Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning based systems”

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 217 records · Page 12

Chapter 16 - Predictive Analytics for Comprehensive Energy Systems State Estimation

Energy sustainability is a subject of concern to many nations in the modern world. It is critical for electric power systems to diversify energy supply to include systems with different physical characteristics, such as wind energy, solar energy, electrochemical energy storage, thermal storage, bio-energy systems, geothermal, and ocean energy. Each system has its own range of control variables and targets. To be able to operate such a complex energy system, big-data analytics become critical to achieve the goal of predicting energy supplies and consumption patterns, assessing system operation conditions, and estimating system states - all providing situational awareness to power system operators. This chapter presents data analytics and machine learning-based approaches to enable predictive situational awareness of the power systems.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A machine learning model for predicting the minimum miscibility pressure of CO 2 and crude oil system based on a support vector machine algorithm approach

CO 2 enhanced oil recovery (EOR) is a potential way for carbon capture, utilization and storage (CCUS). Though, the effect of CO 2 injection is greatly influenced by the reservoir conditions. Typically, Minimum miscible pressure (MMP) is selected as one of the key parameters for the screening and evaluation of prospective CO 2 flooding. Conventional slim tube test is both accurate and widely accepted but it is inefficient. Existing empirical formulas for MMPs are easy to be used but have been proved inaccurate and unreliable. Machine learning-based methods have great advantages in predicting MMP. However, only predication accuracy is discussed for most models without the screening of the main control factors and further validation of the model reliability. In this paper, a new prediction model based on support vector machine (SVM) was developed for pure/impure CO 2 and crude oil system. This study was based on 147 sets of MMP data from the literature with full information on reservoir temperature, oil composition and gas composition. The main control factors were screened by several statistical methods. Unlike the conventional prediction models that verified by only prediction accuracy, learning curve and single factor control variable analysis are further validated to obtain the optimum model.

02 PETROLEUM↗

Autonomous sense and guide machine learning system

A system for generating a machine learning system to generate guidance information based on locations of objects is provided. The system accesses training data that includes training time-of-arrival (“TOA”) information of looks and guidance information for each look. The guidance information is based on a training collection of object locations. The TOA of a look represents, for each object location of a training collection of object locations, times between signals transmitted by transmitters and return signals received by receivers. The return signals represent signals reflected from an object at the object location. The system trains a machine learning system using the training data wherein the machine learning system inputs TOA information and outputs guidance information.

Beer, N. Reginald↗

Deep Reinforcement Scheduling of Energy Storage Systems for Real-time Voltage Regulation in Unbalanced LV Networks with High PV Penetration

The ever-growing higher penetration of distributed energy resources (DERs) in low-voltage (LV) distribution systems brings both opportunities and challenges to voltage support and regulation. This paper proposes a deep reinforcement learning (DRL)-based scheduling scheme of energy storage systems (ESSs) to mitigate system voltage deviations in unbalanced LV distribution networks. The ESS-based voltage regulation problem is formulated as a multi-stage quadratic stochastic program, with the objective of minimizing the expected total daily voltage regulation cost while satisfying operational constraints. While existing voltage regulation methods are mostly focused on onetime- step control, this paper explores a day-horizon systemwide voltage regulation problem. In other words, the size of action and state spaces are extremely high-dimensional and need to be delicately handled. Furthermore, in order to overcome the difficulty of modeling uncertainties and develop a realtime solution, a learn-to-schedule feedback control framework is proposed by adapting the problem to a model-free DRL setting. The proposed algorithm is tested on a customized 6-bus system and a modified IEEE 34-bus system. Simulation results validate the effectiveness and near-optimality of voltage regulation by ESS in comparison with a deterministic quadratic program solution.

