Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “generalizability”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Data‐Driven Engineering of Thermostable Collagen‐Mimetic Peptoid Triple Helices

Collagen-mimetic peptides (CMPs) are engineered molecules designed to replicate the triple-helical structure of natural collagen. A repeating x–y-Gly sequence is the defining motif of CMPs and is critical to their triple-helical structure and stability. Substitutions to the residues occupying the x and y positions present a means to modulate the CMP structure and properties. Peptoid residues—N-substituted glycine derivatives—present an attractive potential substitution due to their thermal stability, proteolytic resistance, biocompatibility, and diverse palette of non-natural side chains, but also tend to introduce a high degree of backbone flexibility that can diminish the stability of the triple helix. In this work, we report a computational active learning cycle comprising molecular dynamics simulation, Gaussian process regression, and Bayesian optimization to computationally identify a number of promising peptoid substitutions predicted to stabilize the desired quaternary structure through side chain interactions and produce stable peptoid-based collagen-like triple helices. To experimentally test the computational predictions, a top candidate identified by the screen was synthesized and imaged using scanning electron microscopy to resolve fibril-like bundles consistent with collagen-like triple helices. This work predicts a number of CMP peptoid substitutions capable of forming stable triple-helical structures, presents a generalizable design strategy for engineering desired peptoid structures, and opens new avenues for the design of peptoid-based biomimetic materials.

active learning↗
DOE OSTI2020

Voxel carving–based 3D reconstruction of sorghum identifies genetic determinants of light interception efficiency

Changes in canopy architecture traits have been shown to contribute to yield increases. Optimizing both light interception and light interception efficiency of agricultural crop canopies will be essential to meeting the growing food needs. Canopy architecture is inherently three-dimensional (3D), but many approaches to measuring canopy architecture component traits treat the canopy as a two-dimensional (2D) structure to make large scale measurement, selective breeding, and gene identification logistically feasible. We develop a high throughput voxel carving strategy to reconstruct 3D representations of sorghum from a small number of RGB photos. Our approach builds on the voxel carving algorithm to allow for fully automatic reconstruction of hundreds of plants. It was employed to generate 3D reconstructions of individual plants within a sorghum association population at the late vegetative stage of development. Light interception parameters estimated from these reconstructions enabled the identification of known and previously unreported loci controlling light interception efficiency in sorghum. The approach is generalizable and scalable, and it enables 3D reconstructions from existing plant high throughput phenotyping datasets. We also propose a set of best practices to increase 3D reconstructions’ accuracy.

3D plant reconstruction↗
DOE OSTI2022

Position-specific carbon isotope analysis of serine by gas chromatography/Orbitrap mass spectrometry, and an application to plant metabolism

Position-specific 13 C/ 12 C ratios within amino acids remain largely unexplored in environmental samples due to methodological limitations. We hypothesized that natural-abundance isotope patterns in serine may serve as a proxy for plant metabolic fluxes including photorespiration. Here we describe an Orbitrap method optimized for the position-specific carbon isotope analysis of serine to test our hypothesis and discuss the generalizability of this method to other amino acids. Position-specific carbon isotope ratios of serine were measured using a Thermo Scientific™ Q Exactive™ GC Orbitrap™. Amino acids were hydrolyzed from Arabidopsis biomass, purified from potential matrix interferences, and derivatized alongside standards. Derivatized serine (N,O-bis(trifluoroacetyl)methyl ester) was isolated using gas chromatography, trapped in a reservoir, and purged into the electron ionization source over tens of minutes, producing fragment ions containing different combinations of atoms from the serine-derivative molecule. The 13 C/ 12 C ratios of fragments with monoisotopic masses of 110.0217, 138.0166, and 165.0037 Da were monitored in the mass analyzer and used to calculate position-specific δ 13 C values relative to a working standard. This methodology constrains position-specific δ 13 C values for nanomole amounts of serine isolated from chemically complex mixtures. The δ 13 C values of fragment ions of serine were characterized with ≤1‰ precisions, leading to propagated standard errors of 0.7–5‰ for each carbon position. Position-specific δ 13 C values differed by up to ca 28 ± 5‰ between serine molecules hydrolyzed from plants grown under contrasting pCO 2 , selected to promote different fluxes through photosynthesis and photorespiration. The method was validated using pure serine standards characterized offline. Here this study presents the first Orbitrap-based measurements of natural-abundance, position-specific carbon isotope variation in an amino acid isolated from a biological matrix. We present a method for the precise characterization of isotope ratios in serine and propose applications probing metabolism in plants. We discuss the potential for extending these approaches to other amino acids, paving the way for novel applications.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Use of Longitudinal Serum Analysis and Machine Learning to Develop a Classifier for Cancer Early Detection

