Search NASA⌕ Search

Engineering topics

Tipireddy, Ramakrishna

Publications and source records attributed to Tipireddy, Ramakrishna.

At least 19 records

Accelerating Scientific Simulations with Bi-Fidelity Weighted Transfer Learning

High-fidelity modeling is an essential design tool for many engineering applications. However, for complex systems, computational cost can be a limiting factor. Analyzing parameter sensitivity, uncertainty quantification, and design optimization require many model evaluations. Surrogate models are often used to develop the relationship between model parameters and quantities of interest. However, in the case of complex systems, surrogate models require several degrees of freedom and, thus, a large number of data points to determine the correct dependencies. For many applications, this may be prohibitively expensive. The reduction of computational requirements can be achieved by leveraging low-fidelity models. Low-fidelity models represent the system at a coarser resolution with the advantage of computational efficiency. Therefore, a bi-fidelity modeling paradigm, which augments the accuracy of a low-fidelity model in a computationally efficient manner by invoking limited runs of a high-fidelity model, can be leveraged to sufficiently balance the accuracy and computational requirements. In this work, a bi-fidelity weighted transfer learning method using neural networks was applied to a computational fluid dynamics heat transfer modeling problem. The transfer learning advantage was investigated as a function of hyperparameters. Our main finding is that the use of a bi-fidelity modeling paradigm achieves accuracy close to that of a high-fidelity Gaussian process model while significantly reducing computational cost. The bi-fidelity model achieves comparable performance with 90 high-fidelity samples-that is, 60% less than the samples needed to achieve similar accuracy without the use of bi-fidelity modeling,

Borowiec, Katarzyna↗

Conditional Karhunen–Loève regression model with Basis Adaptation for high-dimensional problems: Uncertainty quantification and inverse modeling

Here, we propose a methodology for improving the accuracy of surrogate models of the observable response of physical systems as a function of the systems’ spatially heterogeneous parameter fields, with applications to uncertainty quantification and parameter estimation in high-dimensional problems. Practitioners often formulate finite-dimensional representations of spatially heterogeneous parameter fields using truncated unconditional Karhunen–Loève expansions (KLEs) for a certain choice of unconditional covariance kernel and construct surrogate models of the observable response with respect to the KLE coefficients. When direct measurements of the parameter fields are available, we propose improving the accuracy of these surrogate models by representing the parameter fields via conditional Karhunen-Loève expansions (CKLEs). CKLEs are constructed by conditioning the covariance kernel of the unconditional expansion on the direct measurements of the parameter field via Gaussian process regression, and then truncating the corresponding KLE. We apply the proposed methodology to constructing surrogate models via the Basis Adaptation (BA) method of the stationary hydraulic head response, measured at spatially discrete observation locations, of a groundwater flow model of the Hanford Site, as a function of the 1000-dimensional representation of the model’s log-transmissivity field. We find that BA surrogate models of the hydraulic head based on CKLEs are more accurate than BA surrogate models based on unconditional expansions for forward uncertainty quantification tasks. Furthermore, we find that inverse estimates of the hydraulic transmissivity field computed using CKLE-based BA surrogate models are more accurate than those computed using unconditional BA surrogate models.

97 MATHEMATICS AND COMPUTING↗

Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti’s Theorem for Markov Chains

Conformal prediction is a widely used method to quantify uncertainty in settings where the data is independent and identically distributed (IID), or more generally, exchangeable. Conformal prediction takes in a pre-trained classifier and a calibration dataset as inputs, and returns a function which maps feature vectors to subsets of classes. The output of the returned function for a new feature vector is guaranteed to contain the true class with a pre-specified confidence. Despite its success and usefulness in IID settings, extending conformal prediction to non-exchangeable (e.g., Markovian) data in a manner that provably preserves all desirable theoretical properties has largely remained an open problem. As a solution, we extend conformal prediction to the setting of a Hidden Markov Model (HMM) with unknown parameters. The key idea behind the proposed method is to partition the non-exchangeable Markovian data from the HMM into exchangeable blocks by exploiting the de Finetti’s Theorem for Markov Chains discovered by Diaconis and Freedman (1980). The permutations of the exchangeable blocks are then viewed as randomizations of the observed Markovian data from the HMM. The proposed method provably retains all desirable theoretical guarantees offered by the classical conformal prediction framework and is general enough to be useful in many sequential prediction problems.

