Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “ITERATIVE NETWORK”

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 523 records · Page 29

Real-Time Distribution System State Estimation with Asynchronous Measurements

We report state estimation is a fundamental task in power systems. Although distribution systems are increasingly equipped with sensing devices and smart meters, measurements are typically reported at different rates and asynchronously; these aspects pose severe strains on workhorse state estimation algorithms, which are designed to process batches of data collected in a synchronous manner from all the measurement units. In this paper, we develop a novel state estimation algorithm to continuously update the estimate of the state based on measurements received in an asynchronous manner from measurement units. The synthesis of the algorithm hinges on a proximal-point type method, implemented in an online fashion, and capable of processing measurements received sequentially from sensors. A performance analysis is presented by providing bounds on the estimation error in terms of the mean and variance that hold at each iteration and asymptotically. The scheme is also compared with a more traditional Weighted Least Squares estimator that compensates for the lack of measurement data by using, as pseudo measurements, the measurement retrieved during a certain time window. Numerical simulations on the IEEE 37-bus feeder corroborate the analytical findings.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Search for the Higgs Boson and Rare Standard Model Processes in the E T +B-Jets Signature at the Collider Detector at Fermilab

We study rare processes of the standard model of particle physics (SM) in events with missing transverse energy E T , no leptons, and two or three jets, of which at least one is identified as originating from a $b$-quark (E T +b-jets signature). We present a search for the SM Higgs boson produced in association with a $W$ or $Z$ boson when the Higgs decays into \bbbar. We consider the scenario where $Z \to \nu \nu$, or $W \to l \nu$ and the lepton escapes detection. This dissertation analyzes $7.8~\mbox{fb$^{-1}$}$ of data collected by the CDF~II experiment at Fermilab. For the first time, we analyze events with \emph{relaxed kinematic} requirements, yielding an increase of 30- 40\% in acceptance to the $WH/ZH$ signal. We collect events from three different triggers and parametrize the efficiency of their logical combination (OR) using a novel artificial neural network ($NN$) technique. To increase the sensitivity to the signal, we implement a $NN$ to remove the huge instrumental background. An additional $NN$ is used to discriminate the Higgs signal from the remaining background. We check our background modeling by comparing data against backgrounds in many control regions, and find good agreement. Observing no significant excess in the data, we place 95\% confidence level (C.L.) upper limits on the Higgs boson production cross section. For a mass of $115~\mbox{GeV/$c^2$}$ the expected (observed) limit is $2.9$ ($2.3$) times the standard model prediction. Compared to the last iteration of this analysis, this result improves the significance by 10\% throughout the $100-150~\mbox{GeV/$c^2$}$ mass range. This is one of the most sensitive at the Tevatron in this mass range. We cross-check the tools developed in this dissertation by measuring the cross-section of top pair, electroweak single top and diboson ($WZ+ZZ$) production.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Systems and methods for optimal power flow on a radial network

Node controllers and power distribution networks in accordance with embodiments of the invention enable distributed power control. One embodiment includes a node controller including a distributed power control application; a plurality of node operating parameters describing the operating parameter of a node and a set of at least one node selected from the group consisting of an ancestor node and at least one child node; wherein send node operating parameters to nodes in the set of at least one node; receive operating parameters from the nodes in the set of at least one node; calculate a plurality of updated node operating parameters using an iterative process to determine the updated node operating parameters using the node operating parameters that describe the operating parameters of the node and the set of at least one node, where the iterative process involves evaluation of a closed form solution; and adjust node operating parameters.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Low-Power Testing of Losses in Millimeter-Wave Transmission Lines for High-Power Applications

