Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Convolution”

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 1,513 records · Page 84
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

CMOS-Based Single-Cycle in-Memory XOR/XNOR

Big data applications are on the rise, and so is the number of data centers. The ever-increasing massive data pool needs to be periodically backed up in a secure environment. Moreover, a massive amount of securely backed-up data is required for training binary convolutional neural networks for image classification. XOR and XNOR operations are essential for large-scale data copy verification, encryption, and classification algorithms. The disproportionate speed of existing compute and memory units makes the von Neumann architecture inefficient to perform these Boolean operations. Compute-in-memory (CiM) has proved to be an optimum approach for such bulk computations. The existing CiM-based XOR/XNOR techniques either require multiple cycles for computing or add to the complexity of the fabrication process. Here, we propose a CMOS-based hardware topology for single-cycle in-memory XOR/XNOR operations. Our design provides at least 2× improvement in the latency compared with other existing CMOS-compatible solutions. We verify the proposed system through circuit/system-level simulations and evaluate its robustness using a 5000-point Monte Carlo variation analysis. This all-CMOS design paves the way for practical implementation of CiM XOR/XNOR at scaled technology nodes.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2026

Modeling Multi-View Impedance-Based Cross-Geometry SOH Estimator for Li-ion Batteries

Abstract: Accurately estimating battery’s State of Health (SOH) remains challenging when models must generalize across cell designs and operating conditions. Most Electrochemical Impedance Spectroscopy (EIS)-based approaches either (i) hand-engineer a few Nyquist-plot features for shallow models—fast but does not generalize across geometries—or (ii) learn directly from Nyquist plots with deep networks, which removes manual feature extraction, yet still limited to a single plot type. As a result, cross-geometry robustness and deployability on constrained Internet of Things (IoT) devices remain open problems. We propose a compact Convolutional Neural Network (CNN) (∼ 10k parameters) that takes multi-representation EIS inputs—Nyquist (real/imaginary) and phase–magnitude (|Z|/ϕ) stacked as four channels, so the model can learn complementary degradation signatures while remaining small enough for fast inference. We build a dataset from cyclic aging of two geometries (LG INR18650MJ1 cylindrical cells and LIR2032 coin cells), acquire EIS every ten cycles from 10 kHz to 10 mHz (10 points/decade), and evaluate with leave-one-cell-out testing strategy. We further study fusion vs. single-representation inputs and assess feasibility for on-device deployment (e.g., NVIDIA Jetson device). The results show that training on multiple EIS representations improves SOH estimation accuracy and cross-geometry generalization compared to single-representation models, which uses only Nyquist or phase–magnitude plots. This design targets accurate, generalizable SOH prediction without manual feature engineering while enabling practical real-time use.

Bakr, Ahmed [The University of Alabama (UA)]↗
DOE OSTI2021

Efficient Contingency Analysis in Power Systems via Network Trigger Nodes

Modeling failure dynamics within a power system is a complex and challenging process due to multiple inter-dependencies and convoluted inter-domain relationships. Subject matter experts (SMEs) are interested in understanding these failure dynamics for reducing the impact from future disasters (i.e., losses or failures of power system components, such as transmission lines). Contingency analysis (CA) tools enable such ’what-if’ scenario analyses to evaluate the impacts on the power system. Analyzing all possible contingencies among N system components can be computationally expensive. An important step for performing CA is identifying a set of k ‘trigger’ components, which when failed initially can significantly impact the overall system by causing multiple failures. Currently SMEs focus on identifying these trigger components by running expensive simulations on all possible subsets, which quickly becomes infeasible. Hence finding a relevant set of trigger components (contingencies) rapidly to enable efficient and useful CA is crucial.In a collaboration between computer scientists and power system experts, we propose an efficient method for performing CA by exploiting network inter-dependencies in power system components. First, we construct a network with multiple electric grid infrastructure components and dependencies as connections among them. We reformulate the problem of finding a set of trigger components as a problem of identifying critical nodes in the network, which can cascade power failures through connected nodes and cause significant damage to the network. To guide the practical CA tools, we develop a network-based model with a probabilistic edge-weights setup using intricate domain rules. Then we conduct an empirical study on real power system data in the US for both regional and national levels. Firstly, we use power system datasets for the US to create a national-scale domain-driven model. Secondly, we demonstrate that network-based model outperforms the outputs from a real CA tool and show on average 25 × improved selection of contingencies, thereby showcasing practical benefits to the power experts.