Nettasinghe, Don Buddhika Wijayantha↗

Uncertainty Quantification Framework for Predicting Material Response with Large Number of Parameters: Application to Creep Prediction in Ferritic-Martensitic Steels Using Combined Crystal Plasticity and Grain Boundary Models

This paper presents an uncertainty quantification (UQ) framework for the physics-based model prediction of material response with a large number of parameters. The application problem presented in this work is that of predicting creep in Grade 91 steel at 600°C. The material response is defined with a physically based microstructural model with constitutive equations emulating several observed phenomena in Grade 91 and embodied into an explicit geometry mesoscale finite element model for prior austenite grains and grain boundaries. Creep within the grains and in grain boundaries are represented by crystal plasticity for dislocation motion and a physics-based model for cavity growth and nucleation, respectively. The creep behavior of this material is influenced by several parameters, some of which have a wide range of variation based on experimental data. UQ combined with microstructural modeling can discover the core microstructural causes of experimental variability, leading to improved materials with lower variability in critical long-term material properties. In this study, we investigate the model's uncertainty to identify material properties that may be modified during production to increase creep life and analyze different components of the crystal plasticity model for improvements. For this purpose, a quantity of interest is defined as time to minimum creep rate, which correlates well to the creep failure of the material. A deep neural network model was trained and validated to be used as a surrogate for the finite element model. Then, a variance-based sensitivity analysis is performed on the surrogate model to find the Sobol indices of the input parameters in respect to the output quantity of interest. The Sobol indices are used to reduce the dimensionality of the model. Generalized polynomial chaos expansion is used on the reduced basis models to propagate the uncertainty from the input parameters to the quantity of interest using the deep neural network surrogate model. These results are benchmarked against uncertainty propagation using Monte Carlo simulations. In conclusion, the UQ performed through the reduced basis model captures almost all the uncertainty in the model with significantly fewer simulations, making it possible to perform the UQ directly via simulations with the finite element model rather than surrogate machine-learned models.

36 MATERIALS SCIENCE↗

Physics-Informed Gaussian Process Regression for States Estimation and Forecasting in Power Grids

Real-time state estimation and forecasting are critical for the efficient operation of power grids. In this paper, a physics-informed Gaussian process regression (PhI-GPR) method is presented and used for forecasting and estimating the phase angle, angular speed, and wind mechanical power of a three-generator power grid system using sparse measurements. In standard data-driven Gaussian process regression (GPR), parameterized models for the prior statistics are fit by maximizing the marginal likelihood of observed data. In the PhI-GPR method, we propose to compute the prior statistics offline by solving stochastic differential equations (SDEs) governing the power grid dynamics. The short-term forecast of a power grid system dominated by wind generation is complicated by the stochastic nature of the wind and the resulting uncertainty in wind mechanical power. Here, we assume that the power grid dynamics are governed by swing equations, with the wind mechanical power fluctuating randomly in time. We solve these equations for the mean and covariances of the power grid states using the Monte Carlo simulation method. We demonstrate that the proposed PhI-GPR method can accurately forecast and estimate observed and unobserved states. For the considered problem, PhI-GPR has computational advantages over the ensemble Kalman filter (EnKF) method: In PhI-GPR, ensembles are computed offline and independently of the data acquisition process, whereas for EnFK, ensembles are computed online with data acquisition, rendering real-time forecast more challenging. We also demonstrate that the PhI-GPR forecast is more accurate than the EnKF forecast when the random mechanical wind power is non-Markovian. In contrast, the two methods produce similar forecasts for the Markovian mechanical wind power. For observed states, we show that PhI-GPR provides a forecast comparable to the standard data-driven GPR; both forecasts are significantly more accurate than the autoregressive integrated moving average (ARIMA) forecast. We also show that the ARIMA forecast is more sensitive to observation frequency and measurement errors than the PhI-GPR forecast.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Sequential Decision Making (SDM) for Mesh Refinement and Model Selection in Multiscale, Multi-Physics Applications

