Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep”

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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRS2017

BIRCHES and Lunarcubes: Building the First Deep Space Cubesat Broadband IR Spectrometer

The Broadband InfraRed Compact High-resolution Exploration Spectrometer (BIRCHES), which will be described in detail here, is the compact broadband IR spectrometer of the Lunar Ice Cube mission. Lunar Ice Cube is one of 13 6U cubesats that will be deployed by EM1 in cislunar space, qualifying as lunarcubes. The LunarCube paradigm is a proposed approach for extending the affordable CubeSat standard to support access to deep space via cis-lunar/lunar missions. Because the lunar environment contains analogs of most solar system environments, the Moon is an ideal target for both testing critical deep space capabilities and understanding solar system formation and processes. Effectively, as developments are occurring in parallel, 13 prototype deep space cubesats are being flown for EM1. One useful outcome of this ‘experiment’ will be to determine to what extent it is possible to develop a lunarcube ‘bus’ with standardized interfaces to all subsystems using reasonable protocols for a variety of payloads. The lunar ice cube mission was developed as the test case in a GSFC R&D study to determine whether the cubesat paradigm could be applied to deep space, science requirements driven missions, and BIRCHES was its payload. Here, we present the design and describe the ongoing development, and testing, in the context of the challenges of using the cubesat paradigm to fly a broadband IR spectrometer in a 6U platform, including minimal funding and extensive need for leveraging existing assets and relationships on development, the foreshortened schedule for payload delivery on testing, and minimum bandwidth translating into simplified or canned operation.

Chapin, Peter↗
NASA NTRS2018

Toward a NASA Deep Space Optical Communications System

As discussed at SpaceOps in 2016, we expect the data rates from deep space missions to increase approximately one order of magnitude per decade for the next 50 years. The first order of magnitude improvement will come from existing plans for radio frequency (RF) communications including enhancements to both spacecraft and Deep Space Network (DSN) facilities. The next two orders of magnitude are predicted to come from the introduction of deep space optical communications. Studies indicate that optical receive apertures of between 8m12m are desired. The large cost of dedicated receive telescopes makes this method unrealistic – at least in the near-term. The cost of large optical ground terminals is driven primarily by the cost of the optics and by the cost of a stable structure for the telescope. We propose a novel hybrid design in which existing DSN 34m beam waveguide (BWG) radio antennas can be modified to include an 8m equivalent optical primary. By utilizing a low-cost segmented spherical mirror optical design, pioneered by the optical astronomical community, and by exploiting the already existing extremely stable large radio aperture structures in the DSN, we can minimize both of these cost drivers for implementing large optical communications ground terminals. Two collocated hybrid RF/optical antennas could be arrayed to synthesize the performance of an 11.3m receive aperture to support more capable or more distant space missions or used separately to communicate with two optical spacecraft simultaneously. NASA is in the midst of building six new 34m BWG antennas in the DSN. The final two are planned to be built at the DSN Goldstone, California and Canberra complexes. We are now investigating building these last two antennas as RF/optical hybrids. By delaying their operational dates by two years, we would be able to add the 8m optical receive capability for these two antennas while fitting within existing budgetary constraints. This paper describes the hybrid antenna design, the technical challenges being addressed, and plan for using this concept, together with ongoing work on optical flight terminals, to infuse operation optical communications into deep space missions.

Cornwell, Donald M.↗
NASA NTRS2018

Deep Space Optical Communications (DSOC)

NASA’s future deep space science and exploration missions will require enhanced communications and navigation services. Laser communications offers expanded bandwidth and the potential for satisfying this need, with comparable mass and power as state of the art telecommunication systems. Consequently, NASA is planning a Deep Space Optical Communications (DSOC) technology demonstration, to retire the risk for future enhanced optical communication services. NASA’s upcoming Psyche Mission scheduled to launch in August of 2022 plans to host a DSOC flight laser transceiver (FLT) for demonstrating optical links from deep-space to earth. Existing ground assets retrofitted with laser transmitters and photon-counting receivers will be used for the technology demonstration. Advancing optical technology from near-Earth ranges to deep space (> 0.01 astronomical units or AU) involves orders of magnitude increased link difficulty (defined as data-rate squared distance). The plan to bridge the difficulty gap implements new technologies developed over the past two decades. These technologies emphasize high photon efficiency (HPE) with the use of high-peak-to-average power laser transmitters in space, and single photon counting sensitivity detectors, that together support signaling schemes for achieving approximately 23 information bits per detected photon. Implementing HPE schemes relies on accurate and stable pointing of narrow laser beams from space platforms using active control. Key developments needed for future technology infusion, following a successful DSOC technology demonstration, include, cost-effective ground infrastructure, long term reliability of space lasers and detection systems, and solutions for high precision laser ranging. The current status of the DSOC Project and plans for future development will be discussed in this paper.

