Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “dynamic model learning”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Adaptively Learned Modeling for a Digital Twin of Hydropower Turbines with Application to a Pilot Testing System

In the development of a digital twin (DT) for hydropower turbines, dynamic modeling of the system (e.g., penstock, turbine, speed control) is crucial, along with all the necessary data interface, virtualization, and dashboard designs. Since the DT must mimic the actual dynamics of the hydropower turbine accurately, adaptive learning is required to train these dynamic models online so that the models in the DT can effectively follow the representation of the actual hydropower turbine dynamics accurately and reliably. This study presents an adaptive learning method for obtaining the hydropower turbine models for DT development of hydropower systems using the recursive least squares algorithm. To simplify the formulation, the hydropower turbine under consideration was assumed to operate near a fixed operating point, where the system dynamics can be well represented by a set of linear differential equations with constant parameters. In this context, the well-known six-coefficient model for the Francis turbine was formulated as the starting point to obtain input and output models for the turbine. Then, an adaptive learning mechanism was developed to learn model parameters using real-time data from a hydropower turbine testing system. This led to semi-physical modeling, in which first principles and data-driven modeling are integrated to produce dynamic models for DT development. Applications to a pilot system at the Norwegian University of Science and Technology (NTNU) were made, and the models learned adaptively using the data collected from the university’s pilot system. Desired modeling and validation results were obtained.

13 HYDRO ENERGY↗
DOE OSTI2021

A Secure Learning Control Strategy via Dynamic Camouflaging for Unknown Dynamical Systems under Attacks

This paper presents a secure reinforcement learning (RL) based control method for unknown linear time-invariant cyber-physical systems (CPSs) that are subjected to compositional attacks such as eavesdropping and covert attack. We consider the attack scenario where the attacker learns about the dynamic model during the exploration phase of the learning conducted by the designer to learn a linear quadratic regulator (LQR), and thereafter, use such information to conduct a covert attack on the dynamic system, which we refer to as doubly learning-based control and attack (DLCA) framework. We propose a dynamic camouflaging based attack-resilient reinforcement learning (ARRL) algorithm which can learn the desired optimal controller for the dynamic system, and at the same time, can inject sufficient misinformation in the estimation of system dynamics by the attacker. The algorithm is accompanied by theoretical guarantees and extensive numerical experiments on a consensus multi-agent system and on a benchmark power grid model.

Mukherjee, Sayak↗
NASA NTRS1997

Object-Oriented Control System Design Using On-Line Training of Artificial Neural Networks

This report deals with the object-oriented model development of a neuro-controller design for permanent magnet (PM) dc motor drives. The system under study is described as a collection of interacting objects. Each object module describes the object behaviors, called methods. The characteristics of the object are included in its variables. The knowledge of the object exists within its variables, and the performance is determined by its methods. This structure maps well to the real world objects that comprise the system being modeled. A dynamic learning architecture that possesses the capabilities of simultaneous on-line identification and control is incorporated to enforce constraints on connections and control the dynamics of the motor. The control action is implemented "on-line", in "real time" in such a way that the predicted trajectory follows a specified reference model. A design example of controlling a PM dc motor drive on-line shows the effectiveness of the design tool. This will therefore be very useful in aerospace applications. It is expected to provide an innovative and noval software model for the rocket engine numerical simulator executive.

Rubaai, Ahmed↗
DOE OSTI2020

Two-Layer Dynamic Recycling Model (2L-DRM): Learning from Moisture Tracking Models of Different Complexity

Atmospheric moisture tracking models are used to identify and quantify sources and sinks of water in the atmospheric branch of the hydrologic cycle. These models are primarily used to investigate the origin of moisture resulting in precipitation for particular regions around the globe. Moisture tracking models vary widely in their level of complexity, depending on the number of physical processes represented. Complex models are comprehensive in their physical representation, but computationally much more expensive than simple models, which only focus on specific physical processes and use simplifying assumptions. We present the mathematical derivation of the new two-layer dynamical recycling model (2L-DRM), a simple analytical moisture tracking model that relaxes the vertically-integrated formulation of the original one-layer DRM (Dominguez et al., 2006). By comparing the simple DRM to a very complex moisture tracking model that uses water vapor tracers embedded within the Weather Research and Forecast regional climate model (WRF-WVT) for the North American Monsoon region, we pinpoint the absence of vertical wind shear as the main deficiency in the simple DRM. When comparing both simple models (DRM and 2L-DRM) to the WRF-WVT (which we treat as ‘truth’), the 2L-DRM better captures the spatial extent, the net amount and the temporal variability of precipitation that originates from oceanic and local terrestrial sources. The 2L-DRM is well suited to study the large-scale climatological sources of moisture, and for these applications, performs on-par with the much more complex and computationally demanding WRF-WVT model.

