Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine learning operations”

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 1,261 records · Page 70

Ionic Liquids for Direct Air Capture of CO 2 using Electric‐Field‐Mediated Moisture Gradient Process (Final Technical Report)

The final report provides executive summary, a list of publications, and information on training graduate students and postdoctoral researchers. We carried out computational and experimental research on understanding molecular-level mechanism of how CO 2 is absorbed in a solution containing ethylene glycol as the solvent and KOH as the salt in the presence of ionic liquids and under the influence of electric field. In doing so, we developed an automated high-throughput method which allowed us to measure the solubility of CO 2 in a large number of ionic liquids, considerably speeding up the CO 2 solubility measurement. We also demonstrated how varying the concentration of ionic liquids in ethylene glycol can result in a maximum in ionic conductivity. Reaction of CO 2 and subsequent release results in a 50% reduction when the process is operated at an ionic liquid-ethylene glycol concentration yielding maximum ionic conductivity amongst all the ionic liquid-ethylene glycol combinations studied as a part of this research. We utilized machine learning models to identify unique ionic liquid-solvent combinations with ionic conductivity much higher than that measured for ionic liquid-ethylene glycol combinations. We demonstrated that the rate of CO 2 reaction with KOH in ethylene glycol can be optimized with the type of ionic liquid and its concentration. Overall, the research led to publication of 10 peer-reviewed research articles and several presentations at national conferences. We are also in the process of developing additional manuscripts based on the research carried out as a part of this project. Two graduate students and two postdoctoral researchers were supported on the funding.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Inter-Domain Fusion for Enhanced Intrusion Detection in Power Systems: An Evidence Theoretic and Meta-Heuristic Approach

False alerts due to misconfigured or compromised intrusion detection systems (IDS) in industrial control system (ICS) networks can lead to severe economic and operational damage. However, research using deep learning to reduce false alerts often requires the physical and cyber sensor data to be trustworthy. Implicit trust is a major problem for artificial intelligence or machine learning (AI/ML) in cyber-physical system (CPS) security, because when these solutions are most urgently needed is also when they are most at risk (e.g., during an attack). To address this, the Inter-Domain Evidence theoretic Approach for Inference (IDEA-I) is proposed that reframes the detection problem as how to make good decisions given uncertainty. Specifically, an evidence theoretic approach leveraging Dempster–Shafer (DS) combination rules and their variants is proposed for reducing false alerts. A multi-hypothesis mass function model is designed that leverages probability scores obtained from supervised-learning classifiers. Using this model, a location-cum-domain-based fusion framework is proposed to evaluate the detector’s performance using disjunctive, conjunctive, and cautious conjunctive rules. The approach is demonstrated in a cyber-physical power system testbed, and the classifiers are trained with datasets from Man-In-The-Middle attack emulation in a large-scale synthetic electric grid. For evaluating the performance, we consider plausibility, belief, pignistic, and general Bayesian theorem-based metrics as decision functions. To improve the performance, a multi-objective-based genetic algorithm is proposed for feature selection considering the decision metrics as the fitness function. Finally, we present a software application to evaluate the DS fusion approaches with different parameters and architectures.

42 ENGINEERING↗

Network Scale Ubiquitous Volume Estimation Using Tree-Based Ensemble Learning Methods

Currently real-time, ubiquitous volume data for roadway networks remains the key missing dimension in traffic operations. Most volume data are average annual daily traffic (AADT) measures derived from the Highway Performance Monitoring System (HPMS). Although methods to factor the AADT to hourly averages for typical day of week exist, actual volume data is limited to a sparse collection of locations in which volumes are continuously recorded. This paper explores the use of state-of-art machine learning techniques to estimate accurate real-time volume measures that span the highway network providing ubiquitous coverage in space, and point-in-time measures for a specific date and time. Three tree-based ensemble learning models, random forest (RF), gradient boost machine (GBM), and extreme gradient boost (XGBoost), were tested for volume estimation by learning from combined dataset of commercial probe data provided by TomTom, the FHWA's Travel Monitoring Analysis System (TMAS) data, and other infrastructure attributes such as number of lanes, speed limit, and weather. The methods were tested on major corridors and freeways in the metropolitan area of Denver. All three machine learning methods were able to provide hourly volume estimates 24 hours a day, 7 days a week, and 365 days a year with around 18% mean absolute error to true volume and about 5% of error with respect to roadway capacity. The low error measures allow the potential application by transportation agencies.