We report the measurement of small losses in transmission line (TL) components intended for high-power millimeter-wave applications. Measurements were made using two different low-power techniques: a coherent technique using a vector network analyzer (VNA) and an incoherent technique using a radiometer. The measured loss in a 140 GHz 12.7 mm diameter TL system, consisting of 1.7 m of circular corrugated waveguide and three miter bends, is dominated by the miter bend loss. The measured loss was 0.3 {+-} 0.1 dB per miter bend using a VNA; and 0.22 {+-} 0.1 dB per miter bend using a radiometer. Good agreement between the two measurement techniques implies that both are useful for measuring small losses. To verify the methodology, the VNA technique was employed to measure the extremely small transmission loss in a 170 GHz ITER prototype TL system consisting of three lengths of 1 m, 63.5 mm diameter, circular corrugated waveguide and two miter bends. The measured loss of 0.05 {+-} 0.02 dB per miter bend may be compared with the theoretical loss of 0.027 dB per miter bend. These results suggest that low-power testing of TL losses, utilizing a small, simple TL system and a VNA, is a reliable method for evaluating performance of low-loss millimeter-wave TL components intended for use in high-power applications.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Distributed Quantum Learning with co-Management in a Multi-tenant Quantum System

The rapid advancement of quantum computing has pushed classical designs into the quantum domain, breaking physical boundaries for computing-intensive and data-hungry applications with the hope that some systems may provide a quantum speedup. For example, variational quantum algorithms have been proposed for quantum neural networks to train deep learning models on qubits, achieving promising results. Existing quantum learning architectures and systems rely on single, monolithic quantum machines with abundant and stable resources, such as qubits. However, fabricating a large, monolithic quantum device is considerably more challenging than producing an array of smaller devices. In this paper, we investigate a distributed quantum system that combines multiple quantum machines into a unified system. We propose DQuLearn, which divides a quantum learning task into multiple subtasks. Each subtask can be executed distributively on individual quantum machines, with the results looping back to classical machines for subsequent training iterations. Additionally, our system supports multiple concurrent clients and dynamically manages their circuits according to the runtime status of quantum workers. Through extensive experiments, we demonstrate that DQuLearn achieves similar accuracies with significant runtime reduction, by up to 68.7% and an increase per-second circuit processing speed, by up to 3.99 times, in a 4-worker multi-tenant setting.

quantum computing↗

Systems biology approaches towards predictive microbial ecology

Through complex interspecies interactions, microbial processes drive nutrient cycling and biogeochemistry. However, we still struggle to predict specifically which organisms, communities and biotic and abiotic processes are determining ecosystem function and how environmental changes will alter their roles and stability. While the tools to create such a predictive microbial ecology capability exist, cross-disciplinary integration of high-resolution field measurements, detailed laboratory studies and computation is essential. In this perspective, we emphasize the importance of pursuing a multiscale, systems approach to iteratively link ecological processes measured in the field to testable hypotheses that drive high-throughput laboratory experimentation. Mechanistic understanding of microbial processes gained in controlled lab systems will lead to the development of theory that can be tested back in the field. Using N 2 O production as an example, we review the current status of field and laboratory research and layout a plausible path to the kind of integration that is needed to enable prediction of how N-cycling microbial communities will respond to environmental changes. We advocate for the development of realistic and predictive gene regulatory network models for environmental responses that extend from single-cell resolution to ecosystems, which is essential to understand how microbial communities involved in N 2 O production and consumption will respond to future environmental conditions.

59 BASIC BIOLOGICAL SCIENCES↗

Summary report of the 4th IAEA Technical Meeting on Fusion Data Processing, Validation and Analysis (FDPVA)

The objective of the Fourth Technical Meeting on Fusion Data Processing, Validation and Analysis was to provide a platform during which a set of topics relevant to fusion data processing, validation and analysis are discussed with the view of extrapolating needs to next step fusion devices such as ITER. The validation and analysis of experimental data obtained from diagnostics used to characterize fusion plasmas are crucial for a knowledge-based understanding of the physical processes governing the dynamics of these plasmas. This paper presents the recent progress and achievements in the domain of plasma diagnostics and synthetic diagnostics data analysis (including image processing, regression analysis, inverse problems, deep learning, machine learning, big data and physics-based models for control) reported at the meeting. The progress in these areas highlight trends observed in current major fusion confinement devices. A special focus is dedicated on data analysis requirements for ITER and DEMO with a particular attention paid to artificial intelligence for automatization and improving reliability of control processes.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Simplifications for hydronic system models in modelica

