Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “event classification”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Jefferson Laboratory C100 Superconducting Radio-Frequency Cavity Fault Data, 2020

The dataset was created to train machine learning models for the task of identifying the (1) cavity and (2) fault type from C100-type cryomodules at the Thomas Jefferson National Accelerator Facility (Jefferson Lab), thereby replacing the time-consuming efforts of a subject matter expert. Superconducting radio-frequency (SRF) cavity trips represent a significant source of accelerator downtime. Real-time – rather than post-mortem – identification of the offending cavity and classification of the fault type would give control room operators valuable feedback for corrective action planning. The anticipated benefit is increased beam-on-target time for users and provides performance metrics that can be used to improve future cavity designs. A series of 17 RF signals are recorded for each of the 8 cavities in a C100 cryomodule every time a cavity trips. These time-series signals are written to file using a specially designed data acquisition system. The dataset represents fault events recorded during Continuous Electron Beam Accelerator Facility (CEBAF) beam operations between January 18, 2019 and March 9, 2020. The following filtering steps were applied to collected data; (1) only 4 of the 17 signals per cavity are retained (GMES, GASK, CRFP, DETA2) (2) only events with data from each of the eight cavities in the cryomodule are kept, (3) only events that were sampled at 5 kHz were kept, (4) events from cryomodule 0L04 were neglected, (5) events occurring between February 4, 3PM and February 5, 12PM were neglected. As a result of preprocessing, the dataset is comprised of 2,375 unique events. The full dataset is comprised of three files: features.csv, cavity_labels.csv, fault_labels.csv. Each instance in faults.csv includes a timestamp (“date_time”), a label for the cryomodule which experienced the trip (“zone_label”), and 192 features (“feature_1”, “feature_2”... “feature_192”). The features correspond to 6 autoregressive features for each of 4 signals per cavity for each of the 8 cavities (6 × 4 signals/cavity × 8 cavities/cryomodule = 192). To deal with the large variation of signal amplitudes, time-series standardization via the z-score (standard score) function was applied prior to computing the features. For each instance, there is an associated label for the (1) cavity which faulted first (cavity_labels.csv) and (2) the type of fault that caused the trip (fault_labels.csv). The cavity identification can take values of [0, 1, 2, 3, 4, 5, 6, 7, 8] and the fault type can take values of [‘Microphonics’, ‘Quench_100ms’, ‘Controls_Fault’, ‘E_Quench’, ‘Quench_3ms’, ‘Single_Cav_Turn_Off’ , ‘Heat_Riser_Choke’, ‘Multi_Cav_Turn_Off’].

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

The information content of jet quenching and machine learning assisted observable design

Jets produced in high-energy heavy-ion collisions are modified compared to those in proton-proton collisions due to their interaction with the deconfined, strongly-coupled quark-gluon plasma (QGP). In this work, we employ machine learning techniques to identify important features that distinguish jets produced in heavy-ion collisions from jets produced in proton-proton collisions. We formulate the problem using binary classification and focus on leveraging machine learning in ways that inform theoretical calculations of jet modification: (i) we quantify the information content in terms of Infrared Collinear (IRC)-safety and in terms of hard vs. soft emissions, (ii) we identify optimally discriminating observables that are in principle calculable in perturbative QCD, and (iii) we assess the information loss due to the heavy-ion underlying event and background subtraction algorithms. We illustrate our methodology using Monte Carlo event generators, where we find that important information about jet quenching is contained not only in hard splittings but also in soft emissions and IRC-unsafe physics inside the jet. This information appears to be significantly reduced by the presence of the underlying event. We discuss the implications of this for the prospect of using jet quenching to extract properties of the QGP. Since the training labels are exactly known, this methodology can be used directly on experimental data without reliance on modeling. We outline a proposal for how such an experimental analysis can be carried out, and how it can guide future measurements.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Decoding the EEG patterns induced by sequential finger movement for brain-computer interfaces

