Materials Science and Engineering Commons^™

Machine Learning-Driven Process Analysis And Optimization In Solid-State Welding And Fusion-Based Additive Manufacturing, Radif Uddin Ahmed

Master's Theses

In the modern era of advanced manufacturing, optimizing process parameters is pivotal in ensuring the quality and reliability of sophisticated component fabrication. This study presents a novel, data-driven approach to parameter optimization in two cutting-edge manufacturing techniques: Friction Stir Welding (FSW) and Laser Powder Bed Fusion (LPBF). By leveraging machine learning methodologies, this research addresses the critical challenge of efficiently determining optimal process parameters, a task traditionally relying on time-consuming and resource-intensive trial-and-error methods. This study will lead to a robust data-driven framework for process analysis of more advanced manufacturing techniques like the Additive Friction Stir Deposition (AFSD) process. Friction …

Implementation Of Machine Learning Using Deep Neural Networks To Estimate The Failure Risk Caused By Leakage In Pressure Relief Devices, Adi Yudho Wijayanto, Yossi Andreano, M. Ali Yafi Rizky, Dedi Priadi

Journal of Materials Exploration and Findings

The primary objective of deploying Pressure Relief Device (PRD) equipment is to ensure the safety of pressure vessels within a pressurized system. Over time, PRD equipment may degrade and fail to perform its intended function, which must be identified as a failure mode. To mitigate potential risks associated with this, it is recommended that an approach such as risk-based inspection (RBI) be implemented. Despite the widespread adoption of RBI, the method relies on qualitative techniques, leading to significant variations in equipment risk assessments. This study proposes a novel risk analysis method that uses deep learning-based machine learning to develop a …

Mesostructure Reconstruction Of Prepreg Platelet Molded Composite With Artificial Intelligence, Richard Larson

Mechanical & Aerospace Engineering Theses & Dissertations

Prepreg platelet molded composites (PPMC) are long, discontinuous fiber reinforced polymer materials. PPMC are an important subcategory of composite materials as they are processible into geometrically complex structures and can be produced via high-throughput manufacturing processes, however they have higher stiffness and strength as compared to traditional discontinuous fiber reinforced polymers. However, there is inherent randomness in the structure of PPMCs and as such, PPMC parts frequently require per part testing that is cost prohibitive.

Herein, a method using artificial intelligence is proposed as a more cost-effective method of inspecting PPMC parts. Different artificial intelligence (AI) architectures are explored to …

Machine Learning Assisted Discovery Of High-Performance Perovskites For Hydrogen Production, Ximei Zhai

All Dissertations

Hydrogen has significantly contributed to the global energy transition as a clean energy carrier. However, traditional hydrogen production involves energy-intensive processes with heavy carbon emissions. High-temperature water splitting to generate hydrogen has become a promising route for clean hydrogen production. Directly utilizing concentrated solar heat to perform solar thermochemical hydrogen (STCH) production is considered one of the most eco-friendly hydrogen production options. At the same time, high-temperature electrolysis in protonic ceramic electrolysis cells (PCECs) can efficiently utilize intermittent and cost-effective renewable electricity to produce hydrogen. Perovskite oxides with good redox capability and tolerance for oxygen deficiency are considered the most …

On The Use Of Machine Learning And Data-Transformation Methods To Predict Hydration Kinetics And Strength Of Alkali-Activated Mine Tailings-Based Binders, Sahil Surehali, Taihao Han, Jie Huang, Aditya Kumar, Narayanan Neithalath

Electrical and Computer Engineering Faculty Research & Creative Works

The escalating production of mine tailings (MT), a byproduct of the mining industry, constitutes significant environmental and health hazards, thereby requiring a cost-effective and sustainable solution for its disposal or reuse. This study proposes the use of MT as the primary ingredient (≥70%mass) in binders for construction applications, thereby ensuring their efficient upcycling as well as drastic reduction of environmental impacts associated with the use of ordinary Portland cement (OPC). The early-age hydration kinetics and compressive strength of MT-based binders are evaluated with an emphasis on elucidating the influence of alkali activation parameters and the amount of slag or cement …