Tabassum, Anika↗
DOE OSTI2023

A Deep Learning Pipeline for Optimizing Large-scale Phase Field Simulations

Phase field (PF) simulations are computationally expensive but remain a key analysis tool to understand the complex mechanisms of additive manufacturing (AM) processes. Each PF simulation-aided analysis requires thousands of node hours on leadership-class supercomputers. One of the main goals of these analyses is the study of microstructure evolution during the build process which begins with the onset of nucleation. Nucleation occurs under certain thermomechanical conditions which are not known a priori and many PF simulations are required to identify ranges of input thermo-mechanical parameters that can result in the onset of nucleation. Since many of the simulations do not result in nucleation, an analysis campaign often ends up wasting tremendous amounts of precious computing resources executing nucleation-absent simulations. The goal of this work is to design and train deep learning models to inform a PF simulation about the likelihood of the occurrence of nucleation in a future simulation time-step based on the state summary over a finite number of past time-steps of a running simulation. If the prediction determines that the running simulation is unlikely to reach nucleation in the allotted time, then its execution is stopped immediately ultimately resulting in vast reduction in wasted computations when accrued over all the PF simulations typically performed in a single or multiple analysis campaign(s). The paper presents the performance of a machine learning pipeline that uses a convolutional neural network (CNN) model to learn an embedding which is then used with a self-attention network to build a multi-task deep learning model to predict the likelihood of nucleation. The model also predicts the input parameters used in a simulation. Performance is compared with a baseline pipeline that uses an off-the-shelf LeNet-5 model to learn the initial embedding. Despite their smaller size, performance results indicate significant improvement in accuracy of the proposed models compared to the larger baseline models.

Kannan, Ramakrishnan {ramki}↗
DOE OSTI2023

A General Spatiotemporal Imputation Framework for Missing Sensor Data

Many applications from precision agriculture, environmental monitoring and transportation networks rely on data collected across space and time over a large geographic area. Missing data poses a significant challenge for any data-driven inference and control tasks. Data imputation or the estimation of missing data can help fill these gaps by utilizing inherent spatial relationships and temporal patterns. A variety of spatiotemporal imputation models have been developed to address missing data in spatiotemporal datasets. However, these classical methods rely on the assumption that the underlying data follows a smooth trend and fail to provide accurate estimates when there is a large number of missing points in the data. Even though there are machine learning driven tensor completion approaches such as convolutional neural network based tensor completion (CoSTCo) that capture the non-linear relationships in the dataset, the transductive nature makes the algorithm less scalable. Thus, existing approaches for estimating the missing information do not effectively capture all dimensions of the spatiotemporal data structure, resulting in erroneous predictions and poor performance. The main contributions of this paper are: (1) We propose a novel inductive framework (G-LSTM) for missing data imputation that integrates a graph neural network with LSTMs to effectively capture both spatial and temporal dependencies. (2) Experimental results on a traffic dataset demonstrate that the proposed GNN integrated with an LSTM framework achieves improved imputation and maintains steady performance even when there are extreme missing conditions in comparison with the state-of-the-art imputation framework (i.e, CoSTCo). (3) The simulation results on a traffic network show up to 69% reduction in mean absolute error and 61% reduction in root mean square error when compared to CoSTCo.

Tharzeen, Aabila↗
DOE OSTI2023

Artificial Intelligence Designer of Materials and Processes for Advanced Power Generation

In this presentation, ‘deep-freeze’ graphs, ‘convoluted filtering’ networks, ‘mirror-image’ graphs, and adversarial ensemble methods are utilized to support inversion modeling for optimization of the complex compositions and complex processes in design of high-performing alloys, with their properties tailored to the energy application specifications.