Dominguez, Francina↗
DOE OSTI2020

Operator inference for non-intrusive model reduction of systems with non-polynomial nonlinear terms

Here in this work we present a non-intrusive model reduction method to learn low-dimensional models of dynamical systems with non-polynomial nonlinear terms that are spatially local and that are given in analytic form. In contrast to state-of-the-art model reduction methods that are intrusive and thus require full knowledge of the governing equations and the operators of a full model of the discretized dynamical system, the proposed approach requires only the non-polynomial terms in analytic form and learns the rest of the dynamics from snapshots computed with a potentially black-box full-model solver. The proposed method learns operators for the linear and polynomially nonlinear dynamics via a least-squares problem, where the given non-polynomial terms are incorporated on the right-hand side. The least-squares problem is linear and thus can be solved efficiently in practice. The proposed method is demonstrated on three problems governed by partial differential equations, namely the diffusion–reaction Chafee–Infante model, a tubular reactor model for reactive flows, and a batch-chromatography model that describes a chemical separation process. The numerical results provide evidence that the proposed approach learns reduced models that achieve comparable accuracy as models constructed with state-of-the-art intrusive model reduction methods that require full knowledge of the governing equations.

42 ENGINEERING↗
NASA NTRS2022

Deep Interacting Multiple Model Filtering

In this paper, a deep learning-based multiple model estimation framework is presented for the state estimation of hybrid dynamical systems from high dimensional observations such as camera images. A low dimensional vector which represents the measurement of the latent dynamical system and its corresponding variance are learned using a deep encoder neural network. An Interacting Multiple Model (IMM) filter is used to generate the latent state estimates and covariances using multiple dynamical models, which can be learned using backpropagation through time. The state estimates of the dynamical system and the corresponding covariance matrix are generated from the latent state estimates and covariance using a deep decoder neural network. The whole network is trained in an end-to-end manner using a loss function which minimizes the negative log-likelihood of the neural network parameters. Simulation results are presented using a 2D bouncing ball example and estimation error statistics are computed which demonstrates the accuracy and consistency of the estimation.

Ghananeel Rotithor↗
DOE OSTI2020

Physics-constrained Deep Recurrent Neural Models of Building Thermal Dynamics

We develop physics-constrained and control-oriented predictive deep learning models for the thermal dynamics of a real-world commercial office building. The proposed method is based on the systematic encoding of physics-based prior knowledge into a structured recurrent neural architecture. Specifically, our model mimics the structure of the building thermal dynamics model and leverages penalty methods to model inequality constraints. Additionally, we use constrained matrix parameterization based on the Perron-Frobenius theorem to bound the eigenvalues of the learned network weights. We interpret the stable eigenvalues as dissipativeness of the learned building thermal model. We demonstrate the effectiveness of the proposed approach on a dataset obtained from an office building with $20$ thermal zones.

Building Energy, structured neural networks↗
NASA NTRS2018

Southern California Megacity CO2, CH4, and CO Flux Estimates Using Ground- and Space-Based Remote Sensing and a Lagrangian Model

We estimate the overall CO2, CH4, and CO flux from the South Coast Air Basin using an inversion that couples Total Carbon Column Observing Network (TCCON) and Orbiting Carbon Observatory-2 (OCO-2) observations, with the Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model and the Open-source Data Inventory for Anthropogenic CO2 (ODIAC). Using TCCON data we estimate the direct net CO2 flux from the So-CAB to be 104±26 Tg CO2 yr(exp -1) for the study period of July 2013–August 2016. We obtain a slightly higher estimate of 120±30 Tg CO2 yr(exp -1) using OCO-2 data. These CO2 emission estimates are on the low end of previous work. Our net CH4 (360±90 Gg CH4 y(exp -1)) flux estimate is in agreement with central values from previous top-down studies going back to 2010 (342–440 Gg CH4 yr(exp -1)). CO emissions are estimated at 487±122 Gg CO yr(exp -1), much lower than previous top-down estimates (1440 Gg CO yr(exp -1)). Given the decreasing emissions of CO, this finding is not unexpected. We perform sensitivity tests to estimate how much errors in the prior, errors in the covariance, different inversion schemes, or a coarser dynamical model influence the emission estimates. Overall, the uncertainty is estimated to be 25%, with the largest contribution from the dynamical model. Lessons learned here may help in future inversions of satellite data over urban areas.

Total Carbon Column Observing Network (TCCON)↗
DOE OSTI2022

Deep Reinforcement Learning based Model-free On-line Dynamic Multi-Microgrid Formation to Enhance Resilience

Multi-microgrid formation (MMGF) is a promising solution for enhancing power system resilience. This paper proposes a new deep reinforcement learning (RL) based model-free on-line dynamic MMGF scheme. Additionally, the dynamic MMGF problem is formulated as a Markov decision process, and a complete deep RL framework is specially designed for the topologytransformable micro-grids. In order to reduce the large action space caused by flexible switch operations, a topology transformation method is proposed and an action-decoupling Q-value is applied. Then, a convolutional neural network (CNN) based multi-buffer double deep Q-network (CM-DDQN) is developed to further improve the learning ability of the original DQN method. The proposed deep RL method provides real-time computing to support the on-line dynamic MMGF scheme, and the scheme handles a long-term resilience enhancement problem using an adaptive on-line MMGF to defend changeable conditions. The effectiveness of the proposed method is validated using a 7-bus system and the IEEE 123-bus system. The results show strong learning ability, timely response for varying system conditions and convincing resilience enhancement.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Physics-assisted Latent Space Dynamics Learning for Stiff Collisional-radiative Models

