Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Operator 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 1,027 records · Page 57
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Navigating Exascale Operational Data Analytics: From Inundation to Insight

In this paper, we address the challenges in achieving sustainable data-driven efficiency by providing a detailed exploration of the end-to-end operational data analytics (ODA) framework that evolved through two generations of supercomputer systems at the Oak Ridge Leadership Computing Facility (OLCF). This framework addresses large data streams ingested from heavily instrumented HPC environment that accumulates multi-terabytes per day. We outline the multifaceted data life cycle across HPC procurement, operations, and research & development, identifying key obstacles and design decisions that shape effective strategies in building and supporting data pipelines end-to-end. By sharing key insights and lessons learned from our experience, we offer recommendations for the HPC community on enabling sustainable operational data analytics and beyond. Our contributions aim to bridge the gap between potential and real benefits of operational data, guiding future efforts towards integrated and sustainable operational intelligence in high-performance computing environments.

Shin, Woong↗
DOE OSTI2018

Peculiarities of Transition from Operation to Decommissioning for the Chernobyl NPP - 18486

Usually the transition period is supposed to last around 5 years and to cover the eventual defueling of the reactor and the reactor cooling pool, completion of the characterization survey and preparation of all necessary documents to start the decommissioning activities in accordance with the decommissioning strategy chosen and the decommissioning plan approved. It was not the case for the Chernobyl NPP due to a number of reasons and obstacles, including delayed defueling due to unavailability of the storage capacities, lack of preparatory work due to prescheduled decommissioning, luck of experience of RBMK-type reactors decommissioning, influence of the destroyed Chernobyl-4 Unit and related works on site. All these factors not only delayed the completion of the characterization survey, but added complications to development of the decommissioning strategy and the decommissioning plan. De facto the issue of end state is still open as the end state for the destroyed Chernobyl-4 as well as the prospects of the exclusion zone transformation need further clarifications and justifications. As a result, the need to reconsider the standard concept of transition period was recognized already by the end of 2000, when Chernobyl-1 and Chernobyl-2 were out of operation for a few years. It was clear that the personnel had generally a bad perception of the prescheduled permanent shutdown decision and a low motivation to change and to learn. The first signs of organizational degradation were visible and the framework of the operational license did not fit well to prevent it. So it was decided to start the legal and organizational transformation into the decommissioning mode without waiting for polishing of the decommissioning strategy and decommissioning plan as in this case both documents seemed to need further adjustments anyway. The transition period (or the termination of operation as it called in the national nuclear safety regulations) was considered as the first phase of decommissioning to be covered by the decommissioning license. The detailed plan of activities for the transition period with proper safety justification documents was the main part of the relevant license application. Human resource management plan and adoption of the management system were important constituents as well. It was also considered reasonable to start some dismantling works already at this phase to avoid further delays and degradation, the works being carefully justified. Eventually such approach added to streamlining the decommissioning process and to avoid further organizational and technical degradation. Flexibility in transition from operation to decommissioning seems necessary in cases of prescheduled or post-accidental decommissioning but may be also beneficial for a scheduled decommissioning case. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Parallel hybrid quantum-classical machine learning for kernelized time-series classification

Supervised time-series classification garners widespread interest because of its applicability throughout a broad application domain including finance, astronomy, biosensors, and many others. Here, in this work, we tackle this problem with hybrid quantum-classical machine learning, deducing pairwise temporal relationships between time-series instances using a timeseries Hamiltonian kernel (TSHK). A TSHK is constructed with a sum of inner products generated by quantum states evolved using a parameterized time evolution operator. This sum is then optimally weighted using techniques derived from multiple kernel learning. Because we treat the kernel weighting step as a differentiable convex optimization problem, our method can be regarded as an end-to-end learnable hybrid quantum-classical-convex neural network, or QCC-net, whose output is a data set-generalized kernel function suitable for use in any kernelized machine learning technique such as the support vector machine (SVM). Using our TSHK as input to a SVM, we classify univariate and multivariate time-series using quantum circuit simulators and demonstrate the efficient parallel deployment of the algorithm to 127-qubit superconducting quantum processors using quantum multi-programming.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks

Electroconvection is a multiphysics problem involving coupling of the flow field with the electric field as well as the cation and anion concentration fields. Here, we use electroconvection as a benchmark problem to put forward a new data assimilation framework, the DeepM&Mnet, for simulating multiphysics and multiscale problems at speeds much faster than standard numerical methods using pre-trained neural networks. We first pre-train DeepONets that can predict independently each field, given general inputs from the rest of the fields of the coupled system. DeepONets can approximate nonlinear operators and are composed of two sub-networks, a branch net for the input fields and a trunk net for the locations of the output field. DeepONets, which are extremely fast, are used as building blocks in the DeepM&Mnet and form constraints for the multiphysics solution along with some sparse available measurements of any of the fields. We demonstrate the new methodology and document the accuracy of each individual DeepONet, and subsequently we present two different DeepM&Mnet architectures that infer accurately and efficiently 2D electroconvection fields for unseen electric potentials. Furthermore, the DeepM&Mnet framework is general and can be applied for building any complex multiphysics and multiscale models based on very few measurements using pre-trained DeepONets in a “plug-and-play” mode.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Adaptive Deep Reinforcement Learning Algorithm for Distribution System Cyber Attack Defense With High Penetration of DERs

With grid modernization, smart inverters are increasingly used to execute advanced controls for distribution network reliability. However, this also increases the cyber-attack space. Here this paper focuses on the defense approaches to restore the system to normal operation circumstances in the presence of cyber-attacks. A unique deep reinforcement learning (DRL) method is developed to minimize voltage violations and reduce power losses for impacted feeders. The defense problem is reformulated as a Markov decision-making process to dynamically control DERs while minimizing load shedding. This is achieved via an improved soft actor-critic (SAC)-based DRL algorithm, which can govern DER set points and load-shedding scenarios in discrete and continuous modes via the auto-tune entropy and Gaussian policy features. Numerical comparison results on the modified IEEE 123-node system with other control approaches, such as Volt-VAR (VV), Volt-Watt (VW), and model predictive control (MPC) show that the proposed method can eliminate voltage violations and provide feasible control actions that perform complete mitigation of cyber-threats.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Operator inference for non-intrusive model reduction with quadratic manifolds

This paper proposes a novel approach for learning a data-driven quadratic manifold from high-dimensional data, then employing this quadratic manifold to derive efficient physics-based reduced-order models. The key ingredient of the approach is a polynomial mapping between high-dimensional states and a low-dimensional embedding. This mapping consists of two parts: a representation in a linear subspace (computed in this work using the proper orthogonal decomposition) and a quadratic component. The approach can be viewed as a form of data-driven closure modeling, since the quadratic component introduces directions into the approximation that lie in the orthogonal complement of the linear subspace, but without introducing any additional degrees of freedom to the low-dimensional representation. Combining the quadratic manifold approximation with the operator inference method for projection-based model reduction leads to a scalable non-intrusive approach for learning reduced-order models of dynamical systems. Further, applying the new approach to transport-dominated systems of partial differential equations illustrates the gains in efficiency that can be achieved over approximation in a linear subspace.

42 ENGINEERING↗
DOE OSTI2022

Data-driven cyber-attack detection for photovoltaic systems: A transfer learning approach

With increasing exposure to software-based sensing and control, power systems are facing higher risks of cyber/physical attacks. Here, to ensure system stability and minimize the potential economic losses, it is imperative to monitor the operating states and detect those attacks at the early stage. In this paper, a transfer learning method is proposed to detect cyber-attacks in photovoltaic (PV) systems with much less training data. First of all, two PV systems with a different number of PV inverters and power ratings are analyzed and their attack models are studied. Next, an attack detection Convolutional Neural Network (CNN) model was trained with rich amount of data from PV #1. Then, transfer learning was proposed to transfer the well-trained features from PV #1 to PV #2. Lastly, the attack detection model on PV #2 was trained based on the transferred CNN model. The experiment results show that the proposed transfer learning method achieves better accuracy and a faster convergence rate with a much less training dataset than conventional deep learning.

