Search NASA⌕ Search

SEARCH · Search NASA

Results for “data processing steps”

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 343 records · Page 19

Design, Development, and Operation of an Integrated Fluidized Carbon Capture Unit Using Polyethylenimine Sorbents

In this paper, we present the design, development, and operation of a reactor system for CO 2 capture. Modifications were implemented to address differences in sorbent from 180 μm Geldart group B to 115 μm Geldart group A material; operational issues were discovered during experimental trials. The major obstacle in system operation was the ability to maintain a constant circulation of a solid sorbent stemming from this change in sorbent material. The system consisted of four fluid beds, through which a polyamine impregnated sorbent was circulated and adsorption, preheat, regeneration, and cooling processes occurred. Pressure transducers, thermocouples, gas flow meters, and gas composition instrumentation were used to characterize thermal, hydrodynamic, and gas adsorption performance in this integrated unit. A series of shakedown tests were performed and the configuration altered to meet the needs of the sorbent performance and achieve desired target capture efficiencies. Methods were identified, tested, and applied to continuously monitor critical operating parameters including solids circulation rate, adsorbed and desorbed CO 2 , solids inventories, and pressures. The working capacity and CO 2 capture efficiency were used to assess sorbent performance while CO 2 closure was used to define data quality and approach to steady-state. Testing demonstrated >90% capture efficiencies and identified the regenerator to be the process step limiting throughput. Sorbent performance was found to be related to the reactant stoichiometry. Finally, a stochastic model with an exponential dependence on the relative CO 2 /amine concentration was used to describe 90% of the variance in the data.

01 COAL, LIGNITE, AND PEAT↗

Climate Science for a Sustainable Energy Future Atmospheric Radiation Measurement Best Estimate (CSSEFARMBE)

The Climate Science for a Sustainable Energy Future (CSSEF) project is working to improve the representation of the hydrological cycle in global climate models, critical information necessary for decision-makers to respond appropriately to predictions of future climate. In order to accomplish this objective, CSSEF is building testbeds to implement uncertainty quantification (UQ) techniques to objectively calibrate and diagnose climate model parameterizations and predictions with respect to local, process-scale observations. In order to quantify the agreement between models and observations accurately, uncertainty estimates on these observations are needed. The DOE Atmospheric Radiation Measurement (ARM) program takes atmospheric and climate related measurements at three permanent locations worldwide. The ARM VAP called the ARM Best Estimate (ARMBE) [Xie et al., 2010] collects a subset of ARM observations, performs quality control checks, averages them to one hour temporal resolution, and puts them in a standard format for ease of use by climate modelers. ARMBE has been widely used by the climate modeling community as a summary product of many of the ARM observations. However, the ARMBE product does not include uncertainty estimates on the data values. Thus, to meet the objectives of the CSSEF project and enable better use of this data with UQ techniques, we created the CSSEFARMBE data set. Only a subset of the variables contained in ARMBE is included in CSSEFARMBE. Currently only surface meteorological observations are included, though this may be expanded to include other variables in the future. The CSSEFARMBE VAP is produced for all extended facilities at the ARM Southern Great Plains (SGP) site that contain surface meteorological equipment. This extension of the ARMBE data set to multiple facilities at SGP allows for better comparison between model grid boxes and the ARM point observations. In the future, CSSEFARMBE may also be created for other ARM sites. As each site has slightly different instrumentation, this will require additional development to understand the uncertainty characterization associated with instrumentation at those sites. The uncertainty assignment process is implemented into the ARM program’s new Integrated Software Development Environment (ISDE) so that many of the key steps can be used in the future to screen data based on ARM Data Quality Reports (DQRs), propagate uncertainties when transforming data from one time scale into another, and convert names and units into NetCDF Climate and Forecast (CF) standards. These processes are described in more detail in the following sections.

atmospheric↗

Determining the kinetic rate constants of Fe 3 O 4 -to-Fe and FeO-to-Fe reduction by H 2