Building systems and their heating, ventilation and air conditioning flow networks, are becoming increasingly complex. Some building energy simulation tools simulate these flow networks using pressure drop equations. These flow network models typically generate coupled algebraic nonlinear systems of equations, which become increasingly more difficult to solve as their sizes increase. This leads to longer computation times and can cause the solver to fail. These problems also arise when using the equation-based modelling language Modelica and Annex 60-based libraries. This may limit the applicability of the library to relatively small problems unless problems are restructured. This paper discusses two algebraic loop types and presents an approach that decouples algebraic loops into smaller parts, or removes them completely. The approach is applied to a case study model where an algebraic loop of 86 iteration variables is decoupled into smaller parts with a maximum of five iteration variables.

42 ENGINEERING↗

Machine Learning for Real-time Fusion Plasma Behavior Prediction and Manipulation (Final Report)

The goal of this project is to implement real-time analysis of 2D Beam Emission Spectroscopy (BES) data to predict and control transient and high-bandwidth events at DIII-D. In essence, we wish to bring high-bandwidth fluctuation diagnostics into the realm of real-time measurements and control. The BES ML models will necessarily be deep neural networks (DNN) with a “data flow” architecture for compatibility with high-throughput, low-latency evaluation on a field-programmable gate array (FPGA) or other emerging processor technologies. The real-time output will be fed to the plasma control system (PCS) for real-time control tasks, specifically for ELM control and avoidance and for QH-mode access and sustainment. We anticipate that the real-time analysis of fluctuation diagnostics will create new enabling technologies to predict and control transient events such as confinement mode transitions, edge-localized modes, Alfven eigenmode events, and disruptions. The proposed research is aligned with ITER research needs and DIII-D programmatic goals. For instance, the prediction and avoidance of ELM events is critical for ITER machine safety. Also, H-mode access with RMP ELM suppression in ITER is an active research area due to high separatrix density, narrow SOL width, and elevated LH transition power threshold.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Stochastic machine learning via sigma profiles to build a digital chemical space

This work establishes a different paradigm on digital molecular spaces and their efficient navigation by exploiting sigma profiles. To do so, the remarkable capability of Gaussian processes (GPs), a type of stochastic machine learning model, to correlate and predict physicochemical properties from sigma profiles is demonstrated, outperforming state-of-the-art neural networks previously published. The amount of chemical information encoded in sigma profiles eases the learning burden of machine learning models, permitting the training of GPs on small datasets which, due to their negligible computational cost and ease of implementation, are ideal models to be combined with optimization tools such as gradient search or Bayesian optimization (BO). Gradient search is used to efficiently navigate the sigma profile digital space, quickly converging to local extrema of target physicochemical properties. While this requires the availability of pretrained GP models on existing datasets, such limitations are eliminated with the implementation of BO, which can find global extrema with a limited number of iterations. A remarkable example of this is that of BO toward boiling temperature optimization. Holding no knowledge of chemistry except for the sigma profile and boiling temperature of carbon monoxide (the worst possible initial guess), BO finds the global maximum of the available boiling temperature dataset (over 1,000 molecules encompassing more than 40 families of organic and inorganic compounds) in just 15 iterations (i.e., 15 property measurements), cementing sigma profiles as a powerful digital chemical space for molecular optimization and discovery, particularly when little to no experimental data is initially available.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Deblending galaxies with variational autoencoders: A joint multiband, multi-instrument approach

