Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “fast algorithm”

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 739 records · Page 41
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Super Resolving Unrolled Neural Networks for Remote Sensing

In remote sensing systems, the capabilities of the system are constrained by the complex interactions between size, weight, and power (SWAP) of potential designs. In electro-optical (EO) systems, examples of these critical parameters include the system’s sensitivity and resolution. Those parameters can be increased by ever larger optical apertures and focal planes but at the cost of more SWAP. Multi-image super resolution (MISR) techniques allow resolution to be enhanced via computation rather than more sophisticated optical hardware. These algorithms combine multiple images together into a single, higher resolution image, trading temporal resolution and computation for spatial resolution. Fielded MISR techniques, such as Drizzle, can require several hundred images to create a single super resolved image, implying reduced temporal resolution, increased data acquisition load, and limiting mission applications. Iterative techniques, such as model-based image reconstruction and compressive sensing, have been shown to create super resolved images using fewer images than Drizzle. They do this by posing an optimization problem that balances accuracy between a highly accurate physical model and an image model. In the case of super resolution, the physical model is defined by the relation between low resolution input images and the desired high resolution output image. The image model encodes some assumptions about the super resolved image. These assumptions are meant to suppress reconstruction artifacts that arise due to deterministic physical model error, stochastic measurement noise, and potential undersampling. In practice, the performance of iterative methods are limited by imaging models compatible with optimization. Deep learning-based methods can effectively learn image models of arbitrary complexity, but lack the theoretical explainability and robustness of iterative techniques. Consensus equilibrium (CE) generalizes the iterative techniques beyond optimization, enabling blackbox algorithms such as traditional and neural image denoisers to be used as the image model. CE-based approaches retain much of the explainability and robustness of iterative techniques while allowing the expressiveness of machine learning image models to be used. Additionally, by unrolling iterations of CE with an embedded image denoiser, the image denoiser can be further trained and specialized to the specific application with potentially higher quality reconstructions. Under this project, we demonstrated the feasibility of training an unrolled neural network based upon CE. While we didn’t train one, we showed that the CE process is differentiable and its gradient can be tractably computed. We also explored the usage of a variants of CE akin to generative neural works. Most importantly, we applied the CE framework to a number of problems including non-blind deconvolution, upsampling, single-image super resolution, MISR, event-based sensing, and saturated deconvolution. Our MISR prototype creates high quality reconstructions with an order of magnitude fewer images than previous approaches and, critically, produces these reconstructions fast enough for practical usage.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

Global Sensitivity Analysis Using the Ultra‐Low Resolution Energy Exascale Earth System Model

Abstract For decades, Arctic temperatures have increased twice as fast as average global temperatures. As a first step toward quantifying parametric uncertainty in Arctic climate, we performed a variance‐based global sensitivity analysis (GSA) using a fully coupled, ultra‐low resolution (ULR) configuration of version 1 of the U.S. Department of Energy's Energy Exascale Earth System Model (E3SMv1). Specifically, we quantified the sensitivity of six quantities of interests (QOIs), which characterize changes in Arctic climate over a 75 year period, to uncertainties in nine model parameters spanning the sea ice, atmosphere, and ocean components of E3SMv1. Sensitivity indices for each QOI were computed with a Gaussian process emulator using 139 random realizations of the random parameters and fixed preindustrial forcing. Uncertainties in the atmospheric parameters in the Cloud Layers Unified by Binormals (CLUBB) scheme were found to have the most impact on sea ice status and the larger Arctic climate. Our results demonstrate the importance of conducting sensitivity analyses with fully coupled climate models. The ULR configuration makes such studies computationally feasible today due to its low computational cost. When advances in computational power and modeling algorithms enable the tractable use of higher‐resolution models, our results will provide a baseline that can quantify the impact of model resolution on the accuracy of sensitivity indices. Moreover, the confidence intervals provided by our study, which we used to quantify the impact of the number of model evaluations on the accuracy of sensitivity estimates, have the potential to inform the computational resources needed for future sensitivity studies.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