Objective In recent years, motor imagery-based brain–computer interfaces (MI-BCIs) have developed rapidly due to their great potential in neurological rehabilitation. However, the controllable instruction set limits its application in daily life. To extend the instruction set, we proposed a novel movement-intention encoding paradigm based on sequential finger movement. Approach Ten subjects participated in the offline experiment. During the experiment, they were required to press a key sequentially [i.e., Left→Left (LL), Right→Right (RR), Left→Right (LR), and Right→Left (RL)] using the left or right index finger at about 1 s intervals under an auditory prompt of 1 Hz. The movement-related cortical potential (MRCP) and event-related desynchronization (ERD) features were used to investigate the electroencephalography (EEG) variation induced by the sequential finger movement tasks. Twelve subjects participated in an online experiment to verify the feasibility of the proposed paradigm. Main results As a result, both the MRCP and ERD features showed the specific temporal–spatial EEG patterns of different sequential finger movement tasks. For the offline experiment, the average classification accuracy of the four tasks was 71.69%, with the highest accuracy of 79.26%. For the online experiment, the average accuracies were 83.33% and 82.71% for LL-versus-RR and LR-versus-RL, respectively. Significance This paper demonstrated the feasibility of the proposed sequential finger movement paradigm through offline and online experiments. This study would be helpful for optimizing the encoding method of motor-related EEG information and providing a promising approach to extending the instruction set of the movement intention-based BCIs.

Liu, Chang↗
DOE OSTI2020

Neutrino interaction classification with a convolutional neural network in the DUNE far detector

The Deep Underground Neutrino Experiment is a next-generation neutrino oscillation experiment that aims to measure $CP$-violation in the neutrino sector as part of a wider physics program. A deep learning approach based on a convolutional neural network has been developed to provide highly efficient and pure selections of electron neutrino and muon neutrino charged-current interactions. The electron neutrino (antineutrino) selection efficiency peaks at 90% (94%) and exceeds 85% (90%) for reconstructed neutrino energies between 2-5 GeV. The muon neutrino (antineutrino) event selection is found to have a maximum efficiency of 96% (97%) and exceeds 90% (95%) efficiency for reconstructed neutrino energies above 2 GeV. When considering all electron neutrino and antineutrino interactions as signal, a selection purity of 90% is achieved. These event selections are critical to maximize the sensitivity of the experiment to $CP$-violating effects.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Sub-millisecond keyhole pore detection in laser powder bed fusion using sound and light sensors and machine learning

Laser powder bed fusion is a mainstream additive manufacturing technology widely used to manufacture complex parts in prominent sectors, including aerospace, biomedical, and automotive industries. However, during the printing process, the presence of an unstable vapor depression can lead to a type of defect called keyhole porosity, which is detrimental to the part quality. In this study, we developed an effective approach to locally detect the generation of keyhole pores during the printing process by leveraging machine learning and a suite of optical and acoustic sensors. Simultaneous synchrotron x-ray imaging allows the direct visualization of pore generation events inside the sample, offering high-fidelity ground truth. A neural network model adopting SqueezeNet architecture using single-sensor data was developed to evaluate the fidelity of each sensor for capturing keyhole pore generation events. Our comparative study shows that the near infrared images gave the highest prediction accuracy, followed by 100 kHz and 20 kHz microphones, and the photodiode sensitive to processing laser wavelength had the lowest accuracy. Using a single sensor, over 90% prediction accuracy can be achieved with a temporal resolution as short as 0.1 ms. A data fusion scheme was also developed with features extracted using SqueezeNet neural network architecture and classification using different machine learning algorithms. Our work demonstrates the correlation between the characteristic optical and acoustic emissions and the keyhole oscillation behavior, and thereby provides strong physics support for the machine learning approach.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Using Host Galaxy Photometric Redshifts to Improve Cosmological Constraints with Type Ia Supernovae in the LSST Era