ABSTRACT Blending of galaxies has a major contribution in the systematic error budget of weak-lensing studies, affecting photometric and shape measurements, particularly for ground-based, deep, photometric galaxy surveys, such as the Rubin Observatory Legacy Survey of Space and Time (LSST). Existing deblenders mostly rely on analytic modelling of galaxy profiles and suffer from the lack of flexible yet accurate models. We propose to use generative models based on deep neural networks, namely variational autoencoders (VAE), to learn probabilistic models directly from data. We train a VAE on images of centred, isolated galaxies, which we reuse, as a prior, in a second VAE-like neural network in charge of deblending galaxies. We train our networks on simulated images including six LSST bandpass filters and the visible and near-infrared bands of the Euclid satellite, as our method naturally generalizes to multiple bands and can incorporate data from multiple instruments. We obtain median reconstruction errors on ellipticities and r-band magnitude between ±0.01 and ±0.05, respectively, in most cases, and ellipticity multiplicative bias of 1.6 per cent for blended objects in the optimal configuration. We also study the impact of decentring and prove the method to be robust. This method only requires the approximate centre of each target galaxy, but no assumptions about the number of surrounding objects, pointing to an iterative detection/deblending procedure we leave for future work. Finally, we discuss future challenges about training on real data and obtain encouraging results when applying transfer learning.

Arcelin, Bastien↗

Development of the FHR advanced natural circulation analysis code and application to FHR safety analysis

The University of California, Berkeley (UCB) is performing thermal hydraulics safety analysis to develop the technical basis for design and licensing of fluoride-salt-cooled, high-temperature reactors (FHRs). FHR designs investigated by UCB use natural circulation for emergency, passive decay heat removal when normal decay heat removal systems fail. The FHR advanced natural circulation analysis (FANCY) code has been developed for assessment of passive decay heat removal capability and safety analysis of these innovative system designs. The FANCY code uses a one-dimensional, semi-implicit scheme to solve for pressure-linked mass, momentum and energy conservation equations. Graph theory is used to automatically generate a staggered mesh for complicated pipe network systems. Heat structure models have been implemented for three types of boundary conditions (Dirichlet, Neumann and Robin boundary conditions). Heat structures can be composed of several layers of different materials, and are used for simulation of heat structure temperature distribution and heat transfer rate. Control models are used to simulate sequences of events or trips of safety systems. A proportional-integral controller is also used to automatically make thermal hydraulic systems reach desired steady state conditions. A point kinetics model is used to model reactor kinetics behavior with temperature reactivity feedback. The underlying large sparse linear systems in these models are efficiently solved by using direct and iterative solvers provided by the SuperLU code on high performance machines. Input interfaces are designed to increase the flexibility of simulation for complicated thermal hydraulic systems. In conclusion, this paper mainly focuses on the methodology used to develop the FANCY code, and safety analysis of the Mark 1 pebble-bed FHR under development at UCB is performed.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

PipeSight: A High-Performance Computing Platform for Pipeline Integrity Management

