Search NASA⌕ Search

SEARCH · Search NASA

Results for “data driven 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 1,081 records · Page 60
All sourcesNASA NTRSDOE OSTI
DOE OSTI2016

Off-Angle Iris Correction Methods

In many real world iris recognition systems obtaining consistent frontal images is problematic do to inexperienced or uncooperative users, untrained operators, or distracting environments. As a result many collected images are unusable by modern iris matchers. In this chapter we present four methods for correcting off-angle iris images to appear frontal which makes them compatible with existing iris matchers. The methods include an affine correction, a retraced model of the human eye, measured displacements, and a genetic algorithm optimized correction. The affine correction represents a simple way to create an iris image that appears frontal but it does not account for refractive distortions of the cornea. The other method account for refraction. The retraced model simulates the optical properties of the cornea. The other two methods are data driven. The first uses optical flow to measure the displacements of the iris texture when compared to frontal images of the same subject. The second uses a genetic algorithm to learn a mapping that optimizes the Hamming Distance scores between off-angle and frontal images. In this paper we hypothesize that the biological model presented in our earlier work does not adequately account for all variations in eye anatomy and therefore the two data-driven approaches should yield better performance. Results are presented using the commercial VeriEye matcher that show that the genetic algorithm method clearly improves over prior work and makes iris recognition possible up to 50 degrees off-angle.

iris recognition↗
DOE OSTI2022

Process prediction and detection of faults using probabilistic bidirectional recurrent neural networks on real plant data

Attaining Industry 4.0 for manufacturing operations requires advanced monitoring systems and real-time data analytics of plant data, among other topics. We propose a Probabilistic Bidirectional Recurrent Network (PBRN) for industrial process monitoring for the early detection of faults. The model is based on a Gated Recurrent Unit (GRU) neural network that allows the model to retain long-term dependencies between sensor data along a time horizon, hence learning the dynamic behavior of the process. To reduce the false-positive detection rate of the model, we compel the model to learn from a highly noisy sensor reading while outputting noise-free sensor outputs. The performance of the proposed model is compared to other data-driven statistical process monitoring schemes using real plant data from an industrial Air Separations Unit (ASU) containing noisy sensor readings. We show that the model can learn from noisy data without reducing its performance. Using two different fault cases, we demonstrate the model’s ability to carry out early fault detection with average false-positive rates of 2.9% and 4.9% for both fault cases. The missed detection rates are 0.1% and 0.2%, respectively.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Experimental results of a magnetically coupled piezoelectric actuator to relieve microchannel heat exchanger maldistribution

Refrigerant maldistribution is a common issue in microchannel heat exchangers. Refrigerant maldistribution can have significant negative effects on the heat transfer performance and increase the pressure drop, leading to increased superheat temperature at the outlet and increased compressor work, lowering system efficiency. In this work, a novel piezoelectric-driven magnetic actuator (PEDMA) was fabricated and inserted into the inlet header of the microchannel evaporator, with the goal of improving the non-uniformity of the flow distribution by regulating the flow in the header to the microchannels. Two prototype PEDMA designs were tested and showed significant impact on the refrigerant flow in the region of actuation. In the first design, the experimental data showed superheat reductions up to 9 °C when the individual channel temperatures were measured. The second design redistributed the refrigerant such that a 1% increase in capacity was calculated for the whole heat exchanger without significantly impacting the heating efficiency. The experimental results demonstrate the successful operation of the PEDMA devices and represent a new method of active flow distribution control which is based on a simple design with minimal additional energy consumption, and which can be inserted into microchannel heat exchanger headers to potentially relieve the refrigerant maldistribution.

42 ENGINEERING↗
DOE OSTI2020

Toward fusion plasma scenario planning for NSTX-U using machine-learning-accelerated models