Wang, Shengyi↗

Statistical Learning for Nonlinear Model Reduction from Local Simulations of Stochastic and Particle- and Agent-Based Systems

Stochastic physical systems across the sciences that have very high-dimensional state spaces, with a large number of fast degrees of freedom that force direct simulators to proceed by integration steps that are orders of magnitude smaller than events of interests (e.g., particle collisions). Examples range from molecular motion to dynamics of large populations of cells. A grand challenge in the simulation and understanding of such systems is the systematic construction of accurate, interpretable, reduced models, enabling faster simulations, revealing fundamental properties of the dynamics, and predicting phenomena of interest that the original simulator could not reached with sufficient accuracy or within a given computational budget. In this projected we developed novel statistical estimation/machine learning techniques for analyzing and building empirical reduced models for important families of high-dimensional stochastic systems, in particular: - we developed techniques for estimating interaction kernels in interacting particle- and agent-based systems, which are ubiquitous in Physics, Biology and many other sciences, given observed trajectories of the system; - we developed techniques for nonlinear model reduction for high-dimensional stochastic systems that have a small number of unknown, nonlinear slow variables, and a large number of fast modes, that are possibly of large magnitude, given observed short trajectories of the system in the form of bursts of trajectories from different initial conditions; - we developed novel techniques for estimating linear dynamical systems on graphs when both the dynamics and the underlying graph are unknown, and we have a sparse set of space-time observations; - we considered the problem of estimating an unknown nonlinear observation function of a standard process (e.g. Brownian motion), so that we can recognized if an observed dynamics is "just" a nonlinear version of a known dynamics; we also developed benchmarks for learning algorithms aimed at learning and classifying diffusion processes.

97 MATHEMATICS AND COMPUTING↗

Simulated wildfire burned area over the CONUS during 2001-2020

Wildfires have shown increasing trends in both frequency and severity across the Contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth System Models (ESMs). Alternatively, machine learning (ML) based fire models, which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ML4Fire-XGB) that integrates a pretrained eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM). A Fortran-C-Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001-2020, the ML4Fire-XGB model outperforms process-based fire models in terms of spatial distribution and seasonal variations. Sensitivity analysis confirms that the ML4Fire-XGB well captures the responses of the burned area to rising temperatures. The ML4Fire-XGB model has proved to be a new tool for studying vegetation-fire interactions, and more importantly, enables seamless exploration of climate-fire feedback, working as an active component in E3SM.

Liu, Ye↗

Adaptive PV Frequency Control Strategy Based on Real-time Inertia Estimation

The declining cost of solar Photovoltaics (PV) generation is driving its worldwide deployment. As conventional generation with large rotating masses is being replaced by renewable energy such as PV, the power system’s inertia will be affected. As a result, the system’s frequency may vary more dramatically in the case of a disturbance, and the frequency nadir may be low enough to trigger protection relays such as under-frequency load shedding. The existing frequency-watt function mandated in power inverters cannot provide grid frequency support in a loss-of-generation event, as PV plants usually do not have power reserves. Here, a novel adaptive PV frequency control strategy is proposed to reserve the minimum power required for grid frequency support. A machine learning model is trained to predict system frequency response under varying system conditions, and an adaptive allocation of PV headroom reserves is made based on the machine learning model as well as real-time system conditions including inertia. Case studies show the proposed control method meets the frequency nadir requirements using minimal power reserves compared to a fixed headroom control approach.

14 SOLAR ENERGY↗

Improving North American Wildfire Prediction by Integrating a Machine-Learning Fire Model in a Land Surface Model

Wildfires have shown increasing trends in both frequency and severity across the Contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth System Models (ESMs). Alternatively, machine learning (ML) based fire models, which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ML4Fire-XGB) that integrates a pretrained eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM) version 2.1. A Fortran-C-Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001-2020, the ML4Fire-XGB model outperforms process-based fire models in terms of spatial distribution and seasonal variations. Sensitivity analysis confirms that the ML4Fire-XGB well captures the responses of the burned area to rising temperatures. The ML4Fire-XGB model has proved to be a new tool for studying vegetation-fire interactions, and more importantly, enables seamless exploration of climate-fire feedback, working as an active component in E3SM.

