Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Clemson University

Discipline
Keyword
Publication Year
Publication
Publication Type

Articles 1 - 30 of 1675

Full-Text Articles in Engineering

Thermoforming Process Effects On Structural Performance Of Carbon Fiber Reinforced Thermoplastic Composite Parts Through A Manufacturing To Response Pathway, Madhura Limaye, Sai Aditya Pradeep, Anmol Kothari, Sushil Savla, Akshat Agha, Srikanth Pilla, Gang Li Feb 2022

Thermoforming Process Effects On Structural Performance Of Carbon Fiber Reinforced Thermoplastic Composite Parts Through A Manufacturing To Response Pathway, Madhura Limaye, Sai Aditya Pradeep, Anmol Kothari, Sushil Savla, Akshat Agha, Srikanth Pilla, Gang Li

Publications

Thermoforming process of thermoplastic-based continuous CFRP's offer a major advantage in reducing cycle times for large-scale productions, but it can also have a significant impact on the structural performance of the parts by inducing undesirable effects. This necessitates the development of an optimal manufacturing process that minimizes the introduction of undesirable factors in the structure and thereby achieves the targeted mechanical performance. This can be done by first establishing a relationship between the manufacturing process and mechanical performance and successively optimizing it to achieve the desired targets. The current study focuses on the former part, where a manufacturing-to-response (MTR ...


Advanced Anti-Buckling Device Coupled With Real-Time Digital Image Correlation For Complex Cyclic Tension-Compression Testing Of Lightweight Materials, Akshat Agha, Fadi Abu-Farha Jan 2022

Advanced Anti-Buckling Device Coupled With Real-Time Digital Image Correlation For Complex Cyclic Tension-Compression Testing Of Lightweight Materials, Akshat Agha, Fadi Abu-Farha

Publications

In sheet metal forming and stamping operations, modeling the behavior of sheet metal alloys for springback prediction is known to be very challenging, not only because of the complex models needed to account for kinematic hardening (such as the Yoshida-Uemori Model) but more importantly because of the experimental limitations of our ability to perform the complex tests needed to calibrate such models. For instance, reliable monotonic uniaxial compression tests and then cyclic tension-followed-by-compression tests are essential for characterizing the response of the material under those loading conditions, providing quantitative evaluation of the Bauschinger Effect and tension/compression asymmetry in the ...


An Experimental And Computational Study Of 3-Dimensional Compact Windborne Debris Flight, Ta'jon Jordan Dec 2021

An Experimental And Computational Study Of 3-Dimensional Compact Windborne Debris Flight, Ta'jon Jordan

All Theses

In this thesis, the stochastic nature of 3-dimensional compact windborne debris flight is investigated experimentally and computationally. Previous literature (Holmes, 2004) analyzed the impact of strong winds on compact debris with applications to windborne debris flight. Baker (2007) derived the 2-dimensional equations of motion into a generalized dimensionless form that reveals the fundamental controlling parameters of compact debris flight. However, these models assume that compact debris is spherical, and the flight is, therefore, 2-dimensional. However most compact debris is not spherical, and its flight is 3-dimensional. Herein a previously developed model for free-falling compact windborne debris flight (Ahsanulllah et al ...


Development And Application Of A Digital Twin For Chiller Plant Performance Assessment, Mihir Kale Dec 2021

Development And Application Of A Digital Twin For Chiller Plant Performance Assessment, Mihir Kale

All Theses

As the complexity of industrial equipment continues to increase, the management of the individual machines and integrated operations becomes difficult without computer tools. The availability of streaming data from manufacturing floors, plant operations, and deployed fleets can be overwhelming to analyze, although it provides opportunities to improve performance. The use of dedicated monitoring systems in the plant and field to troubleshoot machinery can be integrated within a product lifecycle management (PLM) architecture to offer greater features. PLM offers virtual processes and software tools for the design, analysis, monitoring, and support of engineering systems and products. Within this paradigm, a digital ...


Development And Validation Of An Analytical Modeling Tool For Solar Borehole Heat Exchangers, Adam Ornelles Dec 2021

Development And Validation Of An Analytical Modeling Tool For Solar Borehole Heat Exchangers, Adam Ornelles

All Theses

Current numerical modeling solutions used for subsurface heat flow, such as the Berkeley TOUGH codes, are often difficult to use and time-consuming compared to analytical modeling methods. However, current analytical modeling methods for subsurface heat flow and groundwater cannot accurately model the subsurface in 3 dimensions, a feature paramount to the planning and installation of thermal borehole heat exchangers used in environmental remediation.