The Phase I feasibility study completed as part of this project has led to a number of innovative technologies being developed and has laid the foundation for a successful Phase II effort to commercialize a platform for managing the integrity of pipelines for the damage mechanisms of the new, hybrid-energy based economy. To ground the development efforts and direction of the project, an extensive market research and customer discovery effort was undertaken early in Phase I. Through this effort, a number of pipeline owners and operators were interviewed, and the following key findings were discovered about the pipeline industry: • Small pipeline operators do not have the central engineering groups necessary to perform their own independent analysis of inspection data, but instead rely on summarized tally sheets provided to them by inspection service providers. • The time it takes to go from an inspection to a completed engineering assessment, even for small segments of pipeline, can take anywhere from 30-120 days. During this delay, critical threats can (and have been known to) cause failures. • Uncertainty is often not accounted for in the assessment of pipeline integrity. The tally sheets provided by third-party service providers are almost always deterministic in nature, identifying threats that present a concern only to the current (not the future) integrity of the pipeline. • It is uncommon to apply the latest technologies to perform advanced assessments of damaged pipelines. There is a desire to use more advanced analysis capabilities to assess threats. Many pipeline operators indicated that they would often excavate a pipeline to perform an inspection and find that the damage was not as bad as they anticipated, thus using limited resources unnecessarily. Companies are not consistent in their use of inspection data to determine corrosion rates, and those that do only calculate deterministic corrosion rates. • The industry has prominently relied on time-based inspections but has recently started to transition to risk-based inspections. However, there appears to be no uniform guidance on how to do so while properly accounting for all sources of uncertainty. • Companies are not storing inspection data in a manner that allows for the ready determination of temporal trends. • Predictive maintenance principles and practices are beginning to be used by early adopters • Some pipelines are being re-purposed to transport different process fluids than they were designed for, e.g., H 2 and CO 2 rich process streams to serve the new hybrid-energy based economy, which are presenting new integrity concerns for the existing pipeline network that crisscrosses the United States. As a result of these discoveries, we were able to target the development efforts in Phase I to best serve the needs of the industry. In Phase I, we developed a way to correlate multiple large-scale scans of the pipeline to determine a probabilistic corrosion rate that accounts for all sources of error and uncertainty in the inspection process. This probabilistic corrosion rate can be used to predict the future thickness distribution of the pipe wall. We demonstrate how this analysis may be performed in an analytical fashion and has been implemented in such a manner that it can be readily distributed using GPU computing through integration of the Kokkos programming model. We also make a very novel extension of the analytical corrosion rate model to Bayesian Networks (an explainable AI technique) that can account for non-parametric distributions of corrosion rates. With the predictions made above for the probabilistic corrosion rate and corresponding future distribution of the pipe wall thickness, we can assess the integrity of the pipeline through the use of a probabilistic engineering assessment. We developed a novel screening data analysis approach that can rapidly identify ‘hotspots’ (local thin areas) where the integrity of the pipeline is a concern. Once more, we implemented this screening approach in C++ to leverage GPU computing via the Kokkos programming model. After the critical hotspots are identified, we developed a program that can automatically generate an advanced finite element model of the damaged regions. Since the number of damaged regions that require advanced analysis can number in the thousands, we integrated an open-source container-native workflow engine for orchestrating parallel jobs on the cloud. Initially, these advanced numerical models were only designed to account for loading due to internal pressure. However, in a slight pivot from the initial Phase I proposal, we developed a complete pipe stress analysis program (called Simflex) which can simulate the complete pipeline and its response to thermal expansion, pressure, thermal bowing, weight, wind, earthquake, support displacement, support friction and external forces. This pipe stress analysis program was written generically, to handle any piping system, but contains the features needed to model long pipelines (i.e., it incorporates a model for soil mechanics and can account for the nonlinear boundary conditions necessary to simulate long underground pipelines). This pipe stress analysis program can simulate any segment of the pipeline (simple or complex) under any set of conditions and loads, to determine the supplemental loads (axial forces and bending moments) at the location of damage. This enables the most accurate state of stress to be accounted for in the pipeline, which can prove critical when evaluating the integrity of a damaged region. In the process of developing the technologies to perform the integrity assessment of the pipeline, we also extended one of the industry standard approaches for performing the assessment of local thin areas that extend more in the circumferential direction than the longitudinal direction of the pipeline. This approach was presented to the API 579-1/AS ME FFS-1 steering committee in November 2021 for consideration in the next edition of the industry standard for Fitness-For-Service (expected to be released in 2023). To help pipeline operators make decisions with the results on any integrity assessment, we developed a new approach to the life-cycle management of pipelines which uses a Bayesian Decision Network. The network is designed to help pipeline operators plan and prioritize inspection activities and ultimately make smarter, more cost-effective decisions. The Bayesian approach accounts for all sources of uncertainty and carries them through to the final optimal decisions, providing a probabilistic framework for optimizing inspection intervals. The proof-of-concept networks developed in the feasibility study are complete, verified, and are focused on a subset of the pipeline. To expand this novel approach to the scale necessary for an entire network of pipelines in Phase II, we will leverage the DOE-funded Bengi solver for industrial-scale decision making with Bayesian Networks [22]. Once implemented, we will be able to provide the pipeline industry with a much-needed tool for optimal inspection planning using truly explainable artificial intelligence (XAI). To handle all of these advanced capabilities into a cloud-based platform, the architecture of the Equity Engineering Cloud (EEC) was extended to include Argo Workflows, a framework capable of distributing and managing a massive number of jobs that consume their own resources, such that thousands of serial finite element simulations can be run in parallel. As part of this substantial undertaking, we also integrated Argo Continuous Delivery (CD) into the EEC, to aid with the rapid prototyping and iterations that will be imperative to the success of the PipeSight platform’s Agile development process in Phase II. As part of the pipe stress analysis program, we also developed a custom visualizer that leverages the DOE-funded VTK visualization library. We added custom contouring capabilities and a means for interacting visually with both the inputs and outputs of the pipe stress analysis program. We also developed routines for automating the post-processing of the finite element simulations to determine if any failure criteria are met and to visualize the deformations, stresses and strains in ParaView using the exodus II file format (a subset of netCDF).

