Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learning based systems”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Climatology of Linear Mesoscale Convective System Morphology in the United States based on Random Forests Method

This study uses machine learning methods, specifically the random forest (RF), on a radar-based mesoscale convective system (MCS) tracking dataset to classify the five types of linear MCS morphology in the contiguous United States during the period 2004-2016. The algorithm is trained using radar- and satellite-derived spatial and morphological parameters, and reanalysis environmental information from 5-26yr manually identified nonlinear and five linear MCS modes. The algorithm is then used to automate the classification of linear MCSs over 8 years with high accuracy, providing a systematic, long-term climatology of linear MCSs. Results reveal that nearly 40% of MCSs are classified as linear MCSs, in which half of the linear events belong to the type of system having a leading convective line. The occurrence of linear MCSs shows large annual and seasonal variations. On average, 113 linear MCSs occur annually during the warm season (through March to October), with most of these events clustered from May through August in the central eastern Great Plains. MCS characteristics, including duration, propagation speed, orientation, and system cloud size, have large variability among the different linear modes. The systems having a trailing convective line and the systems having a back-building area of convection typically move more slowly and have higher precipitation rate, and thus have higher potential in producing extreme rainfall and flash flooding. Analysis of the environmental conditions associated with linear MCSs show that the storm-relative flow is of most importance in determining the organization mode of linear MCSs.

Cui, Wenjun↗
NASA NTRS2019

Evaluation of Technology Concepts for Traffic Data Management and Relevant Audio for Datalink in Commercial Airline Flight Decks

Datalink is currently operational for departure clearances and in oceanic environments and is currently being tested in high altitude domestic enroute airspace. Interaction with even simple datalink clearances may create more workload for flight crews than the voice system they replace if not carefully designed. Datalink may also introduce additional complexity for flight crews with hundreds of uplink messages now defined for use. Finally, flight crews may lose airspace awareness and operationally relevant information that they normally pickup from Air Traffic Control (ATC) voice communications with other aircraft (i.e., “party-line” transmissions). Once again, automation may be poised to increase workload on the flight deck for incremental benefit. Datalink implementation to support future air traffic management concepts needs to be carefully considered, understanding human communication norms and especially, the change from voice- to text-based communications modality and its effect on pilot workload and situation awareness. Increasingly autonomous systems, where autonomy is designed to support human-autonomy teaming, may be suited to solve these issues. NASA is conducting research and development of increasingly autonomous systems, utilizing machine-learning algorithms seamlessly integrated with humans whereby task performance of the combined system is significantly greater than the individual components. Increasingly autonomous systems offer the potential for significantly improved levels of performance and safety that are superior to either human or automation alone. Two increasingly autonomous systems concepts - a traffic data manager and a conversational co-pilot - were developed to intelligently address the datalink issues in a complex, future state environment with significant levels of traffic. The system was tested for suitability of datalink usage for terminal airspace. The traffic data manager allowed for automated declutter of the Automatic Dependent Surveillance-Broadcast (ADS-B) display. The system determined relevant traffic for display based on machine learning algorithms trained by experienced human pilot behaviors. The conversational co-pilot provided relevant audio air traffic control messages based on context and proximity to ownship. Both systems made use of the connected aircraft concepts to provide intelligent context to determine relevancy above and beyond proximity to ownship. A human-in-the-loop test was conducted in NASA Langley Research Center’s Integration Flight Deck B-737-800 simulator to evaluate the traffic data manager and the conversational co-pilot. Twelve airline crews flew various normal and non-normal procedures and their actions and performance were recorded in response to the procedural events. This paper details the flight crew performance and evaluation during the events.

Etherington, Timothy↗
DOE OSTI2020

Real-time Intrusion Detection for High-bandwidth Research Networks using Unsupervised Deep Learning