This research developed a novel 3-dimensional analytical modeling tool for solar-powered borehole heat exchangers. The analytical modeling tool can plan thermal remediation systems while being more straightforward to operate than current numerical modeling software. By creating a ...


Design And Fabrication Of A Polymer Fdm Printer Capable Of Build Parameter Monitoring And In-Sit Geometric Monitoring Via Photogrammetry, Travis Roberts Dec 2021

Design And Fabrication Of A Polymer Fdm Printer Capable Of Build Parameter Monitoring And In-Sit Geometric Monitoring Via Photogrammetry, Travis Roberts

All Theses

Additive manufacturing, or 3D printing, is a complex process that creates free-form geometric objects by sequentially placing material in a location to construct an object, usually as a layer-by-layer process. One of the most widespread methods is Fused Deposition Modeling (FDM). FDM is used in many of the consumer-grade polymer 3D printers available today. While consumer grade machines are cheap and plentiful, they lack many of the features desired in a machine used for research purposes and are often closed-source platforms. Commercial-grade models are more expensive and are also usually closed-source platforms that do not offer flexibility for modifications often ...


The Effect Of Using Palm Oil As An Electron Donor For The Reductive Dechlorination Of Trichloroethylene (Tce), Shivani Swamy Dec 2021

The Effect Of Using Palm Oil As An Electron Donor For The Reductive Dechlorination Of Trichloroethylene (Tce), Shivani Swamy

All Theses

TCE is currently remediated using physical methods like air stripping and granular activated carbon adsorption. While physical and chemical processes work on a site-specific basis, biological strategies have been favored as they are economical and reliable. The objective of this work was to determine the feasibility of using palm oil as an electron donor in the reductive dechlorination of TCE to ethene. Palm oil was considered for the study because it is locally grown in many parts of the world. The palm oil that does not meet the industry standards is discarded. Despite the environmental impacts caused by the palm ...


Covid Response: Iterative Model Development In The Deployment Of Hand Sanitation Stations At A Large Public University, Tyler Obrien Dec 2021

Covid Response: Iterative Model Development In The Deployment Of Hand Sanitation Stations At A Large Public University, Tyler Obrien

All Theses

This study illustrates the significance of iterative model development using the deployment of hand sanitizer stations in buildings at Clemson University as a case study. The COVID-19 problem affected Clemson University, a major institution, in several ways requiring adaptations to existing policies and procedures to take place. Following guidelines provided by the Centers for Disease and Control (CDC), the university implemented several new strategies including placing hand sanitizer stations in several buildings on campus in order to try and mitigate the transmission of the virus. This study focuses on learning how the initial decision-making took place to then design a ...


Water Recovery From Bioreactor Mixed Liquors Using Forward Osmosis With Polyelectrolyte Draw Solutions, Calen Raulerson Dec 2021

Water Recovery From Bioreactor Mixed Liquors Using Forward Osmosis With Polyelectrolyte Draw Solutions, Calen Raulerson

All Theses

The objective of this research was to test the feasibility of using forward osmosis (FO) with polyelectrolyte draw solutions to recover water from bioreactor mixed liquors. When combined with an Anaerobic Osmotic Membrane Bioreactor (AnOMBR), such a system could process fecal and food waste from astronauts aboard the International Space Station (ISS) and reclaim important nutrients and water. This project focused on measuring the obtainable water recovery rates from bioreactor effluent, and the identifying challenges associated with the operation.

AnOMBRs feature several advantages over aerobic bioreactors, and non-osmotic anaerobic membrane bioreactors (AnMBR). Anaerobic bioreactors avoid the significant energy costs of ...


Extraction Methodologies And Physicochemical Characterizations Of Nanocellulose Isolated From Kudzu For Potential Sustainable Packaging Applications, Elliott Love Dec 2021

Extraction Methodologies And Physicochemical Characterizations Of Nanocellulose Isolated From Kudzu For Potential Sustainable Packaging Applications, Elliott Love

All Theses

Flexible packaging is an integral part of the food supply chain due to its unique thermal, mechanical, and barrier properties. The many advantages (e.g., lightweight, product protection, reduction in food waste, communication medium, etc.) come with certain drawbacks (low recyclability rate, pollution of ecosystems, etc.). Still, the heavy reliance of the food industry on these products, many of them being non-sustainable polyolefins, is unlikely to diminish in the foreseeable future. Thus, more sustainable alternatives that do not sacrifice performance (machinability, shelf-life, etc.) are needed before pollution becomes irreversible and public outcry insurmountable. Nanocellulose, especially in the form of cellulose ...