A mechanistic model for creep and thermal aging in Alloy 709

This report describes a physics-based model for creep and thermal aging in Alloy 709. Alloy 709 is an advanced austenitic alloy, targeted for use in future Sodium Fast Reactors (SFRs) and other advanced reactors. The material has superior high temperature properties compared to currently qualified 316 and 304 stainless steels. However, the available creep and thermal aging test database for Alloy 709 is significantly more limited compared to the historical materials. The physics-based model developed here is one way to accelerate the qualification of the material by providing more accurate long-term predictions for creep properties and thermal aging, compared to current empirical time-extrapolate techniques. The crystal plasticity finite element model is used to predict the deformation and failure of alloy 709. The same setup for the CPFE model is used in both the baseline model calibration process and the simulation campaigns for parameter inference. Specific constitutive choices are made for Alloy 709 to capture the primary deformation mechanisms. The dislocation creep formulation developed by Hu and Cocks is extended to account for coupled precipitation formation and the grain boundary cavitation model developed by Sham, Needleman, et al. is used to model grain boundary cavitation-induced failure. A novel update algorithm is proposed to render the semi-discrete constitutive update for the Sham-Needleman model unconditionally stable. A progressive calibration approach is adopted based on the observations that several types of material responses can be effectively decoupled. A surrogate model is trained based on full-fledged CPFE simulations to accelerate the forward model evaluations, and stochastic variational inference (SVI) is used to calibrate the unknown microstructural model parameters. The calibrated mechanistic model is used to predict the long-term creep life of Alloy 709, and the predictions are compared against classical empirical approaches.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Turbulent flow characteristics in an 84-pin rod bundle for typical and damaged spacer grids

Hexagonal rod bundles arranged in a tightly packed triangular lattice are extensively used for heat transfer and energy generation applications. Staggered spacer grids are used to maintain the structural integrity of gas-cooled fast reactor (GFR) fuel assemblies, while inducing localized turbulence in flow. Damage to these spacer grids results in a disruption of flow fields within these hexagonal fuel bundles. Experimental flow visualizations are critical to identify the differences in local flow properties that the structural damage may cause. This experimental research investigates the flow-field characteristics at a near-wall and center plane in a prototypical 84-pin GFR fuel assembly. Newly installed typical spacers and spacers subject to naturally occurring damage due to material degradation over prolonged experimentation were investigated. Velocity fields were acquired by utilizing the matched-index-of-refraction method to obtain time-resolved particle image velocimetry measurements for a Reynolds number of 12 000. Reynolds decomposition statistical results divulged differences in the time-averaged velocity, velocity fluctuations, flow anisotropy, and Reynolds stress distributions. Galilean decomposition demarcated the influence of spacer grid damage on the velocity fields. To extract turbulent structures and elucidate mechanisms of flow instabilities, proper orthogonal decomposition analysis was employed. Reduced order flow reconstructions enabled the application of vortex identification algorithms to determine the spatial and statistical characteristics of vortices generated. This research work provides unique experimental data on the spacer grid condition-dependent flow. The results offer a deeper understanding of fluid dynamics behavior to support GFR rod bundle design efforts and computational fluid dynamics model validation.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Reserve Model of Energy Storage in Day-ahead Joint Energy and Reserve Markets: A Stochastic UC Solution

With many favorable advantages including fast response ability in particular, utility-level energy storage systems (ESS) are being integrated into energy and reserve markets to help mitigate uncertain renewable resources and fluctuant demands. This paper discusses a stochastic unit commitment (UC) model to explore capabilities of ESSs in providing valuable grid services by simultaneously joining energy and reserve markets. The proposed reserve model of ESSs presents the following features: (i) two constraints are proposed to formulate ESS’s reserve provision ability in each hour via six operation modes, namely increasing/reducing the level of charge, switching to discharge, increasing/reducing the level of discharge, switching to charge; (ii) as an energy-limited asset, constraints on ESS’s reserve deliverability across multiple hours is introduced to hold enough state of charge (SOC) headroom and floor room, guaranteeing that reserves cleared in individual hours are continuously deliverable over multiple successive hours without violating operation limits. Furthermore, a scenario-based UC model, which addresses uncertainties of renewables and demands, is adopted to evaluate reserves provided by ESSs and generators. To effectively solve the stochastic UC problem, the progressive hedging algorithm with heuristic approaches is discussed. A 6-bus system and a modified IEEE 118-bus system are used to illustrate effectiveness of the proposed approaches.