Intelligent automation and decision support are needed to enhance computational efficiency and robustness in multiscale and multi-physics problems, including materials science, manufacturing, and climate and weather modeling. Current scientific computing approaches for enabling decisions by scientists fail to explore the role of learning, reasoning, and probabilistic planning. Often these decisions are not performed in real-time during the computation but are made prior to the start of the computation, which must be interrupted in order to make changes to the prior choices. Such interruptions at different stages of the computation increase the total computing time and the need for a human expert to frequently monitor the results. State of art scientific computing methods consist of rule-based algorithms that cannot automatically adapt to a dynamically changing computing environment. The development of a Sequential Decision Making (SDM) framework will automate scientific computing by optimizing the policies for mesh refinement, time-stepping, model and algorithm selection, resource allocation, and pre and post-processing. Our agent SDM framework for scientific computing will consist of data-driven learning (Classifier), automated reasoning (contextual knowledge), and probabilistic planning (Reinforcement Learning). In this project, we focused on three problems to demonstrate our SDM framework on a set of ordinary and partial differential equations. Classification of Lorenz system regions using Feed-Forward Neural Networks examined learning in the SDM framework. On the other hand, reasoning and planning in the SDM framework were used in two problems: adaptive time-stepping for nonlinear ODEs using on-policy RL algorithms, and adaptive mesh refinement for 2-D PDEs using off-policy RL algorithms.

97 MATHEMATICS AND COMPUTING↗

MULTISTEP AND CONTINUOUS PHYSICS-INFORMED NEURAL NETWORK METHODS FOR LEARNING GOVERNING EQUATIONS AND CONSTITUTIVE RELATIONS

In this work, we investigate the applicability and relative merit of discrete and continuous versions of physics-informed neural network (PINN) methods for learning unknown governing equations or constitutive relations in a nonlinear dynamical system. In the case of unknown dynamics, entire right-hand-side (RHS) equations of the ordinary differential equations are unknown. In the case of unknown constitutive relations, however, the RHS equations are known up to the specification of constitutive relations (that may depend on the state of the system). We use a deep neural network to model unknown governing equations or constitutive relations. The discrete PINN approach combines classical multistep discretization methods for dynamical systems with neural-network-based machine learning methods. On the other hand, the continuous versions utilize deep neural networks to minimize the residual function for the continuous governing equations. We use the case of a fedbatch bioreactor system to study the effectiveness of these approaches and discuss conditions for their applicability. Our results indicate that the accuracy of the trained neural network models is much higher for the cases where we only have to learn a constitutive relation instead of all dynamics. This finding corroborates the well-known fact from scientific computing that building as much structural information as is available into an algorithm can enhance its efficiency and/or accuracy.

97 MATHEMATICS AND COMPUTING↗

Conditional Karhunen-Loève expansion for uncertainty quantification and active learning in partial differential equation models

We use a conditional Karhunen-Lo` eve (KL) model to quantify and reduce uncertainty in a stochastic partial differential equation (SPDE) problem with partially-known space-dependent coefficient, Y (x). We assume that a small number of Y (x) measurements are available and model Y (x) with a KL expansion. We achieve reduction in uncertainty by conditioning the KL expansion coefficients on measurements. We consider two approaches for conditioning the KL expansion: In Approach 1, we condition the KL model first and then truncate it. In Approach 2, we first truncate the KL expansion and then condition it. We employ the conditional KL expansion together with Monte Carlo and sparse grid collocation methods to compute the moments of the solution of the SPDE problem. Uncertainty of the problem is further reduced by adaptively selecting additional observation locations using two active learning methods. Method 1 minimizes the variance of the PDE coefficient, while Method 2 minimizes the variance of the solution of the PDE. We demonstrate that conditioning leads to dimension reduction of the KL representation of Y (x). For a linear diffusion SPDE with uncertain log-normal coefficient, we show that Approach 1 provides a more accurate approximation of the conditional log-normal coefficient and solution of the SPDE than Approach 2 for the same number of random dimensions in a conditional KL expansion. Furthermore, Approach 2 provides a good estimate for the number of terms of the truncated KL expansion of the conditional field of Approach 1. Finally, we demonstrate that active learning based on Method 2 is more efficient for uncertainty reduction in the SPDE’s states (i.e., it leads to a larger reduction of the variance) than active learning using Method 2.