Application Of Image Processing And Convolutional Neural Networks For Flood Image Classification And Semantic Segmentation, Jaku Rabinder Rakshit Pally Dec 2021

Application Of Image Processing And Convolutional Neural Networks For Flood Image Classification And Semantic Segmentation, Jaku Rabinder Rakshit Pally

All Theses

Floods are among the most destructive natural hazards that affect millions of people across the world leading to severe loss of life and damage to property, critical infrastructure, and the environment. Deep learning algorithms are exceptionally valuable tools for collecting and analyzing the catastrophic readiness and countless actionable flood data. Convolutional neural networks (CNNs) are one form of deep learning algorithms widely used in computer vision which can be used to study flood images and assign learnable weights and biases to various objects in the image. Here, we leveraged and discussed how connected vision systems can be used to embed ...


Tradespace Exploration Of A Uav Conceptual Design Using Model-Based Systems Engineering, Ayan Srivastava Dec 2021

Tradespace Exploration Of A Uav Conceptual Design Using Model-Based Systems Engineering, Ayan Srivastava

All Theses

The objective of this research is to apply model-based systems engineering approaches to the conceptual design of unmanned aerial vehicles. This is accomplished by evaluating the models of aircraft performance, extracting input and output parameters from the models, creating chains of models, and implementing the models in the MATLAB programming language. By following this process, it is possible to identify the global parameters that remain constant across models, the shared input parameters, the dependencies between models, and the feedback loops with the systems models.

The models are currently implemented in two files using Microsoft MS Excel, one is focused on ...


Effect Of Long And Short Chain Fatty Acids On Methane Yield And Microbial Community Composition In Anaerobic Co-Digestion, Emmaline Spier Camposano Dec 2021

Effect Of Long And Short Chain Fatty Acids On Methane Yield And Microbial Community Composition In Anaerobic Co-Digestion, Emmaline Spier Camposano

All Theses

Fats, oils and greases are produced from a variety of industries, including animal rendering operations, vegetable oil processing plants and the hospitality industry. These hydrophobic, COD-rich compounds are known to cause issues in municipal wastewater collection and treatment systems. Anaerobic co-digestion has been shown to be an effective way to treat FOG and presents an opportunity to produce greater quantities of biogas. However, many microorganisms are sensitive to the degradation products of FOG, including long and short chain fatty acids. Two studies were performed to address potential inhibitory effects of both.

The first study co-digested various percentages of FOG with ...


Glycan Functionalization Of Iron Oxide Nanoparticles (Ionps) As A Method Of Inactivating Antibiotic Resistant Neisseria Gonorrhoeae Via A Magnetically Mediated Energy Delivery (Magmed) System, Cedric Taylor Dec 2021

Glycan Functionalization Of Iron Oxide Nanoparticles (Ionps) As A Method Of Inactivating Antibiotic Resistant Neisseria Gonorrhoeae Via A Magnetically Mediated Energy Delivery (Magmed) System, Cedric Taylor

All Theses

With the increase of antibiotic resistant bacteria, current established therapeutic treatment methods are rapidly demonstrating decreasing efficacy. For this project, we are studying a novel alternate mechanism of treating antibiotic resistant bacteria by utilizing magnetic iron oxide nanoparticles (IONPs) coated with a heterobifunctional polyethylene glycol polymer (PEG) and functionalized with glycan structures that can interact with Neisseria gonorrhoeae FA1090. Interaction between the IONPs and bacteria is manipulated by an external alternating magnetic field (AMF) in a process known as magnetically mediated energy delivery (MagMED). Magnetic IONPs were synthesized and reacted with PEG (PEG-IONPs) and functionalized with glycans Gal(α1-3)Gal ...


