Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data provenance”

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 829 records · Page 46

Aftershock Identification Using a Paired Neural Network Applied to Constructed Data

This report is intended to detail the findings of our investigation of the applicability of machine learning to the task of aftershock identification. The ability to automatically identify nuisance aftershock events to reduce analyst workload when searching for events of interest is an important step in improving nuclear monitoring capabilities and while waveform cross - correlation methods have proven successful, they have limitations (e.g., difficulties with spike artifacts, multiple aftershocks in the same window) that machine learning may be able to overcome. Here we apply a Paired Neural Network (PNN) to a dataset consisting of real, high quality signals added to real seismic noises in order to work with controlled, labeled data and establish a baseline of the PNN's capability to identify aftershocks. We compare to waveform cross - correlation and find that the PNN performs well, outperforming waveform cross - correlation when classifying similar waveform pairs, i.e., aftershocks.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

The Microwave-Heated Bumpy Torus: A Concept for Fusion Energy

In the last 3 decades, giant steps in technology and simulations capability have been made for the benefit of all magnetic fusion concepts. This is especially true for virtually a one-of-a-kind device, a microwave-driven bumpy-torus magnetic-fusion-energy system. In the 1980s, the prototype experiment was technology limited, and it was judged based on unrealistic expectations from an incomplete understanding of the machine performance. For those experiments, the machine did not achieve the theoretical stability threshold to demonstrate good plasma confinement. This paper examines the premise that the experimental platform was underpowered, which prevented acceptance of its value for fusion. In this paper, the experimental plasma scaling data with power are reviewed. If, with the advancements of technology and simulations capability of the last 30 years, stable operation can be proven, a much improved device competitive with tokamak and stellarator performance may be possible. The advantages of this concept include steady-state operation, gentle shut down, modular construction for fabrication and maintenance, and the natural diversion of impurities.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

The effect of different annealing temperatures on tin and cadmium telluride phases obtained by a modified chemical route

Graphical abstract: Display Omitted Highlights: ► Synthesis of cadmium and tin telluride. ► Chemical route to obtain pure crystalline cadmium and tin telluride. ► Effect of the annealing temperature on the crystalline phases. ► Removal of tin oxide as side product through thermal treatment. -- Abstract: In this work tin and cadmium telluride were prepared by a modification of a chemical route reported in the literature to obtain metallacycles formed by oxidative addition of tin-tellurium bonds to platinum (II). Through this procedure it was possible to obtain tin and cadmium telluride. X-ray diffraction and X-ray photoelectron spectroscopy were used to identify the crystalline phases obtained as well as the presence of side products. In the case of tin telluride it was identified potassium chloride, metallic tellurium and tin oxide as contaminants. The tin oxidation states were also monitored by {sup 119}Sn Mössbauer spectroscopy. The annealing in hydrogen atmosphere was chosen as a strategy to reduce the tin oxide and promote its reaction with the excess of tellurium present in the medium. The evolution of this tin oxide phase was studied through the annealing of the sample at different temperatures. Cadmium telluride was obtained with high degree of purity (98.5% relative weight fraction) according to the Rietveld refinement of X-ray diffraction data. The modified procedure showed to be very effective to obtain amorphous tin and cadmium telluride and the annealing at 450 °C has proven to be useful to reduce the amount of oxide produced as side product.

36 MATERIALS SCIENCE↗

Unsymmetric Pentacene- and Pentacenequinone-Fused Porphyrins: Understanding the Effect of Cross- and Linear-Conjugation

Unsymmetric pentacenequinone-fused (cross-conjugated) and pentacene-fused (linear-conjugated) porphyrins were designed and synthesized. The cross-conjugated (AM 1 –AM 3 ) and linear-conjugated (AM 5 –AM 7 ) porphyrins displayed strikingly different sets of optical and electronic properties, both of which are unusual and nontypical of porphyrins. MCD, DFT, and TDDFT calculations suggest that multiple charge transfer states exist in both π-conjugated systems, which contributes to the complex absorption and MCD spectra of these molecular systems. The general Gouterman’s four-orbital model used to explain porphyrin spectroscopy led to contradicting theoretical and experimental data, and is thus not applicable for these molecular systems. The “2 + 4” and “3 + 3” active spaces have been deduced and have proven effective to interpret the absorption and MCD spectra of the pentacenequinone-fused (cross-conjugated) and pentacene-fused (linear-conjugated) porphyrins, respectively. Spectroelectrochemistry of AM 5 –AM 7 revealed broad and intense IR absorptions in the range of 1500–2500 nm, illustrating the exceptional ability of these pentacene-fused systems to accommodate positive charges. A pronounced metal effect was observed for pentacene-fused porphyrins. While pentacene-fused Ni(II) porphyrin (AM 6 ) demonstrated an abnormal ability to stabilize pentacene with a half-life of >28.3 days, the half-life of the free base and Zn(II) counterparts were normal, similar to those of pentacene analogues. This work provides important and useful information on guiding new material designs.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Theory of structural phase transition in MgTi{sub 2}O{sub 4}