33 ADVANCED PROPULSION SYSTEMS↗

Students Solving Problems for ISS and Beyond: Inspiring the Next-Generation

Students Solving Problems for ISS and Beyond: Inspiring the Next-Generation Session Title: Students Solving Problems for ISS and Beyond: Inspiring the Next-Generation Session Description: NASA High school students United with NASA to Create Hardware (HUNCH) mission is to empower and inspire students through a Project-Based Learning program where 7-12 grade students learn 21st century skills and can launch their careers through participation in the design and fabrication of real-world valued products for NASA. With six different tracks consisting of Design & Prototype, Culinary Challenge, Softgoods, Precision Machining, Software, and Video Challenge, students are given the opportunity to create solutions for the International Space Station (ISS), the Moon, and beyond. Many projects are requested by the Crew to help ease living conditions, giving students the opportunity to make an impact on the lives of Astronauts. Other projects come directly from NASA and its partners. Join our session to learn how NASA is working with teachers across the country to mentor the next generation of scientists and engineers to solve some of NASA’s greatest challenges. Learning Outcomes: 1. Describe the NASA HUNCH Program, including the program objectives, goals, and strategic partnerships for middle school and high school outreach and advocacy efforts. 2. Identify the innovative strategies NASA is using to work with middle and high school students to solve real-world problems 3. Use the knowledge gained to inspire the next generation of scientists and engineers Session Track: Advocacy & Outreach Specialized Focus Area: Women in Government and Military Learning Level: Foundational Session Format: Listen & Learn Speaker Qualifications: 1. Deboshri Sadhukhan • Current Job Title: Deputy Project Manager • Topic Experience (years of experience related to proposed topic): 1-5 years • Biography: Deboshri Sadhukhan is an engineer for NASA Glenn Research Center (GRC). She has worked on numerous projects — from International Space Station (ISS) fluid technologies, to Orion European Service Module propulsion, to planetary science missions and other game-changing technologies. Her roles have ranged from Project Manager to System Safety Lead. She currently serves as a GRC Regional Mentor for the High school students United with NASA to Create Hardware (HUNCH) program. She also serves as Deputy Project Manager for an ISS payload and Safety & Mission Assurance Lead for a Radioisotope Power Systems project. In these roles, she oversees each phase of a project from beginning to end and provides leadership to increase the reliability, maintainability and system safety of hardware and personnel throughout the system life cycle. She holds a Bachelor of Science in Electrical Engineering from The University of Akron. 2. Nancy Hall • Current Job Title: Project Manager • Topic Experience: 20+ years • Biography: Nancy Rabel Hall earned a B.S. degree in Space Sciences from Florida Institute of Technology and a M.S. degree in Mechanical Engineering from the University of Toledo. She has been at NASA Glenn for over 30 years. She has led several International Space Station experiments that studied how the behavior of fluids and fluid systems behave differently in microgravity as compared to here on Earth. She is also the High school students United with NASA to Create Hardware (HUNCH) project manager, a program that allows students to design and fabricate hardware and softgoods for NASA as well as participate in a culinary and video challenge. She enjoys talking to the public and students about the work being done at NASA as well as showing students how math and science can be fun. She is an amateur radio operator, enjoys playing golf, and reading science fiction and fantasy books.

HUNCH↗

Statistical-learning strategies generate only modestly performing predictive models for urinary symptoms following external beam radiotherapy of the prostate: A comparison of conventional and machine-learning methods

Purpose: Given the paucity of available data concerning radiotherapy-induced urinary toxicity, it is important to ensure derivation of the most robust models with superior predictive performance. This work explores multiple statistical-learning strategies for prediction of urinary symptoms following external beam radiotherapy of the prostate. Methods: The performance of logistic regression, elastic-net, support-vector machine, random forest, neural network, and multivariate adaptive regression splines (MARS) to predict urinary symptoms was analyzed using data from 754 participants accrued by TROG03.04-RADAR. Predictive features included dose-surface data, comorbidities, and medication-intake. Four symptoms were analyzed: dysuria, haematuria, incontinence, and frequency, each with three definitions (grade ≥ 1, grade ≥ 2 and longitudinal) with event rate between 2.3% and 76.1%. Repeated cross-validations producing matched models were implemented. A synthetic minority oversampling technique was utilized in endpoints with rare events. Parameter optimization was performed on the training data. Area under the receiver operating characteristic curve (AUROC) was used to compare performance using sample size to detect differences of ≥0.05 at the 95% confidence level. Results: Logistic regression, elastic-net, random forest, MARS, and support-vector machine were the highest-performing statistical-learning strategies in 3, 3, 3, 2, and 1 endpoints, respectively. Logistic regression, MARS, elastic-net, random forest, neural network, and support-vector machine were the best, or were not significantly worse than the best, in 7, 7, 5, 5, 3, and 1 endpoints. The best-performing statistical model was for dysuria grade ≥ 1 with AUROC ± standard deviation of 0.649 ± 0.074 using MARS. For longitudinal frequency and dysuria grade ≥ 1, all strategies produced AUROC>0.6 while all haematuria endpoints and longitudinal incontinence models produced AUROC<0.6. Conclusions: Logistic regression and MARS were most likely to be the best-performing strategy for the prediction of urinary symptoms with elastic-net and random forest producing competitive results. The predictive power of the models was modest and endpoint-dependent. New features, including spatial dose maps, may be necessary to achieve better models.