Development And Promotion Of Mass Timber Noise Barrier For Highways, Harsh Bothra Dec 2021

Development And Promotion Of Mass Timber Noise Barrier For Highways, Harsh Bothra

All Theses

Highways are some of the biggest causes of noise pollution in the United States of America. To deal with the traffic noise coming from these highways, noise barriers have been erected across major highways. The goal is to reduce as much noise as possible through a sustainable solution. Unfortunately, the use of steel and concrete, commonly used materials, have undesired environmental impacts. A suggested sustainable alternative material would be mass timber. Mass timber products such as cross-laminated timber (CLT) and mass plywood panels (MPP) has attracted the attention of the construction industry in the U.S, as they are sustainable ...


Product Lifecycle Management - Application Of Patterning Methods To Gas Turbine Blades And Creation Of Learning Materials, David Procopio Dec 2021

Product Lifecycle Management - Application Of Patterning Methods To Gas Turbine Blades And Creation Of Learning Materials, David Procopio

All Theses

To compete in the global marketplace, companies need to embrace virtual design and manufacturing methods. Product Lifecycle Management (PLM) embodies both the workflow processes and tools to bring forth products from conception to design to fabrication to service to decommissioning, and to eventual recycling. In response to the growing demand for engineers and technicians with these critical skills, colleges and universities should introduce these virtual tools through seminars, software workshops, and computer laboratory sessions. Some of the opportunities in the PLM Center at Clemson University include short courses on PLM practices, focused software training sessions, hands-on exploration activities, and research ...


Development Of Lambda Factors For Masonry Design With Lightweight Grout, Rumi Shrestha Dec 2021

Development Of Lambda Factors For Masonry Design With Lightweight Grout, Rumi Shrestha

All Theses

Reduction in structural mass, improvement in thermal performance, and reduction in shrinkage cracking through internal curing are some of the reasons that lightweight (LW) aggregates have been used in structures and pavements for decades. However, lightweight grout is still not permitted for use in reinforced masonry construction by the TMS 402/602-16 code. In order to realize the benefits of lightweight grout in U.S. reinforced masonry construction, a codified procedure for its use is required which must be informed by experimental testing.

This research is a pilot project directed to characterize the performance of LW grout in comparison to ...


Chasing Target Zero: Contributing Factors Of Fatal Crashes In South Carolina, Matthew Stanley Dec 2021

Chasing Target Zero: Contributing Factors Of Fatal Crashes In South Carolina, Matthew Stanley

All Theses

South Carolina consistently ranks in the top-10 in fatal crashes per 100,000 capita and 100 million vehicle miles traveled. This thesis summarizes an analysis of contributing factors for fatal crashes in South Carolina. A primary objective of this thesis is to investigate differences in contributing factors for fatal crashes as compared to all crashes in South Carolina. 2018 South Carolina fatal crashes (N=970) and all crashes (N=152,973) were analyzed and compared using classic Venn diagrams to compare differences in contributing factors between fatal crashes and all crashes. Fatal, non-fatal, and all crashes were aggregated into one ...


Analysis Of Deep Learning Methods For Wired Ethernet Physical Layer Security Of Operational Technology, Lucas Torlay Dec 2021

Analysis Of Deep Learning Methods For Wired Ethernet Physical Layer Security Of Operational Technology, Lucas Torlay

All Theses

The cybersecurity of power systems is jeopardized by the threat of spoofing and man-in-the-middle style attacks due to a lack of physical layer device authentication techniques for operational technology (OT) communication networks. OT networks cannot support the active probing cybersecurity methods that are popular in information technology (IT) networks. Furthermore, both active and passive scanning techniques are susceptible to medium access control (MAC) address spoofing when operating at Layer 2 of the Open Systems Interconnection (OSI) model. This thesis aims to analyze the role of deep learning in passively authenticating Ethernet devices by their communication signals. This method operates at ...


Investigation On Effects Of Lactate Adaptation Using Metabolic Indicators And Amino Acids To Explore Cell Metabolism, Lisa Uy Dec 2021

Investigation On Effects Of Lactate Adaptation Using Metabolic Indicators And Amino Acids To Explore Cell Metabolism, Lisa Uy

All Theses

Biopharmaceutical products are drugs that are made from living cells. One protein type of high importance to biopharmaceuticals is monoclonal antibodies. Monoclonal antibodies allow for highly specific, targeted treatment of diseases and detection of molecules related to diseases. With major roles in detecting and/or treating diseases like human immunodeficiency virus (HIV), coronavirus disease 2019 (COVID-19), and some cancers, monoclonal antibodies are in demand. This demand has led to a need for efficient cell culture systems to produce high yields of protein with minimal waste. The most commonly used cell culture system for these high-value proteins is Chinese hamster ovary ...