14 SOLAR ENERGY↗
DOE OSTI2022

Revenue prediction for integrated renewable energy and energy storage system using machine learning techniques

Revenue estimation for integrated renewable energy and energy storage systems is important to support plant owners or operators’ decisions in battery sizing selection that leads to maximized financial performances. A common approach to optimizing revenues of a hybrid hydro and energy storage system is using mixed-integer linear programming (MILP). Although MILP models can provide accurate production cost estimations, they are typically very computationally expensive. To provide a fast yet accurate first-step information to hydropower plant owners or operators who consider integrating energy storage systems, we propose an innovative approach to predicting optimal revenues of an integrated energy generation and storage system. In this study, we examined the performance of two prediction techniques: Generalized Additive Models (GAMs) and machine learning (ML) models developed based on artificial neural networks (ANN). Predictive equations and models are generated based on optimized solutions from a market participation optimization model, the Conventional Hydropower Energy and Environmental Resource System (CHEERS) model. The two predicting techniques reduce the computational time to evaluate annual revenue for one set of battery configurations from 3 h to 1 to 4 min per run while also being implementable with significantly less data. The model validation prediction errors of developed GAMs and ML models are generally below 5%; for model testing predictions, the ML models consistently outperform the regression equations in terms of root mean square errors. This new approach allows plant owners, operators, or potential investors to quickly access multiple battery configurations under different energy generation and market scenarios. This new revenue prediction method will therefore help reduce the barriers, and thereby promoting the deployment of battery hybridization with existing renewable energy sources.

13 HYDRO ENERGY↗
DOE OSTI2023

Data-driven analysis and prediction of wastewater treatment plant performance: Insights and forecasting for sustainable operations

Here this study presents a comprehensive performance and forecasting analysis of the As-Samra wastewater treatment plant (WWTP) in Jordan, with two main objectives. Firstly, a thorough evaluation of the plant's performance is conducted. The analysis involves independently assessing historical operational conditions, plant production, and their statistical correlations using various statistical techniques. The second objective focuses on developing a data-driven forecasting approach to predict the plant's production one month in advance, using multiple machine learning models. The results highlight the effectiveness of principal component analysis (PCA) in simplifying operational data, revealing distinct operational clusters, and identifying seasonal production patterns while showing correlations between operational conditions and overall power production. The support vector machine (SVM) forecasting model emerged as the top performer, showcasing the potential of a hybrid forecasting approach. The findings offer valuable perspectives for enhancing operational efficiency, refining production planning, and ultimately improving the environmental impact of the plant.

42 ENGINEERING↗
DOE OSTI2024

Photovoltaic Inverter Failure Mechanism Estimation Using Unsupervised Machine Learning and Reliability Assessment

This article introduces a data-driven approach to assessing failure mechanisms and reliability degradation in outdoor photovoltaic (PV) string inverters. The manufacturer's stated PV inverter lifetime can vary due to the impact of operating site conditions. To address limitations in degradation estimation through accelerated testing, condition monitoring, or degradation modeling, we propose a machine learning (ML) oriented approach. Utilizing data from a 1.4 MW PV power plant operational since 2016, with 46 string PV inverters tied to the grid, we employ the unsupervised one-class support vector machine ML technique to analyze inverter and sensor data, capable of classifying humidity cycling and temperature fluctuations as dominant failure mechanisms. Utilizing the anomaly alert relationship and alert details specific to the inverter, the level of PV inverter output is considered as its availability or available reliability. Subsequently, a continuous Markov model is applied to six-month alert data, revealing an average stated reliability of 20% after 20 years of continuous operation. These results support recommendations for time-bound preventive measures to enhance PV inverter reliability under diverse outdoor conditions. Furthermore, the approach provides a nondestructive, top–down, and generalized method for analyzing any commercial PV inverter exposed to outdoor conditions, contingent on the availability of relevant data.