54 ENVIRONMENTAL SCIENCES↗

Backpropagation-based learning with local derivative approximation and memory replay in biologically plausible neural systems

When learning, the brain modifies individual synaptic connections to reach a desired behavior. Animal and human brains have been shown to be incredibly capable of learning complex and varied functions across a wide variety of tasks. In recent years, artificial neural networks, inspired by human and animal brains, have shown great capabilities in learning a wide variety of difficult tasks. However, artificial neural networks primarily teach themselves through the use of backpropagation, a learning method which has no clear analogue within the brain. Additionally, Artificial Neural Networks primarily use continuous activation functions, which differ significantly from the spiking neuronal behavior present in the brain. In this paper, we discuss and demonstrate a biologically plausible learning method that approximates backpropagation through two techniques on Spiking Neural Networks. First, we show that the local temporal derivatives that are necessary for backpropagation can be approximately recovered through reconstruction using spike timings. Second, we show that through learning during a sleep phase, inspired by neuroscience research into memory replay, the localized parallel feedback path can learn to approximate the derivative through the forward path weight matrix, thus solving the weight transport problem. Lastly, we demonstrate that the combination of these two methods can approach or exceed the accuracy of backpropagation-based methods for a variety of neuromorphic vision tasks while maintaining biological plausibility.

42 ENGINEERING↗

Independent malware detection architecture

A system and method (referred to as the system) detect malware by training a rule-based model, a functional based model, and a deep learning-based model from a memory snapshot of a malware free operating state of a monitored device. The system extracts a feature set from a second memory snapshot captured from an operating state of the monitored device and processes the feature set by the rule-based model, the functional-based model, and the deep learning-based model. The system identifies identifying instances of malware on the monitored device without processing data identifying an operating system of the monitored device, data associated with a prior identification of the malware, data identifying a source of the malware, data identifying a location of the malware on the monitored device, or any operating system specific data contained within the monitored device.

Smith, Jared M.↗

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↗

Reinforcement Learning‐Based Adaptation of Grid Following Inverter's Internal Controller to Networked Microgrids' Strengths

The varying topological configurations, generator commitments and dispatches, and dynamic load demand lead to changing system's strengths during the operations of networked microgrids. When the system's strengths significantly change, the fixed control gains at large devices may result in unsatisfactory system performance; this necessitates the tuning of the control gains at large devices to adapt to the changing system's strengths. In this paper, observer-based reinforcement learning (RL) is utilised to automatically tune the proportional-integral (PI) gains of phase lock loop (PLL) controller of grid-following (GFL) inverters to adapt to the changing strengths of microgrids and networked microgrids. The RL agent in this framework augments an observer predicting system's strengths, from which the RL control policy will adjust accordingly to tune the PLL controller's gains towards the system's strengths. Also, to enhance the control performance, the recently introduced Barrier function-based RL framework is leveraged for the design of reward function to prevent the high frequency nadir. An operational 26 kV electric distribution system, which is modelled as networked microgrids, is used to illustrate the need and effectiveness of the proposed RL-tuned control.

frequency response↗

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↗

Machine-Learning-Assisted Hybrid Earth System Modelling

We propose a novel hybrid modeling approach that combines a physics-based, numerical model of the Earth system with a machine learning model. We also envision to integrate the hybrid model training with a data assimilation cycle, so that new observations update both the state estimate used as initial conditions and the machine learning model parameters.