Conditioned Karhunen-Lo` eve expanion, machine lea↗

FPDetect: Efficient Reasoning About Stencil Programs Using Selective Direct Evaluation

We present FPDetect, a low-overhead approach for detecting logical errors and soft errors affecting stencil computations without generating false positives. We develop an offline analysis that tightly estimates the number of floating-point bits preserved across stencil applications. This estimate rigorously bounds the values expected in the data space of the computation. Violations of this bound can be attributed with certainty to errors. FPDetect helps synthesize error detectors customized for user-specified levels of accuracy and coverage. FPDetect also enables overhead reduction techniques based on deploying these detectors coarsely in space and time. Experimental evaluations demonstrate the practicality of our approach.

97 MATHEMATICS AND COMPUTING↗

Physics-informed Machine Learning Method for Forecasting and Uncertainty Quantification of Partially Observed and Unobserved States in Power Grids

We present a physics-informed Gaussian Process Regression (GPR) model to predict the phase angle, angular speed, and wind mechanical power from a limited number of measurements. In the traditional data-driven GPR method, the form of the Gaussian Process covariance matrix is assumed and its parameters are found from measurements. In the physics-informed GPR, we treat unknown variables (including wind speed and mechanical power) as a random process and compute the covariance matrix from the resulting stochastic power grid equations. We demonstrate that the physics-informed GPR method is significantly more accurate than the standard data-driven one for immediate forecasting of generators' angular velocity and phase angle. We also show that the physics-informed GPR provides accurate predictions of the unobserved wind mechanical power, phase angle, or angular velocity when measurements from only one of these variables are available. The immediate forecast of observed variables and predictions of unobserved variables can be used for effectively managing power grids (electricity market clearing, regulation actions) and early detection of abnormal behavior and faults. The physics-based GPR forecast time horizon depends on the combination of input (wind power, load, etc.) correlation time and characteristic (relaxation) time of the power grid and can be extended to short and medium-range times.

machine learning, power grid, forecasting, Gaussia↗

Quantification, Trade-off Analysis, and Optimal Checkpoint Placement for Reliability and Availability

Checkpointing is the most widely used technique in high-performance computing (HPC) to ensure the application progress in the presence of failures. In this paper, we present mathematical models of the checkpointing systems to quantify their reliability and availability. We perform trade-off analysis with respect to resource costs and reliability. Then, we explore the optimal checkpoint placement for checkpointing systems to maximize system availability. Finally, in a rigorous manner, we comparatively analyze the behavior of redundant systems where replication and repair mechanisms are employed. We postulate that the proposed models can aid system designers, who can instantiate our models to assess and quantify the availability and reliability of systems of interest. Our study demonstrates that the configuration with most reliable and available systems depends on the parameter settings.

Subasi, Omer↗

Aviation Transportation, Cyber Threats, and Network-of-Networks: Modeling Perspectives for Translating Theory to Practice

Understanding aviation transportation infrastructure system behavior and coupling with communication networks is essential for securing and restoring functionality against cyber-enabled threats. While significant progress has been made in the past decade on developing infrastructure resilience theories based on network structure and operations, translating and generalizing them to real-world practice has often been challenging due to imperfect data and inapplicability of modeling assumptions. These typically include: 1) stylized network structures without uncertainty, 2) node homogeneity, 3) static criticality measures, and 4) unrealistic cascade models originating from single points of failure. This paper presents modeling perspectives that aim to address these theory-to-practice challenges using a well-grounded network-of-networks (NoN) construct. Real-world modeling challenges are identified and a network theory-guided conceptual NoN model is developed that may be operationalized with the U.S. national airspace system airport network (NASAN) and Federal Aviation Administration (FAA) communication network as application domain. Improving accuracy in loss of functionality estimates due to cyber events in communication networks and cascading air travel delay impacts is key for informing consequence-based decision support and risk/contingency analyses.

