the "model-based" system, a commercially available package developed by QSI (Qualtech Systems, Inc.), TEAMS (Testability Engineering and Maintenance System) has been selected for deployment to aid in diagnosis. In the context of this particular deployment, distinctions among the use of the terms "data-driven," "rule-based," and "model-based," can be found in. Although there are three different categories of algorithms that have been selected for deployment, our main focus in this chapter will be on the evaluation of three candidates for data-driven anomaly detection. These algorithms will be evaluated upon their capability for robustly detecting incipient faults or failures in the ground-based phase of pre-launch space shuttle operations, rather than based oil heritage as performed in previous studies. Robust detection will allow for the achievement of pre-specified minimum false alarm and/or missed detection rates in the selection of alert thresholds. All algorithms will also be optimized with respect to an aggregation of these same criteria. Our study relies upon the use of Shuttle data to act as was a proxy for and in preparation for application to Ares I-X data, which uses a very similar hardware platform for the subsystems that are being targeted (TVC - Thrust Vector Control subsystem for the SRB (Solid Rocket Booster)).
As aviation systems in commercial operations continue to grow in complexity, the anomalies exhibited by these systems become more elaborate and difficult to detect. To address the challenge of detecting these complex anomalies, deep learning models have been used extensively in aviation anomaly detection studies, at the expense of end-user interpretability. Aiming to maintain the same level of interpretability as traditional threshold-exceedance methods, we continue our development of prediction models using ordinal patterns and their distributions throughout the flight. Specifically, this study extends our work into multiclass anomaly detection using sensor fusion based on Dempster-Shafer theory (DST), a second-order probability theory used to combine information from different sources of evidence. Our approach uses DST toreduce the uncertainty in the class predictions of an ensemble of classifiers. These classifiers rely on the similarity between flight data and class templates to make a prediction of the state of the aircraft. Our approach aims to take advantage of simple models trained on interpretable features (ordinal patterns) to correctly predict an anomaly and identify the flight dynamics linked to the anomaly. Our results show an improvement when using DST-based sensor fusion over simple majority voting. Additionally, our results provide insight into aircraft states linked to rare high-risk anomalies.
Nonlinear observers were originally developed based on the ideas of variable structure control, and for the purpose of detecting disturbances in complex systems. In this anomaly detection application, these observers were designed for estimating the distributed state of fluid flow in a pipe described by a class of advection equations. The observer algorithm uses collected data in a piping system to estimate the distributed system state (pressure and velocity along a pipe containing liquid gas propellant flow) using only boundary measurements. These estimates are then used to further estimate and localize possible anomalies such as leaks or foreign objects, and instrumentation metering problems such as incorrect flow meter orifice plate size. The observer algorithm has the following parts: a mathematical model of the fluid flow, observer control algorithm, and an anomaly identification algorithm. The main functional operation of the algorithm is in creating the sliding mode in the observer system implemented as software. Once the sliding mode starts in the system, the equivalent value of the discontinuous function in sliding mode can be obtained by filtering out the high-frequency chattering component. In control theory, "observers" are dynamic algorithms for the online estimation of the current state of a dynamic system by measurements of an output of the system. Classical linear observers can provide optimal estimates of a system state in case of uncertainty modeled by white noise. For nonlinear cases, the theory of nonlinear observers has been developed and its success is mainly due to the sliding mode approach. Using the mathematical theory of variable structure systems with sliding modes, the observer algorithm is designed in such a way that it steers the output of the model to the output of the system obtained via a variety of sensors, in spite of possible mismatches between the assumed model and actual system. The unique properties of sliding mode control allow not only control of the model internal states to the states of the real-life system, but also identification of the disturbance or anomaly that may occur.
The use of residential heating, ventilation, and air conditioning (HVAC) to shift peak demand or provide ancillary services is a potential solution in the presence of older grids and distributed renewables. However, to ensure the efficient use of devices, utilities need to accurately forecast the load and adopt error correction schemes when necessary. While significant theoretical research exists in the area of predictive control of HVAC, little experimental evidence exists. The lack of experimental data in turn causes researchers to be unprepared for unsystematic errors which emerge due to the higher complexity of the data generating process. This study offers an anomaly detection methodology that uses unsupervised machine learning algorithms to detect and isolate these errors with different forecast error ranges. The results of anomaly detection procedure can then be used for error correction and would eventually help develop better predictive controllers. The methodology is tested using real world data from a smart neighborhood that currently operates in Atlanta. GA.