One of the most promising devices for realizing power production through nuclear fusion is the tokamak. To maximize performance, it is preferable that tokamak reactors achieve advanced operating scenarios characterized by good plasma confinement, improved magnetohydrodynamic (MHD) stability, and a largely non-inductively driven plasma current. Such scenarios could enable steady-state reactor operation with high \emph{fusion gain} --- the ratio of produced fusion power to the external power provided through the plasma boundary. Precise and robust control of the evolution of the plasma boundary shape as well as the spatial distribution of the plasma current, density, temperature, and rotation will be essential to achieving and maintaining such scenarios. The complexity of the evolution of tokamak plasmas, arising due to nonlinearities and coupling between various parameters, motivates the use of model-based control algorithms that can account for the system dynamics. In this work, a learning-based accelerated model trained on data from the National Spherical Torus Experiment Upgrade (NSTX-U) is employed to develop planning and control strategies for regulating the density and temperature profile evolution around desired trajectories. The proposed model combines empirical scaling laws developed across multiple devices with neural networks trained on empirical data from NSTX-U and a database of first-principles-based computationally intensive simulations. The reduced execution time of the accelerated model will enable practical application of optimization algorithms and reinforcement learning approaches for scenario planning and control development. An initial demonstration of applying optimization approaches to the learning-based model is presented, including a strategy for mitigating the effect of leaving the finite validity range of the accelerated model. The approach shows promise for actuator planning between experiments and in real-time.

machine learning↗
DOE OSTI2025

A Study on Co-existing Heterogeneous Wireless Networks for Data Transmission within a Nuclear Facility

Deployment of wireless technologies is a salient need for modernization, automation and improved operation of nuclear power plants (NPPs). As a single technology cannot support the ever-changing needs, it is required to have a heterogeneous wireless network architecture to address the different technical and economic challenges. However, the coexistence of these multiband heterogeneous wireless networks brings numerous challenges due to the factors including dissimilarity in their channel access mechanism, distance between nodes, transmit power level and many more. This paper develops real-world experiments and simulations of wireless coexistence for Wi-Fi, Fifth generation cellular (5G) and Zigbee in the unlicensed band to understand the challenges and opportunities. The experiments were conducted over the Platform for Open Wireless Data-driven Experimental Research (POWDER) testbed at the university of Utah. In addition, this paper is the first to propose a novel packet rate control technique at the network layer to create temporary opportunities for 5G or Zigbee signal transmissions focusing its application in a nuclear facility while using the shared band. The performance of the proposed coexistence solution is validated with experimental results and simulation.

5G↗
DOE OSTI2025

Neural chaos: A spectral stochastic neural operator

Building surrogate models for operators with uncertainty quantification capabilities is essential for many engineering applications where randomness–such as variability in material properties, boundary conditions, and initial conditions–is unavoidable. Polynomial Chaos Expansion (PCE) is widely recognized as a go-to method for constructing stochastic surrogates in both intrusive and non-intrusive ways, and it has recently been used in the context of operator learning. However, its application becomes challenging for complex or high-dimensional processes, as achieving accuracy requires higher-order polynomials, which can increase computational demand and/or the risk of overfitting. Furthermore, PCE requires specialized treatments to manage random variables that are not independent, and these treatments may be problem-dependent or may fail with increasing complexity. Here, in this work, we adopt the same formalism as the spectral expansion used in PCE; however, we replace the classical polynomial basis functions with neural network (NN) basis functions to leverage their expressivity. To achieve this, we propose an algorithm that identifies NN-parameterized basis functions in a purely data-driven manner, without any prior assumptions about the joint distribution of the random variables involved, whether independent or dependent, or about their marginal distributions. The proposed algorithm identifies each NN-parameterized basis function sequentially, ensuring they are orthogonal with respect to the data distribution. The basis functions are constructed directly on the joint stochastic variables without requiring a tensor product structure or assuming independence of the random variables. This approach may offer greater flexibility for complex stochastic models, while simplifying implementation compared to the tensor product structures typically used in PCE to handle random vectors. This is particularly advantageous given the current state of open-source packages, where building and training neural networks can be done with just a few lines of code and extensive community support. We demonstrate the effectiveness of the proposed scheme through several numerical examples of varying complexity and provide comparisons with classical PCE.

Polynomial chaos expansion↗
DOE OSTI2019

Development of Solenoid-Driven and Pneumatic Punches for Launching High- Z Cryogenic Pellets for Tokamak Disruption Mitigation Experiments