Romanov, Vyacheslav↗
DOE OSTI2025

Dynamical Sketching for Enhanced Communication Efficiency in Federated Learning

Federated learning (FL) has revolutionized distributed machine learning by enabling collaborative model training without sharing local data. However, communication efficiency and privacy guarantees remain significant challenges. This paper introduces a dynamic sketching mechanism in FL, optimizing the trade-off between communication efficiency and model accuracy. By dynamically selecting the sketch matrix size, our approach adapts to the evolving characteristics of the data and the model, ensuring optimal performance across diverse scenarios. We leverage Bayesian optimization to systematically tune the sketch parameters, achieving an effective balance between resource efficiency and model performance. Experimental results on the MNIST dataset using a convolutional neural network (CNN) architecture validate the proposed method's efficiency and scalability. Our dynamic sketching approach significantly outperforms fixed-size sketching techniques, achieving higher compression ratios (up to 62x) and providing better privacy guarantees while maintaining high model accuracy. These findings highlight the robustness and versatility of our approach and make it a valuable solution for privacy-preserving, communication-efficient federated learning.

Afrose, Sharmin [ORNL]↗
DOE OSTI2026

Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training

Distributed training increases the number of batches processed per iteration either by scaling-out (adding more nodes) or scaling-up (increasing the batch-size). However, the largest configuration does not necessarily yield the best performance. Horizontal scaling introduces additional communication overhead, while vertical scaling is constrained by computation cost and device memory limits. Thus, simply increasing the batch-size leads to diminishing returns: training time and cost decrease initially but eventually plateaus, creating a knee-point in the time/cost vs. batch-size pareto curve. The optimal batch-size therefore depends on the underlying model, data and available compute resources. Large batches also suffer from worse model quality due to the well-known “generalization gap”. In this paper, we present Tula, an online service that automatically optimizes time, cost, and convergence quality for large-batch training of convolutional models. It combines parallel-systems modeling with statistical performance prediction to identify the optimal batchsize. Tula predicts training time and cost within 7.5−14% error across multiple models, and achieves up to 20× overall speedup and improves test accuracy by ≈9% on average over standard large-batch training on various vision tasks, thus successfully mitigating the generalization gap and accelerating training at the same time.

Tyagi, Sahil [ORNL] (ORCID:0009000783144745)↗
DOE OSTI2021

Exploring Autoencoder-based Error-bounded Compression for Scientific Data

Error-bounded lossy compression is becoming an indispensable technique for the success of today's scientific projects with vast volumes of data produced during the simulations or instrument data acquisitions. Not only can it significantly reduce data size, but it also can control the compression errors based on user-specified error bounds. Autoencoder (AE) models have been widely used in image compression, but few AE-based compression approaches support error-bounding features, which are highly required by scientific applications. To address this issue, we explore using convolutional autoencoders to improve error-bounded lossy compression for scientific data, with the following three key contributions. (1) We provide an in-depth investigation of the characteristics of various autoencoder models and develop an error-bounded autoencoder-based framework in terms of the SZ model. (2) We optimize the compression quality for main stages in our designed AE-based error-bounded compression framework, fine-tuning the block sizes and latent sizes and also optimizing the compression efficiency of latent vectors. (3) We evaluate our proposed solution using five real-world scientific datasets and comparing them with six other related works. Experiments show that our solution exhibits a very competitive compression quality from among all the compressors in our tests. In absolute terms, it can obtain a much better compression quality (100%similar to 800% improvement in compression ratio with the same data distortion) compared with SZ2.1 and ZFP in cases with a high compression ratio.

Liu, Jinyang↗
DOE OSTI2021

Mitigating Catastrophic Forgetting in Deep Learning in a Streaming Setting Using Historical Summary