Lossy Compression And Its Application On Large Scale Scientific Datasets, Tasmia Reza Dec 2021

Lossy Compression And Its Application On Large Scale Scientific Datasets, Tasmia Reza

All Theses

High Performance Computing (HPC) applications are always expanding in data size and computational complexity. It is becoming necessary to consider fault tolerance and system recovery to reduce computation and resource cost in HPC systems. The computation of modern large scale HPC applications are facing bottleneck due to computation complexities, increased runtime and large data storage requirements. These issues can not be ignored in current supercomputing era. Data compression is one of the effective ways to address data storage issue. Among data compression, the lossy compression is much more feasible and efficient than the traditional lossless compression due to low I ...


Theoretical Development And Numerical Validation Of An Asymmetric Linear Bilateral Control Model For An Automated Truck Platoon, M Sabbir Salek Dec 2021

Theoretical Development And Numerical Validation Of An Asymmetric Linear Bilateral Control Model For An Automated Truck Platoon, M Sabbir Salek

All Theses

In this study, the author theoretically develops and numerically validates an asymmetric linear bilateral control model (LBCM) for an automated truck platoon, in which the motion information (i.e., position and speed) from the immediate leading truck and the immediate following truck are weighted differently. The novelty of the asymmetric LBCM is that using this model, all the follower trucks in a platoon can adjust their acceleration and deceleration to closely follow a constant desired time headway at all times to improve platoon operational efficiency while maintaining local and string stability. The author theoretically proves the local stability of the ...


Deriving Generalized Temperature-Dependent Material Models For Masonry Through Fire Tests And Machine Learning, Aditya Avinash Daware Dec 2021

Deriving Generalized Temperature-Dependent Material Models For Masonry Through Fire Tests And Machine Learning, Aditya Avinash Daware

All Theses

Masonry is one of the oldest and commonly used building materials in the construction industry. Among a variety of benefits, masonry provides low-cost construction, fire, and weather protection as well as thermal and sound insulation. In addition, masonry has superior material properties at elevated temperatures which is reflected by its slow degradation of its mechanical and thermal properties. Literature shows that we do not have a uniform material model that describes the mechanical degradation of masonry under fire conditions. As such, this limits the use of masonry in fire-based performance design of masonry structures. To bridge this knowledge gap, this ...


Deep Learning Based Speech Enhancement And Its Application To Speech Recognition, Ju Lin Dec 2021

Deep Learning Based Speech Enhancement And Its Application To Speech Recognition, Ju Lin

All Dissertations

Speech enhancement is the task that aims to improve the quality and the intelligibility of a speech signal that is degraded by ambient noise and room reverberation. Speech enhancement algorithms are used extensively in many audio- and communication systems, including mobile handsets, speech recognition, speaker verification systems and hearing aids. Recently, deep learning has achieved great success in many applications, such as computer vision, nature language processing and speech recognition. Speech enhancement methods have been introduced that use deep-learning techniques, as these techniques are capable of learning complex hierarchical functions using large-scale training data. This dissertation investigates the deep learning ...


Coupled Thermal Mechanical Analysis Methodology For Thermal Performance Evaluation And Failure Mode Identification Of Thermal Barrier Coatings For Heavy Duty Diesel Engines, Sean Moser Dec 2021

Coupled Thermal Mechanical Analysis Methodology For Thermal Performance Evaluation And Failure Mode Identification Of Thermal Barrier Coatings For Heavy Duty Diesel Engines, Sean Moser

All Dissertations

Consumer demand and government regulation, as well as the Department of Energy’s SuperTruck program has motivated extraordinary effort to maximize the heavy-duty diesel engine’s thermal efficiency. Thermal barrier coatings (TBCs) provide an avenue for increasing the thermal efficiency of the mixing controlled combustion (MCC) process through the reduction of heat transfer losses. The myriad of previous studies presents conflicting conclusions, both in the merit of TBCs for cycle improvement, and also for coating durability and potential adverse effects from coating failure. While the most recent studies with thin thermal barrier coatings (~100-250 µm) have shown a majority of ...