We perform a rigorous cosmology analysis on simulated Type Ia supernovae (SNe Ia) and evaluate the improvement from including photometric host galaxy redshifts compared to using only the "z spec " subset with spectroscopic redshifts from the host or SN. We use the Deep Drilling Fields (~50 deg 2 ) from the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC) in combination with a low-z sample based on Data Challenge2. The analysis includes light-curve fitting to standardize the SN brightness, a high-statistics simulation to obtain a bias-corrected Hubble diagram, a statistical+systematics covariance matrix including calibration and photo-z uncertainties, and cosmology fitting with a prior from the cosmic microwave background. Compared to using the z spec subset, including events with SN+host photo-z results in (i) more precise distances for z > 0.5, (ii) a Hubble diagram that extends 0.3 further in redshift, and (iii) a 50% increase in the Dark Energy Task Force figure of merit (FoM) based on the w 0 w a CDM model. Analyzing 25 simulated data samples, the average bias on w 0 and w a is consistent with zero. The host photo-z systematic of 0.01 reduces FoM by only 2% because (i) most z < 0.5 events are in the z spec subset, (ii) the combined SN+host photo-z has ×2 smaller bias, and (iii) the anticorrelation between fitted redshift and color self-corrects distance errors. To prepare for analyzing real data, the next SN Ia cosmology analysis with photo-zs should include non–SN Ia contamination and host galaxy misassociations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Deep Learning Based Superconducting Radio-Frequency Cavity Fault Classification at Jefferson Laboratory

This work investigates the efficacy of deep learning (DL) for classifying C100 superconducting radio-frequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. CEBAF is a large, high-power continuous wave recirculating linac that utilizes 418 SRF cavities to accelerate electrons up to 12 GeV. Recent upgrades to CEBAF include installation of 11 new cryomodules (88 cavities) equipped with a low-level RF system that records RF time-series data from each cavity at the onset of an RF failure. Typically, subject matter experts (SME) analyze this data to determine the fault type and identify the cavity of origin. This information is subsequently utilized to identify failure trends and to implement corrective measures on the offending cavity. Manual inspection of large-scale, time-series data, generated by frequent system failures is tedious and time consuming, and thereby motivates the use of machine learning (ML) to automate the task. This study extends work on a previously developed system based on traditional ML methods (Tennant and Carpenter and Powers and Shabalina Solopova and Vidyaratne and Iftekharuddin, Phys. Rev. Accel. Beams, 2020, 23, 114601), and investigates the effectiveness of deep learning approaches. The transition to a DL model is driven by the goal of developing a system with sufficiently fast inference that it could be used to predict a fault event and take actionable information before the onset (on the order of a few hundred milliseconds). Because features are learned, rather than explicitly computed, DL offers a potential advantage over traditional ML. Specifically, two seminal DL architecture types are explored: deep recurrent neural networks (RNN) and deep convolutional neural networks (CNN). We provide a detailed analysis on the performance of individual models using an RF waveform dataset built from past operational runs of CEBAF. In particular, the performance of RNN models incorporating long short-term memory (LSTM) are analyzed along with the CNN performance. Furthermore, comparing these DL models with a state-of-the-art fault ML model shows that DL architectures obtain similar performance for cavity identification, do not perform quite as well for fault classification, but provide an advantage in inference speed.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

SPC-70791 Rev 0 MARVEL Inert Gas Subsystem, Secondary Coolant Management Subsystem, and Secondary Coolant Cover Gas Subsystem Tubing and Valve Specification

This specification covers the requirements and details for the selection, testing, cleaning, marking, shipping, inspection and installation (including welding) of the Inert Gas Subsystem, Secondary Coolant Management Subsystem, and Secondary Cover Gas Management Subsystem from the Valve Panel up to the classification division, the patch panel of the upper confinement. Including NaK, argon, eutectic gallium indium tin (eGaInSn), and helium fill tubing, valves, and hangers. These systems consist of the necessary straight lengths, elbows, reducers, fittings, tube connections, instrument taps, and valves called for by applicable drawings. All components shall be procured as ASME Section III Class 2 unless otherwise modified hereinafter. Pressure relief valves have been sized to prevent overpressure in the event there is full regulator flow. This is documented in ECAR-7365.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗
DOE OSTI2020