With the rapid evolution of malicious software, cyber threats have become increasingly sophisticated, employing advanced obfuscation techniques to evade traditional detection methods. This study presents a hybrid anomaly detection approach applied to obfuscated malware. Even though there is a large body of research in this field, existing malware detection techniques have some drawbacks, such as requiring large amounts of data, trustworthiness (imprecise results) of algorithms, and advanced obfuscation. To overcome these challenges, there is a need to employ solid and efficient techniques for malware detection. This paper proposes a hybrid approach, combining an autoencoder with traditional machine-learning methods to create an efficient malware detection framework. We used the malware memory dataset (MalMemAnalysis-2022) to evaluate this framework. The results indicate that our proposed approach can detect obfuscated malware when a deep autoencoder used for feature learning is combined with logistic regression, and it is extremely fast with an Accuracy, Detection Rate (DR), Matthew Correlation Coefficient(MCC), and Statistical Parity Difference
The ever-increasing use of information technology (IT) in health care presents new challenges to patient care. Information errors arising from the use of Health IT and their implications on care delivery and patient outcomes have been widely reported. Information errors can lead to changes in clinical decisions, care processes, and care outcomes, among others. An altered care process, for example, could interrupt the sequence of care, which could lead to changes in care decisions and/or changes in care outcomes. We define interruptions in the care process as anomalies in the care sequence. In this paper, we present a new approach based on the higher-order network (HON) representation to detect anomalies in sequential health care data using electronic health records. The results show that there are higher-order dependencies in health care data; and that the use of HON representation is more effective than the first-order network representation for detecting anomalies in sequential health care data.
The development of analysis methods to distinguish potential beyond the Standard Model phenomena in a model-agnostic way can significantly enhance the discovery reach in collider experiments. However, the typical machine learning (ML) algorithms employed for this task require fixed length and ordered inputs that break the natural permutation invariance in collision events. To address this, a semi-supervised anomaly detection tool is presented that takes a variable number of particle-level inputs and leverages a signal model to encode this information into a permutation invariant, event-level representation via supervised training with a Particle Flow Network (PFN). Data events are then encoded into this representation and given as input to an autoencoder for unsupervised ANomaly deTEction on particLe flOw latent sPacE (ANTELOPE), classifying anomalous events based on a low-level and permutation invariant input modeling. Performance of the ANTELOPE architecture is evaluated on simulated samples of hadronic processes in a high energy collider experiment, showing good capability to distinguish disparate models of new physics.
In a large hospital system, a network of hospitals relies on electronic health records (EHRs) to make informed decisions regarding their patients in various clinical domains. Consequently, the dependability of the health information technology (HIT) systems responsible for collecting EHR data is of utmost importance for patient safety. Recently, novel methods and tools aimed at identifying anomalies in EHR data to bolster the reliability of HIT systems have been introduced. However, these existing methods and tools primarily concentrate on individual hospitals, which limits our understanding of system-wide anomalous events and their potential impact on patient safety across multiple hospitals. In this article, we introduce a new approach to detecting anomalies in EHR data within a network of hospitals. This is achieved by combining advanced machine learning techniques with graph algorithms to create a tool capable of swiftly identifying and responding to deviations. Our proposed approach employs a combination of five machine learning models, harnessing the unique strengths of each model to provide a more robust detection system. The detected anomalies are then represented as graphs, allowing us to recognize patterns across the hospital network. This aids in identifying anomalies that span multiple medical facilities, potentially indicating broader system-level risks. Extensive real-world testing of our approach demonstrated its ability to offer actionable insights compared to existing methods. Additionally, its scalable design ensures seamless integration into existing HIT infrastructures.
The accuracy of distribution system state estimation may be significantly impacted by the existence of bad measure-ments and unexpected topology errors. This paper proposes a data-driven Graph Convolutional Network (GCN) for anomaly detection, including bad measurements and topology change events. Compared to many existing machine learning approaches, the proposed approach embeds both spatial-temporal measure-ment correlations, which allows us to detect and distinguish different anomalies. Numerical results carried out on the IEEE 37-node system demonstrate that the proposed-based method can obtain high accuracy in detecting bad data and topology changes as compared to other approaches, even in the presence of high PV penetrations.