A theory of phase transition in MgTi{sub 2}O{sub 4} is proposed based on a study of the order-parameter symmetry, thermodynamics, and mechanisms of formation of the atomic and orbital structure of the low-symmetry MgTi{sub 2}O{sub 4} phase. The critical order parameter (which induces a phase transition) is determined. It is shown that the calculated MgTi{sub 2}O{sub 4} tetragonal structure is a result of displacements of magnesium, titanium, and oxygen atoms; ordering of oxygen atoms; and the participation of d{sub xy}, d{sub xz}, and d{sub yz} orbitals. The contribution of noncritical representations to ion displacements is proven to be insignificant. The existence of various metal clusters in the tetragonal phase has been established by calculation in correspondence with experimental data. It is shown (within the Landau theory of phase transitions) that phase states can be changed as a result of both first- and second-order phase transitions: the high-symmetry phase borders two low-symmetry phases by second-order transition lines, while the border between low-symmetry phases is a first-order transition line.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Generative AI for Power Grid Operations

Generative artificial intelligence (AI) has captured into the mainstream, demonstrating capabilities that once belonged solely to the realm of human cognition. From defeating world champions in complex games to generating human-quality text and images, Generative AI has proven its potential to revolutionize countless industries. The electric power grid is no exception. Generative AI's ability to process vast amounts of data rapidly, assist decision support and identify patterns could significantly enhance power grid operations. For example, Generative AI could improve state estimation where measurements are not available or integrate renewable energy sources more efficiently with probabilistic forecasting. The key contributions of this whitepaper are outlined below: (1) Comprehensive overview of Generative AI's applications in power grid operations: It highlights the opportunities in areas such as forecasting, state estimation, and demonstrating the potential for enhancing efficiency, reliability, and resilience. (2) Expanding Generative AI's impact through synergies with emerging technologies: The paper introduce NREL developed eGridGPT and explores how AI orchestration, multi-agent systems, and Digital Twins can collaborate to optimize grid operations, addressing the complexities of a decarbonized and electrified future. (3) In-depth analysis of challenges in implementing Generative AI: This includes considerations like data availability and quality, model validation, certification, and ethical concerns, ensuring responsible AI deployment. (4) Emphasizing human-AI collaboration: The whitepaper underscores the importance of trustworthy, transparency, and explainability in AI systems to promote seamless interaction between human operators and AI, ultimately improving decision-making. (5) Exploring future research and development: It identifies critical areas for further advancement to fully realize Generative AI's potential in power grid operations. This whitepaper serves as a valuable resource for researchers, practitioners, and policymakers looking to harness Generative AI for a more reliable, stable, and cost-effective power grid.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Solar concentrator panel and gore testing in the JPL 25-foot space simulator

The optical imaging characteristics of parabolic solar concentrator panels (or gores) have been measured using the optical beam of the JPL 25-foot space simulator. The simulator optical beam has been characterized, and the virtual source position and size have been determined. These data were used to define the optical test geometry. The point source image size and focal length have been determined for several panels. A flux distribution of a typical solar concentrator has been estimated from these data. Aperture photographs of the panels were used to determine the magnitude and characteristics of the reflecting surface errors. This measurement technique has proven to be highly successful at determining the optical characteristics of solar concentrator panels.

