In many areas of constrained optimization, representing all possible constraints that give rise to an accurate feasible region can be difficult and computationally prohibitive for online use. Satisfying feasibility constraints becomes more challenging in high-dimensional, non-convex regimes which are common in engineering applications. A prominent example that is explored in the manuscript is the security-constrained optimal power flow (SCOPF) problem, which minimizes power generation costs, while enforcing system feasibility under contingency failures in the transmission network. In its full form, this problem has been modeled as a nonlinear two-stage stochastic programming problem. In this work, we propose a hybrid structure that incorporates and takes advantage of both a high-fidelity physical model and fast machine learning surrogates. Neural network (NN) models have been shown to classify highly non-linear functions and can be trained offline but require large training sets. In this work, we present how model-guided sampling can efficiently create datasets that are highly informative to a NN classifier for non-convex functions. We show how the resultant NN surrogates can be integrated into a non-linear program as smooth, continuous functions to simultaneously optimize the objective function and enforce feasibility using existing non-linear solvers. Overall, this allows us to optimize instances of the SCOPF problem with an order of magnitude CPU improvement over existing methods.
Waveform cross-correlation is a sensitive phase-matched filtering technique that can detect seismic events for nuclear explosion monitoring. However, there are outstanding challenges with correlation detectors, most notably a direct dependence on the completeness of the waveform template library. To ameliorate these challenges, we investigate how dynamic time warping (DTW) may make waveform correlation more robust. DTW analyzes the differences between two time series and attempts to “warp” one time series relative to another in a recursive manner. We apply DTW to synthetic earthquake and recorded explosion templates to expand the capability of correlation detectors. We explore what conditions (e.g., source, station distance, frequency bands) and/or DTW algorithms generate stronger correlation scores. We show that DTW performs well on noisy signals and can dramatically improve the cross-correlation coefficient between a template and data-stream waveform. We conclude with recommendations on how to utilize DTW in nuclear monitoring detection.
Nuclear power plants (NPPs) are considering flexible plant operations to take advantage of excess thermal and electrical energy. One option for NPPs is to pursue hydrogen production through high temperature electrolysis as an alternate revenue stream to remain economically viable. The intent of this study is to investigate the risk of a hydrogen production facility in close proximity to an NPP. A 100 MW, 500 MW, and 1,000 MW facility are evaluated herein. Previous analyses have evaluated preliminary designs of a hydrogen production facility in a conservative manner to determine if it is feasible to co-locate the facility within 1 km of an NPP. This analysis specifically evaluates the risk components of different hydrogen production facility designs, including the likelihood of a leak within the system and the associated consequence to critical NPP targets. This analysis shows that although the likelihood of a leak in an HTEF is not negligible, the consequence to critical NPP targets is not expected to lead to a failure given adequate distance from the plant.
Recent work in neuromorphic computing has proposed a range of new architectures for Spiking Neural Network (SNN)-based systems. However, neuromorphic design lacks a framework to facilitate exploration of different SNN-based architectures and aid with early design decisions. While there are various SNN simulators, none can be used to rapidly estimate latency and energy of different spiking architectures. We show that while current spiking designs differ in implementation, they have common features which can be represented as a generic architecture template. We describe an initial version of a framework that simulates a range of neuromorphic architectures at an abstract time-step granularity. We demonstrate our simulator by modeling Intel's Loihi platform, estimating time-varying energy and latency with less than 10% mean error for various sizes of a two-layer SNN.
The table presented below suggests the basic information that should be covered in a facility NMAC Plan for an NMAC program that is designed for nuclear security. The topics are appropriate for and should be addressed by all facilities in their NMAC Plans. They are appropriate for NMAC Plans for nuclear power plants, research reactors, fuel manufacturing facilities, facilities that produce medical isotopes, and other facilities. The difference is in the intensity with which the various measures are applied and the thoroughness of the description of the application (i.e., the program requirements). The robustness of a facility NMAC program and the content of its NMAC Plan should be graded in accordance with the type of facility and the category of its nuclear material.
In this paper, we highlight how computational properties of biological dendrites can be leveraged for neuromorphic applications. Specifically, we demonstrate analog silicon dendrites that support multiplication mediated by conductance-based input in an interception model inspired by the biological dragonfly. We also demonstrate spatiotemporal pattern recognition and direction selectivity using dendrites on the Loihi neuromorphic platform. These dendritic circuits can be assembled hierarchically as building blocks for classifying complex spatiotemporal patterns.
The growth of helium bubbles impacts structural integrity of materials in nuclear applications. Understanding helium bubble nucleation and growth mechanisms is critical for improved material applications and aging predictions. Systematic molecular dynamics simulations have been performed to study helium bubble nucleation and growth mechanisms in Fe70Ni11Cr19 stainless steels. First, helium cluster diffusivities are calculated at a variety of helium cluster sizes and temperatures for systems with and without dislocations. Second, the process of diffusion of helium atoms to join existing helium bubbles is not deterministic and is hence studied using ensemble simulations for systems with and without vacancies, interstitials, and dislocations. We find that bubble nucleation depends on diffusion of not only single helium atoms, but also small helium clusters. Defects such as vacancies and dislocations can significantly impact the diffusion kinetics due to the trapping effects. Vacancies always increase the time for helium atoms to join existing bubbles due to the short-range trapping effect. This promotes bubble nucleation as opposed to bubble growth. Interestingly, dislocations can create a long-range trapping effect that reduces the time for helium atoms to join existing bubbles. This can promote bubble growth within a certain region near dislocations.
A robust data-management infrastructure is a key enabler for National Security Enterprise (NSE) capabilities in artificial intelligence and machine learning. This document describes efforts from a team of researchers at Sandia National Laboratories, Los Alamos National Laboratory, and Livermore National Laboratory to complete ASC Level II milestone #8854 “Assessment of Data-Management Infrastructure Needs for Production use of Advanced Machine learning and Artificial Intelligence.”
The Xyce XDM Netlist Translator is a software solution developed by Sandia National Laboratories for translating SPICE netlists into a format readable by Xyce, Sandia’s internally developed SPICE-compatible simulation tool.
This paper describes a summer internship project undertaken at Sandia National Labs (SNL), both current status and future work. The project was to explore various machine learning approaches for use on turbulent flow data. Specifically, unsupervised classification of turbulent flow data was explored. First, the usage of models in this field is discussed, and several issues in the common usage of the models are identified. Solutions to these issues are then proposed, in the form of a Bayesian filtering approach which probabilistically incorporates multiple sources of data to improve confidence in a result. Several types of sensors are suggested for this method, the incorporation of which range from semi-supervised learning approaches to fully unsupervised. These approaches are then tested on several turbulent flow cases.