Nowadays, data generated by large-scale scientific experiments are on the scale of petabytes per month. These data are transferred through dedicated high-bandwidth networks across distributed collaboration sites for processing, storage, and analysis. Like general purpose networks, research networks experience attacks. However, monitoring traffic in such high-bandwidth network environments is challenging with conventional deep packet inspection (DPI)- based network intrusion detection systems (NIDS). Recently, machine learning (ML) algorithms have shown potential in detecting anomalous patterns with better generalizability and faster speed. Compared to the general purpose networks, traffic movement in research network is less volatile and more likely to benefit from the ML-based anomaly analysis. We present ThunderSecure, an efficient AI-powered system for detecting anomalies in 100G research networks. ThunderSecure implements a high-throughput packet processing infrastructure using multi-cores and GPUs. It takes time-series statistics from a variety of network measurements and uses 2D Convolutional Neural Network (CNN) to explore both spatial and temporal dependencies in network data stream. Patterns of science data traffic are learned with a one-class neural network, which blends an Adversarial Autoencoder (AAE) with Gaussian mixture density estimation. Testing traffic flows exhibiting significant deviations from the learned baseline of normality are marked as anomalies. We trained ThunderSecure on hundreds of billions of science data packets recorded from a 100G research network at Fermi National Accelerator Laboratory. The detection performance was evaluated on traffic captured from the same research network days and weeks after the training with different types of attack flows injected. To the best of our knowledge, this is the first ML work in the area of network anomaly detection that has been validated on such extreme scale datasets. Results show that ThunderSecure can recognize science data traffic that are captured long after the training and make nearly certain detection on those with anomalous flows injected, even in the case when the anomaly-to-normal mixing ratio is 0.1%.

Gong, Qian↗
DOE OSTI2021

Ensemble Learning Based Convex Approximation of Three-Phase Power Flow

Though the convex optimization has been widely used in power systems, it still cannot guarantee to yield a tight (accurate) solution to some problems. To mitigate this issue, this paper proposes an ensemble learning based convex approximation for alternating current (AC) power flow equations that differs from the existing convex relaxations. The proposed approach is based on three-phase quadratic power flow equations in rectangular coordinates. To develop this data-driven convex approximation of power flows, the polynomial regression (PR) is first deployed as a basic learner to fit convex relationships between the independent and dependent variables. Then, ensemble learning algorithms such as gradient boosting (GB) and bagging are introduced to combine learners to boost model performance. Based on the learned convex approximation of power flow, optimal power flow (OPF) is formulated as a convex quadratic programming problem. The simulation results on IEEE standard cases of both balanced and unbalanced systems show that, in the context of solving OPF, the proposed data-driven convex approximation outperforms the conventional semi-definite programming (SDP) relaxation in both accuracy and computational efficiency, especially in the cases that the conventional SDP relaxation fails

Convex approximation↗
NASA NTRS1996

Automated Decomposition of Model-based Learning Problems

A new generation of sensor rich, massively distributed autonomous systems is being developed that has the potential for unprecedented performance, such as smart buildings, reconfigurable factories, adaptive traffic systems and remote earth ecosystem monitoring. To achieve high performance these massive systems will need to accurately model themselves and their environment from sensor information. Accomplishing this on a grand scale requires automating the art of large-scale modeling. This paper presents a formalization of [\em decompositional model-based learning (DML)], a method developed by observing a modeler's expertise at decomposing large scale model estimation tasks. The method exploits a striking analogy between learning and consistency-based diagnosis. Moriarty, an implementation of DML, has been applied to thermal modeling of a smart building, demonstrating a significant improvement in learning rate.

Williams, Brian C.↗
DOE OSTI2021

Assessing Adaptive Irrigation Impacts on Water Scarcity in Nonstationary Environments—A Multi‐Agent Reinforcement Learning Approach

Abstract One major challenge in water resource management is to balance the uncertain and nonstationary water demands and supplies caused by the changing anthropogenic and hydroclimate conditions. To address this issue, we developed a reinforcement learning agent‐based modeling (RL‐ABM) framework where agents (agriculture water users) are able to learn and adjust water demands based on their interactions with the water systems. The intelligent agents are created by a reinforcement learning algorithm adapted from the Q‐learning algorithm. We illustrated this framework in a case study where the RL‐ABM is two‐way coupled with the Colorado River Simulation System (CRSS), a long‐term planning model used for the administration of the Colorado River Basin, for assessing agriculture water uses impacts on water scarcity. Seventy‐eight intelligent agents are simulated, which can be grouped into three categories based on their parameter values: the “aggressive” (swift actions; low regrets), the “forward‐looking conservative” (mild actions; high regrets; fast learning), and the “myopic conservative” (mild actions; median regrets; slow learning). The ABM‐CRSS results showed that the major reservoirs in the Upper Colorado Basin might experience more frequent water shortages due to the increasing water uses compared to the original CRSS results. If the drought continues, the case study also demonstrates that agents can learn and adjust their demands.