Automating Selective Area Electron Diffraction Phase Identification Using Machine Learning, Nathaniel Tomczak, Jennifer Carter

Faculty Scholarship

Selective area electron diffraction (SAED) patterns can provide valuable insight into the structure of a material. However, the manual identification of collected patterns can be a significant bottleneck in the overall phase classification workflow. In this work, we utilize the recent advances in computer vision and machine learning (ML) to automate the indexing of SAED patterns. The performance of six different ML algorithms is demonstrated using metallic plutonium-zirconium alloys. The most successful approach trained a neural network (NN) to make a classification of the phase and zone axis, and then utilized a second NN to synthesize multiple independent predictions of …

Predicting Compressive Strength Of Concrete Incorporating Fly Ash, Blast Furnace Slag, And Superplasticizer Using Machine Learning Techniques, Muhammad Faisal Yaqub

2024 REYES Proceedings

Concrete is the second most essential element in the construction industry, and its strength requirements vary based on the specific conditions of each project. However, determining the compressive strength of concrete involves laboratory tests, which wastes a lot of time and money. Researchers have developed machine learning models that predict the compressive strength of cement-based concrete having various mixes. In this research, the compressive strength of concrete incorporating fly ash, blast furnace slag, and superplasticizer is predicted using different machine learning models, namely, Linear Regression, Random Forest Regression, Decision Tree Regression, Extreme Gradient Boosting, Light Gradient Boosting, AdaBoost, and CatBoost …

Machine Learning-Assisted Multiscale Simulation And Design Optimization Of Composite Jackets Under Low-Velocity Impacts, Masoud Mohammadi

Graduate Theses, Dissertations, and Problem Reports (ETD)

This research presents the development of a data-driven machine learning-assisted approach to simulate and optimize the design of composite materials subjected to low-velocity impacts. It focuses on a specific type of hybrid composite comprised of fiberglass and Kevlar fabrics stitched with Kevlar threads. The study begins by creating a multiscale finite element simulation for the composite under a low-velocity impact, which operates across three scales: microscale, mesoscale, and macroscale. This simulation accepts various inputs, such as different layer configurations and orientations, and provides impact outputs including maximum load and energy absorption capacity and displacement at failure.

Python and MATLAB scripts …

Machine-Learning-Assisted Design Of Deep Eutectic Solvents Based On Uncovered Hydrogen Bond Patterns, Usman Lame Abbas, Yuxuan Zhang, Joseph Tapia, Md Selim, Jin Chen, Jian Shi, Qing Shao

Markey Cancer Center Faculty Publications

Non-ionic deep eutectic solvents (DESs) are non-ionic designer solvents with various applications in catalysis, extraction, carbon capture, and pharmaceuticals. However, discovering new DES candidates is challenging due to a lack of efficient tools that accurately predict DES formation. The search for DES relies heavily on intuition or trial-and-error processes, leading to low success rates or missed opportuni- ties. Recognizing that hydrogen bonds (HBs) play a central role in DES formation, we aim to identify HB features that distinguish DES from non-DES systems and use them to develop machine learning (ML) models to discover new DES systems. We first analyze the …

Predictions Of Lattice Parameters In Niti High-Entropy Shape-Memory Alloys Using Different Machine Learning Models, Tu-Ngoc Lam, Jiajun Jiang, Min-Cheng Hsu, Shr-Ruei Tsai, Mao-Yuan Luo, Shuo-Ting Hsu, Wen-Jay Lee, Chung-Hao Chen, E-Wen Huang

Electrical & Computer Engineering Faculty Publications

This work applied three machine learning (ML) models—linear regression (LR), random forest (RF), and support vector regression (SVR)—to predict the lattice parameters of the monoclinic B19′ phase in two distinct training datasets: previously published ZrO₂-based shape-memory ceramics (SMCs) and NiTi-based high-entropy shape-memory alloys (HESMAs). Our findings showed that LR provided the most accurate predictions for a_c, a_m, b_m, and c_m in NiTi-based HESMAs, while RF excelled in computing βm for both datasets. SVR disclosed the largest deviation between the predicted and actual values of lattice parameters for both training datasets. A combination approach …