Early detection of solid tumors through a simple screening process, such as the proteomic analysis of biofluids, has the potential to significantly alter the management and outcomes of cancers. The application of advanced targeted proteomics measurements and data analysis strategies to uniformly collected serum or plasma samples would enable longitudinal studies of cancer risk, progression, and response to therapy that have the potential to significantly reduce cancer burden in general. In this article, we describe a generalizable workflow combining robust, multiplexed targeted proteomics measurements applied to longitudinal samples from the Department of Defense Serum Repository with a Random Forest machine learning method for developing and initially evaluating the performance of candidate biomarker panels for early detection of cancers. The effectiveness of this approach was demonstrated in a cohort of 175 head and neck squamous cell carcinoma patients. The outlined protocols include methods for sample preparation, instrument analysis, and data analysis and interpretation using this workflow.

Longitudinal analysis, machine learning, cancer, e↗
DOE OSTI2021

Energy and Emission Prediction for Mixed-Vehicle Transit Fleets Using Multi-task and Inductive Transfer Learning

Public transit agencies are focused on making their fixed-line bus systems more energy efficient by introducing electric (EV) and hybrid (HV) vehicles to their fleets. However, because of the high upfront cost of these vehicles, most agencies are tasked with managing a mixed-fleet of internal combustion vehicles (ICEVs), EVs, and HVs. In managing mixed-fleets, agencies require accurate predictions of energy use for optimizing the assignment of vehicles to transit routes, scheduling charging, and ensuring that emission standards are met. The current state-of-the-art is to develop separate neural network models to predict energy consumption for each vehicle class. Although different vehicle classes’ energy consumption depends on a varied set of covariates, we hypothesize that there are broader generalizable patterns that govern energy consumption and emissions. In this paper, we seek to extract these patterns to aid learning to address two problems faced by transit agencies. First, in the case of a transit agency which operates many ICEVs, HVs, and EVs, we use multi-task learning (MTL) to improve accuracy of forecasting energy consumption. Second, in the case where there is a significant variation in vehicles in each category, we use inductive transfer learning (ITL) to improve predictive accuracy for vehicle class models with insufficient data. As this work is to be deployed by our partner agency, we also provide an online pipeline for joining the various sensor streams for fixed-line transit energy prediction. Here, we find that our approach outperforms vehicle-specific baselines in both the MTL and ITL settings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Multi-task Parallelism for Robust Pre-training of Graph Foundation Models on Multi-source, Multi-fidelity Atomistic Modeling Data

Graph foundation models using graph neural networks promise sustainable, efficient atomistic modeling. To tackle challenges of processing multi-source, multi-fidelity data during pre-training, recent studies employ multi-task learning, in which shared message passing layers initially process input atomistic structures regardless of source, then route them to multiple decoding heads that predict data-specific outputs. This approach stabilizes pre-training and enhances a model’s transferability to unexplored chemical regions. Preliminary results on approximately four million structures are encouraging, yet questions remain about generalizability to larger, more diverse datasets and scalability on supercomputers. We propose a multi-task parallelism method that distributes each head across computing resources with GPU acceleration. Implemented in the open-source HydraGNN architecture, our method was trained on over 24 million structures from five datasets and tested on the Perlmutter, Aurora, and Frontier supercomputers, demonstrating efficient scaling on all three highly heterogeneous super-computing architectures.