Bhatia, Udit↗

Stochastic correlation analysis to rank the impact of intermittent wind generation on unreliability margins of power systems

Power systems are vulnerable to extreme contingencies (like an outage of a major generating substation or transmission line) that can cause significant generation and load loss and can lead to further cascading outages of other transmission facilities and generators in the system. Power systems operators take time-ahead actions (real time to day ahead) actions based on forecasted data as well as telemetry. However, there is a probability of extreme swings in wind generation that can push the power system that is already close to system boundaries into unreliable states. Increasing penetration on wind generation and uncertainties in short term forecast can move the system into operational states that can violate N-1 reliability criteria. While the power system planning accounts for worst case analyses to mitigate such emergencies, it is necessary to understand the spatial and temporal correlation of load buses with intermittent wind generation. The ranking of wind generators based on stochastic correlation to unreliability margins of load buses provides an insight of system vulnerabilities that can be corrected by appropriate emergency controls. A Monte-Carlo simulation of wind uncertainty forecast is performed to identify the probability distributions of unreliability margins. Ranking of wind generators is performed based on stochastic correlation analysis of the wind power generated and the load losses at the buses. This helps in not only identifying weak buses in the power system but also in identifying the vulnerable wind locations to plan for system reinforcements. Power system modeling and hybrid simulation to calculate unreliability margins are performed using DCAT and demonstrated on the 32-bus Nordic test system.

generators, wind forecasting, wind power generatio↗

Stochastic basis adaptation and spatial domain decomposition for partial differential equations with random coefficients

We present a novel approach for high-dimensional stochastic partial differential equations that decomposes the computational domain into smaller disjoint subdomains and reduces the random dimension in each subdomain to save computational costs. The proposed approach combines spatial domain decomposition and stochastic basis adaptation in each subdomain. We adapt the stochastic basis in each subdomain such that the local solution has a low-dimensional random space representation. To compute the stochastic solution in each subdomain, we use the Neumann-Neumann algorithm, where we first estimate the interface solution and then evaluate the interior solution in each subdomain using the interface solution as a boundary condition. The interior solutions in each subdomain are computed independently of each other, which reduces the operation count from $\approx O(N^\alpha)$ to $\approx O(M^\alpha),$ where $N$ is the total number of degrees of freedom, $M$ is the number of degrees of freedom in each subdomain, and the exponent $\alpha>1$ depends on the uncertainty quantification method used. In addition, the localized nature of solutions makes the proposed approach highly parallelizable. We illustrate the accuracy and efficiency of the approach for a steady-state diffusion equation with a random space-dependent diffusion coefficient.