The electric power grid is increasingly becoming susceptible to cyber attacks that exploit vulnerabilities in the smart grid control, information, and physical layers. Successful cyber attacks can have catastrophic impacts on the social and economic well-being of any nation all over the globe. It has, thus, become imperative to secure the smart grid against such adversarial actions to ensure stable, secure, and reliable operation of the grid. The existing research and industry practices prove to be inadequate in terms of providing pragmatic and effective defense methodologies and measures for long-term cybersecurity planning and real-time cybersecurity for grid operation. For example, existing works lack models that incorporate uncertain behavior of cyber-attackers and pragmatic defense measures for cyber risk assessment and cybersecurity investment optimization which often provide unreliable and strictly qualitative solutions to these problems. At the same time, with the growing number of cyber incidents in the grid, there still exists a need to develop attack-resilient algorithms for wide-area monitoring, protection, and control (WAMPAC) applications like the wide-area voltage control systems (WAVCS) for Flexible AC Transmissions Systems (FACTS) that lack in scalable and feasible solutions from the cybersecurity perspective. This dissertation proposes novel models and methodologies for: (1) Cybersecurity planning, and (2) Cybersecurity for system operation. The cybersecurity planning is achieved through cyber risk assessment and cybersecurity resource investment optimization for long-term cybersecurity of the grid using game theory and attack-defense trees. Cybersecurity for system operation consists of development of cyber anomaly detection and mitigation algorithms for flexible AC transmission system (FACTS) controller-based wide-area voltage control systems (WAVCS) using machine learning (ML), and software defined networking-based moving target defense network routing for achieving real-time cyber-physical security for grid operations. This is followed by hardware-in-the-loop (HIL) implementation and evaluation of these attack prevention, detection, and mitigation algorithms and methodologies showcasing their feasibility in a close to real-world environment. For cybersecurity planning, a novel approach involving a combination of game theory and attack defense trees (ADT) for optimal cybersecurity resource allocation in the smart grid is proposed. This methodology involves modeling of the cyber-physical smart grid substations as ADTs, defining attacker costs, defense costs, and attack probabilities for attack access points. Using game theoretical formulation, optimal defense strategies for the defender of the system to invest cybersecurity resources in the grid are obtained. Additionally, a game-theoretic framework is developed for quantitative cyber-physical risk assessment of the grid under a dynamically changing cyber threat space and uncertain behavior of cyber attackers which is further used to optimize investments in the smart grid's cybersecurity resources. The attacker, defender, and the smart grid system are modeled while incorporating attacker-stochasticity and federal guidelines for smart grid cybersecurity. This allows quantification of threat, vulnerabilities, and attack impact of the grid for quantitative risk assessment. The defender's budget to invest in the security resources in the grid is optimized based on the strategies leading to minimum system risk. The evaluation of the proposed solutions highlight the feasibility for practical implementation of these methodologies and algorithms in the smart grid, while taking the federal requirements and guidelines for smart grid security into consideration. For achieving cybersecurity for system operation, attack prevention, detection, and mitigation algorithms and methodologies are developed specifically for FACTS-based WAVCS. Anomaly detection and mitigation in the WAVCS are achieved using algorithms based on machine learning which involves offline training and testing of ML models with CPS datasets incorporating physics-based features that allow accurate distinction between system faults and cyber attacks. For attack prevention, a methodology based on software defined network (SDN)-based moving target defense (MTD) network routing is proposed that enables prevention of Denial of Service (DoS) type attacks on the smart grid communication system. Subsequently, these methodologies and algorithms are implemented and evaluated on an HIL testbed that allows for real-time attack prevention, detection, and mitigation of emulated cyber attacks on the WAVCS in a close to real-world environment. The results show highly accurate and efficient performance of the implemented algorithms and methodologies with the smart grid system operating within the NERC's system operation limits even in the presence of DoS and data integrity cyber attacks. This work opens up future research opportunities in other directions such as (1) Expanding cybersecurity planning methodologies to real-time cyber contingency analysis with different game formulations; and (2) Applying the cybersecurity for system operation algorithms to broader categories of wide-area control applications.
Machine learning and deep neural networks (DNNs) have been proposed as a tool to identify anomalies in computer network communications. However, due the obfuscated nature of off-the-shelf machine learning models, their output often does not provide enough information to isolate the source of the anomaly to take corrective measures. In this article, we introduce the network transformer (NeT), a DNN model for anomaly detection that incorporates the graph structure of the communication network in order to improve interpretability. Further, the presented approach has the following advantages: first, enhanced interpretability by incorporating the graph structure of computer networks; second, provides a hierarchical set of features that enables analysis at different levels of granularity; second, self-supervised training that does not require labeled data. The NeT model was evaluated on a set of anomalous scenarios executed in a real industrial control system. The presented approach successfully identified the anomalies, the devices affected, and the specific connections causing the anomalies, providing a data-driven hierarchical approach to analyze the behavior of a cyber network.