Lupo Pasini, Massimiliano [ORNL] (ORCID:0000000249↗
DOE OSTI2023

Fast and accurate reduced-order modeling of a MOOSE-based additive manufacturing model with operator learning

One predominant challenge in additive manufacturing (AM) is to achieve specific material properties by manipulating manufacturing process parameters during the runtime. Such manipulation tends to increase the computational load imposed on existing simulation tools employed in AM. The goal of the present work is to construct a fast and accurate reduced-order model (ROM) for an AM model developed within the Multiphysics Object-Oriented Simulation Environment (MOOSE) framework, ultimately reducing the time/cost of AM control and optimization processes. Our adoption of the operator learning (OL) approach enabled us to learn a family of differential equations produced by altering process variables in the laser’s Gaussian point heat source. More specifically, we used the Fourier neural operator (FNO) and deep operator network (DeepONet) to develop ROMs for time-dependent responses. Furthermore, we benchmarked the performance of these OL methods against a conventional deep neural network (DNN)-based ROM. Ultimately, we found that OL methods offer comparable performance and, in terms of accuracy and generalizability, even outperform DNN at predicting scalar model responses. The DNN-based ROM afforded the fastest training time. Furthermore, all the ROMs were faster than the original MOOSE model yet still provided accurate predictions. FNO had a smaller mean prediction error than DeepONet, with a larger variance for time-dependent responses. Unlike DNN, both FNO and DeepONet were able to simulate time series data without the need for dimensionality reduction techniques. Finally, the present work can help facilitate the AM optimization process by enabling faster execution of simulation tools while still preserving evaluation accuracy.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Chatter detection in simulated machining data: a simple refined approach to vibration data

Vibration monitoring is a critical aspect of assessing the health and performance of machinery and industrial processes. This study explores the application of machine learning techniques, specifically the Random Forest (RF) classification model, to predict and classify chatter—a detrimental self-excited vibration phenomenon—during machining operations. While sophisticated methods have been employed to address chatter, this research investigates the efficacy of a novel approach to an RF model. The study leverages simulated vibration data, bypassing resource-intensive real-world data collection, to develop a versatile chatter detection model applicable across diverse machining configurations. The feature extraction process combines time-series features and Fast Fourier Transform (FFT) data features, streamlining the model while addressing challenges posed by feature selection. By focusing on the RF model’s simplicity and efficiency, this research advances chatter detection techniques, offering a practical tool with improved generalizability, computational efficiency, and ease of interpretation. The study demonstrates that innovation can reside in simplicity, opening avenues for wider applicability and accelerated progress in the machining industry.

42 ENGINEERING↗
DOE OSTI2026

Rerouting reductant flux via protein tethering enhances biohydrogen production in Thermococcus kodakarensis

Microbes that generate copious amounts of hydrogen (H 2 ) via dark fermentation are a promising means to evolve and improve renewable biofuels. Many anaerobic hyperthermophilic archaea, such as the fast-growing, genetically tractable, heterotroph Thermococcus kodakarensis, produce generous quantities of H2 and provide an idealized platform to further optimize naturally high levels of biohydrogen reduction. Precise genetic manipulations and modifications to growth conditions have already resulted in substantial increases to H2 output but additional improvements are desired. An unexamined and potentially valuable route towards increased H 2 production is to tether select electron donor and acceptor proteins together to reroute and maximize the flow of electrons towards H 2 production. Such strategies have shown promise in Bacteria and Eukarya but have not yet been investigated in thermophilic Archaea. Here, we generate and evaluate twelve novel T. kodakarensis strains wherein a proteinaceous electron carrier (a ferredoxin, Fd) is physically tethered to the membrane-bound-hydrogenase (MBH), the sole H 2 producing enzyme, to direct electron flux towards biohydrogen generation. Growth assessments and H 2 output measurements demonstrate that strains encoding protein-fusions evolve up to ~ 40% more H2 per cell than the host strain. Eliminating H 2 consumption and alternative routes of electron sinks in concert with protein tethering further increased H2 output per cell for a maximum increase of ~ 66% over the host strain. Our results demonstrate that rerouting electron flux via protein tethering coupled with the elimination of reductant sinks is a promising means towards improved biohydrogen production in T. kodakarensis. KEY POINTS: Protein tethering between redox proteins can reroute electron flux in vivo. Enforced protein proximity results in ~ 40% increases in H2 production per cell. Protein-tethering provides a generalizable framework to redirect redox metabolism.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Integrated modeling for assessing climate change impacts on water resources and hydropower potential in the Himalayas