25 ENERGY STORAGE↗
DOE OSTI2021

In-situ Photophysical Monitors and Corrective Algorithms for Photovoltaic Film Deposition and Rapid Thermal Processing in Scalable Roll-to-Roll Manufacturing

This project evaluated three photophysics-based approaches for in situ process monitoring of the scalable deposition of perovskite photovoltaic films. Based on stakeholder input and the results of laboratory trials and literature analysis, two techniques, angle resolved elastic light scattering (ARLS) and time-resolved photoluminescence (TRPL) were prototyped and demonstrated with a mixture of simulation, offline and online tests. Also, a hybrid gas flow and humidity control enclosure was constructed and demonstrated to stabilize the ambient conditions around the slot die deposition process and were demonstrated to meet the target humidity control in situ. Due in part to a delayed start and COVID-related lab restrictions and personnel changes, some of the milestones were not met. In spite of these challenges, however, both techniques were prototyped through several iterations and demonstrated significant promise for rapid in line perovskite characterization within the targeted characterization time windows and these techniques are under further development for use in DE-FOA000235:2357-1586. The TRPL system was fully mounted and demonstrated on the scaled slot die roll to roll and sheet coating systems at the Washington Clean Energy Testbeds (WCET). Motivated by significant internal and stakeholder interest, the successful prototyping achieved here, the ongoing need for in-situ characterization for the scale-up of perovskite manufacturing, and the benefits of in situ photophysical characterization for future funded process development research, we are continuing with the principle aims of the project to develop effect in situ photophysical probes for fast analysis of the optoelectronic and structural quality of sheet based and roll to roll process perovskites. TRPLS and ARLS probes proposed in the project are to be completed with external support from the Washington Research Foundation at the WCET. We are currently actively engaged in the acquisition of components and plan to complete and test the probes within three months. It is our intention that these probes will then be used in ongoing perovskite development with our research and commercialization partners including First Solar and other member of the US MAP consortium in future funded development work.

14 SOLAR ENERGY↗
DOE OSTI2021

Measuring an ultrashort, ultraviolet pulse in a slowly responding, absorbing medium

Frequency-resolved optical gating (FROG) is a common technique for measuring ultrashort laser pulses using an instantaneous, nonlinear-optical interaction as a fast time-gate to measure the pulse intensity and phase. But at high frequencies, materials are often absorbing and it is not always possible to find a medium with a fast nonlinear-optical response. Here we show that an ultrashort, ultraviolet (UV) pulse can be measured in a strongly absorbing medium, using the absorption as the nonlinear-optical time-gate. To do this, we build on our recent implementation of FROG, known as induced-grating cross-correlation FROG (IG XFROG), where an unknown, higher-frequency pulse creates a transient grating that is probed with a lower-frequency, more easily detectable reference pulse. We demonstrate this with an 800 nm reference pulse to characterize 400 nm or 267 nm pulses using ZnS as the nonlinear-optical medium, which is absorptive at and below 400 nm. By scanning the delay between the two UV pulses which create the transient grating, we show that the phase-sensitive instantaneous four-wave-mixing contribution to the nonlinear signal field can be detected and separated from the slower, incoherent part of the response. Measuring a spectrally-resolved cross-correlation in this way and then applying a simple model for the response of the medium, we show that a modified generalized projections (GP) phase-retrieval algorithm can be used to extract the pulse amplitude and phase. We test this approach by measuring chirped UV pulses centered at 400 nm and 267 nm. Since interband absorption (or even photoionization) is not strongly wavelength-dependent, we expect IG XFROG to be applicable deeper into the UV.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2022