Dennison, E. W.↗

Accomplishments at NASA Langley Research Center in rotorcraft aerodynamics technology

In recent years, the development of aerodynamic technology for rotorcraft has continued successfully at NASA LaRC. Though the NASA Langley Research Center is not the lead NASA center in this area, the activity was continued due to facilities and individual capabilities which are recognized as contributing to helicopter research needs of industry and government. Noteworthy accomplishments which contribute to advancing the state of rotorcraft technology in the areas of rotor design, airfoil research, rotor aerodynamics, and rotor/fuselage interaction aerodynamics are described. Rotor designs were defined for current helicopters and evaluated in wind tunnel testing. These designs have incorporated advanced airfoils defined analytically and also proven in wind tunnel tests. A laser velocimetry system has become a productive tool for experimental definition of rotor inflow/wake and is providing data for rotorcraft aerodynamic code validation.

Wilson, John C.↗

ERBE and CERES broadband scanning radiometers

Broadband scanning radiometers have been used extensively on earth-orbiting satellites to measure the Earth's outgoing radiation. The resulting estimates of longwave and shortwave fluxes have played an important role in helping to understand the Earth's radiant energy balance or budget. The Clouds and the Earth Radiant Energy System (CERES) experiment is expected to include instruments with three broadband scanning radiometers. The design of the CERES instrument will draw heavily from the flight-proven Earth Radiation Budget Experiment (ERBE) scanner instrument technology and will benefit from the several years of ERBE experience in mission operations and data processing. The discussion starts with a description of the scientific objectives of ERBE and CERES. The design and operational characteristics of the ERBE and CERES instrument are compared and the two ground-based data processing systems are compared. Finally, aspects of the CERES data processing which might be performed in near real-time aboard a spacecraft platform are discussed, and the types of algorithms and input data requirements for the onboard processing system are identified.

Weaver, William L.↗

Mid-Latitude Atmospheric Variability Between 20-60 KM from Rocketsonde Measurements

The information obtained from deployment of instrumented meteorological rockets provides middle atmospheric data in a region that is difficult to measure by other means. In the last two decades, in-situ measurements of the middle atmosphere have become less frequent and only originate from a handful of locations. However, the value of these measurements continues to be proven through the validation of remote sensing techniques, support of other payloads sampling the region, and as importantly, the continued study of the rocket datasets with the details and trends that they hold. Wallops Island (37.8 N, 75.5 W) has one of the longest meteorological rocket data records available with relatively few system changes. Two particular periods from this record are studied: (1) January/February and (2) July/August, 1977. Both data sets consist of Super-Loki meteorological rockets with a Datasonde and Starute payload, which yield temperature and wind profiles. The January/February set consists of almost daily launches with days with multiple launches interspersed through January. In the July/August set, rockets were launched for thirty consecutive days at nearly the same time daily from Wallops Island. This campaign was immediately followed by sets of multiple launches with up to six launches per day separated by hours and in some cases minutes. The unique nature of the data allows a detailed examination of the atmosphere's short-term variability. These results are compared to the current views of middle atmospheric dynamics and turbulence from altitudes in the range of 20-60 km.

Schauer, A. G.↗

EAQUATE: An International Experiment for Hyper-Spectral Atmospheric Sounding Validation

The international experiment called EAQUATE (European AQUA Thermodynamic Experiment) was held in September 2004 in Italy and the United Kingdom to demonstrate certain ground-based and airborne systems useful for validating hyperspectral satellite sounding observations. A range of flights over land and marine surfaces were conducted to coincide with overpasses of the AIRS instrument on the EOS Aqua platform. Direct radiance evaluation of AIRS using NAST-I and SHIS has shown excellent agreement. Comparisons of level 2 retrievals of temperature and water vapor from AIRS and NAST-I validated against high quality lidar and drop sonde data show that the 1K/1km and 10%/1km requirements for temperature and water vapor (respectively) are generally being met. The EAQUATE campaign has proven the need for synergistic measurements from a range of observing systems for satellite cal/val and has paved the way for future cal/val activities in support of IASI on the European Metop platform and CrIS on the US NPP/NPOESS platform.

Taylor, J. P.↗

Radiological Survey of Contaminated Installations of Research Reactor before Dismantling in High Dose Conditions with Complex for Remote Measurements of Radioactivity - 12069