As aviation systems in commercial operations continue to grow in complexity, the anomalies exhibited by these systems become more elaborate and difficult to detect. To address the challenge of detecting these complex anomalies, deep learning models have been used extensively in aviation anomaly detection studies, at the expense of end-user interpretability. Aiming to maintain the same level of interpretability as traditional threshold-exceedance methods, we continue our development of prediction models using ordinal patterns and their distributions throughout the flight. Specifically, this study extends our work into multiclass anomaly detection using sensor fusion based on Dempster-Shafer theory (DST), a second-order probability theory used to combine information from different sources of evidence. Our approach uses DST to reduce the uncertainty in the class predictions of an ensemble of classifiers. These classifiers rely on the similarity between flight data and class templates to make a prediction of the state of the aircraft. Our approach aims to take advantage of simple models trained on interpretable features (ordinal patterns) to correctly predict an anomaly and identify the flight dynamics linked to the anomaly. Our results show an improvement when using DST-based sensor fusion over simple majority voting. Additionally, our results provide insight into aircraft states linked to rare high-risk anomalies.
This report summarizes the design and pilot demonstration of a framework called Grid Guard that was created to provide increased data and device trustworthiness to electric grid devices by leveraging distributed ledger technology (DLT), specifically blockchain. Grid Guard contains a combination of core cryptographic methods such as the secure hash algorithm (SHA), and asymmetric cryptography, private permissioned blockchain, baselining configuration data, consensus algorithm (Raft) and the Hyperledger Fabric (HLF) framework. The system implements a low energy, fast, and robust enhancement to system trustworthiness within and across electric grid systems such as substations, control centers and metering infrastructures. Blockchain is a distributed database structured that provides a practically unalterable (immutable) timeline of stored transactions. By relying on hashing and the Raft consensus algorithm, if an entity tries to illegitimately alter a record at one instance of the database the other ledger nodes are not altered. They work to cross-reference each other and easily locate any incorrectly added data and remove it. The bulk raw data is stored in an off-chain storage (outside of the blockchain ledger) and a hash of this baseline data is stored in the Blockchain ledger via hashing windows of time-series and configuration data, after aggregation and filtering. The bulk off-chain data repository is then considered to be trust-anchored using the hashes stored in the blockchain. To secure the electric grid testbed devices and data, device configuration baselines were compared to those baselines that had been previously stored in the ledger. Statistical baselines for device configurations, network communication patterns, and high-speed sensor data are calculated and then stored off-chain and hashes stored in the ledger. Measurements such as three-phase voltage and current, frequency, breaker status, protection scheme settings, network configuration settings (and other device configuration artifacts) and network traffic features (packet interarrival times) are compared every minute or other selected time windows. During phase 1 of the Grid Guard DLT project different DLT technologies were studies, and an assessment was performed on DLT technology vulnerabilities, uses, and key characteristics. DLT consensus protocols were studies (e.g., RAFT, named after Reliable, Replicated, Redundant, And Fault-Tolerant). Also, cryptography, public, private and permissioned or permissionless systems were assessed. Grid Guard implements a permissioned private DLT. Consensus algorithm selection and choice of DLT implementation depended heavily on the use-case. For this use-case, parameters were selected to measure performance and existing tools for assessment. Benchmarking was performed theoretically and practically. During phase 2 hashed transactions/blocks were inserted into the ledger every second. During phase 2 of the Grid Guard DLT project, a prototype framework was developed and demonstrated for attestation of critical substation devices and data using precision timing systems that use PTP and IRIG-B protocols) on a testbed of operational devices that emulated a distribution substation, control center, and power metering infrastructure using real Operational Technology (OT). The testbed includes OT devices such as protective relays, human machine interfaces (HMI), and power meters. To determine when to collect and compare system and network baselines, an initial examination of an anomaly detection capability to identify malicious manipulation of data streams was conducted. The resulting anomaly detection was demonstrated in a set of experiments and leveraged to trigger device artifact attestation checks. Attestation checks occur against device configuration baselines when compared with the immutable blockchain-stored baselines, which provided a cryptographically supported means by which to store baselines. The electrical substation-grid testbed was created to test the Grid Guard framework. The testbed emulates the operations of a portion of a power grid and SCADA systems as closely as possible. The testbed integrates real protocols, mainly IEC 61850 standard protocols, such as the Sampled Value (SV) and the GOOSE protocols. The testbed also supports DNP3 and other layer 2 and layer 3 protocols such as Telnet, SSH, SFTP/FTP and other proprietary protocols needed to connect to industrial control system equipment. The testbed emulates real power conditions using the OpalRT hardware-in-the-loop (HIL) device which can create fault situations that cannot be easily tested on real systems. The electrical substation-grid testbed was created using real measurement, communication, and protection devices that electrical utilities commonly use.