Biswas, Abhijit↗
NASA NTRS2020

Impact-driven mobilization of deep crustal brines on dwarf planet Ceres

Ceres, the only dwarf planet in the inner Solar System, appears to be a relict ocean world. Data collected by NASA's Dawn spacecraft provided evidence that global aqueous alteration within Ceres resulted in a chemically evolved body that remains volatile-rich(1). Recent emplacement of bright deposits sourced from brines attests to Ceres being a persistently geologically active world(2,3), but the surprising longevity of this activity at the 92-km Occator crater has yet to be explained. Here, we use new high-resolution Dawn gravity data to study the subsurface architecture of the region surrounding Occator crater, which hosts extensive young bright carbonate deposits (faculae). Gravity data and thermal modelling imply an extensive deep brine reservoir beneath Occator, which we argue could have been mobilized by the heating and deep fracturing associated with the Occator impact, leading to long-lived extrusion of brines and formation of the faculae. Moreover, we find that pre-existing tectonic cracks may provide pathways for deep brines to migrate within the crust, extending the regions affected by impacts and creating compositional heterogeneity. The long-lived hydrological system resulting from the impact might also occur for large impacts in icy moons, with implications for creation of transient habitable niches over time.High-resolution data of Ceres's bright spots (faculae), obtained by Dawn's second extended mission, suggest the existence of a deep brine-rich reservoir that emerged to the surface through long-lived cryovolcanic activity as a consequence of the impact that created Occator crater.

C. A. Raymond↗
NASA NTRSDate not supplied

A Common Habitat Deep Space Exploration Vehicle for Transit and Orbital Operations

When outfitted as a habitat, the SLS Core Stage Liquid Oxygen Tank is a pressure vessel that can be used to support human exploration in deep space. An exploration spacecraft can be constructed with this habitat, known as the Common Habitat, as its central element. More than just a transit vehicle, this spacecraft is a Deep Space Exploration Vehicle – a microgravity science laboratory capable of conducting research with onboard human crews throughout the inner solar system. Supplied with propellant by LEO depots, preliminary trajectory and v estimates indicate that the spacecraft can perform fly-by or orbital missions with trajectories close enough to the sun to intersect the orbit of Mercury or far enough away to fly by the main belt asteroid Vesta. Its primary mission, however, is to support human expeditions to Mars. Many, though not all, of the pressurized and unpressurized elements that compose the Deep Space Exploration Vehicle can also be used in surface base camps on the Moon and Mars. In additional to traditional space science disciplines, the spacecraft offers unique potential for small asteroid retrieval and for artificial gravity research. Three launches are used to deploy the spacecraft, but thirty-nine launches are used to deliver propellant to orbit to fully fuel the spacecraft for deep space missions. Key operations in a Mars crewed mission are described to illustrate how the vehicle is used and forward work is listed to mature the spacecraft concept.

Robert L. Howard Jr.↗
NASA NTRS2021

Thermal Radiator for CO2 Deposition in Deep Space Transit (FY21 XHab Final Report - University of North Texas)