Marginal unbiased score expansion and application to CMB lensing

Here, we present the marginal unbiased score expansion (MUSE) method, an algorithm for generic high-dimensional hierarchical Bayesian inference. MUSE performs approximate marginalization over arbitrary non-Gaussian latent parameter spaces, yielding Gaussianized asymptotically unbiased and near-optimal constraints on global parameters of interest. It is computationally much cheaper than exact alternatives like Hamiltonian Monte Carlo (HMC), excelling on funnel problems which challenge HMC, and does not require any problem-specific user supervision like other approximate methods such as variational inference or many simulation-based inference methods. MUSE makes possible the first joint Bayesian estimation of the delensed Cosmic Microwave Background (CMB) power spectrum and gravitational lensing potential power spectrum, demonstrated here on a simulated data set as large as the upcoming South Pole Telescope 3G 1500 deg 2 survey, corresponding to a latent dimensionality of ~6 million and of order 100 global bandpower parameters. On a subset of the problem where an exact but more expensive HMC solution is feasible, we verify that MUSE yields nearly optimal results. We also demonstrate that existing spectrum-based forecasting tools which ignore pixel-masking underestimate predicted error bars by only ~10%. This method is a promising path forward for fast lensing and delensing analyses which will be necessary for future CMB experiments such as SPT-3G, Simons Observatory, or CMB-S4, and can complement or supersede existing HMC approaches. The success of MUSE on this challenging problem strengthens its case as a generic procedure for a broad class of high-dimensional inference problems.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

A Combined Computer Vision and Deep Learning Approach for Rapid Drone-Based Optical Characterization of Parabolic Troughs

Optical accuracy is a primary driver of parabolic trough concentrating solar power (CSP) plant performance, but can be damaged by wind loads, gravity, error during installation, and regular plant operation. Collecting and analyzing optical measurements over an entire operating parabolic trough plant is difficult, given the large scale of typical installations. Distant Observer, a software tool developed at the National Renewable Energy Laboratory, uses images of the absorber tube reflected in the collector mirror to measure both surface slope in the parabolic mirror and offset of the absorber tube from the ideal focal point. This technology has been adapted for fast data collection using low-cost commercial drones, but until recently still required substantial human labor to process large amounts of data. A new method leveraging advanced deep learning and computer vision tools can drastically reduce the time required to process images. This new method addresses the primary analysis bottleneck, identifying featureless, reflective mirror corner points to a high degree of accuracy. Recent work has shown promising results using computer vision methods. The combined deep learning and computer vision approach presented here proved highly effective and has the potential to further automate data collection and analysis, making the tool more robust. The method presented in this paper automatically identified 74.3% of mirror corners within 2 pixels of their manually marked counterparts and 91.9% within 3 pixels. This level of accuracy is sufficient for practical Distant Observer analysis within a target uncertainty. A commercial drone collected video of over 100 parabolic trough modules at an operating CSP plant to demonstrate the deep learning and computer vision method's usefulness in processing large amounts of data. These troughs were successfully analyzed using Distant Observer, paired with the new deep learning and computer vision algorithm, and can provide plant operators and trough designers with valuable insight about plant performance, operating strategies, and plant-wide optical error trends.

computer vision↗
DOE OSTI2024

Model-Based Detection of Coordinated Attacks (DCA) in Distribution Systems

The fast-paced growth in digitization of smart grid components enhances system observability and remote-control capabilities through efficient communication. However, enhanced connectivity results in heightened system vulnerability towards cybersecurity risks in the cyber-physical power system. Coordinated cyber-attacks (CCA), when undetected, lead to system-wide impact in terms of large disturbances or widespread outages. Detecting CCA in the cyber layer is critical to thwart cyber-attacks in real-time before the attack impacts the physical system. The challenge of locating CCA stems from the complex grid dynamics, making it difficult to distinguish between normal operational variations and cyber-attack impact. CCA often employs multiple attack vectors targeting geographically distributed components, further complicating CCA identification. Existing research in intrusion detection is primarily focused on the transmission network and limited to detecting individual attacks. In this paper, a novel proactive DCA strategy is proposed for early detection of CCA by establishing correlations among distinct attack events through model-based reinforcement learning that utilizes abductive reasoning to conclude the attacker goal. The solution includes understanding the system model, learning the system dynamics, and correlating individual cyber-attacks to extract the attacker’s objective. The developed learning algorithm identifies the most probable attack path to reach the attacker’s objective by predicting the next attack steps. A DNP3-based cyber-physical co-simulation testbed is developed to test the proposed algorithm using the IEEE 13-node test feeder.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Model predictive control of heating, ventilation, and air conditioning (HVAC) systems: A state-of-the-art review