Steel production using coal accounts for ~ 8% of global carbon emissions. “Green Steel” is a new grand concept proposed recently to make steel from iron ores using renewable derived “Green Hydrogen” to achieve zero carbon emission. The kinetics and rate-limiting steps of iron ore reduction into iron with H 2 as a reducing agent is critically important to the success of this new technology. While reduction of Fe 2 O 3 into Fe by H 2 follows multiple steps, the past research on this topic mainly deals with the overall averaged kinetics, giving little information on the elemental and rate-limiting steps. In this work, we report a kinetic study specifically design to attain kinetic rate constants of one-step reduction of Fe 3 O 4 -to-Fe and FeO-to-Fe. Guided by thermodynamics, we show first how to create in situ the desirable starting oxide phases, i.e., Fe 3 O 4 and FeO, with precisely controlled the ratio of partial pressures of H 2 O and H 2 . We then show time-dependent raw H 2 O content data collected by a mass spectrometer and the processed reduction data to extract kinetic rate constants. We found that the kinetics of the two one-step reduction reactions follows nicely the Johnson-Mehl-Avrami (JMA) phase transformation model. The one-step reduction mechanisms and activation energy are also discussed.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Methodology for Clustering High-Resolution Spatiotemporal Solar Resource Data

In this report, we introduce a methodology to achieve multiple levels of spatial resolution reduction of solar resource data, with minimal impact on data variability, for use in energy systems modeling. The selection of an appropriate clustering algorithm, parameter selection including cluster size, methods of temporal data segmentation, and methods of cluster evaluation are explored in the context of a repeatable process. In describing this process, we illustrate the steps in creating a reduced resolution, but still viable, dataset to support energy systems modeling, e.g. capacity expansion or production cost modeling. This process is demonstrated through the use of a solar resource dataset; however, the methods are applicable to other resource data represented through spatiotemporal grids, including wind data. In addition to energy modeling, the techniques demonstrated in this paper can be used in a novel top-down approach to assess renewable resources within many other contexts that leverage variability in resource data but require reduction in spatial resolution to accommodate modeling or computing constraints.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Monitoring Waste Tanks Using Guided Wave Technology - 18576

There are many challenges associated with the inspections of double-shell storage tanks containing radioactive waste, including limited space for accessibility and maneuverability, environments with high radiation, temperature and toxicity, and unknown physical conditions. Contents of the tank and limited space may prevent access of scanning devices that employ conventional NDE techniques such as ultrasonics, eddy current, or magnetic based methods. Resolving these challenges will become more urgent as the nuclear industry is forced to address the complications of the aging nuclear infrastructure - specifically at tank storage locations on laboratory sites across the DOE complex. A powerful, new approach to inspecting and monitoring the structural integrity of large structures, such as double-shelled tanks, is being developed using ultrasonic guided waves. Acoustic waves that propagate in a plate or other structure where the wavelength is larger than the thickness of the structure are known as ultrasonic guided waves. Ultrasonic guided waves can potentially propagate distances of tens to hundreds of feet in plate-like structures, such as those that comprise the walls and bottom of a storage tank. Guided waves enable the examination of relatively large inspection volumes from the outside surface of the structure. In double-shell tanks, the technology offers promise for examining the floor of the structure or the walls by placing guided wave sensors at accessible locations in the annulus. This guided wave technology has the capability to detect and localize areas of damage or degradation. While guided wave has recently been used in the nuclear and oil and gas industries for inspecting one-dimensional piping systems, current research is developing methods to apply this technology to the two-dimensional surfaces of double-shell storage tanks. Permanently installed sensors are being developed which would remotely collect data that would be analyzed to monitor the structural condition of the tank. Initial tests have been conducted on single plate structures to study guided wave interaction with various shapes and sizes of pertinent simulated damage mechanisms, and the experimental results were compared with hybrid finite-element numerical models. Dispersion curves were calculated to study guided wave modes and their properties in carbon steel plates and to evaluate behaviors at joints between plates. The next steps in the research process include applying the transmitters and sensors to full scale mockups, developing more mature data interpretation, and then demonstrations at an actual site. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Surrogate models for development of unconventional shale reservoirs by an integrated numerical approach of hydraulic fracturing, flow and geomechanics, and machine learning

We develop well-completion surrogate models by taking an integrated workflow of hydraulic fracturing, flow, geomechanics, and machine learning simulation. There are three steps in the proposed workflow. First, history-matching processes are conducted with the field data including pumping and production data for characterization. Second, full-physics simulation is performed with various parameters of the field development (e.g., cluster spacing, clusters per stage, pumping rates and times, amount of proppant, and well spacing) to generate multiple simulation results by changing the parameters of the completion design with well-known hydraulic fracturing, reservoir, geomechanics simulators to calculate fracture geometry, reservoir depressurization, induced stress changes. The workflow is demonstrated over a field in the Southern Midland Basin. Here, we take two completion scenarios: a single well case followed by a multi-well case. Finally, a Long Short-Term Memory (LSTM) machine learning algorithm is employed to create surrogate models that can replicate the full-physics simulation results. Furthermore, results show that the trained models applied in the single well and multi-well cases for a particular geological system can provide good accuracy close to those provided by full-physics simulations. Specifically, the site-specific surrogate models can predict fracture parameters (length, height, and surface area) and cumulative production accurately with computational efficiency, suggesting our proposed workflow can be used as a pragmatic tool for expediting the well completion optimization process.