This UNT Senior design team was tasked by NASA to develop a variable conductance thermal radiator prototype for CO2 deposition for deep space transit. NASA selects university teams every year to partake in the X-HAB Academic Innovation Challenge, with this year’s number of teams being six. Air Revitalization is a crucial system for any space travel, be it for Low Earth Orbit, such as the International Space Station, or for deep space transit. Current systems, such as the Carbon Dioxide Removal Apparatus aboard the ISS, require upkeep and maintenance, which cannot be done on long distance space missions. For the past several years, NASA has done research on Cryogenic systems for Carbon Dioxide removal. These systems operate on the fact that Carbon Dioxide freezes at a higher temperature than Oxygen and Nitrogen, so Carbon Dioxide can be frozen out of the cabin atmosphere without the use of filters, which degrade over time. To cool the cabin air down to a temperature where Carbon Dioxide freezes, Stirling cryocoolers have been used, which have shown promise in the hope of Carbon Dioxide deposition for Cabin Air Revitalization. Cryogenic systems are much more reliable but require significant energy input to operate. Physical systems, such as radiators, have generally not been used for this task, as there is a need to be able to “turn off” the rejection of heat to allow the frozen carbon dioxide to be collected. However, with working fluids pumped through a physical radiator, that aspect of operation can be achieved. The goal of this challenge is to determine the effectiveness of a variable conductance thermal radiator that can reject heat to deep space, without the use of a dedicated cryocooler to remove energy from the cabin air. The proposed design uses piping, hot and cold working fluids, and non-condensable gas to absorbl heat from the cabin air on one side of the radiator and reject the heat to deep space by means of thermal radiation. As well, the system will allow for the recovery of deposited Carbon Dioxide. The UNT X-HAB 2021 team will create a model radiator and test its performance with simulated heat sources and sinks and extrapolate those data points to analyze for real world conditions.

Travis Seaver↗
NASA NTRS2020

Multi-Agent Motion Planning using Deep Learning for Space Applications

State-of-the-art motion planners cannot scale to a large number of systems. Motion planning for multiple agents is an NP (non-deterministic polynomial-time) hard problem, so the computation time increases exponentially with each addition of agents. This computational demand is a major stumbling block to the motion planner's application to future NASA missions involving the swarm of space vehicles. We applied a deep neural network to transform computationally demanding mathematical motion planning problems into deep learning-based numerical problems. We showed optimal motion trajectories can be accurately replicated using deep learning-based numerical models in several 2D and 3D systems with multiple agents. The deep learning-based numerical model demonstrates superior computational efficiency with plans generated 1000 times faster than the mathematical model counterpart.

Madani, Ramtin↗
NASA NTRS2021

Autonomy for Deep Space Communications and Navigation

In more than 50 years of deep space exploration, the number and complexity of the world’s space missions have continued to increase. This has placed increasing demands on deep space communication and navigation. However, these demands have been met in spite of an essentially level overall budget. One of the reasons for this this has been the continual application of autonomy in various forms. The NASA Deep Space Network’s implementation of “Fol-low the Sun Operations” is a recent example – but certainly not the only one. During this same period, the end-to-end information system has been increasingly automated through the application of packet telemetry and virtual channels. Fully autonomous spacecraft navigation has been demonstrated, and more limited autonomy has been applied to the operational navigation process. This paper will show how autonomy and automation capabilities have been infused into operational deep space mission communication and navigation in both flight and ground systems as appropriate. It will further discuss ongoing work aimed at increasing the level of autonomy in the future, leverag-ing recent research and application of autonomy in everyday life.

Chang, Susan↗
NASA NTRS2019

8.4 M Deep Space Habitat– Medical Bay Concept Design and Human Factors Engineering Analysis

Maintaining crew health throughout long duration deep space missions presents significant new design challenges. Since communication with Earth will be limited and it is not possible to return in the event of a medical emergency it is critical that medical care on a deep space mission be as autonomous as possible. The goal of this project was to design and assess a medical system concept for the Deep Space Habitat Concept Demonstrator derived from the core stage of the Space Launch System. The Medical Bay was designed as a primary location to support the medical care of4 crew members on a1000-daymission. It includes workspace, stowage, and direct access to all necessary medical equipment and supplies. A Human Factors Engineering Analysis was conducted to test ergonomic effectiveness and system requirement compliance. This initial design will continue to be used by the Human Factors Engineering Team and the Advanced Concepts Office at NASA’s Marshall Spaceflight Center for further demonstration, analysis, and design conception for deep space travel.