Decontamination and decommissioning of the research reactors MR (Testing Reactor) and RFT (Reactor of Physics and Technology) has recently been initiated in the National Research Center (NRC) 'Kurchatov institute', Moscow. These research reactors have a long history and many installations - nine loop facilities for experiments with different kinds of fuel. When decommissioning nuclear facilities it is necessary to measure the distribution of radioactive contamination in the rooms and at the equipment at high levels of background radiation. At 'Kurchatov Institute' some special remote control measuring systems were developed and they are applied during dismantling of the reactors MR and RFT. For a survey of high-level objects a radiometric system mounted on the robotic Brokk vehicle is used. This system has two (4π and collimated) dose meters and a high resolution video camera. Maximum measured dose rate for this system is ∼8.5 Sv/h. To determine the composition of contaminants, a portable spectrometric system is used. It is a remotely controlled, collimated detector for scanning the distribution of radioactive contamination. To obtain a detailed distribution of contamination a remote-controlled gamma camera is applied. For work at highly contaminated premises with non-uniform background radiation, another camera is equipped with rotating coded mask (coded aperture imaging). As a result, a new system of instruments for remote radioactivity measurements with wide range of sensitivity and angular resolution was developed. The experience and results of measurements in different areas of the reactor and at its loop installations, with emphasis on the radioactive survey of highly-contaminated samples, are presented. These activities are conducted under the Federal Program for Nuclear and Radiation Safety of Russia. Adaptation of complex remote measurements of radioactivity and survey of contaminated installations of research reactor before dismantling in high dose conditions has proven successful. The radioactivity measuring devices for operation at high, non-uniform dose background were tested in the field and a new data of measurement of contamination distribution in the premises and installations were obtained. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Complete Structural Model of Escherichia coli RNA Polymerase from a Hybrid Approach

The Escherichia coli transcription system is the best characterized from a biochemical and genetic point of view and has served as a model system. Nevertheless, a molecular understanding of the details of E. coli transcription and its regulation, and therefore its full exploitation as a model system, has been hampered by the absence of high-resolution structural information on E. coli RNA polymerase (RNAP). We use a combination of approaches, including high-resolution X-ray crystallography, ab initio structural prediction, homology modeling, and single-particle cryo-electron microscopy, to generate complete atomic models of E. coli core RNAP and an E. coli RNAP ternary elongation complex. The detailed and comprehensive structural descriptions can be used to help interpret previous biochemical and genetic data in a new light and provide a structural framework for designing experiments to understand the function of the E. coli lineage-specific insertions and their role in the E. coli transcription program. Transcription, or the synthesis of RNA from DNA, is one of the most important processes in the cell. The central enzyme of transcription is the DNA-dependent RNA polymerase (RNAP), a large, macromolecular assembly consisting of at least five subunits. Historically, much of our fundamental information on the process of transcription has come from genetic and biochemical studies of RNAP from the model bacterium Escherichia coli. More recently, major breakthroughs in our understanding of the mechanism of action of RNAP have come from high resolution crystal structures of various bacterial, archaebacterial, and eukaryotic enzymes. However, all of our high-resolution bacterial RNAP structures are of enzymes from the thermophiles Thermus aquaticus or T. thermophilus, organisms with poorly characterized transcription systems. It has thus far proven impossible to obtain a high-resolution structure of E. coli RNAP, which has made it difficult to relate the large collection of genetic and biochemical data on RNAP function directly to the available structural information. Here, we used a combination of approaches - high-resolution X-ray crystallography of E. coli RNAP fragments, ab initio structure prediction, homology modeling, and single-particle cryo-electron microscopy - to generate complete atomic models of E. coli RNAP. Our detailed and comprehensive structural models provide the heretofore missing structural framework for understanding the function of the highly characterized E. coli RNAP.

59 BASIC BIOLOGICAL SCIENCES↗

Ocean topography experiment (TOPEX) radar altimeter

A spaceflight qualified Radar Altimeter capable of achieving the TOPEX Mission measurement precision requirement of 2-centimeters, is provided and its performance (Engineering Assessment) will be evaluated after launch and continuously during its 3-year mission operational period. Information will be provided to JPL about the calibration of the TOPEX Radar Altimeter. The specifications for the required data processing algorithms which will be necessary to convert the Radar Altimeter mission telemetry data into the geophysical data will also be provided. The stringent 2 cm precision requirement for ocean topography determination from space necessitated examining existing Radar Altimeter designs for their applicability towards TOPEX. As a result, a system configuration evolved using some flight proven designs in conjunction with needed improvements which include: (1) a second frequency or channel to remove the range delay or apparent height bias caused by the electron content of the ionosphere; (2) higher transmit pulse repetition frequencies for correlation benefits at higher sea states to maintain precision; and (3) a faster microprocessor to accommodate two channels of altimetry data. Additionally, examination of past altimeter programs associated data processing algorithms was accomplished to establish the TOPEX-class Radar Altimeter data processing algorithms, and the necessary direction was outlined to begin to generate these for the TOPEX Mission.