Adaptable Monitoring Package Development and Deployment: Lessons Learned for Integrated Instrumentation at Marine Energy Sites

Integrated instrumentation packages are an attractive option for environmental and ecological monitoring at marine energy sites, as they can support a range of sensors in a form factor compact enough for the operational constraints posed by energetic waves and currents. Here we present details of the architecture and performance for one such system—the Adaptable Monitoring Package—which supports active acoustic, passive acoustic, and optical sensing to quantify the physical environment and animal presence at marine energy sites. we describe cabled and autonomous deployments and contrast the relatively limited system capabilities in an autonomous operating mode with more expansive capabilities, including real-time data processing, afforded by shore power or in situ power harvesting from waves. Across these deployments, we describe sensor performance, outcomes for biological target classification algorithms using data from multibeam sonars and optical cameras, and the effectiveness of measures to limit biofouling and corrosion. On the basis of these experiences, we discuss the demonstrated requirements for integrated instrumentation, possible operational concepts for monitoring the environmental and ecological effects of marine energy converters using such systems, and the engineering trade-offs inherent in their development. Overall, we find that integrated instrumentation can provide powerful capabilities for observing rare events, managing the volume of data collected, and mitigating potential bias to marine animal behavior. These capabilities may be as relevant to the broader oceanographic community as they are to the emerging marine energy sector.

16 TIDAL AND WAVE POWER↗
DOE OSTI2020

Feature identification or classification using task-specific metadata

Innovations in the identification or classification of features in a data set are described, such as a data set representing measurements taken by a scientific instrument. For example, a task-specific processing component, such as a video encoder, is used to generate task-specific metadata. When the data set includes video frames, metadata can include information regarding motion of image elements between frames, or other differences between frames. A feature of the data set, such as an event, can be identified or classified based on the metadata. For example, an event can be identified when metadata for one or more elements of the data set exceed one or more threshold values. When the feature is identified or classified, an output, such as a display or notification, can be generated. Although the metadata may be useable to generate a task-specific output, such as compressed video data, the identifying or classifying is not used solely in production of, or the creation of an association with, the task-specific output.

Teuton, Jeremy R.↗
DOE OSTI2022

Avoiding thermal runaway in lithium-ion batteries using ultrasound detection of early failure mechanisms

Thermal runaway leading to catastrophic failure has slowed the adoption of lithium-ion batteries, highlighting the need for early warning systems. In this work, ultrasound is used to detect physical changes in 0.950 Ah Li-ion battery cells by inducing conditions associated with thermal runaway. Ultrasound signal features are extracted as the batteries are cycled under baseline conditions and subsequently subjected to constant current and voltage overcharges. Two conditions identifying failure are defined: a warning to detect the start of overcharge and an emergency stop (E-stop), to immediately take the battery out of service. Using changes in ultrasound signal features, consistent warning and stopping classifications are applied to all failure experiments. On average, a warning notification was issued after 15% of the overcharge time and an E-stop was triggered after 35% of total overcharge duration before failure. Further testing suggests that it is possible to avoid thermal runaway by reacting to intermediate, warning notifications prior to an immediate E-stop. In other words, not only can detection derived by ultrasound identify battery failure before a catastrophic event, but can also provide early, actionable warnings so that overcharges can be detected and corrected quickly enough so the battery does not need to be decommissioned.

25 ENERGY STORAGE↗
DOE OSTI2022

Classification and Fusion of Two Disparate Data Streams and Nuclear Dissolutions Application

We consider two streams of data or measurements with disparate qualities and time resolutions that need to be classified. The first stream consists of higher quality data at a coarser time resolution, and the other consists of lower quality data at a finer time resolution. We present a fuser-switch method that fuses the set of classifiers of each stream separately and switches between them. We show that this method provides classification decisions at a finer time resolution with superior detection and false alarm probabilities compared to individual classifiers, under the statistical independence and time resolution ratio conditions. When classifiers are trained using machine learning methods, we show that this superior performance is guaranteed with a confidence probability specified by the classifiers' generalization equations. We use these results to provide analytical foundations for previous practical results that achieved significant performance improvements in classifying Pu/Np target dissolution events at a radiochemical processing facility.