Regional hydroclimatic variability and change can affect water resources and hydropower generation. It is essential to assess hydropower potential under current and future climatic conditions to inform the design and operation of hydropower infrastructures. Here, we employ an integrated modeling framework to assess the impact of projected hydroclimatic conditions on water resource systems and hydropower generation. The integrated framework samples climate model outputs under different scenarios to force a hydrologic model and produces streamflow projections. The projected streamflows are inputs for the future hydropower potential assessment. We implement the framework in the central Himalayan river basin. Our results demonstrate substantial spatiotemporal variability in different water balance components (precipitation, evapotranspiration, and water yield) under current and future climatic conditions. For the Himalayan Tila river basin, the annual average energy production is expected to increase under future hydroclimatic conditions (up to 39% in Tila-2 hydropower project, suggested by ensemble mean). Furthermore, this increase in energy is driven mainly by the increased streamflow projections, particularly during the dry season and in the late century. Our results highlight the impacts of hydroclimatic variability in hydropower productions and are of practical use to provide decision-relevant information for designing and operating hydropower infrastructures. The integrated modeling framework presented here is region-specific; however, the approach is reproducible, and the overall insights are generalizable across the Himalayan region.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Integrated energy-water-land nexus planning in the Colorado River Basin (Argentina)

Integrated energy-water-land (EWL) planning promotes synergies and avoids conflicts in ways that sector-specific planning approaches cannot. Many important decisions that influence emerging EWL nexus issues are implemented at regional (e.g., large river basin, electricity grid) and sub-regional (e.g., small river basin, irrigation district) scales. However, actual implementation of integrated planning at these scales has been limited. Simply collecting and visualizing data and interconnections across multiple sectors and sub-regions in a single modeling platform is a unique endeavor in many regions. This study introduces and applies a novel approach to linking together multiple sub-regions in a single platform to characterize and visualize EWL resource use, EWL system linkages within and among sub-regions, and the EWL nexus implications of future policies and investments. This integrated planning methodology is applied in the water-stressed Colorado River Basin in Argentina, which is facing increasing demands for agricultural and fossil fuel commodities. Guided by stakeholders, this study seeks to inform basin planning activities by characterizing and visualizing (1) the basin’s current state of EWL resources, (2) the linkages between sectors within and among basin sub-regions, and (3) the EWL nexus implications of planned future agricultural development activities. Results show that water scarcity, driven in part by human demands that have historically reached 60% of total surface water supply, poses a substantial constraint to economic development in the basin. The Colorado basin has the potential to serve as a testbed for crafting novel and generalizable sub-regional EWL planning approaches capable of informing the EWL planning dialogue globally.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Towards a unified nonlocal, peridynamics framework for the coarse-graining of molecular dynamics data with fractures

Molecular dynamics (MD) has served as a powerful tool for designing materials with reduced reliance on laboratory testing. However, the use of MD directly to treat the deformation and failure of materials at the mesoscale is still largely beyond reach. In this work, we propose a learning framework to extract a peridynamics model as a mesoscale continuum surrogate from MD simulated material fracture data sets. Firstly, we develop a novel coarse-graining method, to automatically handle the material fracture and its corresponding discontinuities in the MD displacement data sets. Inspired by the weighted essentially non-oscillatory (WENO) scheme, the key idea lies at an adaptive procedure to automatically choose the locally smoothest stencil, then reconstruct the coarse-grained material displacement field as the piecewise smooth solutions containing discontinuities. Then, based on the coarse-grained MD data, a two-phase optimization-based learning approach is proposed to infer the optimal peridynamics model with damage criterion. In the first phase, we identify the optimal nonlocal kernel function from the data sets without material damage to capture the material stiffness properties. Then, in the second phase, the material damage criterion is learnt as a smoothed step function from the data with fractures. As a result, a peridynamics surrogate is obtained. As a continuum model, our peridynamics surrogate model can be employed in further prediction tasks with different grid resolutions from training, and hence allows for substantial reductions in computational cost compared with MD. We illustrate the efficacy of the proposed approach with several numerical tests for the dynamic crack propagation problem in a single-layer graphene. Our tests show that the proposed data-driven model is robust and generalizable, in the sense that it is capable of modeling the initialization and growth of fractures under discretization and loading settings that are different from the ones used during training.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Riverine dissolved organic matter transformations increase with watershed area, water residence time, and Damköhler numbers in nested watersheds