Recent advancements in scientific equipment and the adaptation of electronics and the Internet of Things (IoT) in our everyday lives resulted in large and complex data production at a high rate. Making meaningful and timely knowledge discovery at a modest cost from this big data is difficult for computing power and storage limitations. Training deep learning models incrementally in a streaming setting can help us with overcoming these limitations. However, in a well-known phenomenon named catastrophic forgetting, incrementally trained models increasingly perform poorly on the past data. To mitigate catastrophic forgetting in training in a streaming setting, we propose constructing a historical summary over time and use the summary with newly arrived data during incremental training. We propose various data summarization techniques such as random sampling, micro clustering, coreset computation, and Auto Encoders to counteract catastrophic forgetting. We built a pipeline for incremental training with a historical summary for training deep learning models for streaming data. We demonstrate the effectiveness of historical summary in mitigating catastrophic forgetting using three case studies involving three different deep learning applications: an Artificial Neural Network (ANN) for classification task on MNIST dataset, a language model (RNN-LM) on the WikiText2 dataset, and a Convolutional Neural Network (CNN), ResNet50 to classify the ImageNet dataset. Through the training of the models, we observe that catastrophic forgetting is evident in ANN and CNN but not in an RNN. For the first task, our method recovers up to 47.9% lost accuracy due to catastrophic forgetting. For the third task, the historical summary recovers classification accuracy by up to 25%. For the second task, though there is not proof of catastrophic forgetting, the training performance (PPL) improves by up to 26% with historical summary.

Dash, Sajal↗
DOE OSTI2020

Data-driven Cyberattack Detection for Photovoltaic (PV) Systems through Analyzing Micro-PMU Data

With increasing exposure to software-based sensing and control, Photovoltaic (PV) systems are facing higher risks of cyber attacks. Here, to ensure the system stability and minimize potential economic losses, it is imperative to monitor operating states and detect attacks at the early stage. To meet this demand, Micro-Phasor Measurement Units (μPMU) are increasingly popular in monitoring distribution networks. However, due to the relatively low sampling rate, μPMU has not yet been used to detect and classify cyber-attacks in power electronics enabled smart grid. To our knowledge, this is one of the first attempts to use μPMU to detect cyber attacks that degrade the performance of power electronics systems. We propose to apply data-driven methods on micro-PMU data to implement attack detection. We have evaluated data-driven methods, including decision tree (DT), K-nearest neighbor (KNN), support vector machine (SVM), artificial neural network (ANN), long short-term memory (LSTM) and convolutional neural network (CNN). The proposed CNN model achieves the required performances with the highest 99.23% accuracy and 0.9963 F 1 score.

14 SOLAR ENERGY↗
DOE OSTI2021

A Survey: Handling Irregularities in Neural Network Acceleration with FPGAs

In the last decade, Artificial Intelligence (AI) through Deep Neural Networks (DNNs) has penetrated virtually every aspect of science, technology, and business. Many types of DNNs have been and continue to be developed, including Convolutional Neural Networks (CNNs), Recurrent Neural Net- works (RNNs), and Graph Neural Networks (GNNs). The overall problem for all of these Neural Networks (NNs) is that their target applications generally pose stringent constraints on latency and throughput, while also having strict accuracy requirements. There have been many previous efforts in creating hardware to accelerate NNs. The problem designers face is that optimal NN models typically have significant irregularities, making them hardware-unfriendly. In this paper, we first define the problems in NN acceleration by characterizing common irregularities in NN processing into 4 types; then we summarize the existing works that handle the four types of irregularities efficiently using hardware, especially FPGAs; finally, we provide a new vision of next-generation FPGA-based NN acceleration: that the emerging heterogeneity in the next-generation FPGAs is the key to achieving higher performance.

Geng, Tong↗
DOE OSTI2022

Neuromorphic Accelerator for Deep Spiking Neural Networks with NVM Crossbar Arrays

In this paper, we present a scalable digital hardware accelerator based on non-volatile memory arrays capable of realizing deep convolutional spiking neural networks (SNNs). Our design studies are conducted using a compact model for spin-transfer torque random access memory (STT-RAM) devices. Large networks are realized by tiling multiple cores which communicate by transmitting spike packets via an on-chip routing network. Compared to an equivalent SRAM based core design, we show that the STT-RAM based design achieves nearly 15X higher GSOPS (Synaptic Operations per Second) per Watt per mm 2 making it a promising platform for realizing systems with significant area and power limitations.