Rao, Nageswara↗
DOE OSTI2021

Training Spiking Neural Networks with Synaptic Plasticity under Integer Representation

Neuromorphic computing is emerging as a promising Beyond Moore computing paradigm that employs event-triggered computation and non-von Neumann hardware. Spike Timing Dependent Plasticity (STDP) is a well-known bio-inspired learning rule that relies on activities of locally connected neurons to adjust the weights of their respective synapses. In this work, we analyze a basic STDP rule and its sensitivity on the different hyperparameters for training spiking neural networks (SNNs) with supervision, customized for a neuromorphic hardware implementation with integer weights. We compare the classification performance on four UCI datasets (iris, wine, breast cancer and digits) that depict varying levels of complexity. We perform a search for optimal set of hyperparameters using both grid search and Bayesian optimization. Through the use of Bayesian optimization, we show the general trends in hyperparameter sensitivity in SNN classification problem. With the best sets of hyperparameters, we achieve accuracies comparable to some of the best performing SNNs on these four datasets. With a highly optimized supervised STDP rule we show that these accuracies can be achieved with just 20 epochs of training.

Kulkarni, Shruti↗
DOE OSTI2022

Dictionary Learning with Accumulator Neurons

The Locally Competitive Algorithm (LCA) uses local competition between non-spiking leaky integrator neurons to infer sparse representations, allowing for potentially real-time execution on massively parallel neuromorphic architectures such as Intel's Loihi processor. Here, we focus on the problem of inferring sparse representations from streaming video using dictionaries of spatiotemporal features optimized in an unsupervised manner for sparse reconstruction. Non-spiking LCA has previously been used to achieve unsupervised learning of spatiotemporal dictionaries composed of convolutional kernels from raw, unlabeled video. We demonstrate how unsupervised dictionary learning with spiking LCA (\hbox{S-LCA}) can be efficiently implemented using accumulator neurons, which combine a conventional leaky-integrate-and-fire (\hbox{LIF}) spike generator with an additional state variable that is used to minimize the difference between the integrated input and the spiking output. We demonstrate dictionary learning across a wide range of dynamical regimes, from graded to intermittent spiking, for inferring sparse representations of both static images drawn from the CIFAR database as well as video frames captured from a DVS camera. On a classification task that requires identification of the suite from a deck of cards being rapidly flipped through as viewed by a DVS camera, we find essentially no degradation in performance as the LCA model used to infer sparse spatiotemporal representations migrates from graded to spiking. We conclude that accumulator neurons are likely to provide a powerful enabling component of future neuromorphic hardware for implementing online unsupervised learning of spatiotemporal dictionaries optimized for sparse reconstruction of streaming video from event based DVS cameras.

artificial intelligence↗
DOE OSTI2020

How Low Can You Go? Using Synthetic 3D Imagery to Drastically Reduce Real-World Training Data for Object Detection

Deep convolutional neural networks (DCNNs) currently provide state-of-the-art performance on image classification and object detection tasks, and there are many global security mission areas where such models could be extremely useful. Crucially, the success of these models is driven in large part by the widespread availability of high-quality open source data sets such as Image Net, Common Objects in Context (COCO), and KITTI, which contain millions of images with thousands of unique labels. However, global security relevant objects-of-interest can be difficult to obtain: relevant events are low frequency and high consequence; the content of relevant images is sensitive; and adversaries and proliferators seek to obscure their activities. For these cases where exemplar data is hard to come-by, even fine-tuning an existing model with available data can be effectively impossible. Recent work demonstrated that models can be trained using a combination of real-world and synthetic images generated from 3D representations; that such models can exceed the performance of models trained using real-world data alone; and that the generated images need not be perfectly realistic (Tremblay, et al., 2018). However, this approach still required hundreds to thousands of real-world images for training and fine tuning, which for sparse, global security-relevant datasets can be an unrealistic hurdle. In this research, we validate the performance and behavior of DCNN models as we drive the number of real-world images used for training object detection tasks down to a minimal set. We perform multiple experiments to identify the best approach to train DCNNs from an extremely small set of real-world images. In doing so, we: Develop state-of-the-art, parameterized 3D models based on real-world images and sample from their parameters to increase the variance in synthetic image training data; Use machine learning explainability techniques to highlight and correct through targeted training the biases that result from training using completely synthetic images; and Validate our results by comparing the performance of the models trained on synthetic data to one another, and to a control model created by fine-tuning an existing ImageNet-trained model with a limited number (hundreds) of real-world images.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Big Data Analytics for Long-Term Meteorological Observations at Hanford Site