uncertainty quantification, basis adaptation↗

ROBUST ONLINE MONITORING FOR CALIBRATION ASSESSMENT OF TRANSMITTERS AND INSTRUMENTATION

Robust online monitoring (OLM) technologies are expected to enable the extension or elimination of periodic sensor calibration intervals in operating and new reactors. Specifically, the next generation of OLM technology is expected to include newly developed advanced algorithms that improve monitoring of sensor/system performance and enable the use of plant data to derive information that currently cannot be measured. These advances in OLM technologies will improve the safety and reliability of current and planned nuclear power systems through improved accuracy and increased reliability of sensors used to monitor key parameters. In this paper, we discuss an overview of research being performed within the Nuclear Energy Enabling Technologies (NEET)/Advanced Sensors and Instrumentation (ASI) program, for the development of OLM algorithms to use sensor outputs and, in combination with other available information, 1) determine whether one or more sensors are out of calibration or failing and 2) replace a failing sensor with reliable, accurate sensor outputs. Algorithm development is focused on the following OLM functions: • Signal validation – fault detection and selection of acceptance criteria • Virtual sensing – signal value prediction and acceptance criteria • Response-time assessment – fault detection and acceptance criteria selection A GP-based uncertainty quantification (UQ) method previously developed for UQ in OLM, was adapted for use in sensor-fault detection and virtual sensing. For signal validation, the various components to the OLM residual (which is computed using an AAKR model) were explicitly defined and modeled using a GP. Evaluation was conducted using flow loop data from multiple sources. Results using experimental data from laboratory-scale flow loops indicate that the approach, while capable of detecting sensor drift, may be incapable of discriminating between sensor drift and model inadequacy. This may be due to a simplification applied in the initial modeling, where the sensor degradation is assumed to be stationary. In the case of virtual sensors, the GP model was used in a predictive mode to estimate the correct sensor reading for sensors that may have failed. Results have indicated the viability of using this approach for virtual sensing. However, the GP model has proven to be computationally expensive, and so alternative algorithms for virtual sensing are being evaluated. Finally, automated approaches to performing noise analysis for extracting sensor response time were developed. Evaluation of this technique using laboratory-scale data indicates that it compares well with manual techniques previously used for noise analysis. Moreover, the automated and manual approaches for noise analysis also compare well with the current “gold standard”, hydraulic ramp testing, for response time monitoring. Ongoing research in this project is focused on further evaluation of the algorithms, optimization for accuracy and computational efficiency, and integration into a suite of tools for robust OLM that are applicable to monitoring sensor calibration state in nuclear power plants.

calibration interval extension↗

Virtual sensors for robust on-line monitoring (OLM) and Diagnostics

Unscheduled shutdown of nuclear power facilities for recalibration and replacement of faulty sensors can be expensive and disruptive to grid management. In this work, we present virtual (software) sensors that can replace a faulty physical sensor for a short duration thus allowing recalibration to be safely deferred to a later time. The virtual sensor model uses a Gaussian process model to process input data from redundant and other nearby sensors. Predicted data includes uncertainty bounds including spatial association uncertainty and measurement noise and error. Using data from an instrumented cooling water flow loop testbed, the virtual sensor model has predicted correct sensor measurements and the associated error corresponding to a faulty sensor.

Analytical study↗

Virtual sensors for robust on-line monitoring (OLM) and diagnostics - 197

Unscheduled shutdown of nuclear power facilities for recalibration and replacement of faulty sensors can be expensive and disruptive to grid management. In this work, we present virtual (software) sensors that can replace a faulty physical sensor for a short duration thus allowing recalibration to be safely deferred to a later time. The virtual sensor model uses a Gaussian process model to process input data from redundant and other nearby sensors. Predicted data includes uncertainty bounds including spatial association uncertainty and measurement noise and error. Using data from an instrumented cooling water flow loop test bed, the virtual sensor model has predicted correct sensor measurements and the associated error corresponding to a faulty sensor. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Agent-Centric Approach for Cybersecurity Decision-Support with Partial Observability

Generating automated cyber resilience policies for real-world settings is a challenging research problem that must account for uncertainties in system state over time and dynamics between attackers and defenders. In addition to understanding attacker and defender motives and tools, and identifying “relevant” system and attack data, it is also critical to develop rigorous mathematical formulations representing the defender’s decision-support problem under uncertainty. Game-theoretic approaches involving cyber resource allocation optimization with Markov decision processes (MDP) have been previously proposed in the literature. Moreover, advancements in reinforcement learning approaches have motivated the development of partially observable stochastic games (POSGs) in various multi-agent problem domains with partial information. Recent advances in cyber-system state space modeling have also generated interest in potential applicability of POSGs for cybersecurity. However, as is the case in strategic card games such as poker, research challenges using game-theoretic approaches for practical cyber defense applications include: 1) solving for equilibrium and designing efficient algorithms for large-scale, general problems; 2) establishing mathematical guarantees that equilibrium exists; 3) handling possible existence of multiple equilibria; and 4) exploitation of opponent weaknesses. Inspired by advances in solving strategic card games while acknowledging practical challenges associated with the use of game-theoretic approaches in cyber settings, this paper proposes an agent-centric approach for cybersecurity decision-support with partial system state observability.

Tipireddy, Ramakrishna↗