Mitigation of disruption events in future high energy density tokamaks is essential for machine longevity. The creation of runaway electrons, large electromagnetic forces, and high localized heat loads during a disruption can be devastating to machine components. Shattered pellet injection is currently the most effective method of disruption mitigation. Injection of cryogenically solidified deuterium, neon, or argon (or mixtures thereof) have been shown to efficiently radiate thermal energy of the plasma so that the heat load is distributed on the walls of the machine. Pellets are formed by desublimating gas in the barrel of a pipe gun and fired using a pulse of high-pressure light gas. Current gas gun designs cannot reach sufficient pressure to dislodge pure neon and argon pellets at low temperatures because the material strength is too high. Pellet temperatures must be kept low (to well below the triple-point temperature of the material) to ensure minimal gas flow into the machine due to vapor pressure of the pellet. A gas-driven punch device has been designed and tested to dislodge pure neon or argon pellets. The breakaway strength of a pellet is proportional to the surface area of the pellet in contact with the inner diameter of the barrel. As pellets get larger in diameter, the amount of force needed to dislodge them increases. To better understand the mechanics behind how a punch dislodges a pellet, a solenoid-operated punch was designed so that kinetic energy of the punch, when striking a pellet, can be varied by changing input current to the solenoid. This solenoid punch will be used to determine kinetic energy versus pellet surface area threshold for breakaway. These data will be used to design mechanical punches for use in a high-field tokamak environment. Furthermore, this paper outlines the modeling, design, experimental testing, and results of the punch development activities.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2015

The NO v A simulation chain

The NO v A experiment is a two-detector, long-baseline neutrino experiment operating in the recently upgraded NuMI muon neutrino beam. Simulating neutrino interactions and backgrounds requires many steps including: the simulation of the neutrino beam flux using FLUKA and the FLUGG interface, cosmic ray generation using CRY, neutrino interaction modeling using GENIE, and a simulation of the energy deposited in the detector using GEANT4. To shorten generation time, the modeling of detector-specific aspects, such as photon transport, detector and electronics noise, and readout electronics, employs custom, parameterized simulation applications. We will describe the NO v A simulation chain, and present details on the techniques used in modeling photon transport near the ends of cells, and in developing a novel data-driven noise simulation. Due to the high intensity of the NuMI beam, the Near Detector samples a high rate of muons originating in the surrounding rock. In addition, due to its location on the surface at Ash River, MN, the Far Detector collects a large rate ((˜) 140 kHz) of cosmic muons. Furthermore, we will discuss the methods used in NO v A for overlaying rock muons and cosmic ray muons with simulated neutrino interactions and show how realistically the final simulation reproduces the preliminary NO v A data.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Online Model-Free DER Dispatch Via Adaptive Voltage Sensitivity Estimation and Chance Constrained Programming

This paper proposes an online data-driven distributed energy resource management system (DERMS) for distribution system optimal DER dispatch as well as voltage regulation. Here, the key innovation is to leverage the Local Sensitivity Factor (LSF) for transforming the DER control into a computationally efficient linear programming (LP) problem. By taking real-time measurements, the estimation of LSF eliminates the need for an accurate distribution system model as well as full nodal load information, which is difficult to achieve in practice. A robust recursive least squares method is also developed to ensure the robust estimation of LSF, which is initialized using reasonable values from model-derived LSFs. This allows the system to adapt to changing operational conditions effectively. A scenario-based, chance-constrained framework is further employed to ensure voltage remains within acceptable limits in the presence of measurement and estimation uncertainties. Test results on a real-world, 759-node distribution network located in western Colorado, U.S., validate the effectiveness and robustness of the proposed control approach and demonstrate its superior performance as compared to alternative methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2017

Dominant Controls of Downdip Afterslip and Viscous Relaxation on the Postseismic Displacements Following the M w 7.9 Gorkha, Nepal, Earthquake

Here, we analyze three-dimensional GPS coordinate time series from continuously operating stations in Nepal and South Tibet and calculate the initial 1 year postseismic displacements. We first investigate models of poroelastic rebound, afterslip, and viscoelastic relaxation individually and then attempt to resolve the trade-offs between their contributions by evaluating the misfit between observed and simulated displacements. We compare kinematic inversions for distributed afterslip with stress-driven afterslip models. The modeling results show that no single mechanism satisfactorily explains near- and far-field postseismic deformation following the Gorkha earthquake. When considering contributions from all three mechanisms, we favor a combination of viscoelastic relaxation and afterslip alone, as poroelastic rebound always worsens the misfit. The combined model does not improve the data misfit significantly, but the inverted afterslip distribution is more physically plausible. The inverted afterslip favors slip within the brittle-ductile transition zone downdip of the coseismic rupture and fills the small gap between the mainshock and largest aftershock slip zone, releasing only 7% of the coseismic moment. Our preferred model also illuminates the laterally heterogeneous rheological structure between India and the South Tibet. The transient and steady state viscosities of the upper mantle beneath Tibet are constrained to be greater than 10 18 Pa s and 10 19 Pa s, whereas the Indian upper mantle has a high viscosity ≥10 20 Pa s. The viscosity in the lower crust of southern Tibet shows a clear trade-off with its southward extent and thickness, suggesting an upper bound value of ~8 × 10 19 Pa s for its steady state viscosity.