A growing number of physical objects with embedded sensors with typically high volume and frequently updated data sets has accentuated the need to develop methodologies to extract useful information from big data for supporting decision making. This study applies a suite of data analytics and core principles of data science to characterize near real-time meteorological data with a focus on extreme weather events. To highlight the applicability of this work and make it more accessible from a risk management perspective, a foundation for a software platform with an intuitive Graphical User Interface (GUI) was developed to access and analyze data from a decommissioned nuclear production complex operated by the U.S. Department of Energy (DOE, Richland, USA). Exploratory data analysis (EDA), involving classical non-parametric statistics, and machine learning (ML) techniques, were used to develop statistical summaries and learn characteristic features of key weather patterns and signatures. The new approach and GUI provide key insights into using big data and ML to assist site operation related to safety management strategies for extreme weather events. Specifically, this work offers a practical guide to analyzing long-term meteorological data and highlights the integration of ML and classical statistics to applied risk and decision science.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

A contextual sensor system for non-intrusive machine status and energy monitoring

Event-driven contexts in manufacturing occur pervasively as a result of interactions among involved entities such as machines, workers, materials, and environment. One of the primary tasks in smart manufacturing is to derive a context-aware system conveniently incorporating worker knowledge for generating timely actionable intelligence for workers on factory floor and supervisors to respond. In this paper, we propose to design a human-and-machine interaction recognition framework by using a causality concept to collect contextual data for classifications of normal and abnormal machine operations. The causes and effects are between workers and machines for this initial research. To apply the causality to recognize worker interactions, initially a reliable way to identify the states of machines is necessary. The proposed contextual sensor system, consisting of a power meter for measuring machine operation conditions, a visual camera for capturing worker and machine interactions via a finite state machine model, and an algorithm for determining power signatures of individual components via energy disaggregation is implemented on semiconductor fabrication machines (manual or PLC controlled) each with multiple components. The experiment results demonstrate its context extraction capability such as components states and their corresponding energy usage in real time as well as its ability to identify anomalous operation conditions.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

Smart sensor for online situational awareness in power grids

Waveforms in power grids typically reveal a certain pattern with specific features and peculiarities driven by the system operating conditions, internal and external uncertainties, etc. This prompts an observation of different types of waveforms at the measurement points (substations). An innovative next-generation smart sensor technology includes a measurement unit embedded with sophisticated analytics for power grid online surveillance and situational awareness. The smart sensor brings additional levels of smartness into the existing phasor measurement units (PMUs) and intelligent electronic devices (IEDs). It unlocks the full potential of advanced signal processing and machine learning for online power grid monitoring in a distributed paradigm. Within the smart sensor are several interconnected units for signal acquisition, feature extraction, machine learning-based event detection, and a suite of multiple measurement algorithms where the best-fit algorithm is selected in real-time based on the detected operating condition. Embedding such analytics within the sensors and closer to where the data is generated, the distributed intelligence mechanism mitigates the potential risks to communication failures and latencies, as well as malicious cyber threats, which would otherwise compromise the trustworthiness of the end-use applications in distant control centers. The smart sensor achieves a promising classification accuracy on multiple classes of prevailing conditions in the power grid and accordingly improves the measurement quality across the power grid.

Dehghanian, Payman↗