Geomechanics↗

Modeling the formation of Sedan Crater using the FLAG and HOSS codes

Numerical modeling of explosion crater formation requires accounting for complex physical processes. Numerical validation of explosion cratering is an important step in modeling and requires experimental data for comparison. Models using discrete elements and continuum models have both benefits and drawbacks to their approaches. In this work, we consider both an arbitrary Lagrangian–Eulerian (ALE) hydrocode and a finite discrete element method (FDEM) approach to modeling the formation of the Sedan crater, the largest human-made crater in the United States. The Sedan crater formed from an underground nuclear detonation in the Nevada desert as part of Project Plowshare. Our models show that the continuum approach of the hydrocode matched well compared to early test time prior to the mound rupture and subsequent fireball venting, when most of the alluvium exhibited fluid behavior. Our FDEM approach matched the final crater dimensions well, after material had settled back into the crater, when material strength and solid mechanics play key roles. Our work shows how leveraging the benefits of multiple numerical approaches can lead to better understanding of complex physical problems, especially problems with limited experimental data. By using a continuum approach to early-time hydrodynamics and an FDEM approach to later-time solid mechanics, we can better understand the different physical regimes of explosion crater formation.

36 MATERIALS SCIENCE↗

Multiphase Modeling in a Parallel Plate Fluidized Bed Receiver for Concentrating Solar Power

A novel high temperature particle solar receiver is developed by using a light trapping planar cavity configuration. As particles fall through the cavity, the concentrated solar radiation warms the boundaries of the receiver and in turn heats the particles. Particles flow through the system, forming a packed bed at the lower end, leaving the system from the bottom at a constant flow rate. Air is introduced to the system as the fluidizing medium to improve particle heat transfer and mixing. A laboratory scale cavity receiver is built and a near IR quartz lamp is used to provide flux to the vertical wall of the heat exchanger. The system is modeled using a continuum two-fluid method. The computational model matches the experimental system size and the particle size distribution is assumed monodisperse. A conduction model that accounts for the effects of solid concentration is implemented, and the heat flux boundary condition matches the experimental setup. Radiative heat transfer is estimated using a widely used correlation during the post-processing step to determine an overall heat transfer coefficient. The model is validated against testing data and achieves less than 30% discrepancy and a heat transfer coefficient greater than 1000 W/m2K.

CSP↗

Revisiting Temporal Blocking Stencil Optimizations

Iterative stencils are used widely across the spectrum of High Performance Computing (HPC) applications. Many efforts have been put into optimizing stencil GPU kernels, given the prevalence of GPU-accelerated supercomputers. To improve the data locality, temporal blocking is an optimization that combines a batch of time steps to process them together. Under the observation that GPUs are evolving to resemble CPUs in some aspects, we revisit temporal blocking optimizations for GPUs. We explore how temporal blocking schemes can be adapted to the new features in the recent Nvidia GPUs, including large scratchpad memory, hardware prefetching, and device-wide synchronization. We propose a novel temporal blocking method, EBISU, which champions low device occupancy to drive aggressive deep temporal blocking on large tiles that are executed tile-by-tile. We compare EBISU with state-of-the-art temporal blocking libraries: STENCILGEN and AN5D. We also compare with state-of-the-art stencil auto-tuning tools that are equipped with temporal blocking optimizations: ARTEMIS and DRSTENCIL. Over a wide range of stencil benchmarks, EBISU achieves speedups up to 2.53x and a geometric mean speedup of 1.49x over the best state-of-the-art performance in each stencil benchmark.