60 APPLIED LIFE SCIENCES↗

A machine learning approach to thermal conductivity modeling: A case study on irradiated uranium-molybdenum nuclear fuels

A deep neural network was developed for the purpose of predicting thermal conductivity with a case study performed on irradiated nuclear fuel. Traditional thermal conductivity modeling approaches rely on existing theoretical frameworks that describe known, relevant phenomena that govern the microstructural evolution processes during neutron irradiation (such as recrystallization, and pore size, distribution and morphology). Current empirical modeling approaches, however, do not represent all irradiation test data well. We develop a machine learning approach to thermal conductivity modeling that does not require a priori knowledge of a specific material microstructure and system of interest. Our approach allows re-searchers to probe dependency of thermal conductivity on a variety of reactor operating and material conditions. The purpose of building such a model is to allow for improved predictive capabilities linking structure-property-processing-performance relationships in the system of interest (here, irradiated nuclear fuel), which could lead to improved experimental test planning and characterization. The uranium-molybdenum system is the fuel system studied in this work, and historic irradiation test data is leveraged for model development. Our model achieved a mean absolute percent error of approximately 10%. Results indicate our model generalizes well to never before seen data, and thus use of deep learning methods for material property predictions from limited, historic irradiation data is a viable approach. This work challenges the current paradigm in materials science, where material property models are based on limited experimental data fitted to low-dimensionality phenomenological models, or by simulations in which fundamental equations are explicitly solved. The work presented here aims to demonstrate the potential and limitations of machine learning in the field of materials science and material property modeling.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Spatiotemporal features of traffic help reduce automatic accident detection time

Quick and reliable automatic detection of traffic accidents is of paramount importance to save human lives in transportation systems. However, automatically detecting when accidents occur has proven challenging, and minimizing the time to detect accidents (TTDA) by using traditional features in machine learning (ML) classifiers has plateaued. We hypothesize that accidents affect traffic farther from the accident location than previously reported. Therefore, leveraging traffic signatures from neighboring sensors that are adjacent to accidents should help improve their detection. We confirm this hypothesis by using verified ground-truth accident data, traffic data from radar detection system sensors, and light and weather conditions and show that we can minimize the TTDA while maximizing classification performance by considering spatiotemporal features of traffic. Specifically, we compare the performance of different ML classifiers (i.e, logistic regression, random forest, and XGBoost) when controlling for different numbers of neighboring sensors and TTDA horizons. We use data from interstates 75 and 24 in the metropolitan area that surrounds Chattanooga, TN. Our results show that the XGBoost classifier produces the best results by detecting accidents as quickly as 1.0 min after their occurrence with an area under the receiver operating characteristic curve of up to 83% and an average precision of up to 49%. We describe limitations, open challenges, and how the proposed framework can be used for quicker operational accident detection.