58 GEOSCIENCES↗
DOE OSTI2023

Ultrafast Molecular Frame Quantum Tomography

Here, we develop and experimentally demonstrate a methodology for a full molecular frame quantum tomography (MFQT) of dynamical polyatomic systems. We exemplify this approach through the complete characterization of an electronically nonadiabatic wave packet in ammonia (NH 3 ). The method exploits both energy and time-domain spectroscopic data, and yields the lab frame density matrix (LFDM) for the system, the elements of which are populations and coherences. The LFDM fully characterizes electronic and nuclear dynamics in the molecular frame, yielding the time- and orientation-angle dependent expectation values of any relevant operator. For example, the time-dependent molecular frame electronic probability density may be constructed, yielding information on electronic dynamics in the molecular frame. In NH 3 , we observe that electronic coherences are induced by nuclear dynamics which nonadiabatically drive electronic motions (charge migration) in the molecular frame. Here, the nuclear dynamics are rotational and it is nonadiabatic Coriolis coupling which drives the coherences. Interestingly, the nuclear-driven electronic coherence is preserved over longer timescales. In general, MFQT can help quantify entanglement between electronic and nuclear degrees of freedom, and provide new routes to the study of ultrafast molecular dynamics, charge migration, quantum information processing, and optimal control schemes.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2026

ChatMPI: LLM-Driven MPI Code Generation for HPC Workloads

The Message Passing Interface (MPI) standard plays a crucial role in enabling scientific applications for parallel computing and is an essential component in high-performance computing (HPC). However, implementing MPI code manually—especially applying a proper domain decomposition and communication pattern—is a challenging and error-prone task. We present ChatMPI, an AI assistant for MPI parallelization of sequential C codes. In our analysis, we focus on testing six essential HPC workloads, which are based on Basic Linear Algebra Subprograms levels 1, 2, and 3 as well as sparse, stencil, and iterative operations. We analyze the process of creating ChatMPI by using the ChatHPC library. This lightweight large language model (LLM)–based infrastructure enables HPC experts to efficiently create and supervise trustworthy AI capabilities for critical HPC software tasks. We study the data required for training (fine-tuning) ChatMPI to generate parallel codes that not only use MPI syntax correctly but also apply HPC techniques to reduce memory communication and maximize performance by using proper work decomposition. With a relatively small training dataset composed of a few dozen prompts and fewer than 15 minutes of fine-tuning on one node equipped with two NVIDIA H100 GPUs, ChatMPI elevates trustworthiness for MPI code generation of current LLMs (e.g., Code Llama, ChatGPT-4o and ChatGPT 5). Additionally, we evaluate the performance of the MPI codes generated by ChatMPI in comparison with the ones generated by ChatGPT-4o and ChatGPT-5. The codes generated by ChatMPI provide up to a 4 × boost in performance by using better problem decomposition, communication patterns, and HPC techniques (e.g., communication avoiding).

Valero Lara, Pedro [ORNL] (ORCID:0000000214794310)↗
DOE OSTI2025

Image-Driven Hybrid Structural Analysis Based on Continuum Point Cloud Method with Boundary Capturing Technique

Conventional approaches for the structural health monitoring of infrastructures often rely on physical sensors or targets attached to structural members, which require considerable preparation, maintenance, and operational effort, including continuous on-site adjustments. This paper presents an image-driven hybrid structural analysis technique that combines digital image processing (DIP) and regression analysis with a continuum point cloud method (CPCM) built on a particle-based strong formulation. Polynomial regressions capture the boundary shape change due to the structural loading and precisely identify the edge and corner coordinates of the deformed structure. The captured edge profiles are transformed into essential boundary conditions. This allows the construction of a strongly formulated boundary value problem (BVP), classified as the Dirichlet problem. Capturing boundary conditions from the digital image is novel, although a similar approach was applied to the point cloud data. It was shown that the CPCM is more efficient in this hybrid simulation framework than the weak-form-based numerical schemes. Unlike the finite element method (FEM), it can avoid aligning boundary nodes with regression points. A three-point bending test of a rubber beam was simulated to validate the developed technique. The simulation results were benchmarked against numerical results by ANSYS and various relevant numerical schemes. The technique can effectively solve the Dirichlet-type BVP, yielding accurate deformation, stress, and strain values across the entire problem domain when employing a linear strain model and increasing the number of CPCM nodes. In addition, comparative analysis with conventional displacement tracking techniques verifies the developed technique’s robustness. The proposed technique effectively circumvents the inherent limitations of traditional monitoring methods resulting from the reliance on physical gauges or target markers so that a robust and non-contact solution for remote structural health monitoring in real-scale infrastructures can be provided, even in unfavorable experimental environments.