58 GEOSCIENCES↗

Data-driven learning of Mori–Zwanzig operators for isotropic turbulence

Developing reduced-order models for turbulent flows, which contain dynamics over a wide range of scales, is an extremely challenging problem. In statistical mechanics, the Mori–Zwanzig (MZ) formalism provides a mathematically exact procedure for constructing reduced-order representations of high-dimensional dynamical systems, where the effects due to the unresolved dynamics are captured in the memory kernel and orthogonal dynamics. Turbulence models based on MZ formalism have been scarce due to the limited knowledge of the MZ operators, which originates from the difficulty in deriving MZ kernels for complex nonlinear dynamical systems. In this work, we apply a recently developed data-driven learning algorithm, which is based on Koopman's description of dynamical systems and Mori's linear projection operator, on a set of fully resolved isotropic turbulence datasets to extract the Mori–Zwanzig operators. With data augmentation using known turbulence symmetries, the extracted Markov term, memory kernel, and orthogonal dynamics are statistically converged and the generalized fluctuation–dissipation relation can be verified. The properties of the memory kernel and orthogonal dynamics, and their dependence on the choices of observables are investigated to address the modeling assumptions that are commonly used in MZ-based models. A series of numerical experiments are then constructed using the extracted kernels to evaluate the memory effects on prediction. The results show that the prediction errors are strongly affected by the choice of observables and can be further reduced by including the past history of the observables in the memory kernel.

97 MATHEMATICS AND COMPUTING↗

Automated Dynamic Demand Response Implementation on a Micro-grid

In this paper, we describe a system for real-time automated Dynamic and Sustainable Demand Response with sparse data consumption prediction implemented on the University of Southern California campus microgrid. Supply side approaches to resolving energy supply-load imbalance do not work at high levels of renewable energy penetration. Dynamic Demand Response (D 2 R) is a widely used demand-side technique to dynamically adjust electricity consumption during peak load periods. Our D 2 R system consists of accurate machine learning based energy consumption forecasting models that work with sparse data coupled with fast and sustainable load curtailment optimization algorithms that provide the ability to dynamically adapt to changing supply-load imbalances in near real-time. Our Sustainable DR (SDR) algorithms attempt to distribute customer curtailment evenly across sub-intervals during a DR event and avoid expensive demand peaks during a few sub-intervals. It also ensures that each customer is penalized fairly in order to achieve the targeted curtailment. We develop near linear-time constant-factor approximation algorithms along with Polynomial Time Approximation Schemes (PTAS) for SDR curtailment that minimizes the curtailment error defined as the difference between the target and achieved curtailment values. Our SDR curtailment problem is formulated as an Integer Linear Program that optimally matches customers to curtailment strategies during a DR event while also explicitly accounting for customer strategy switching overhead as a constraint. We demonstrate the results of our D 2 R system using real data from experiments performed on the USC smartgrid and show that 1) our prediction algorithms can very accurately predict energy consumption even with noisy or missing data and 2) our curtailment algorithms deliver DR with extremely low curtailment errors in the 0.01-0.05 kWh range.

Kuppannagari, Sanmukh R.↗

Additive Manufacturing – A New Challenge for Automation and Robotics

Additive manufacturing (AM) is a rapidly growing technology descended from the first stereolithography systems. AM describes a variety of material deposition technologies for forming objects in a digital manner layer-by-layer under computer control. Now commonly known as 3D printing, AM quickly branched out into several key directions – material extrusion, sheet lamination, direct energy deposition, vat polymerization, powder bed fusion, binder jetting, and material jetting. The common factor in all AM branches is a foundation in robotics and automation. While most of the mechanical 3D printing structures are based on simple gantry systems, there are Gough-Stewart platforms and, more recently, six or more DoF manipulator-based systems that have been developed. Currently available commercial systems are based on open-loop control with minimum sensing capabilities; the latest systems in development are starting to take advantage of complex feedback loops and layers of advanced sensing and data logging. The Manufacturing Demonstration Facility of Oak Ridge National Laboratory is leading the efforts in applying advanced robotics in the creation of large-scale 3D printers. The recent demonstration of an additively manufactured excavator at the CONEXPO 2017 exhibition in Las Vegas showed that the use of cutting edge robotics and automation is essential for the next generation of additive systems. The future of AM will heavily rely on advanced robotics, machine learning, and the internet of things. This paper summarizes progress in AM; presents the practical aspects, challenges, and lessons learned in developing robotic-based AM systems; and outlines the needs and future directions of robotics for AM.

Nycz, Andrzej↗