Influencing The Inflammatory Response Through Multi-Scale Geometry, Antibiotic Release, And Fluid Management In A Textile-Based Biomaterial Wound Dressing, Elizabeth Gianino Dec 2021

Influencing The Inflammatory Response Through Multi-Scale Geometry, Antibiotic Release, And Fluid Management In A Textile-Based Biomaterial Wound Dressing, Elizabeth Gianino

All Dissertations

The total population of diagnosed and undiagnosed diabetes mellitus in the United states is expected to rise by 54% between the years of 2015 and 2030 contributing to $200 billion in health care expense. The exponential rise in common diabetic wounds, such as diabetic foot ulcers, puts a large population at risk for complications such as infection, amputation, and even death. Peripheral neuropathy leading to late diagnoses, patient non-compliance, and lack of holistic treatment options all contribute to complications with the incidence of new ulcer formation after treatment reaching 50%. This work explores the design, development, and in vitro evaluation ...


Towards Understanding Protein Immobilization Rules Through Site-Specific Covalent Immobilization Of T4 Lysozyme, Maxwell Hilbert Dec 2021

Towards Understanding Protein Immobilization Rules Through Site-Specific Covalent Immobilization Of T4 Lysozyme, Maxwell Hilbert

All Dissertations

Soluble enzymes have the unique ability to assist the conversion of complex substrates in fewer steps compared to conventional chemical synthesis; however, when immobilized to a surface, the insoluble enzyme's activity and stability can suffer in its new environment. To improve upon future immobilized enzyme efficacy, a fundamental understanding of the interactions across the enzyme, linker, and surface during covalent, site-specific immobilization that can be detrimental to its activity is required. More specifically, using a well-characterized and model enzyme, T4 lysozyme (T4L), 28 different cysteine attachment points' effects on site-specifically immobilized activity are examined. Different combinations of heterobifunctional amine-to-sulfhydryl ...


Seismic Performance Assessment Of Building Contents: Monetary Losses And Injuries, Sereen Majdalaweyh Dec 2021

Seismic Performance Assessment Of Building Contents: Monetary Losses And Injuries, Sereen Majdalaweyh

All Dissertations

Building contents include all the components that are not attached to the building which the owners place after the construction phase, such as furniture, electrical equipment, glassware, and other personal items. Loss and damage assessment of building contents proved to be challenging in performance-based earthquake engineering frameworks because of the data sparsity. Damages to building contents during an earthquake not only cause monetary losses; tumbling and over-toppling of heavy building contents could result in injuries and even deaths of occupants. While major advancements have been made in performance-based earthquake engineering; however, the focus is mainly on damages and collapse risk ...


A Youthful Metaverse: Towards Designing Safe, Equitable, And Emotionally Fulfilling Social Virtual Reality Spaces For Younger Users, Divine Maloney Dec 2021

A Youthful Metaverse: Towards Designing Safe, Equitable, And Emotionally Fulfilling Social Virtual Reality Spaces For Younger Users, Divine Maloney

All Dissertations

Social virtual reality (VR) represents the modern rendition of the metaverse, this dissertation aims to fill the research gaps while highlighting trends of youth in VR. The scientific contributions of this research include 1) expanding the current HCI understanding of the social dynamics and the interactions of teens in emerging novel online digital spaces; 2) bridging two research areas that have not been widely studied in HCI, social VR and young users in social VR; and 3) generating design implications to inform the design of future social VR platforms to better support and protect teens’ online social experiences, results which ...


Deep Learning-Guided Prediction Of Material’S Microstructures And Applications To Advanced Manufacturing, Jianan Tang Dec 2021

Deep Learning-Guided Prediction Of Material’S Microstructures And Applications To Advanced Manufacturing, Jianan Tang

All Dissertations

Material microstructure prediction based on processing conditions is very useful in advanced manufacturing. Trial-and-error experiments are very time-consuming to exhaust numerous combinations of processing parameters and characterize the resulting microstructures. To accelerate process development and optimization, researchers have explored microstructure prediction methods, including physical-based modeling and feature-based machine learning. Nevertheless, they both have limitations. Physical-based modeling consumes too much computational power. And in feature-based machine learning, low-dimensional microstructural features are manually extracted to represent high-dimensional microstructures, which leads to information loss.

In this dissertation, a deep learning-guided microstructure prediction framework is established. It uses a conditional generative adversarial network (CGAN ...