Chemistry↗
DOE OSTI2016

Advanced Computational Accident Scenario Modeling for Safety Margin Economic Analysis

The intent of this research is to establish a new tool in the Risk Informed Safety Margin Characterization (RISMC) tool-kit for the fiscal analysis of potential power plant upgrades. This is being done by providing proof-of-concept of the Safety Margin Economic Evaluation (SMEE) methodology of performing cost-benefit analyses of potential Nuclear Power Plant (NPP) upgrades to allow for more data-driven decision making with regards to nuclear safety. To this end, the RAVEN code developed by the Idaho National Laboratory is being used to perform a cost-benefit analysis of several potential power plant safety upgrades to compare the material cost of the upgrades with the probabilistic benefit of avoiding accident scenario consequences to find the most cost effective safety upgrades. Additionally, the MELCOR and MACCS2 codes developed by the Sandia National Laboratory are being used for accident scenario modeling. Evaluating potential NPP upgrades is concluded by doing a detailed cost-benefit analysis of the upgrades. The cost of the upgrade is the direct material cost of implementing, maintaining, and operating the upgrade at an NPP for the projected duration of its lifetime. The benefit of the upgrade is more complex, and is essentially the Risk avoided, where Risk is defined as Consequences multiplied by Probability. Here, Consequences is the economic impact of a severe accident and/or nuclear release and Probability is the likelihood that an NPP upgrade will prevent or mitigate a severe accident, reducing or even eliminating its Consequences. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2017

A Unified Data-Driven Approach for Programming In Situ Analysis and Visualization: An Interim Report of Sandia Sub-Team Contributions

As we look ahead to next generation high performance computing platforms, the placement and movement of data is becoming the key-limiting factor on both performance and energy efficiency. Furthermore, the increased quantities of data the systems are capable of generating, in conjunction with the insufficient rate of improvements in the supporting I/0 infrastructure, is forcing applications away from the off-line post-processing of data towards techniques based on in ,situ analysis and visualization. Together, these challenges are shaping how we will both design and develop effective, performant and energy-efficient software. In particular, the challenges highlight the need for data and data-centric operations to be fundamental in the reasoning about, and optimization of, scientific workflows on extreme-scale architectures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Instrumentation and Control Selection for the 12 GeV Hall-B Magnets at Jefferson Lab

Here, as part of the Jefferson Lab 12 GeV accelerator upgrade, the Experimental Physics Hall B detector system requires two superconducting magnets – a Torus and a Solenoid. The specifications required maximum space for the detectors which led to the choice of conduction cooling for each magnet. The Torus consists of 6 trapezoidal 'race-track'-type coils connected in series with an operating current of 3770 A. The Solenoid is an actively shielded 5 Tesla magnet consisting of 5 coils connected in series operating at 2416 A. Within the hall the two magnets are located in close proximity to each other and are surrounded by particle detectors. We describe the philosophy behind the instrumentation selection and control design that accounts for this proximity and other challenging working conditions. We describe the choice of sensor technologies, as well as the control and data acquisition methods. The magnet power and cryogenic control sub-systems are implemented using Allen Bradley Control Logix 1756-L72 Programmable Logic Controllers. Sensor instrumentation read-backs are routed into the PLC via National Instruments cRIO hardware (Field Programmable Gate Arrays or FPGA/RT application) using Jefferson Lab designed FPGA-based multi-sensor-excitation-chassis. Configuration, monitoring, and alarm handlers for the magnet systems are provided via an Experimental Physics Instrumentation & Control System interface (EPICS). Failure Modes and Effects Analysis (FMEA) and the requirement to monitor critical parameters during operation guided the selection of instrumentation and associated hardware. The design of the quench protection and voltage tap sub-systems was driven by the anticipated level of voltages developed during a magnet quench. The primary hard-wired quench detection and protection sub-system together with the secondary PLC-based protection sub-system is also discussed. The successful commissioning and subsequent performance of these magnets demonstrates the robustness of the design and implementation approach that was adopted by the Jefferson Lab team and serves as an excellent 'How To' guide for future projects of this size and complexity.