14 SOLAR ENERGY↗
DOE OSTI2024

Barriers to adopting artificial intelligence and machine learning technologies in nuclear power

Artificial intelligence and machine learning (AI/ML) technologies offer unique opportunities to transform nuclear plant operations and power generation. Benefits will be felt not only within existing analog and digital instrumentation and control, but also within work processes, the integration of people with technology and most importantly, the business case. The application of this new technology can help simplify complex problems and produce more effective decision-making, making nuclear power safer, more efficient, and more economically viable in the current energy market. Nonetheless, there are potential barriers to its adoption that must be overcome. The purpose of this paper is to categorize, review, and discuss barriers to AI/ML adoption within the nuclear power industry, with a focus on existing commercial reactors. Unique considerations for advanced reactors are also offered. Here we provide a comprehensive overview of the historical, technical, and business barriers that the industry faces, as well as stakeholder readiness, and end-user acceptance. We underscore the importance of user experience and offer potential solutions in overcoming each barrier. These include provisions for easier plant data access, a friendly regulatory environment, and investment in user trust and explainable AI.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2019

Enhanced Quantum Synchronization via Quantum Machine Learning

Abstract The quantum synchronization between a pair of two‐level systems inside two coupled cavities is studied. By using a digital–analog decomposition of the master equation that rules the system dynamics, it is shown that this approach leads to quantum synchronization between both two‐level systems. Moreover, in this digital–analog block decomposition, the fundamental elements of a quantum machine learning protocol can be identified, in which the agent and the environment (learning units) interact through a mediating system, namely, the register. If the algorithm can be additionally equipped with a classical feedback mechanism, which consists of projective measurements in the register, reinitialization of the register state, and local conditional operations on the agent and environment subspace, a powerful and flexible quantum machine learning protocol emerges. Indeed, numerical simulations show that this protocol enhances the synchronization process, even when every subsystem experiences different loss/decoherence mechanisms, and gives the flexibility to choose the synchronization state. Finally, an implementation is proposed, based on current technologies in superconducting circuits.

Cárdenas‐López, Francisco A.↗
DOE OSTI2022

A Comparison of Machine Learning Methods for Frequency Nadir Estimation in Power Systems

An increasing penetration level of inverter-based renewable energy resources changes the inertia of power systems, posing challenges for maintaining the desired system frequency stability. An accurate frequency nadir estimation is crucial for power system operators to prepare preventive actions against large frequency excursions. In this paper, five machine learning methods - linear regression, gradient boosting, support vector regression, an artificial neural network, and XGBoost - are applied to two different datasets, i.e., 1) the unit generation dataset and 2) the system total inertia and headroom dataset, for the prediction of the frequency nadir. The training and testing datasets are generated through extensive generation scheduling simulations using Multi-timescale Integrated Dynamic and Scheduling (MI-DAS) toolbox on the Western Electricity Coordinating Council 240-bus system with high renewable penetration levels. Numerical results show that all five machine learning methods perform well in predicting the nadir frequency of the system. Among them, the gradient boosting and the XGBoost are clear winners yielding the best prediction accuracy in terms of four evaluation metrics.

data driven↗
DOE OSTI2016

Learning Team Review 2016-0001: Installing Outlets for Programmatic Equipment

The purpose of a Learning Team is to transfer and communicate the information into operational feedback and improvement. We want to pay attention to the small things that go wrong because they are often early warning signals and may provide insight into the health of the whole system. An ESR was placed in the October of 2015 to move/install a number of 120V and 208V outlets in 455-104B to support programmatic furnace needs. Electrical design review was completed for ESR 22217 on February 22, 2016 and a Design Change Form completed describing the modification needed as: demolish 1 existing receptacle and circuit leaving conduit and jbox for use to install new receptacle and 5 new receptacles/circuits are required and one existing receptacle is to be relocated, listed under FSR 149229. The FSR scope of work was written:: Please have the Electricians come out to perform demolition (1ea.), installation (6ea.)& relocation (1ea.) of receptacles / circuits. ESR 22217 & DCF-16-35-0455-1281 is in place for this work. Coordinate final receptacle locations with Laboratory Resident. Contact John Dunwoody or O-MC for this information. WO# 545580-01 was signed on April 20, 2016.: Electricians to perform demolition, installation, & relocation of receptacles / circuits PER attached DCF-16-0455-1281-SK-1.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