33 ADVANCED PROPULSION SYSTEMS↗

Autonomous System Subversion Tactics: Prototypes and Recommended Countermeasures

One of the fielding requirements for Advanced and Small Modular Reactors (AR/SMR) is the ability to support remote and autonomous operations. Autonomous Control Systems (ACS) are found on platforms such as Autonomous Space Vehicles, Cruise Missiles, and advanced driver-assistance systems. Each of these ACS implementations depends upon a set of decision support subsystems responsible for supporting Autonomous Mission Managers (names vary based upon field and author preferences). These Autonomous Mission Managers receive inputs from system sensors (e.g., LIDAR collection from an automobile travelling down a street; transients from a nuclear reactor), and perform a set of classifications (e.g., Red Traffic Light; Small Pedestrian at 10m; Load Rejection; Single Coolant Pump Trip), and then use these classifications in combination with recommendation algorithms to achieve platform goals (e.g., Stop the Vehicle at the Traffic Light, Avoid the Small Pedestrian; Trip the Reactor to prevent a Safety Event). The design, implementation, and fielding of an ACS capability will alter the cyber-attack surface such that existing risk management plans will need to be updated to include how to protect and defend against data-science and decision-support-system attack classes. These attack classes would include protection of the design and training environments where algorithm selection and testing and training data would be obvious attack vectors. These attack classes would also require an informed set of detection and response procedures to identify anomalous behaviors and document best practices for anomaly assessment and vulnerability mitigation and remediation. Last year we published a Cyber Threat Assessment Methodology for Autonomous and Remote Operations for AR/SMRs along with a companion publication on Cyber Attack and Defense Use Cases. The focus of the methodology was on describing and enumerating ACS processes, components, and functions such that security engineers could: evaluate subversion options against the target; identify threat actor attributes and capabilities derived from each subversion option; and identify security controls and response countermeasures. The Use Cases document offered detailed methodology examples including an assessment of a Military Base SMR, an Autonomous System Decision Loop, and implementation of AR/SMR Machine Learning algorithms. Our proposal at the end of last year was to focus on implementation of subversion prototypes related to the last Use Case area: AR/SMR Machine Learning (ML) Algorithms. We included six attack scenarios in our Use Cases paper: a Poisoning Attack against ML functions implemented using an FPGA; a Trojaning Attack against ML classifiers exploiting the excitability of Nuclear Engineers; a Backdooring Attack against ML Training environments to ensure persistence of an attack vector; a False Positive Evasion Attack against multi-factor Access Control Systems using clever inputs; an Inference Attack against ML models by an Insider with access to the Operational environment; and an Adversarial Reprogramming Attack against a Material Access Control Video Surveillance System. At the beginning of this year these six attack scenarios were provided to our research teams at Georgia Tech and Idaho State University and each team successfully implemented a subversion attack against a ML implementation to include transient misclassifications. While this is a notable outcome from this type of research, this paper offers the reader insight into not only how to structure and execute these types of attacks, but into the thought process behind how the researcher investigated the problem space, performed initial algorithm implementation, and the trial-and-error behind arriving at the successful subversion prototypes. We include in this paper a set of associated Scenarios on how these subversion prototypes could be implemented and an initial set of guidance for AR/SMR architects, Nuclear Regulators, and Cyber Defenders to implement awareness and defense capabilities into their current operational portfolios.

42 ENGINEERING↗

Time Series Classification for Locating Forced Oscillation Sources

Here, this article presents a machine learning based time-series classification method for using synchrophasor measurements to locate the source of forced oscillation (FO) for fast disturbance removal. First, multivariate time series (MTS) matrices are constructed by the most informative measurements selected by sequential feature selection from each power plant. Then, the Mahalanobis matrix is trained such that the Mahalanobis distance between the MTSs from the same class (i.e., with the same FO source location) are minimized and from different classes (i.e., with different FO source locations) are maximized. This allows MTSs to be classified by classifiers with class membership corresponding to the location of each FO source. To meet the runtime requirements of online matching, class templates are constructed to reduce data size and improve matching efficiency. To account for uncertainty in identifying the exact beginning of an FO event, dynamic time warping is used to align the out-of-sync MTSs. IEEE 39bus and WECC 179bus systems are used for algorithm development and validation. Simulation results demonstrate that the algorithm meets online operation runtime requirement with high accuracy using misaligned data sets.

42 ENGINEERING↗

Machine learning for modern power distribution systems: Progress and perspectives

The application of machine learning (ML) to power and energy systems (PES) is being researched at an astounding rate, resulting in a significant number of recent additions to the literature. As the infrastructure of electric power systems evolves, so does interest in deploying ML techniques to PES. However, despite growing interest, the limited number of reported real-world applications suggests that the gap between research and practice is yet to be fully bridged. To help highlight areas where this gap could be narrowed, this article discusses the challenges and opportunities in developing and adapting ML techniques for modern electric power systems, with a particular focus on power distribution systems. These systems play a crucial role in transforming the electric power sector and accommodating emerging distributed technologies to mitigate the impacts of climate change and accelerate the transition to a sustainable energy future. The objective of this article is not to provide an exhaustive overview of the state-of-the-art in the literature, but rather to make the topic accessible to readers with an engineering or computer science background and an interest in the field of ML for PES, thereby encouraging cross-disciplinary research in this rapidly developing field. To this end, the article discusses the ways in which ML can contribute to addressing the evolving operational challenges facing power distribution systems and identifies relevant application areas that exemplify the potential for ML to make near-term contributions. At the same time, key considerations for the practical implementation of ML in power distribution systems are discussed, along with suggestions for several potential future directions.