12 GeV↗
DOE OSTI2014

Flexible and Scalable Data Fusion using Proactive, Schemaless Information Services

Exascale data environments are fast approaching, driven by diverse structured and unstructured data such as system and application telemetry streams, open-source information capture, and on-demand simulation output. Storage costs having plummeted, the question is now one of converting vast stores of data to actionable information. Complicating this problem are the low degrees of awareness across domain boundaries about what potentially useful data may exist, and write-once-read- never issues (data generation/collection rates outpacing data analysis and integration rates). Increasingly, technologists and researchers need to correlate previously unrelated data sources and artifacts to produce fused data views for domain-specific purposes. New tools and approaches for creating such views from vast amounts of data are vitally important to maintaining research and operational momentum. We propose to research and develop tools and services to assist in the creation, refinement, discovery and reuse of fused data views over large, diverse collections of heterogeneously structured data. We innovate in the following ways. First, we enable and encourage end-users to introduce customized index methods selected for local benefit rather than for global interaction (flexible multi-indexing). We envision rich combinations of such views on application data: views that span backing stores with different semantics, that introduce analytic methods of indexing, and that define multiple views on individual data items. We specifically decline to build a big fused database of everything providing a centralized index over all data, or to export a rigid schema to all comers as in federated query approaches. Second, we proactively advertise these application-specific views so that they may be programmatically reused and extended (data proactivity). Through this mechanism, both changes in state (new data in existing view collected) and changes in structure (new or derived view exists) are made known. Lastly, we embrace found data heterogeneity by coupling multi-indexing to backing stores with appropriate semantics (as opposed to a single store or schema).

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2020

An Applied Strategy for Using Empirical and Hybrid Models in Online Monitoring

The monitoring of plant equipment for failure prediction is one of the key contributors to operation and maintenance (O&M) costs for a nuclear power plant (NPP) because O&M monitoring depends on labor-intensive activities that are required to meet high equipment reliability standards. These activities rely primarily on humans for information gathering, condition diagnosis, and predictive analysis. Online monitoring aims to automate these activities by relying on sensors to replace human information gathering and machine learning to replace human analysis and decision making. To facilitate automated monitoring, a systematic strategy for anomaly detection is needed to optimally use the available sensor data, empirical models, and physics-supported models. This strategy is essential to provide credible reasoning on why and when an empirical (i.e., purely data-driven) versus hybrid (i.e., physics-supported) approach should be used and to determine the ideal mix of these two approaches for a defined anomaly detection scope. The extant methods usually adopt an ad hoc trial-and-error approach that, in addition to being time-consuming and costly, is also highly subjective; it is impacted by the background and the skill set of the personnel making the decisions. Thus, such an approach cannot guarantee an optimum outcome. This represents the motivation of the current research effort, which is focused on devising a scientifically supported strategy for the optimum selection of anomaly detection methods. This report presents a detailed assessment of the main anomaly detection techniques within the empirical or hybrid method streams. Empirical methods include pattern, statistical, and causal inference. Hybrid methods include the use of physics models to train and test data methods, reduce data dimensionality, reduce data-model complexity, augment data, and reduce empirical uncertainty; hybrid methods also include the use of data to tune physics models. The listed techniques within these two streams represent the vast majority of techniques performed for anomaly detection. Using the techniques as outcomes, a strategy was developed to enable a systematic decision-making process to lead to one of these techniques. The strategy is driven by key decision points related to data relevance, simple modeling feasibility, data inference, physics-modeling value, data dimensionality, physics knowledge, method of validation, performance, data availability and suitability for training and testing, cause-effect, entropy inference, and model fitting. Each of these decision points in the strategy is explained in detail in this report with examples, along with the scientific basis behind the decisions and outcomes in common and simplified terminology. The strategy is developed for use by any NPP staff with basic engineering or science knowledge. A user-friendly graphical state flow diagram was also developed as a visual presentation of the strategy. The strategy was tested and demonstrated through two pilot projects for the application of anomaly detection at an NPP. Each pilot had two use cases: an initial case in which certain decisions were made that resulted in one or more empirical techniques and a revised use case where one or more key decisions were modified resulting in using a set of hybrid methods.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