High Fidelity Digital Twins for BWRX-300 Critical Systems

This project developed and demonstrated digital-twin technology for advanced nuclear systems under the ARPA-E GEMINA program, with a focus on the BWRX-300 small modular reactor. The primary objective was to reduce operation and maintenance (O&M) costs through predictive health monitoring and model-based fault detection. The project combined MIT’s high-fidelity physics models and machine-learning and digital-twin algorithms, and GE Hitachi’s digital-twin algorithms and operational expertise to build physics-based digital twins capable of real-time system monitoring and maintenance scheduling.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Physics-based Models, Machine Learning, and Experiment: Towards Understanding Complex Electrode Degradation

Degradation phenomena in Li-ion batteries are highly complex, coupled, and sensitive to use history and operating conditions. In this study, we show how tracking model parameters in continuum-level physics-based models, expedited by machine learning, can be useful in testing hypotheses for degradation mechanisms. An exemplary analysis using this approach is presented for a set of lithium trivanadate ( L i x V 3 O 8 ) cathodes cycled over a range of current rates. A simple cell revival process is combined with the parameter estimates over the course of cycling to extract valuable insights into cathode evolution and eliminate hypothesized degradation mechanisms for these cathodes. The presented approach is expected to be broadly applicable for degradation analysis of other electrodes.

25 ENERGY STORAGE↗
DOE OSTI2020

Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems

In this work, we present Lift & Learn, a physics-informed method for learning low-dimensional models for large-scale dynamical systems. The method exploits knowledge of a system’s governing equations to identify a coordinate transformation in which the system dynamics have quadratic structure. This transformation is called a lifting map because it often adds auxiliary variables to the system state. The lifting map is applied to data obtained by evaluating a model for the original nonlinear system. This lifted data is projected onto its leading principal components, and low-dimensional linear and quadratic matrix operators are fit to the lifted reduced data using a least-squares operator inference procedure. Analysis of our method shows that the Lift & Learn models are able to capture the system physics in the lifted coordinates at least as accurately as traditional intrusive model reduction approaches. This preservation of system physics makes the Lift & Learn models robust to changes in inputs. Numerical experiments on the FitzHugh–Nagumo neuron activation model and the compressible Euler equations demonstrate the generalizability of our model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Deep reinforcement learning assisted co-optimization of Volt-VAR grid service in distribution networks

With the increasing penetration of distributed energy resources in distribution networks, Volt-VAR control and optimization (VVC/VVO) have become very important to ensure an acceptable quality of service to all customers. System operators can rely on slow-responding utility devices, including capacitor banks and on-load tap changing transformers, along with fast-responding battery and photovoltaic (PV) inverters for the VVC/VVO implementation. Because of variations in response time of these two classes of devices, and different control actions (discrete versus continuous), coordinated and optimal scheduling and operation have become of utmost importance. Here, this paper develops a look-ahead deep reinforcement learning (DRL)-based multi-objective VVO technique to improve the voltage profile of active distribution networks, decrease network and inverter power loss, and save the operational cost of the grid. It proposes a deep deterministic policy gradient (DDPG)-based approach to schedule the optimal reactive and/or active power set-points of fast-responding inverters, and a deep Q-network (DQN)-based DRL agent to schedule the discrete decisions variables of slow-responding assets. The reactive power output of PV and battery smart inverters are scheduled at 30-minute intervals and the capacitors’ commitment status is scheduled with several hour intervals. The proposed framework is validated on the modified IEEE 34-bus and 123-bus test cases with embedded PV and PV-plus-storage. To validate the efficacy of the proposed VVO, it is compared with several scenarios, including the base case without VVO, localized droop control of DERs, DDPG-only, and twin delayed DDPG (TD3) agent-based DRL techniques. The results justify the superior performance of the proposed method to improve the voltage profile, reduce network power loss, and minimize the look-ahead grid operational cost while minimizing the undesirable power losses in inverters as a result of power factor adjustments.

24 POWER TRANSMISSION AND DISTRIBUTION↗