Marković, Marija (ORCID:0000000247839837)↗

Integrated Systems Health Management for Sustainable Habitats (Using Sustainability Base as a Testbed)

Habitation systems provide a safe place for astronauts to live and work in space and on planetary surfaces. They enable crews to live and work safely in deep space, and include integrated life support systems, radiation protection, fire safety, and systems to reduce logistics and the need for resupply missions. Innovative health management technologies are needed in order to increase the safety and mission-effectiveness for future space habitats on other planets, asteroids, or lunar surfaces. For example, off-nominal or failure conditions occurring in safety-critical life support systems may need to be addressed quickly by the habitat crew without extensive technical support from Earth due to communication delays. If the crew in the habitat must manage, plan and operate much of the mission themselves, operations support must be migrated from Earth to the habitat. Enabling monitoring, tracking, and management capabilities on-board the habitat and related EVA platforms for a small crew to use will require significant automation and decision support software.Traditional caution and warning systems are typically triggered by out-of-bounds sensor values, but can be enhanced by including machine learning and data mining techniques. These methods aim to reveal latent, unknown conditions while still retaining and improving the ability to provide highly accurate alerts for known issues. A few of these techniques will briefly described, along with performance targets for known faults and failures. Specific system health management capabilities required for habitat system elements (environmental control and life support systems, etc.) may include relevant subsystems such as water recycling systems, photovoltaic systems, electrical power systems, and environmental monitoring systems. Sustainability Base, the agency's flagship LEED-platinum certified green building acts as a living laboratory for testing advanced information and sustainable technologies that provides an opportunity to test novel machine learning and controls capabilities. In this talk, key features of Sustainability Base that make it relevant to deep space habitat technology and its use of these kinds of subsystems previously listed will be presented. The fact that all such systems require less power to support human occupancy can be used as a focal point to serve as a testbed for deep space habitats that will need to operate within finite energy budgets.

Systems Health Management↗

Interpretable Deep Learning for Advancing Field-Enhanced Catalysis

This DOE Early Career project developed a physics-informed, interpretable AI-and-modeling framework to understand and exploit electric-field effects in heterogeneous catalysis, with ammonia cracking and synthesis as a representative pathway. The team built and validated methods to map local electric fields on metal surfaces and nanoparticles, showing that low-coordination features (tips/edges/corners) can concentrate fields by several-fold relative to flat facets. Using DFT-generated datasets, the project created physics-guided machine learning models that rapidly predict local electric fields and field-dependent adsorption energetics with near-DFT accuracy while reducing computational cost by orders of magnitude. These predictions were integrated with microkinetic modeling to quantify how field-dipole interactions reshape reaction energetics and mechanisms, enabling large increases in predicted catalytic rates and substantial reductions in operating temperature under favorable field conditions. To accelerate discovery of earth-abundant catalysts, the project combined interpretable ML screening (with electronic-structure descriptors identified as key drivers) with a generative inverse-design workflow based on diffusion models and physics constraints. The resulting closed-loop approach, linking simulation, mechanistic modeling, and AI, provides reusable tools and datasets for designing catalysts and operating conditions in field-enhanced catalysis, with broad relevance to electrostatic catalysis, plasma catalysis, electrocatalysis, and other energy-related chemical transformations.

30 DIRECT ENERGY CONVERSION↗

Data assimilation in operator algebras

We develop an algebraic framework for sequential data assimilation of partially observed dynamical systems. In this framework, Bayesian data assimilation is embedded in a nonabelian operator algebra, which provides a representation of observables by multiplication operators and probability densities by density operators (quantum states). In the algebraic approach, the forecast step of data assimilation is represented by a quantum operation induced by the Koopman operator of the dynamical system. Moreover, the analysis step is described by a quantum effect, which generalizes the Bayesian observational update rule. Projecting this formulation to finite-dimensional matrix algebras leads to computational schemes that are i) automatically positivity-preserving and ii) amenable to consistent data-driven approximation using kernel methods for machine learning. Moreover, these methods are natural candidates for implementation on quantum computers. Applications to the Lorenz 96 multiscale system and the El Niño Southern Oscillation in a climate model show promising results in terms of forecast skill and uncertainty quantification.