24 POWER TRANSMISSION AND DISTRIBUTION↗

Active and Transfer Learning of High-Dimensional Neural Network Potentials for Transition Metals

Classical molecular dynamics (MD) simulations represent a very popular and powerful tool for materials modeling and design. The predictive power of MD hinges on the ability of the interatomic potential to capture the underlying physics and chemistry. There have been decades of seminal work on developing interatomic potentials, albeit with a focus predominantly on capturing the properties of bulk materials. Such physics-based models, while extensively deployed for predicting the dynamics and properties of nanoscale systems over the past two decades, tend to perform poorly in predicting nanoscale potential energy surfaces (PESs) when compared to high-fidelity first-principles calculations. These limitations stem from the lack of flexibility in such models, which rely on a predefined functional form. Machine learning (ML) models and approaches have emerged as a viable alternative to capture the diverse size-dependent cluster geometries, nanoscale dynamics, and the complex nanoscale PESs, without sacrificing the bulk properties. Here, in this study, we introduce an ML workflow that combines transfer and active learning strategies to develop high-dimensional neural networks (NNs) for capturing the cluster and bulk properties for several different transition metals with applications in catalysis, microelectronics, and energy storage, to name a few. Our NN first learns the bulk PES from the high-quality physics-based models in literature and subsequently augments this learning via retraining with a higher-fidelity first-principles training data set to concurrently capture both the nanoscale and bulk PES. Our workflow departs from status-quo in its ability to learn from a sparsely sampled data set that nonetheless covers a diverse range of cluster configurations from near-equilibrium to highly nonequilibrium as well as learning strategies that iteratively improve the fingerprinting depending on model fidelity. All the developed models are rigorously tested against an extensive first-principles data set of energies and forces of cluster configurations as well as several properties of bulk configurations for 10 different transition metals. Our approach is material agnostic and provides a methodology to transfer and build upon the learnings from decades of seminal work in molecular simulations on to a new generation of ML-trained potentials to accelerate materials discovery and design.

36 MATERIALS SCIENCE↗

Applications of Lifted Nonlinear Cuts to Convex Relaxations of the AC Power Flow Equations

Here, we demonstrate that valid inequalities, or lifted nonlinear cuts (LNC), can be projected to tighten the Second Order Cone (SOC), Convex DistFlow (CDF), and Network Flow (NF) relaxations of the AC Optimal Power Flow (AC-OPF) problem. We conduct experiments on 38 cases from the PGLib-OPF library, showing that the LNC strengthen the SOC and CDF relaxations in 100% of the test cases, with average and maximum differences in the optimality gaps of 6.2% and 17.5% respectively. The NF relaxation is strengthened in 46.2% of test cases, with average and maximum differences in the optimality gaps of 1.3% and 17.3% respectively. We also study the trade-off between relaxation quality and solve time, demonstrating that the strengthened CDF relaxation outperforms the strengthened SOC formulation in terms of runtime and number of iterations needed, while the strengthened NF formulation is the most scalable with the lowest relaxation quality improvement due to these LNC.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Three-dimensional coherent X-ray diffraction imaging via deep convolutional neural networks