Hung, Fengwei↗
DOE OSTI2024

Learning model combining convolutional deep neural network with a self-attention mechanism for AC optimal power flow

Alternating current optimal power flow (OPF) analysis is critical for efficient and reliable operation of power systems. For large systems or repetitive computations, the traditional methods such as the direct and gradient methods, or non-traditional methods, such as the genetic algorithm and simulating annealing, are time-consuming and unsuitable for real-time computing. The work in this paper proposes a novel framework to obtain the optimal solution of power flow in real-time using a combination of convolutional neural networks and a self-attention mechanism. All parameters of the power networks are rearranged in an image-like shape of a multi-channel image where each channel is a two-dimensional matrix. The proposed approach is adaptive with every input size of power systems as well as frequent variations of network topologies without intervention to the framework core. The encompassment of all power system contexts in which all parameters of internal elements, generation costs, and topology information are included, contributes to the higher accuracy of inference compared to other current machine-learning-based OPF-solving methods. Besides, the proposed framework established on ubiquitous platforms is effortlessly integrated into current infrastructures of power systems, and the great efficiency along with the computation speed may serve as a critical point for practical implications, such as enabling faster decision-making during real-time operations, predicting system contingencies, and remedial actions based on an offline pre-trained model. Furthermore, this supervised learning process is applied to the dataset of four case studies of meshed power systems: the IEEE 5-bus system (IEEE-5), the IEEE 30-bus system (IEEE-30), the IEEE 39-bus system (IEEE-39), and the IEEE 57-bus system (IEEE-57) to prove the efficacy of the proposed method.

42 ENGINEERING↗
DOE OSTI2025

ELM2.1-XGBfire1.0: improving wildfire prediction by integrating a machine learning fire model in a land surface model

Wildfires have shown increasing trends in both frequency and severity across the contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth system models (ESMs). Alternatively, fire models based on machine learning (ML), which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ELM2.1-XGBFire1.0) that integrates an eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM) version 2.1. A Fortran–C–Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001–2019, the ELM2.1-XGBFire1.0 outperforms process-based fire models in terms of spatial distribution and seasonal variations. The ELM2.1-XGBFire1.0 has proven to be a new tool for studying vegetation–fire interactions and, more importantly, enables seamless exploration of climate–fire feedback, working as an active component of E3SM.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Machine Learning Based Resilience Testing of an Address Randomization Cyber Defense

Moving target defenses (MTDs) are widely used as an active defense strategy for thwarting cyberattacks on cyber-physical systems by increasing diversity of software and network paths. Recently, machine Learning (ML) and deep Learning (DL) models have been demonstrated to defeat some of the cyber defenses by learning attack detection patterns and defense strategies. It raises concerns about the susceptibility of MTD to ML and DL methods. Here, in this article, we analyze the effectiveness of ML and DL models when it comes to deciphering MTD methods and ultimately evade MTD-based protections in real-time systems. Specifically, we consider a MTD algorithm that periodically randomizes address assignments within the MIL-STD-1553 protocol—a military standard serial data bus. Two ML and DL-based tasks are performed on MIL-STD-1553 protocol to measure the effectiveness of the learning models in deciphering the MTD algorithm: 1) determining whether there is an address assignments change i.e., whether the given system employs a MTD protocol and if it does 2) predicting the future address assignments. The supervised learning models (random forest and k-nearest neighbors) effectively detected the address assignment changes and classified whether the given system is equipped with a specified MTD protocol. On the other hand, the unsupervised learning model (K-means) was significantly less effective. The DL model (long short-term memory) was able to predict the future addresses with varied effectiveness based on MTD algorithm's settings.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2024

Topological Interpretability for Deep Learning

With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based decision systems is an increasing concern, especially in high-risk systems such as criminal justice or medical diagnosis, where incorrect inferences may have tragic consequences. Despite their successes in providing solutions to problems involving real-world data, deep learning (DL) models cannot quantify the certainty of their predictions. These models are frequently quite confident, even when their solutions are incorrect. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text by employing techniques from topological and geometric data analysis. We create a graph of a model's feature space and cluster the inputs into the graph's vertices by the similarity of features and prediction statistics. We then extract subgraphs demonstrating high-predictive accuracy for a given label. These subgraphs contain a wealth of information about features that the DL model has recognized as relevant to its decisions. We infer these features for a given label using a distance metric between probability measures, and demonstrate the stability of our method compared to the LIME and SHAP interpretability methods. This work establishes that we may gain insights into the decision mechanism of a DL model. This method allows us to ascertain if the model is making its decisions based on information germane to the problem or identifies extraneous patterns within the data.