97 MATHEMATICS AND COMPUTING↗

Tsdat: An Open-Source Data Standardization Framework for Marine Energy and Beyond

Many organizations are tasked with the collection and processing of large quantities of data from various measurement devices. Data reported from these sources are often not interoperable with datasets and software used by analysts and other organizations in the same domain, introducing barriers for collaboration on large-scale projects. This poses a particular problem for cross-device comparisons and machine learning applications, which rely on large quantities of data from multiple sources. To address these challenges, the open-source Time-Series Data Pipelines (Tsdat) Python framework was developed by Pacific Northwest National Laboratory, with strategic guidance and direction provided by the National Renewable Energy Laboratory and Sandia National Laboratories to facilitate collaboration and accelerate advancements in the marine energy domain through the development of an open-source ecosystem of tools. This paper will describe the Tsdat framework and the data standards within which it operates. A beta version of Tsdat has been released and is being used by several projects in marine energy, wind energy, and building energy systems.

big data↗

Recurrent Neural Network Attention Mechanisms for Interpretable System Log Anomaly Detection

Deep learning has recently demonstrated state-of-the art performance on key tasks related to the maintenance of computer systems, such as intrusion detection, denial of service attack detection, hardware and software system failures, and malware detection. In these contexts, model interpretability is vital for administrator and analyst to trust and act on the automated analysis of machine learning models. Deep learning methods have been criticized as black box oracles which allow limited insight into decision factors. In this work we seek to "bridge the gap'' between the impressive performance of deep learning models and the need for interpretable model introspection. To this end we present recurrent neural network (RNN) language models augmented with attention for anomaly detection in system logs. Our methods are generally applicable to any computer system and logging source. By incorporating attention variants into our RNN language models we create opportunities for model introspection and analysis without sacrificing state-of-the art performance. We demonstrate model performance and illustrate model interpretability on an intrusion detection task using the Los Alamos National Laboratory (LANL) cyber security dataset, reporting upward of 0.99 area under the receiver operator characteristic curve despite being trained only on a single day's worth of data.

Anomaly detection, Attention, Recurrent Neural Net↗

MHD, disruptions and control physics: Chapter 4 of the special issue: on the path to tokamak burning plasma operation

In this chapter, we review the progress in MHD stability, disruptions and control in magnetic fusion research that has occurred over the past (more than) one and a half decades since the publication by Hender et al in 2007 on the same topic as part of the update of ITER Physics Basis. During this period, remarkable progress has been achieved in the understanding of the basic physics and overall control of MHD instabilities through a wide spectrum of dedicated experiments, theory and modeling. The sawtooth activities are probably today one of the best understood of MHD events and very robust control schemes have been developed for reliable operation of tokamaks through core heating. Similarly, significant improvements have been achieved in understanding and control of neoclassical tearing modes, resistive wall modes or locked modes and their control through ECCD or error field control. The field of disruption prediction through application of artificial intelligence, machine learning or deep learning methods, which had already started at the time of the 2007 review, has progressed significantly due to general progress in these fields and application of newer, more sophisticated algorithms. However, although remarkable progress has been achieved in the field of Disruptions, their understanding, prediction, possible avoidance and mitigation still remain probably the most active fields of R&D globally in this field. This is especially because reactor grade machines like ITER and DEMO will be much less tolerant in respect of disruptions and runaway currents, and their occurrences must be either avoided altogether or minimized to an acceptable value without causing any significant hindrance to robust machine operations. This review is intended to present a broad spectrum of the R&D that has occurred in this field in support of ITER, which will also be of immense significance for all future machines, especially reactors like DEMO.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

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↗

AXEAP : a software package for X-ray emission data analysis using unsupervised machine learning

The Argonne X-ray Emission Analysis Package ( AXEAP ) has been developed to calibrate and process X-ray emission spectroscopy (XES) data collected with a two-dimensional (2D) position-sensitive detector. AXEAP is designed to convert a 2D XES image into an XES spectrum in real time using both calculations and unsupervised machine learning. AXEAP is capable of making this transformation at a rate similar to data collection, allowing real-time comparisons during data collection, reducing the amount of data stored from gigabyte-sized image files to kilobyte-sized text files. With a user-friendly interface, AXEAP includes data processing for non-resonant and resonant XES images from multiple edges and elements. AXEAP is written in MATLAB and can run on common operating systems, including Linux, Windows, and MacOS.

97 MATHEMATICS AND COMPUTING↗