Abstract As a critical component of coherent X-ray diffraction imaging (CDI), phase retrieval has been extensively applied in X-ray structural science to recover the 3D morphological information inside measured particles. Despite meeting all the oversampling requirements of Sayre and Shannon, current phase retrieval approaches still have trouble achieving a unique inversion of experimental data in the presence of noise. Here, we propose to overcome this limitation by incorporating a 3D Machine Learning (ML) model combining (optional) supervised learning with transfer learning. The trained ML model can rapidly provide an immediate result with high accuracy which could benefit real-time experiments, and the predicted result can be further refined with transfer learning. More significantly, the proposed ML model can be used without any prior training to learn the missing phases of an image based on minimization of an appropriate ‘loss function’ alone. We demonstrate significantly improved performance with experimental Bragg CDI data over traditional iterative phase retrieval algorithms.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Implementation of AI/DEEP learning disruption predictor into a plasma control system

Abstract This paper reports on advances in the state‐of‐the‐art deep learning disruption prediction models based on the Fusion Recurrent Neural Network (FRNN) originally introduced in a 2019 NATURE publication [ https://doi.org/10.1038/s41586‐019‐1116‐4 ]. In particular, the predictor now features not only the “disruption score,” as an indicator of the probability of an imminent disruption, but also a “sensitivity score” in real time to indicate the underlying reasons for the imminent disruption. This adds valuable physics interpretability for the deep learning model and can provide helpful guidance for control actuators now implemented into a modern plasma control system (PCS). The advance is a significant step forward in moving from modern deep learning disruption prediction to real‐time control and brings novel AI‐enabled capabilities relevant for application to the future burning plasma ITER system. Our analyses use large amounts of data from JET and DIII‐D vetted in the earlier NATURE publication. In addition to “when” a shot is predicted to disrupt, this paper addresses reasons “why” by carrying out sensitivity studies. FRNN is accordingly extended to use more channels of information, including measured DIII‐D signals such as (i) the “n1rms” signal that is correlated with the n = 1 modes with finite frequency, including neoclassical tearing mode and sawtooth dynamics; (ii) the bolometer data indicative of plasma impurity control; and (iii) “q‐min”—the minimum value of the safety factor relevant to the key physics of kink modes. The additional channels and interpretability features expand the ability of the deep learning FRNN software to provide information about disruption subcategories as well as more precise and direct guidance for the actuators in a PCS.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Data Federation Challenges in Remote Near-Real-Time Fusion Experiment Data Processing

Fusion energy experiments and simulations provide critical information needed to plan future fusion reactors. As next-generation devices like ITER move toward long-pulse experiments, analyses, including AI and ML, should be performed in a wide range of time and computing constraints, from near-real-time constraints, between-shot analysis, and to campaign-wide long-term analysis. However, the data volume, velocity, and variety make it extremely challenging for analyses using only local computational resources. Researchers need the ability to compose and execute workflows spanning edge resources to large-scale high-performance computing facilities.We present Delta, a system to address data analysis challenges, including AI/ML, in fusion science, by leveraging the ADIOS I/O library and middleware, to support executing science workflows over the wide area network for near-real-time streaming. We discuss the data federation challenges in performing remote workflows, focusing on on-going research work in (1) managing, reducing, and streaming data to minimize I/O and data movement overheads, (2) decompressing and reorganizing data for analysis, and (3) executing workflows for automated data analysis. We introduce examples for deep-learning based data analysis for the fusion domain and demonstrate how we use Delta to construct end-to-end workflows for a fusion device in Korea, connecting a remote DOE facility in the USA. The capability demonstrated by this project is the basis for improving the state of the art for near-real-time data federation amongst remote facilities.

Choi, Jong Youl↗