Zhang, Lingqi↗

Letter Report: LAW Simulant Development for Cast Stone Screening Test

More than 56 million gallons of radioactive and hazardous waste are stored in 177 underground storage tanks at the U.S. Department of Energy’s (DOE’s) Hanford Site in southeastern Washington State. The Hanford Tank Waste Treatment and Immobilization Plant (WTP) is being constructed to treat the wastes and immobilize them in a glass waste form. The WTP includes a pretreatment facility to separate the wastes into a small volume of high-level waste (HLW) containing most of the radioactivity and a larger volume of low-activity waste (LAW) containing most of the nonradioactive chemicals. The HLW will be converted to glass in the HLW vitrification facility for ultimate disposal at an offsite federal repository. At least a portion (~35%) of the LAW will be converted to glass in the LAW vitrification facility and will be disposed of onsite at the Integrated Disposal Facility (IDF). The pretreatment and HLW vitrification facilities will have the capacity to treat and immobilize the wastes destined for each facility. However, a second facility will be needed for the expected volume of additional LAW requiring immobilization. A cementitious waste form known as Cast Stone is being considered to provide the required additional LAW immobilization capacity. The Cast Stone waste form must be acceptable for disposal in the IDF. The Cast Stone waste form and immobilization process must be tested to demonstrate that the final Cast Stone waste form can comply with waste acceptance criteria for the IDF disposal facility and that the immobilization processes can be controlled to consistently provide an acceptable waste form product. Further, the waste form must be tested to provide the technical basis for understanding the long term performance of the waste form in the IDF disposal environment. These waste form performance data are needed to support risk assessment and performance assessment (PA) analyses of the long-term environmental impact of the waste disposal in the IDF. A testing program was developed in fiscal year (FY) 2012 describing in some detail the work needed to develop and qualify Cast Stone as a waste form for the solidification of Hanford LAW (Westsik et al. 2012). Included within Westsik et al. (2012) is a section on the near-term needs to address Tri-Party Agreement Milestone M-062-40ZZ. The objectives of the testing program to be conducted in FY 2013 and FY 2014 are to: • Determine an acceptable formulation for the LAW Cast Stone waste form. • Evaluate sources of dry materials for preparing the LAW Cast Stone. • Demonstrate the robustness of the Cast Stone waste form for a range of LAW compositions. • Demonstrate the robustness of the formulation for variability in the Cast Stone process. • Provide Cast Stone contaminant release data for PA and risk assessment evaluations. The first step in determining an acceptable formulation for the LAW Cast Stone waste form is to conduct screening tests to examine expected ranges in pretreated LAW composition, waste stream concentrations, dry-materials sources, and mix ratios of waste feed to dry blend. A statistically designed test matrix will be used to evaluate the effects of these key parameters on the properties of the Cast Stone as it is initially prepared and after curing. The second phase of testing will focus on selection of a baseline Cast Stone formulation for LAW and demonstrating that Cast Stone can meet expected waste form requirements for disposal in the IDF. It is expected that this testing will use the results of the screening tests to define a smaller suite of tests to refine the composition of the baseline Cast Stone formulation (e.g. waste concentration, water to dry mix ratio, waste loading).

Russell, Renee L.↗

Adaptive Recovery Model: Designing Systems for Testing Tracing and Vaccination to Support COVID-19 Recovery Planning.

This report documents a new approach to designing disease control policies that allocate scarce testing, contact tracing, and vaccination resources to better control community transmission of COVID19 or similar diseases. The Adaptive Recovery Model (ARM) combines a deterministic compartmental disease model with a stochastic network disease propagation model to enable us to simulate COVID-19 community spread through the lens of two complementary modeling motifs. ARM contact networks are derived from cell-phone location data that have been anonymized and interpreted as individual arrivals to specic public locations. Modeling disease spread over these networks allows us to identify locations within communities conducive to rapid disease spread. ARM applies this model- and data-derived abstractions of community transmission to evaluate the effectiveness of disease control measures including targeted social distancing, contact tracing, testing and vaccination. The architecture of ARM provides a unique capacity to help decision makers understand how best to deploy scarce testing, tracing and vaccination resources to minimize disease-spread potential in a community. This document details the novel mathematical formulations underlying ARM, presents a dynamical stability analysis of the deterministic model components, a sensitivity analysis of control parameters and network structure, and summarizes a process for deriving contact networks from cell-phone location data. An example use case steps through applying ARM to evaluate three targeted social distancing policies using Bernalillo County, New Mexico as an exemplar test locale. This step-by-step analysis demonstrates how ARM can be used to measure the relative performance of competing public health policies. Initial scenario tests of ARM shows that ARMs design focus on resource utilization rather than simple incidence prediction can provide decision makers with additional quantitative guidance for managing ongoing public health emergencies and planning future responses.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Mid-IR UAV-based sensing platform with deep learning to Identify and Quantify Gaseous Emission in Gas Flares