Abstract Quantifying the relative influence of factors and processes controlling riverine ecosystem function is essential to predicting future conditions under global change. Dissolved organic matter (DOM) is a fundamental component of riverine ecosystems that fuels microbial food webs, influences nutrient and light availability, and represents a significant carbon flux globally. The heterogeneous nature of DOM molecular composition and its propensity for interaction (i.e., functional diversity) can characterize riverine ecosystem function across spatiotemporal scales. To investigate fundamental drivers of DOM diversity, we collected seasonal water samples from 42 nested locations within five watersheds spanning multiple watershed sizes (~ 5 to 30,000 km 2 ) across the United States. Patterns in DOM molecular richness, aromaticity, relative abundance of N-containing formulas, and putative biochemical transformations derived from high-resolution mass spectrometry were assessed across gradients of explanatory variables associated with watershed characteristics (e.g., watershed area, water residence time, land cover). We found that putative biochemical transformations were more strongly related to explanatory variables across watersheds than common bulk DOM parameters and that watershed area, surface water residence time and derived Damköhler numbers representing DOM reactivity timescales were strong predictors of DOM diversity. The data also indicate that catchment-specific land cover factors can significantly influence DOM diversity in diverging directions. Overall, the results highlight the importance of considering water residence time and land cover when interpreting longitudinal patterns in DOM chemistry and the continued challenge of identifying generalizable drivers that are transferable across watershed and regional scales for application in Earth system models. This work also introduces a Findable Accessible Interoperable Reusable (FAIR) dataset (> 300 samples) to the community for future syntheses.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior

The increasing incidence and severity of wildfires underscores the necessity of accurately predicting their behavior. While high-fidelity models derived from first principles offer physical accuracy, they are too computationally expensive for use in real-time fire response. Low-fidelity models sacrifice some physical accuracy and generalizability via the integration of empirical measurements, but enable real-time simulations for operational use in fire response. Machine learning techniques have demonstrated the ability to bridge these objectives by learning first-principles physics while achieving computational speedups. While deep learning approaches have demonstrated the ability to predict wildfire propagation over large time periods, time-resolved fire-spread predictions are needed for active fire management. Here, in this work, we evaluate the ability of deep learning approaches in accurately modeling the time-resolved dynamics of wildfires. We use an autoregressive process in which a convolutional recurrent deep learning model makes predictions that propagate a wildfire over 15 min increments. We apply the model to four simulated datasets of increasing complexity, containing both field fires with homogeneous fuel distribution as well as real-world topologies sampled from the California region of the United States. We show that even after 100 autoregressive predictions representing more than 24 h of simulated fire spread, the resulting models generate stable and realistic propagation dynamics, achieving a Jaccard score between 0.89 and 0.94 when predicting the resulting fire scar. The inference time of the deep learning models are examined and compared, and directions for future work are discussed.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Machine Learning Moment Closure Models for the Radiative Transfer Equation III: Enforcing Hyperbolicity and Physical Characteristic Speeds

This is the third paper in a series in which we develop machine learning (ML) moment closure models for the radiative transfer equation. In our previous work (Huang et al. in J Comput Phys 453:110941, 2022), we proposed an approach to learn the gradient of the unclosed high order moment, which performs much better than learning the moment itself and the conventional $P_N$ closure. However, while the ML moment closure has better accuracy, it is not able to guarantee hyperbolicity and has issues with long time stability. In our second paper (Huang et al., in: Machine learning moment closure models for the radiative transfer equation II: enforcing global hyperbolicity in gradient based closures, 2021. arXiv:2105.14410), we identified a symmetrizer which leads to conditions that enforce that the gradient based ML closure is symmetrizable hyperbolic and stable over long time. The limitation of this approach is that in practice the highest moment can only be related to four, or fewer, lower moments. In this paper, we propose a new method to enforce the hyperbolicity of the ML closure model. Motivated by the observation that the coefficient matrix of the closure system is a lower Hessenberg matrix, we relate its eigenvalues to the roots of an associated polynomial. Here, we design two new neural network architectures based on this relation. The ML closure model resulting from the first neural network is weakly hyperbolic and guarantees the physical characteristic speeds, i.e., the eigenvalues are bounded by the speed of light. The second model is strictly hyperbolic and does not guarantee the boundedness of the eigenvalues. Several benchmark tests including the Gaussian source problem and the two-material problem show the good accuracy, stability and generalizability of our hyperbolic ML closure model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Haar-Like Wavelets on Hierarchical Trees