Due to the fast advancement of communication and information technology, intelligent buildings have garnered great interest. These buildings can forecast weather, ambient temperature, and sun irradiation and can modify heating, ventilation, and air conditioning (HVAC) operations appropriately, based on current and previous data. This change is intended to reduce HVAC system energy usage while maintaining an appropriate degree of thermal comfort and indoor air quality. Since its inception, model predictive control (MPC) has been one of the prospective solutions for HVAC management systems to reduce both costs and energy usage. Additionally, MPC is becoming increasingly practical as the processing capacity of building automation systems increases and a large quantity of monitored building data becomes available. MPC also provides the potential to improve the energy efficiency of HVAC systems via its capacity to consider limitations, to predict disruptions, and to factor in multiple competing goals such as interior thermal comfort and building energy consumption. Although substantial research has been conducted on MPC in building HVAC systems, there is a shortage of critical reviews and a lack of a comprehensive framework that formulates and defines the applications. Here, this article provides a comprehensive state-of-the-art overview of MPC in HVAC systems. Detailed discussions of modeling approaches and optimization algorithms are included. Numerous design aspects such as prediction horizon, occupancy behavior, building type, and cost function, that impact MPC performance are discussed in detail. The technical characteristics, advantages, and disadvantages of various types of modeling software are discussed. The primary objective of this work is to highlight critical design characteristics for the MPC control scheme and to give improved suggestions for future research. Moreover, numerous prospective scenarios have been suggested that might provide future research direction.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

Phase-field modeling of thermally-grown oxide and damage evolution in environmental barrier coatings

Silicon carbide-based ceramic matrix composites protected by environmental barrier coatings (EBCs) present a promising materials solution for next-generation gas turbines. Developing more robust and efficient EBCs is therefore of significant technological importance. During the service in high-temperature oxidative environments, there is a thermally grown oxide (TGO) layer, spontaneously formed in the EBC system. TGO is recognized as a critical factor for the degradation and failure of EBCs, yet the detailed mechanisms of TGO growth and its effect on EBC failure remain unclear. In this study we develop a comprehensive chemo-mechano-phase-field model to simulate growth of the TGO in EBCs, factoring in creep and deformation, and especially the cracking behaviors. The volume expansion due to TGO growth and the resulting large inelastic deformation are addressed by using our recently developed, so-called incremental realization of inelastic deformation (IRID) algorithm, in combination with an adapted Hu-Chen spectral solver for elasticity. Simulations of TGO growth are performed considering different growth modes of TGOs determined mainly by the ratio of oxidant permeability in the topcoat to that in the TGO itself. Large-scale three-dimensional (3D) simulations are performed to model the formation of interconnecting vertical/channel cracks (often called ‘mud cracks’). The simulated crack morphology are in excellent agreement with the experimental observations from the literature. The simulations also provide insights into the cracking of EBCs and its dependence on the structure and constituent properties of the coating system. Furthermore, these results demonstrate the developed damage model can be a useful tool for design of more durable EBCs.

Cracking↗
DOE OSTI2023

Smart Manufacturing Pathways for Industrial Decarbonization and Thermal Process Intensification