This report details the development and evaluation of a Mid-Infrared (Mid-IR) Unmanned Aerial Vehicle (UAV)-based sensing platform integrated with deep learning algorithms for the identification and quantification of gaseous emissions in gas flares. The project, spearheaded by Omega Optics, Inc., aimed to address environmental monitoring challenges by leveraging advanced photonic technologies and autonomous UAV operations. The research focused on designing, optimizing, and fabricating photonic crystal waveguides and grating couplers to enhance the sensitivity and accuracy of gas detection. A comprehensive drone-based system was developed, featuring a miniaturized sensor, GPS module, and microcontroller communication network for real-time gas concentration monitoring. The system's adaptive sampling algorithm, implemented using the Robot Operating System (ROS), enables autonomous detection and localization of gas emission sources. Preliminary results demonstrate the platform's capability to detect and monitor gas emissions with high precision, cost-effectiveness, and scalability. Future work will expand upon this foundation by introducing 3D wind model-based learning for dynamic environmental conditions and further enhancing the user interface and data processing algorithms to support broader environmental monitoring applications. Overall, this project represents a significant step forward in UAV-based environmental sensing technologies, offering robust solutions for detecting and mitigating the impacts of gaseous emissions on public health and safety.

47 OTHER INSTRUMENTATION↗

Apple Strength Issues

Strength of the apple parts has been noticed to decrease, especially those installed by the new induction heating system since the LEP campaign started. Fig. 1 shows the ultimate tensile strength (UTS), yield strength (YS), and elongation of the installed or installation-simulated apples on various systems. One can clearly see the mean values of UTS and YS of the post-LEP parts decreased by about 8 ksi and 6 ksi respectively from those of the pre-LEP parts. The slight increase in elongation seen in Fig.1 can be understood from the weak inverse relationship between the strength and elongation in metals. Fig.2 shows the weak correlation between the YS and elongation of the parts listed in Fig. 1. Strength data listed in Figure 1 were re-plotted as histograms in Figs. 3 and 4. Figs. 3a and 4a show histograms of all UTS and YS data. Figs. 3b and 4b shows histograms of pre-LEP data and Figs. 3c and 4c of post-LEP data. Data on statistical scatter of tensile strengths have been rarely published by material suppliers. Instead, only the minimum 'guaranteed' strength data are typically presented. An example of strength distribution of aluminum 7075-T6 sheet material, listed in Fig. 5, show that its scatter width of both UTS and YS for a single sheet can be about 6 ksi and for multi-lot scatter can be as large as 11 ksi even though the sheets have been produced through well-controlled manufacturing process. By approximating the histograms shown in Figs. 3 and 4 by a Gaussian or similar type of distribution curves, one can plausibly see the strength reductions in the later or more recent apples. The pre-LEP data in Figs. 3b and 4b show wider scatter than the post-LEP data in Figs. 3c and 4c and seem to follow the binomial distribution of strength indicating that the apples might have been made from two different lots of material, either from two different vendors or from two different melts of perhaps slightly different chemical composition by a single vendor. The post-LEP apples seem to have been from a single batch of material. The pre-LEP apples of the weak strength and the post-LEP apples with even weaker strength could have been made of the same batch of material, and the small strength differential might be due to the difference in the induction heating system. If the pre-LEP apples with the lower strength and the post LEP apples are made from the same batch of material, their combined scatter of strength data would be wider and can be understood as a result of the additional processing steps of stress relief and induction heating as discussed.

36 MATERIALS SCIENCE↗

Strategic Petroleum Reserve equation of state model development : current performance against measured data.

This report documents the progression of crude oil phase behavior modeling within the U.S. Strategic Petroleum Reserve vapor pressure program during the period 2004-2009. Improvements in quality control on phase behavior measurements in 2006 coupled with a growing body of degasification plant operations data have created a solid measurement baseline that has served to inform and significantly improve project understanding on phase behavior of SPR oils. Systematic tuning of the model based on proven practices from the technical literature have shown to reduce model bias and match observed data very well, though this model tuning effort is currently in process at SPR and based on preliminary data. The current report addresses many of the steps that have helped to build a strong baseline of data coupled with sufficient understanding of model features so that calibration is possible.