Here, discrete wavelet methods, originally formulated in the setting of regularly sampled signals, can be adapted to data defined on a point cloud if some multiresolution structure is imposed on the cloud. A wide variety of hierarchical clustering algorithms can be used for this purpose, and the multiresolution structure obtained can be encoded by a hierarchical tree of subsets of the cloud. Prior work introduced the use of Haar-like bases defined with respect to such trees for approximation and learning tasks on unstructured data. This paper builds on that work in two directions. First, we present an algorithm for constructing Haar-like bases on general discrete hierarchical trees. Second, with an eye towards data compression, we present thresholding techniques for data defined on a point cloud with error controlled in the $L$ $\infty$ norm and in a Hölder-type norm. In a concluding trio of numerical examples, we apply our methods to compress a point cloud dataset, study the tightness of the $L$ $\infty$ error bound, and use thresholding to identify MNIST classifiers with good generalizability.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Emerging Tools to Support DILI Assessment in Clinical Trials with Abnormal Baseline Serum Liver Tests or Pre-existing Liver Diseases

Abstract Based on the late Dr. Hyman Zimmerman’s observation that hepatocellular drug-induced liver injury (DILI) leading to jaundice carries a ≥ 10% fatality risk (coined as Hy’s law by others), evaluation of Drug-Induced Serious Hepatotoxicity (eDISH) continues to play a central role in the assessment of a study drug’s liability for acute hepatocellular DILI. The eDISH identifies drugs in clinical trials with DILI fatality (death or transplant) risk that may be unacceptable in a post-market setting. As a two-dimensional graph that plots peak total bilirubin (TB) versus peak serum aminotransferase levels for each patient during study drug or comparator treatment, eDISH identifies potential cases of acute, modest, and serious hepatocellular DILI for in-depth analysis of liver tests (LT) and clinical course so that the likelihood of causal association with the study drug can be determined. Unfortunately, the generalizable utility of this tool only pertains to trials enrolling patients with normal or near normal (NNN) baseline (BL) serum LTs. The eDISH does not necessarily apply to trials of patients with abnormal baseline (ABN-BL) LTs that often coincide with underlying liver disorders. Because drug development programs being reviewed by the FDA increasingly target liver disorders, we are often challenged to evaluate DILI risk in trials of patients with ABN-BL LTs. Also, the high background prevalence of metabolic dysfunction associated steatotic liver disease (MASLD) means patients with LTs above NNN may need to be enrolled in trials treating non-liver disorders to reflect the target population. Such study populations create challenges for industry and regulators because eDISH may not reliably categorize or identify potential cases of DILI for further analysis, as it so efficiently does in NNN-BL trials. We describe the main functionalities of eDISH in NNN-BL trials to understand what should be emulated by new tools or eDISH modifications. We then discuss non-eDISH–based plots that may be useful in ABN-BL trials.

Amirzadegan, Jasmine↗
DOE OSTI2023

A Siamese CNN + KNN-Based Classification Framework for Non-intrusive Load Monitoring

Through the development of smart grids, programs such as demand side response, have been presented as auxiliary services to the real-time operation of distributed networks. In order to provide consumers information on their energy consumption, so that a modulation in consumption is possible, non-intrusive load monitoring has been introduced as an solution to this pattern recognition problem. Non-intrusive load monitoring enables the modeling of electrical loads connected to the low-voltage system, considering only a single measurement point. Presented state-of-the-art solutions though, consider availability of data as well as representation of all possible classes of the environment. This is of course a most conservative hypothesis, since in real-life applications availability of such data is much difficult, as well as the dynamic behavior of models is implicitly evolving in time. Here, a framework that uses neural Siamese networks with k-nearest neighbor clustering is presented toward non-intrusive load monitoring. Online learning feature is implemented, which relaxes the hypothesis of data requirements as well addresses the evolving nature of load profile. k-nearest clustering allows nonlinear characteristic space modelling. Test results using synthetics and real-life data show that the solution, besides obtaining a good generalizability in the classification, also obtained results with an accuracy of 95.77%.

24 POWER TRANSMISSION AND DISTRIBUTION↗