Rapid decarbonization is fast becoming the primary environmental and sustainability initiative for many economic sectors. Industry consumes more than 30 % of all primary energy in the United States and accounts for nearly 25 % of all greenhouse gas (GHG) emissions. More than 70 % of energy consumed by the industrial sector is related to thermal processes, which are also the largest contributors of carbon emissions, overwhelmingly due to the combustion of fossil fuels. Thermal process intensification (TPI) seeks to dramatically improve the energy performance of thermal systems through technology pillars focusing on alternative energy sources and processes, supplemental technologies, and waste heat management. The impacts of TPI have significant overlap with the goals of industrial decarbonization (ID) that seeks to phase out all GHG emissions from industrial activities. Emerging supplemental technologies such as smart manufacturing (SM) and the industrial internet of things (IoT) enable significant opportunities for the optimization of manufacturing processes. Combining strategies for TPI and ID with SM and IoT can open and enhance existing opportunities for saving time and energy via approaches such as tighter control of temperature zones, better adjustment of thermal systems for variations in production levels and feedstock properties, and increased process throughput. Data collected by smart processes will also enable new advanced solutions such as digital twins and machine learning algorithms to further improve thermal system savings. Herein, this paper examines the individual pathways of TPI, ID, and SM and how the combination of all three can accelerate energy and GHG reductions.

42 ENGINEERING↗
DOE OSTI2020

Fast inference of Boosted Decision Trees in FPGAs for particle physics

We describe the implementation of Boosted Decision Trees in the hls4ml library, which allows the translation of a trained model into FPGA firmware through an automated conversion process. Thanks to its fully on-chip implementation, hls4ml performs inference of Boosted Decision Tree models with extremely low latency. With a typical latency less than 100 ns, this solution is suitable for FPGA-based real-time processing, such as in the Level-1 Trigger system of a collider experiment. These developments open up prospects for physicists to deploy BDTs in FPGAs for identifying the origin of jets, better reconstructing the energies of muons, and enabling better selection of rare signal processes.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

Parallel-in-Time Simulation of Lindblad's Equation

Constructing fast quantum logic gates is critical to building a scalable quantum computer. We consider a qudit, a quantum version of a bit that can take an arbitrary number of states, coupled with a cavity. In this project, we wish to force the qudit to reach the 0-state, for any possible initial state. The coupled system changes in time according to Lindblad’s equation, an ordinary differential equation on the density matrix of the quantum system. Lindblad’s equation contains some parameters that we can control, so-called control functions. We seek control functions which force the qudit to the 0-state within 2 microseconds, which is much faster than what is currently done in practice. The search method is gradient descent, a numerical optimization method that uses gradient information to iteratively improve the control parameters. My contribution to this project is an attempt to speed up the computation of the gradient. It currently takes about 40 seconds to compute the gradient which involves solving a set of ODEs sequentially. Current supercomputers have thousands of cores, but sequential computations can only make use of 1 core at a time. We wish to divide up the work better, so that we can use many more cores at once. To this end, we have implemented the Multigrid Reduction in Time (MGRIT) algorithm. We perform a systematic parameter search on how to best apply this algorithm. Results indicate a 25 percent speed up for solving Lindblad’s equation and determining how close the final state is the 0-state.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

An analysis of fluff formation in metallic fuel via data analyzes from EBR-II experiments and BISON fuel code modeling

During the operation of EBR-II, it was found that a highly porous structure (over 40% area fraction) formed at the top of several fuel columns. Previous work has shown that this structure, designated fluff in this paper, contains a significant fraction of fuel elements (e.g., U and Pu) which could potentially impact neutronics. This work aims in analyzing the formation mechanism of this microstructure so its impact can be incorporated into future metallic fuel modeling codes and algorithms. This paper details a preliminary examination into the formation mechanisms of fluff by performing qualitative and statistical analysis of EBR-II experimental data. Additionally, the operating conditions that have the greatest impact on fluff formation were determined based on this data set. Also, BISON fuel code simulations were used to help postulate potential fluff formation mechanisms. From this analysis it was found that the largest contributors to fluff formation were fuel burnup and composition, with fluff formation exhibiting a roughly linear positive correlation with increasing burnup and a negative correlation with increasing Pu content. It was also found that higher pin operating temperatures decreased fluff formation but only for U-10Zr fuels.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems

We report faults in Heating, Ventilation, and Air Conditioning (HVAC) systems of buildings result in significant energy waste in building operation. With fast-growing sensing data availability and advancement in computing, computational modeling has demonstrated strong capability to detect and diagnose HVAC system faults, hence, ensuring efficient building operation. This paper comprehensively reviews the state-of-the-art computing-based fault detection and diagnosis (FDD) for HVAC systems. Overall, the reviewed computing-based FDD methods are classified as two major approaches: knowledge-based and data-driven approaches. We then identify multiple important topics, including data availability, training data size, data quality, approach generality, capability, interpretability, and required modeling efforts, along with corresponding metrics to summarize the most updated FDD development. Generally, the knowledge-based approaches are further divided as physics-based modeling, Diagnostic Bayesian Network, and performance indicator-based methods while data-driven approaches include supervised learning, unsupervised learning, and regression and statistics-based methods. State-of-the-art FDD development, remaining challenges, and future research directions are further discussed to push forward FDD in practice. Availability of fault data, capability of existing methods to deal with complex fault situations (such as simultaneous faults), modeling interpretability for data-driven methods, and required engineering efforts for physics-based methods are identified as remaining challenges in FDD development. Improving modeling fidelity and reducing modeling efforts are essential for applying physics-based methods in real buildings. Meanwhile, addressing fault data availability, increasing algorithm adaptability, and handling multiple faults are essential to further enhance the applicability of data-driven FDD approaches.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Deep learning to estimate permeability using geophysical data

Time-lapse electrical resistivity tomography (ERT) is a popular geophysical method to estimate three-dimensional (3D) permeability fields from electrical potential difference measurements. Traditional inversion and data assimilation methods are used to ingest this ERT data into hydrogeophysical models to estimate permeability. Due to ill-posedness and the curse of dimensionality, existing inversion strategies provide poor estimates and low resolution of the 3D permeability field. Recent advances in deep learning provide us with powerful algorithms to overcome this challenge. This paper presents a deep learning (DL) framework to estimate the 3D subsurface permeability from time-lapse ERT data. To test the feasibility of the proposed framework, we train DL-enabled inverse models on simulation data. Each measurement in both synthetic and field data is standardized by removing the mean and scaling the time-series to unit variance. This pre-processing step is necessary to bring simulation data closer to field observations. Subsurface process models based on hydrogeophysics are used to generate this synthetic data. Training performed on limited simulation data resulted in the DL model over-fitting. An advanced data augmentation based on mixup is implemented to generate additional training samples to overcome this issue. This mixup technique creates weakly labeled (low-fidelity) samples from strongly labeled (high-fidelity) data. The weakly labeled training data is then used to develop DL-enabled inverse models and reduce over-fitting. As both time-lapse ERT (1133048 features/realization) and 3D permeability (585453 features/realization) data samples are from a high-dimensional space, principal component analysis (PCA) is employed to reduce dimensionality. Encoded ERT and encoded permeability are generated using the trained PCA estimators. A deep neural network is then trained to map the encoded ERT to encoded permeability. This mixup training and unsupervised learning allowed us to build a fast and reasonably accurate DL-based inverse model under limited simulation data. Results show that proposed weak supervised learning can capture salient spatial features in the 3D permeability field. Quantitatively, the average mean squared error (in terms of the natural log) on the strongly labeled training, validation, and test datasets is less than 0.5. The R 2 -score (global metric) is greater than 0.75, and the percent error in each cell (local metric) is less than 10%. Finally, an added benefit in terms of computational cost is that the proposed DL-based inverse model is at least O(10 4 ) times faster than running a forward model once it is trained. Data generation, DL model training, and hyperparameter tuning to identify optimal neural network architectures utilized high-performance computing resources while the DL inference is performed on a standard laptop. Approximately, O(10 5 ) processor hours are used for generating data and DL tuning and training. We acknowledge that the data generation and DL model development are expensive. But once a DL model is trained, it can be re-used for inversion rapidly for the given system, with set physics and domain. Note that traditional inversion may require multiple forward model simulations (e.g., in the order of 10 to 1000), which are very expensive. This computational savings ≈ O(10 5 ) – O(10 7 )) makes the proposed DL-based inverse model attractive for subsurface imaging and real-time ERT monitoring applications due to fast and yet reasonably accurate estimations of permeability field.

58 GEOSCIENCES↗