02 PETROLEUM↗

Analytics for Metabolic Engineering

Realizing the promise of metabolic engineering has been slowed by challenges related to moving beyond proof-of-concept examples to robust and economically viable systems. Key to advancing metabolic engineering beyond trial-and-error research is access to parts with well-defined performance metrics that can be readily applied in vastly different contexts with predictable effects. As the field now stands, research depends greatly on analytical tools that assay target molecules, transcripts, proteins, and metabolites across different hosts and pathways. Screening technologies yield specific information for many thousands of strain variants, while deep omics analysis provides a systems-level view of the cell factory. Efforts focused on a combination of these analyses yield quantitative information of dynamic processes between parts and the host chassis that drive the next engineering steps. Overall, the data generated from these types of assays aid better decision-making at the design and strain construction stages to speed progress in metabolic engineering research.

59 BASIC BIOLOGICAL SCIENCES↗

Magnetic Field Reconstruction for a Realistic Multi-Point, Multi-Scale Spacecraft Observatory

Future in situ space plasma investigations will likely involve spatially distributed observatories comprised of multiple spacecraft, beyond the four and five spacecraft configurations currently in operation. Inferring the magnetic field structure across the observatory, and not simply at the observation points, is a necessary step towards characterizing fundamental plasma processes using these unique multi-point, multi-scale data sets. We propose improvements upon the classic first-order reconstruction method, as well as a second-order method, utilizing magnetometer measurements from a realistic nine-spacecraft observatory. The improved first-order method, which averages over select ensembles of four spacecraft, reconstructs the magnetic field associated with simple current sheets and numerical simulations of turbulence accurately over larger volumes compared to second-order methods or first-order methods using a single regular tetrahedron. Using this averaging method on data sets with fewer than nine measurement points, the volume of accurate reconstruction compared to a known magnetic vector field improves approximately linearly with the number of measurement points.

79 ASTRONOMY AND ASTROPHYSICS↗

Method and system for reducing errors in vehicle weighing systems

A method and system (10, 23) for determining vehicle weight to a precision of <0.1%, uses a plurality of weight sensing elements (23), a computer (10) for reading in weighing data for a vehicle (25) and produces a dataset representing the total weight of a vehicle via programming (40-53) that is executable by the computer (10) for (a) providing a plurality of mode parameters that characterize each oscillatory mode in the data due to movement of the vehicle during weighing, (b) by determining the oscillatory mode at which there is a minimum error in the weighing data; (c) processing the weighing data to remove that dynamical oscillation from the weighing data; and (d) repeating steps (a)-(c) until the error in the set of weighing data is <0.1% in the vehicle weight.

Hively, Lee M↗

Enhancing Unknown Waveform Detection by Learning Intra and Inter-domain Dependencies with Advanced Attention Fusion Mechanisms

Detection of unknown waveforms in mission-critical communications is a crucial area of interest for the Department of Energy (DoE). Traditional methods and recent deep learning-based approaches often assume that the training set includes all possible classes, which is impractical for detecting new waveforms. This limitation gives rise to the problem of open-set recognition (OSR), which involves correctly identifying known classes while detecting and rejecting unknown or unseen classes. To address this limitation, we propose a novel dual-domain complex-valued neural architecture that jointly processes time-domain and frequency-domain signal representations using transformer mechanisms. A transformer model is a deep learning architecture that uses self-attention mechanisms to process and learn relationships in sequential data. Our model employs a cosine similarity loss to extract domain-specific features and incorporates a transformer architecture in the latent space to weigh the importance of different features from the time and frequency domains. The transformer layer includes stacked self-attention and cross-attention modules to learn intra-domain and inter-domain dependencies, creating a more holistic signal representation. An attention-based fusion module intelligently combines the time and frequency-domain features using multi-head attention, enabling the network to learn the optimal feature for each domain in each input signal. Quantitative results demonstrate the impact of these architectural choices on overall performance, showing significant improvement after incorporating self and cross-attention modules and using complex attention fusion over simple weighted fusion. Our ongoing work will focus on addressing the limitations of threshold-based OSR methods by developing a novel generative framework that integrates a conditional diffusion probabilistic model (DPM). DPM is a generative framework that learns to synthesize complex data by reversing a gradual noising process using a neural network trained to denoise step-by-step. Our goal is to leverage the inherent strengths of DPMs for identifying unknown signals more robustly. One primary advantage of using a DPM is its ability to provide a more reliable anomaly score based on the model's reconstruction error, rather than relying solely on classifier confidence. Additionally, the iterative denoising process of DPMs makes this approach naturally resilient to low Signal-to-Noise Ratio (SNR) conditions, where traditional methods often fail. By implementing this generative framework, we aim to enhance the model's capability to accurately detect unknown waveforms and maintain performance in challenging environments.

99 - GENERAL AND MISCELLANEOUS↗