Rossi, L. C.↗

Modeling the Formation and Eruption of Coronal Structures by Linking Data-Driven Magnetofrictional and MHD Simulations for AR 12673

Context .The data-driven and time-dependent modeling of coronal magnetic fields is crucial for understanding solar eruptions. These efforts are complicated by the challenges of finding a balance between physical realism and computing efficiency. One possible technique is to couple two modeling approaches. Aims . Our aim here is to showcase our progress in using time-dependent magnetofrictional model (TMFM) results as input to dynamical magnetohydrodynamic (MHD) simulations. However, due to the different evolution processes in these two models, using TMFM snapshots in an MHD simulation is nontrivial. We address these issues, both physically and numerically, discuss the incompatibility of the TMFM output to serve as the initial condition in MHD simulations, and show our methods of mitigating this. The evolution of the flux systems and the cause of the eruption are investigated. Methods . TMFM is a prevalent approach that has proven to be a very useful tool in the study of the formation of unstable structures in the solar corona. In particular, it is capable of incorporating observational data as initial and boundary conditions and requires shorter computational time compared to MHD simulations. To leverage the efficiency of data-driven TMFM and also to simulate eruptive events in the MHD framework, one can apply TMFM up to a certain time before the expected eruption(s) and then proceed with the simulation in the full or ideal MHD regime in order to more accurately capture the eruption process. Results . We show the results of a benchmark test case with a linked TMFM and MHD simulation to study the evolution of NOAA active region 12673. A rise of a twisted flux bundle through the MHD simulation domain is observed, but we find that the rate of the rise and the altitude reached depends on the time of the TMFM snapshot that was used to initialize the MHD simulation and the helicity injected into the system. The analysis suggested that torus instability and slip-running reconnection could play an important role in the eruption. Conclusions . The results show that the linkage of TMFM and zero-β MHD models can be successfully used to model the eruptive coronal magnetic fields.

F. Daei↗

The health care and life sciences community profile for dataset descriptions

Access to consistent, high-quality metadata is critical to finding, understanding, and reusing scientific data. However, while there are many relevant vocabularies for the annotation of a dataset, none sufficiently captures all the necessary metadata. This prevents uniform indexing and querying of dataset repositories. Towards providing a practical guide for producing a high quality description of biomedical datasets, the W3C Semantic Web for Health Care and the Life Sciences Interest Group (HCLSIG) identified Resource Description Framework (RDF) vocabularies that could be used to specify common metadata elements and their value sets. The resulting guideline covers elements of description, identification, attribution, versioning, provenance, and content summarization. This guideline reuses existing vocabularies, and is intended to meet key functional requirements including indexing, discovery, exchange, query, and retrieval of datasets, thereby enabling the publication of FAIR data. The resulting metadata profile is generic and could be used by other domains with an interest in providing machine readable descriptions of versioned datasets.

Science & Technology - Other Topics↗

NASA’s Moon Trek Portal: New Capabilities Supporting Mission Planning and Engagement