Spannaus, Adam↗
DOE OSTI2024

Towards intelligent emergency control for large-scale power systems: Convergence of learning, physics, computing and control

Here, this paper has delved into the pressing need for intelligent emergency control in large-scale power systems, which are experiencing significant transformations and are operating closer to their limits with more uncertainties. Learning-based control methods are promising and have shown effectiveness for intelligent power system control. However, when they are applied to large-scale power systems, there are multifaceted challenges such as scalability, adaptiveness, and security posed by the complex power system landscape, which demand comprehensive solutions. The paper first proposes and instantiates a convergence framework for integrating power systems physics, machine learning, advanced computing, and grid control to realize intelligent grid control at a large scale. Our developed methods and platform based on the convergence framework have been applied to a large (more than 3000 buses) Texas power system, and tested with 56 000 scenarios. Our work achieved a 26% reduction in load shedding on average and outperformed existing rule-based control in 99.7% of the test scenarios. The results demonstrated the potential of the proposed convergence framework and DRL-based intelligent control for the future grid.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Deciphering Degradation: Machine Learning on Real-World Performance Data (Final Report)

This project addresses a fundamental flaw in solar PV research and solar project financing; the assumed rate of degradation for solar plants. The solar industry currently relies on an out-dated report that observed a 0.5% degradation rate based on a small sample size of systems (~100). While the research conducted at the time was new and innovative, the solar community has not updated this research and universally applies this 0.5% degradation assumption in financial models. Our project updates this assumption by analyzing observed degradation from the industry’s largest dataset of operating solar assets (>10,000 systems) and creating the first machine-learning model based on these observed results to quantify and identify features that drive degradation. There are two strategic goals for this award: reduce the cost of capital (enable solar to attract more capital) and improve the reliability of solar itself. These dual goals are achieved by leveraging an industry dataset to observe system degradation on a large scale, deploying advanced data analysis and machine learning methods to quantify and predict system reliability, and engaging with industry stakeholders to help them accurately price degradation in financial models.

14 SOLAR ENERGY↗
DOE OSTI2018

Minimizing Barriers in Learning for On-Call Radiology Residents—End-to-End Web-Based Resident Feedback System

Feedback is an essential part of medical training, where trainees are provided with information regarding their performance and further directions for improvement. In diagnostic radiology, feedback entails a detailed review of the differences between the residents’ preliminary interpretation and the attendings’ final interpretation of imaging studies. While the on-call experience of independently interpreting complex cases is important to resident education, the more traditional synchronous “read-out” or joint review is impossible due to multiple constraints. Without an efficient method to compare reports, grade discrepancies, convey salient teaching points, and view images, valuable lessons in image interpretation and report construction are lost. We developed a streamlined web-based system, including report comparison and image viewing, to minimize barriers in asynchronous communication between attending radiologists and on-call residents. Our system provides real-time, end-to-end delivery of case-specific and user-specific feedback in a streamlined, easy-to-view format. We assessed quality improvement subjectively through surveys and objectively through participation metrics. Our web-based feedback system improved user satisfaction for both attending and resident radiologists, and increased attending participation, particularly with regards to cases where substantive discrepancies were identified.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2020

Reinforcement-based Program Induction in a Neural Virtual Machine

We present a neural virtual machine that can be trained to perform algorithmic tasks. Rather than combining a neural controller with non-neural memory storage as has been done in the past, this architecture is purely neural and emulates tape-based memory via fast associative weights (onestep learning). Here we formally define the architecture, and then extend the system to learn programs using recurrent policy gradient reinforcement learning based on examples of program inputs labeled with corresponding output targets, which are compared against actual output to generate a sparse reward signal. We describe the policy gradient training procedure used, and report its empirical performance on a number of smallscale list processing tasks, such as finding the maximum list element, filtering out certain elements, and reversing the order of the elements. These results show that program induction via reinforcement learning is possible using sparse rewards and solely neural computations.