Mary Claire Mancl↗
NASA NTRSDate not supplied

Exploration Medical Capability - Advancing Medical System Design and Risk-Informed Decision Making for Deep Space Exploration

BACKGROUND: Within NASA’s Human Research Program, the Exploration Medical Capability (ExMC) Element has three primary focus areas: clinical and scientific research, systems engineering and trade space analysis, and technology development and demonstrations. These focus areas feed into the overarching goal of enabling progressively Earth-Independent Medical Operations (EIMO), a new paradigm that will be necessary for future Artemis and Mars medical and vehicle systems. This EIMO end state aligns with NASA’s Moon to Mars Objectives, which clearly outline the need for NASA deep space exploration missions to reduce their reliance upon Earth and become increasingly autonomous, in preparation for the first human Mars mission. OVERVIEW: To advance exploration medical systems and ultimately, integrated crew health and performance systems, ExMC’s portfolio includes: funding ground development & testing of novel medical capabilities; creation of new approaches for the development of medical protocols and procedures; deployment of innovative technologies into analog environments; technology demonstrations in spaceflight; and eventual transition to operations of new capabilities for deep space exploration missions. The portfolio also includes: pharmaceutical research targeting stability, pharmacokinetics, and pharmacodynamics; integrated data architectures and clinical decision support tools; and systems engineering and trade space analysis tools to assist NASA in the development of future medical system models as well as the medical system requirements that can serve as a foundation for deep space exploration missions. All of these investments are done in a collaborative and coordinated fashion with other NASA stakeholders, such as the Environmental Control and Life Support Systems – Crew Health and Performance System Capability Leadership Team and the Health and Medical Technical Authority. DISCUSSION: In this presentation, ExMC will provide an overview of our work from across our portfolio, all of which will inform future EIMO efforts at NASA. ExMC’s research and development investments are targeted to reduce the human system risks associated with deep space exploration to the Moon and Mars.

Kris Lehnhardt↗
NASA NTRSDate not supplied

Designing Experiments for SpinSat, A Novel Variable-Gravity-and-Radiation Platform for Deep-Space Science

Conducting experiments to measure the effects of deep-space radiation and reduced gravity on biological and physical systems remains challenging. The result is a substantial knowledge gap that poses risks to our ability to sustain life and conduct critical operations in deep space. The SpinSat spacecraft platform is designed to bridge such gaps by providing low-cost, reliable, and frequent access to deep space. A disk-shaped rotating satellite that can provide artificial gravity and exposure to space radiation simultaneously, SpinSat is designed to accommodate payloads in a CubeSat form factor (with at least 48 “U” volume), providing power, communications, and a benign thermal environment. It is orbit-agnostic, enabling access to a variety of radiation environments (Van Allen belts, deep space, cis-lunar); and can be equipped with shielding to mimic planetary radiation environments, for both short- and long-term experiments. Because of its versatility and prioritization of late loading for biological payloads, it is well suited to host a wide range of ranging from human tissues and organoids to microorganisms, plants, chemistry, and regolith. Here, we present examples of potential experiment concepts for SpinSat, and discuss the details of how experimental designs could interact with the platform. Potential SpinSat studies have diverse applications, including fundamental radiation biology and DNA repair; cancer biology and countermeasure development; space agriculture; bioproduction of nutrients and pharmaceuticals; understanding regolith dynamics in low gravity; prebiotic chemistry and panspermia. We will further highlight ideas for SpinSat-compatible experimental hardware, existing and in development, and experiment-relevant details on SpinSat capabilities including artificial gravity, potential radiation environments, data, and power. This presentation will aim to provide investigators with the high-level technical information necessary to inspire experiments for SpinSat. We also seek to stimulate conversation and to gain community input on accommodations needs to help guide the evolving design of this platform.

experiment design↗
NASA NTRSDate not supplied

Developing Autonomous Technologies for Biological Missions to Deep Space

In upcoming biological missions beyond low Earth orbit (LEO), the use of autonomous instrumentation will allow scientists to perform a variety of experiments, including the characterization of the response to different space environments (Moon, Mars, interplanetary space) using biological models like microbes, plants, organoids, and tissue chips. BioSentinel is an ongoing deep space mission, currently at over 50 million kilometers from Earth and the first instrument developed to perform biological experiments beyond LEO. Even though the primary objective of this CubeSat mission was to investigate the effects of the deep space radiation environment on budding yeast, the spacecraft bus (i.e., all the subsystems that support the biological payload like power, thermal, data telemetry, navigation, etc.) can accommodate a variety of biological (and physical) experiments and model organisms. LEIA, an upcoming CLPS mission to the lunar surface, uses a microfluidic and optical instrument based on BioSentinel to study the effects of the lunar environment on different cellular processes and on bioproduction of antioxidants. A new series of science mission concepts are being proposed to be accommodated into platforms like BioSentinel. These missions will investigate the response of a variety of organisms to the deep space environment, including but not limited to single-cell eukaryotes, cyanobacteria, plants (including crops), organoids, and tissue chips. In addition to optical absorbance measurements like the ones performed in BioSentinel (and LEIA), we are investigating the use of fluorescence detection, microscopy, sequencing devices, etc. Thus, instruments like the ones proposed here can be adapted to a variety of platforms like free-flyers, deployable payloads, landers, rovers, and the lunar Gateway. These technologies can be used as steppingstones for establishing a sustained human presence on the Moon and in deep space while providing knowledge for the development of potential countermeasures.