Kulkarni, Shruti↗
DOE OSTI2023

Deep Learning Based Workflow for Accelerated Industrial X-Ray Computed Tomography

X-ray computed tomography (XCT) is an important tool for high-resolution non-destructive characterization of additively-manufactured metal components. XCT reconstructions of metal components may have beam hardening artifacts such as cupping and streaking which makes reliable detection of flaws and defects challenging. Furthermore, traditional workflows based on using analytic reconstruction algorithms require a large number of projections for accurate characterization - leading to longer measurement times and hindering the adoption of XCT for in-line inspections. In this paper, we introduce a new workflow based on the use of two neural networks to obtain high-quality accelerated reconstructions from sparse-view XCT scans of single material metal parts. The first network, implemented using fully-connected layers, helps reduce the impact of BH in the projection data without the need of any calibration or knowledge of the component material. The second network, a convolutional neural network, maps a low-quality analytic 3D reconstruction to a high-quality reconstruction. Using experimental data, we demonstrate that our method robustly generalizes across several alloys, and for a range of sparsity levels without any need for retraining the networks thereby enabling accurate and fast industrial XCT inspections.

Rahman, Obaid↗
DOE OSTI2023

Hyperparameter Optimization and Feature Inclusion in Graph Neural Networks for Spiking Implementation

Graph convolutional networks leverage both graph structures and features on nodes and edges for improved learning performance in comparison with classical machine learning approaches. Spiking neuromorphic computers natively implement network-like computation and have been shown to be successful at implementing graph learning without features. Incorporating graph features brings the challenge of efficient feature representation and balancing the contribution of topology and features in learning. In this work, we present our design of a simulated network of spiking neurons to perform semi-supervised learning on graph data using both the graph structure and the node features. We explore various design choices, present preliminary results, and discuss the opportunities for using neuromorphic computers for this task in the future.

Cong, Guojing↗
DOE OSTI2023

Attention-Augmented Parametric Kernel Graph Neural Network (APKGNN) for Node Classification

We present a new graph neural network, the Attention-based Parametric-Kernel augmented Graph Neural Network (APKGNN), developed for node classification tasks. Despite extensive work on modeling multi-faceted relationships between connected nodes of a graph, the effect of attention on edge features mapped to relationships has not yet been analyzed through learning representation. This study derives such an attention vector by first calculating node features corresponding to endpoints of an edge and then aggregating these with extracted local intrinsic patches of a given graph to generate augmented local patch vectors. This process uses a parametric kernel based on Gaussian mixture models (GMMs) to embed local neighborhoods of the graph in local patches. The patch vectors then convolve with the above node features to produce an updated node representation. We show that this new learning representation (APKGNN) achieves higher node classification accuracy on tasks - both standard benchmarks (Cora, PubMed, Citeseer) and new experimental short text corpora where nodes correspond to text documents and words. This implementation of the GNN convolution layer outperforms state-of-the-art (SOTA) algorithms, achieving higher training, validation, and test accuracy by a significant margin on three standard benchmark data sets under both SOTA experimental settings and those for new testbeds.

Bose, Avishek↗
DOE OSTI2024

Neuro-Spark: A Submicrosecond Spiking Neural Networks Architecture for In-Sensor Filtering

Neuro-Spark, which is a new neuromorphic architecture with a field-programmable gate array (FPGA) implementation for ultrafast spiking neural network (SNN) inference at the edge, facilitates smart-pixel in-sensor filtering for high-energy physics experiments at the Large Hadron Collider (LHC). Utilizing the evolutionary optimization for neuromorphic systems (EONS) training method, we generate compact SNN models with 91% signal efficiency, akin to convolutional neural networks but with half the parameters. However, deploying near the detector poses a challenge because the SNN must handle a sustained input data rate exceeding 1013 GB/s. To overcome this, we propose a novel hardware architecture that uses high-level synthesis to construct a tuned architecture for the EONS-trained SNN. In addition to the analysis and validation with an AMD Xilinx Artix-A7 FPGA, our solution consumes only ç24% of FPGA LUT and flipflops. We also introduce an innovative quantization method that reduces FPGA resource utilization by ç15% without compromising accuracy. Our FPGA implementation achieves computing latency of ç10 ns for smart-pixel application inference on an edge FPGA.

Miniskar, Narasinga Rao↗