Katz, Garrett E.↗
NASA NTRS1999

Reinforcement Learning in a Nonstationary Environment: The El Farol Problem

This paper examines the performance of simple learning rules in a complex adaptive system based on a coordination problem modeled on the El Farol problem. The key features of the El Farol problem are that it typically involves a medium number of agents and that agents' pay-off functions have a discontinuous response to increased congestion. First we consider a single adaptive agent facing a stationary environment. We demonstrate that the simple learning rules proposed by Roth and Er'ev can be extremely sensitive to small changes in the initial conditions and that events early in a simulation can affect the performance of the rule over a relatively long time horizon. In contrast, a reinforcement learning rule based on standard practice in the computer science literature converges rapidly and robustly. The situation is reversed when multiple adaptive agents interact: the RE algorithms often converge rapidly to a stable average aggregate attendance despite the slow and erratic behavior of individual learners, while the CS based learners frequently over-attend in the early and intermediate terms. The symmetric mixed strategy equilibria is unstable: all three learning rules ultimately tend towards pure strategies or stabilize in the medium term at non-equilibrium probabilities of attendance. The brittleness of the algorithms in different contexts emphasize the importance of thorough and thoughtful examination of simulation-based results.

Bell, Ann Maria↗
DOE OSTI2022

High-fidelity model-driven deception platform for cyber-physical systems

A system is described for protecting a cyber-physical system against a potential attacker of the cyber-physical system. The system includes at least one processor configured to: collect historical information about the cyber-physical system, and train, based on the historical information, a machine-learned model to predict future conditions of at least a portion of the cyber-physical system. Responsive to detecting an input signal to the cyber-physical system, the system is configured to output an alert to the cyber-physical system indicative of a potential attacker, and respond to the input signal by simulating, based on the future conditions predicted by the machine-learned model, functionality and communications of the at least a portion of the cyber-physical system.

Edgar, Thomas W.↗
DOE OSTI2023

Bayesian GAN-Based False Data Injection Attack Detection in Active Distribution Grids With DERs

Advancements in information and communication technologies have revolutionized monitoring and control capabilities within smart grids. However, it also brings new vulnerabilities to data acquisition systems and state estimation functions, which attackers can subtly tamper with the measurement data through compromising the communication network. Moreover, the high penetration of renewable energy sources with the inherited characteristics of uncertainty and variability further complicates the design of effective intrusion detection systems. In this paper, a Bayesian deep learning-based approach is developed to detect cyber attacks and maintain the security of smart grids. Our method specifically addresses the prevalent issue of imbalanced data in real power systems, which arises from the predominance of normal system operations over compromised or attacked states. Employing a novel Bayesian GAN-based technique, our approach successfully discriminates between secure and compromised measurement data, even in scenarios with significant data imbalance. Furthermore, the proposed method accommodates various practical application factors, ensuring accurate intrusion detection despite the presence of measurement noise. The feasibility and effectiveness of the proposed detection mechanism are validated by testing on IEEE 13-node and 123-node test systems. Simulation results and comparisons with literature methods demonstrate the superiority of proposed cybersecurity solutions.

Bayesian GAN↗
NASA NTRS1993

The Generic Spacecraft Analyst Assistant (gensaa): a Tool for Developing Graphical Expert Systems

During numerous contacts with a satellite each day, spacecraft analysts must closely monitor real-time data. The analysts must watch for combinations of telemetry parameter values, trends, and other indications that may signify a problem or failure. As the satellites become more complex and the number of data items increases, this task is becoming increasingly difficult for humans to perform at acceptable performance levels. At NASA GSFC, fault-isolation expert systems are in operation supporting this data monitoring task. Based on the lessons learned during these initial efforts in expert system automation, a new domain-specific expert system development tool named the Generic Spacecraft Analyst Assistant (GenSAA) is being developed to facilitate the rapid development and reuse of real-time expert systems to serve as fault-isolation assistants for spacecraft analysts. Although initially domain-specific in nature, this powerful tool will readily support the development of highly graphical expert systems for data monitoring purposes throughout the space and commercial industry.

Hughes, Peter M.↗