Sergio R Santa Maria↗
DOE OSTI2024

Impurity gas detection for SNF canisters using probabilistic deep learning and acoustic sensing *

Abstract Monitoring impurity gases in spent nuclear fuel (SNF) canisters is a novel structural health monitoring approach for SNF in dry storage. The SNF canisters are sealed containers that do not facilitate visual access to the inside. Acoustic sensing can be deployed by taking advantage of the pathways unobstructed by internal hardware. Although the ultrasonic time-of-flight measurement can provide valuable information, it is limited in its ability to discern the concentration of only one impurity gas. As such, deep learning algorithms, particularly convolutional neural networks (CNNs), offer a promising solution. In this study, CNN-based probabilistic deep learning models were implemented to detect and quantify multiple impurity gases in helium. An experimental platform was established to simulate canister conditions, and ultrasonic test data were collected. The presence of argon and air in helium at concentrations ranging from 0% to 1.2% at increments of 0.05% was considered. The multi-layer perceptron, decision tree, and logistic regression classifiers achieved high accuracies when distinguishing pure helium from helium with impurities. CNN with dropout layers and CNN using maximum likelihood estimation showed a similar performance, indicating their ability to capture uncertainties. The ensemble CNN model exhibited improved predictions and the ability to balance individual gas concentration by integrating 1D- and 2D-CNN models. These findings contribute probabilistic deep learning solutions for impurity gas detection and analysis within SNF canisters, thus ensuring safe storage and management of SNFs.

47 OTHER INSTRUMENTATION↗
NASA NTRS2024

Growth Rate of Deep Convective System Cloud Shields: Satellite Observations and Km-Scale Radiative Convective Equilibrium Simulations

Deep convection gives rise to large upper level clouds that strongly interact with radiation and are important to the climate energy budget. From an object-oriented perspective, these individual deep cloud systems are characterized by a well depicted cloud shield life cycle, starting with small cloud extents that grow at varying rates before decaying and vanishing. A simple formulation of the growth rate of the cloud shield has been proposed that links together the growth rate on the convective part of the cloud, the mass flux of both the convective and stratiform parts of the cluster and a simple removal sink term (Elsaesser et al., 2022). In this presentation we first show using a suite of satellite observations (infrared from geostationary satellites, GPM radar, etc.) that the functional form of the proposed equation is well suited to quantify the shield growth rate. We then focus on RCE simulations, with deep cloud system objects post processed, to explore the relative role of each term of the growth rate budget. Three different models are used in the same RCEMIP-like configurations. The results show that the budget equation works very well for each model, although the time constants require model-dependent adjustments. We will further show in Vienna the commonalities and the specificities of each model.

Deep convection↗
DOE OSTI2026

Unlocking plant-microbial interactions in deep Mollisols in the Midwestern US: Linking depth gradients in roots, microbial activity, and soil carbon in agroecosystems

Deep-rooted plants may build soil carbon (C) stocks, but most research has focused on shallow soils, leaving gaps in our understanding of how shifts in the balance between decomposition and C inputs drive soil C accumulation with depth. Thus, our objectives were to: (1) link depth gradients in root biomass with microbial activity and soil C stocks down to 1 m, and (2) examine the potential of simple C inputs to prime soil C across depths. To this end, we dug 5 quantitative soil pits in Argiudolls under mature perennial miscanthus plots in the SoyFACE Farm (Champaign-Urbana, IL). We added 13 C labeled glucose to our soils to determine the fate of simple C inputs with depth. We found that fine root biomass, total soil C, mineral-associated organic C (MAOC), particulate organic C (POC), and microbial activity (as measured by potential enzyme activity) declined with depth. POC declined more rapidly than MAOC, resulting in an increase in the ratio of MAOC-to-POC. Root biomass, enzyme activity (either acid phosphatase or n-acetyl-glucosaminadase) activity, and microbial respiration explained 74% and 38% of the variability in soil total C and MAOC, respectively, while POC was dependent on root biomass and microbial respiration (47%). Although the incorporation of simple 13 C inputs into MAOC was similar across depths, these inputs led to greater net MAOC losses in shallow soils than in deeper soils between 50 and 100 cm. The divergent impact of simple C inputs across depths may suggest that MAOC in shallow soils is more susceptible to priming losses, while C inputs into deep soils may instead be more persistent. Collectively, our results suggest that depth gradients in soil C stocks represents a balance between inputs, decomposition, and microbial necromass production and that increases in root C inputs by deep-rooted plants may have the potential to build stable MAOC.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Deep-learning based artificial intelligence tool for melt pools and defect segmentation