Abstract With the ongoing development of Distributed Energy Resources (DER) communication networks, the imperative for strong cybersecurity and data privacy safeguards is increasingly evident. DER networks, which rely on protocols such as Distributed Network Protocol 3 and Modbus, are susceptible to cyberattacks such as data integrity breaches and denial of service due to their inherent security vulnerabilities. This paper introduces an innovative Federated Learning (FL)‐based anomaly detection system designed to enhance the security of DER networks while preserving data privacy. Our models leverage Vertical and Horizontal Federated Learning to enable collaborative learning while preserving data privacy, exchanging only non‐sensitive information, such as model parameters, and maintaining the privacy of DER clients' raw data. The effectiveness of the models is demonstrated through its evaluation on datasets representative of real‐world DER scenarios, showcasing significant improvements in accuracy and F1‐score across all clients compared to the traditional baseline model. Additionally, this work demonstrates a consistent reduction in loss function over multiple FL rounds, further validating its efficacy and offering a robust solution that balances effective anomaly detection with stringent data privacy needs.
NASA is developing new capabilities that will enable future human exploration missions while reducing mission risk and cost. The Fault Detection, Isolation, and Recovery (FDIR) project aims to demonstrate the utility of integrated vehicle health management (IVHM) tools in the domain of ground support equipment (GSE) to be used for the next generation launch vehicles. In addition to demonstrating the utility of IVHM tools for GSE, FDIR aims to mature promising tools for use on future missions and document the level of effort - and hence cost - required to implement an application with each selected tool. One of the FDIR capabilities is anomaly detection, i.e., detecting off-nominal behavior. The tool we selected for this task uses a data-driven approach. Unlike rule-based and model-based systems that require manual extraction of system knowledge, data-driven systems take a radically different approach to reasoning. At the basic level, they start with data that represent nominal functioning of the system and automatically learn expected system behavior. The behavior is encoded in a knowledge base that represents "in-family" system operations. During real-time system monitoring or during post-flight analysis, incoming data is compared to that nominal system operating behavior knowledge base; a distance representing deviation from nominal is computed, providing a measure of how far "out of family" current behavior is. We describe the selected tool for FDIR anomaly detection - Inductive Monitoring System (IMS), how it fits into the FDIR architecture, the operations concept for the GSE anomaly monitoring, and some preliminary results of applying IMS to a Space Shuttle GSE anomaly.
Physics beyond the Standard Model that is resonant in one or more dimensions has been a longstanding focus of countless searches at colliders and beyond. Recently, many new strategies for have been developed, where sideband information can be used in conjunction with modern machine learning, in order to generate synthetic datasets representing the Standard Model background. Until now, this approach was only able to accommodate a relatively small number of dimensions, limiting the breadth of the search sensitivity. Using recent innovations in point cloud generative models, we show that this strategy can also be applied to the full phase space, using all relevant particles for the anomaly detection. As a proof of principle, we show that the signal from the R&D dataset from the LHC Olympics is findable with this method, opening up the door to future studies that explore the interplay between depth and breadth in the representation of the data for anomaly detection. Published by the American Physical Society 2024
Big Area Additive Manufacturing (BAAM) of composites requires significant time, energy, and material, so it is critical to reduce production inefficiencies to make functional parts without multiple iterations. Statistical process control coupled with Principal Component Analysis (PCA) is a powerful technique that provides a quick, computationally inexpensive, and intuitive way for operators to detect defects that form in a manufacturing process without massive datasets. Recently, a combined index that is a weighted sum of the Hotelling's T 2 and squared residual error statistics has been proposed that can be monitored in one chart, improving interpretation accuracy and simplicity. However, the literature does not offer a formal method to optimise the weights. Here, we introduce two new approaches to the traditional weight selection approach using simulated and BAAM image data. Approach 1 uses a theoretically motivated optimum inspired by probabilistic principal component analysis. Approach 2 systematically varies the ratio of the weights to find the optimum. We show that approach 1 delivers optimal anomaly detection performance in select cases while approach 2 fares better in practice. Surprisingly, we also show that choosing a more complex PCA model has a minimal negative impact on anomaly detection performance compared to a more simplistic model.