Collisional-radiative (CR) models describe the atomic processes in a plasma by tracking the population density in the ground and excited states for each charge state of the atom/ion. These models predict important plasma properties such as charge state distributions and radiative emissivity and opacity. Accurate descriptions of the CR balance of the plasma are essential in fusion whole device modeling, especially when significant impurities are introduced into the plasmas. In an integrated fusion plasma and CR simulation, a CR model, which is a high-dimensional stiff ODE, needs to be solved on each grid point in the configuration space, and can overwhelm the overall computational cost. In this work, we propose a machine-learning-based method that discovers a latent space and learns its corresponding latent dynamics, which can capture the essential physics to make accurate predictions at much lower online computational cost. The proposed approach is physics-assisted, due to its combination of a physical latent space and a data-driven latent space. It has been demonstrated that the proposed architecture can predict both the full-order CR dynamics and a physical quantity of interest accurately.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Prospects of federated machine learning in fluid dynamics

Physics-based models have been mainstream in fluid dynamics for developing predictive models. In recent years, machine learning has offered a renaissance to the fluid community due to the rapid developments in data science, processing units, neural network based technologies, and sensor adaptations. So far in many applications in fluid dynamics, machine learning approaches have been mostly focused on a standard process that requires centralizing the training data on a designated machine or in a data center. In this article, we present a federated machine learning approach that enables localized clients to collaboratively learn an aggregated and shared predictive model while keeping all the training data on each edge device. We demonstrate the feasibility and prospects of such a decentralized learning approach with an effort to forge a deep learning surrogate model for reconstructing spatiotemporal fields. Our results indicate that federated machine learning might be a viable tool for designing highly accurate predictive decentralized digital twins relevant to fluid dynamics.

36 MATERIALS SCIENCE↗
NASA NTRS2004

Learning to Control Advanced Life Support Systems

Advanced life support systems have many interacting processes and limited resources. Controlling and optimizing advanced life support systems presents unique challenges. In particular, advanced life support systems are nonlinear coupled dynamical systems and it is difficult for humans to take all interactions into account to design an effective control strategy. In this project. we developed several reinforcement learning controllers that actively explore the space of possible control strategies, guided by rewards from a user specified long term objective function. We evaluated these controllers using a discrete event simulation of an advanced life support system. This simulation, called BioSim, designed by Nasa scientists David Kortenkamp and Scott Bell has multiple, interacting life support modules including crew, food production, air revitalization, water recovery, solid waste incineration and power. They are implemented in a consumer/producer relationship in which certain modules produce resources that are consumed by other modules. Stores hold resources between modules. Control of this simulation is via adjusting flows of resources between modules and into/out of stores. We developed adaptive algorithms that control the flow of resources in BioSim. Our learning algorithms discovered several ingenious strategies for maximizing mission length by controlling the air and water recycling systems as well as crop planting schedules. By exploiting non-linearities in the overall system dynamics, the learned controllers easily out- performed controllers written by human experts. In sum, we accomplished three goals. We (1) developed foundations for learning models of coupled dynamical systems by active exploration of the state space, (2) developed and tested algorithms that learn to efficiently control air and water recycling processes as well as crop scheduling in Biosim, and (3) developed an understanding of the role machine learning in designing control systems for advanced life support.

Subramanian, Devika↗
DOE OSTI2025

Dynamic in-context learning with conversational models for data extraction and materials property prediction

The advent of natural language processing and large language models (LLMs) has revolutionized the extraction of data from unstructured scholarly papers. However, ensuring data trustworthiness remains a significant challenge. In this paper, we introduce PropertyExtractor, an open-source tool that leverages advanced conversational LLMs such as Google gemini-pro and OpenAI gpt-4, blends zero-shot with few-shot in-context learning, and employs engineered prompts for the dynamic refinement of structured information hierarchies—enabling autonomous, efficient, scalable, and accurate identification, extraction, and verification of material property data. Our tests on material data demonstrate precision and recall that exceed 95% with an error rate of ∼9%, highlighting the effectiveness and versatility of the toolkit. Finally, databases for 2D material thicknesses, a critical parameter for device integration, and energy bandgap values are developed using PropertyExtractor. In particular, for the thickness database, the rapid evolution of the field has outpaced both experimental measurements and computational methods, creating a significant data gap. Our work addresses this gap and showcases the potential of PropertyExtractor as a reliable and efficient tool for the autonomous generation of various material property databases, advancing the field.

Ekuma, Chinedu E. (ORCID:0000000258527556)↗