Accelerating fabrication of additively manufactured components with precise microstructures is important for quality and qualification of built parts, as well as for a fundamental understanding of process improvement. Accomplishing this requires fast and robust characterization of melt pool geometries and structural defects in images. This paper proposes a pragmatic approach based on implementation of deep learning models and self-consistent workflow that enable systematic segmentation of defects and melt pools in optical images. Deep learning is based on an image-to-image translation–conditional generative adversarial neural network architecture. An artificial intelligence (AI) tool based on this deep learning model enables fast and incrementally more accurate predictions of the prevalent geometric features, including melt pool boundaries and printing-induced structural defects. We present statistical analysis of geometric features that is enabled by the AI tool, showing strong spatial correlation of defects and the melt pool boundaries. The correlations of widths and heights of melt pools with dataset processing parameters show the highest sensitivity to thermal influences resulting from laser passes in adjacent and subsequent layer passes. The presented models and tools are demonstrated on the aluminum alloy and datasets produced with different sets of processing parameters. However, they have universal quality and could easily be adapted to different material compositions. The method can be easily generalized to microstructural characterizations other than optical microscopy.

additive manufacturing↗
DOE OSTI2026

Deep learning for time series forecasting: a survey of recent advances

Time series forecasting plays a critical role in numerous real-world applications, such as finance, healthcare, transportation, and scientific computing. In recent years, deep learning has become a powerful tool for modeling complex temporal patterns and improving forecasting accuracy. This survey provides an overview of recent deep learning approaches for time series forecasting, involving various architectures including RNNs, CNNs, GNNs, transformers, large language models, MLP-based models, and diffusion models. We first identify key challenges in the field, such as temporal dependency, efficiency, and cross-variable dependency, which drive the development of forecasting techniques. Then, the general advantages and limitations of each architecture are discussed to contextualize their adaptation in time series forecasting. Furthermore, we highlight promising design trends like multi-scale modeling, decomposition, and frequency-domain techniques, which are shaping the future of the field. This paper serves as a compact reference for researchers and practitioners seeking to understand the current landscape and future trajectory of deep learning in time series forecasting.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Inverse design of hypoeutectoid pearlite steel microstructures using a deep learning and genetic algorithm optimization framework

Goal-oriented microstructure design in metallic materials is a challenging task due to complex structure-property relationships. Traditional experimental and computational approaches are time-intensive and economically inefficient, limiting their applicability for large-scale design space exploration. Here, in this work, we propose an end-to-end framework that integrates deep learning models with genetic optimization to design microstructures with targeted mechanical properties. Deep learning models enable accurate forward design, while their integration with genetic optimization enables efficient inverse design within a few hours, compared to days or weeks using conventional finite element simulations. The framework combines experimental characterization and finite element modeling to analyze the influence of microstructural features on the mechanical behavior of hypoeutectoid steels. Data from both experiments and simulations are used to train the deep learning models. To demonstrate its effectiveness, we apply the framework to 0.63% carbon steel with proeutectoid ferrite and pearlite phases, commonly used in industrial applications. In this study, 2D microstructures were used for modeling, selected primarily for computational efficiency and to establish proof of concept. The framework successfully optimizes microstructures for targeted yield strength, ultimate strength, and stress concentration factors while significantly reducing computational time. Beyond hypoeutectoid steels, this scalable framework can be extended to other material systems and integrated with additive manufacturing, offering an efficient approach for accelerating microstructure design for specific engineering applications.

ConvLSTM↗