Introduction: NASA’s Moon Trek (https://trek.nasa.gov/moon/) is one of a growing number of interactive, browser-based, online portals for planetary data visualization and analysis produced by NASA’s Solar System Treks Project (SSTP). Moon Trek continues to be enhanced with new data and new capabilities enabling it to facilitate the planning and conducting of upcoming lunar missions by NASA, its commercial partners, and its international partners, as well as advancing its role as a valuable outreach tool. A Comprehensive Online Web Portal: Developed at NASA’s Jet Propulsion Laboratory (JPL) and managed as a project of NASA’s Solar System Exploration Research Virtual Institute (SSERVI) at NASA Ames Research Center, Moon Trek is a browser-based web portal. The portal provides easy-to-use tools for browsing, data layering, data product blending, and feature search among thousands of data products covering topography, mineralogy, elemental abundance, geology, and much more. Visualizations are provided in var-ious map projections, interactive 3D viewing, and in virtual reality. Using an in-house stereo workflow, SSTP is able to produce new NAC-based high-resolution mosaics and DEMs. Diverse Applications for Lunar Exploration: Baseline analytic tools available to all users include dis-tance measurement, elevation profiling, sun angle calculation, and 3D print file generation. More advanced account-level tools allow users to perform more computationally intensive analyses. These include ray-traced lighting analysis for user-specified areas over user-specified time/date ranges and time intervals, electro-static surface potential analysis, subsetting of large data products, slope analysis, and Lunar Laser Ranging geometry calculation. Artificial intelligence (AI) and ma-chine learning (ML) based tools have been implemented for crater detection and hazard analysis, boulder detection and hazard analysis, and rockfall detection. New Tools Facilitating Exploration: Additional, new tools have recently been added and others are in development, offering even greater functionality in con-ducting analyses of potential landing sites and areas of surface operations. The new Line-of-Sight tool facilitates communications planning between locations on the lunar surface, between any given site on the lunar surface and a specified ground station on the Earth, and between a site on the lunar surface and a relay asset in lunar orbit, all taking into account local lunar topography. The new Data Plotter tool provides both tabular and graphical representations of pixel values along a user specified path for a growing number of data products. The new NAC Finder tool will identify and pro-vide access to NAC images that intersect a user-defined path or bounded area. The SSTP development team is looking to leverage the capabilities of its existing AI and ML crater, boulder, and rockfall detection and analysis tools, and extend that technology to a generalized feature detector that can be trained on instances of specific types of landforms and then search the lunar surface for more examples of such features. New traverse planning tools are being developed with use cases in generalized concept studies and specific mission planning in mind. These will facilitate finding optimal traverse paths based on constraints such as slope, lighting, hazard avoidance, and communications. These will be complemented by new traverse visualization capabilities. Users will be able to interactively ride along with a rover, examining 3D views of the terrain while adjusting camera height and viewing angle along with selecting different data layer overlays to drape across the terrain. Engaging the Public: The capabilities being developed for mission planning are being leveraged to further enhance Moon Trek’s proven utility as a valuable public outreach resource. This includes providing multiple lev-els of engagement with different points of entry. At its simplest level, promoting understanding through visualization, media and the public will be able to easily visualize and conduct their own exploration of lunar sites targeted by NASA and its partners. For a more in-depth experience, we are working with our stakeholders to promote understanding through interaction by extend-ing our current landing site and traverse analysis capabilities, making simplified access to these tools available to those who want to explore more deeply key factors in planning a mission through interactive and possibly even gamified experiences. The highest degree of public outreach, focusing on engagement through scientific participation, could be achieved through our work with missions and the NASA Office of the Chief Scientist on Moon Trek’s extension as a tool with specialized capabilities for facilitating citizen science. In such scenarios, participants become members of extended mis-sion science teams, using dedicated and integrated interfaces to analyze mission data to help answer questions key to lunar science and exploration. We are work-ing with NASA’s Office of Communications, museums, planetariums, and the media to help them easily integrate accurate, detailed visualizations of NASA’s lunar destinations and exploration into their content/productions and to engage diverse audiences in diverse venues.

Moon Trek↗

Evaluating Image Classification Deep Convolutional Neural Network Architectures for Remaining Useful Life Estimation of Turbofan Engines

Accurate estimation of the remaining useful life (RUL) is a key component of condition-based maintenance (CBM) and prognosis and health management (PHM). Data-based models for the estimation of RUL are of particular interest because expert knowledge of systems is not always available, and physical modeling is often not feasible. Additionally, using data-based models, which make decisions based on raw sensor data, allow features to be learned instead of manually determined. In this work, deep convolutional neural network (CNN) architectures are investigated for their ability to estimate the RUL of turbofan engines. To improve the accuracy of the models, CNN architectures, which have proven successful in image classification, are implemented and tested. Specifically, the blocks used in the Visual Geometry Group (VGG) architecture, inception modules used in the GoogLeNet architecture, and residual blocks used in the ResNet architecture are incorporated. To account for varying flight lengths, the input to the models is a window of time series data collected from the engine under test. Window locations at the climb, cruise, and descent stages are considered. To further improve the RUL estimations, multiple overlapping windows at each location are used. This increases the amount of training data available and is found to increase the accuracy of the resulting RUL estimations by averaging the estimates from all overlapping segments. The model is trained and tested using the new Commercial Modular Aero-Propulsion System Simulation (N-CMAPSS) data set, and high prognosis accuracy was achieved. Furthermore, this work expands on the model developed and used in the 2021 PHM Society Data Challenge, which received second place.

convolutional neural networks↗