The Impacts Of Impurities And Stress State On Polycrystalline Ice Deformation And Investigations Into The Densification Of Polar Firn, Ayobami Oladapo Ogunmolasuyi

Dartmouth College Ph.D Dissertations

Glacier ice cores are unparalleled natural archives of past climate, containing ancient air and impurities. Understanding glacier and ice sheet behavior and their impact on impurity records is crucial for interpreting ice core records. H₂SO₄ is particularly significant, as it provides the strongest evidence for the diffusion of chemical signals and decreases the strength of single crystals and polycrystals of ice. However, its effects on recrystallization, grain growth, and fabric development mechanisms, as well as the effects of grain boundaries on its post-depositional diffusion remain unclear.

This thesis investigates the effects of the microstructural location of H …

Moisture Effects On Visible Near-Infrared And Mid-Infrared Soil Spectra And Strategies To Mitigate The Impact For Predictive Modeling, Francis Hettige Chamika Anuradha Silva

Theses and Dissertations

Instrumental disparities and soil moisture are two of the key limitations in implementing spectroscopic techniques in the field. This study sought to address these challenges through two objectives. The first objective was to assess Visible-near infrared (VisNIR) and mid-infrared (MIR) spectroscopic approaches and explore the feasibility of transferring calibration models between laboratory and portable spectrometers. The second objective addressed the challenge of soil moisture and its impact on spectra. The portable spectrometers demonstrated comparable performance to their laboratory-based counterparts in both regions. Spiking with extra-weight, was the most effective calibration transfer method eliminating disparities between instruments. The samples were rewetted …

Atomistic-Informed And Machine Learning-Assisted Crystal Plasticity Modeling For Materials Interface, Ibrahim Altarabsheh

Doctoral Dissertations

This dissertation presents a comprehensive study that addresses two critical challenges in the field of computational materials science and engineering from nano- to mesoscale. First, to overcome the well-acknowledged length scale limitation associated with atomistic simulations, a novel two-step approach is introduced for a probabilistic prediction of stress-strain curves in terms of material volume. The method combines Molecular Dynamics (MD) simulations and a multioutput Gaussian process (MOGP) with Bayesian analysis to model stress-strain behavior and predict stress and strain values. The model effectively captures the intricate three-stage curve shape exhibited in stress-strain plots, discerning key points such as yielding, hardening, …

On The Prediction Of The Mechanical Properties Of Limestone Calcined Clay Cement: A Random Forest Approach Tailored To Cement Chemistry, Taihao Han, Bryan K. Aylas-Paredes, Jie Huang, Ashutosh Goel, Narayanan Neithalath, Aditya Kumar

Materials Science and Engineering Faculty Research & Creative Works

Limestone calcined clay cement (LC3) is a sustainable alternative to ordinary Portland cement, capable of reducing the binder's carbon footprint by 40% while satisfying all key performance metrics. The inherent compositional heterogeneity in select components of LC3, combined with their convoluted chemical interactions, poses challenges to conventional analytical models when predicting mechanical properties. Although some studies have employed machine learning (ML) to predict the mechanical properties of LC3, many have overlooked the pivotal role of feature selection. Proper feature selection not only refines and simplifies the structure of ML models but also enhances these models' prediction performance and interpretability. This …

Experimental And Machine Learning Studies On Chitosan-Polyacrylamide Copolymers For Selective Separation Of Metal Sulfides In The Froth Flotation Process, Keitumetse Monyake, Taihao Han, Danish Ali, Lana Z. Alagha, Aditya Kumar

Mining Engineering Faculty Research & Creative Works

The froth flotation process is extensively used for the selective separation of valuable base metal sulfides from uneconomic associated minerals. However, in this complex multiphase process, various parameters need to be optimized to ensure separation selectivity and peak performance. In this study, two machine learning (ML) models, artificial neural network (ANN) and random forests (RF), were used to predict the efficiency of in-house synthesized chitosan-polyacrylamide copolymers (C-PAMs) in the depression of iron sulfide minerals (i.e., pyrite) while valuable base metal sulfides (i.e., galena and chalcopyrite) were floated using nine flotation variables as inputs to the models. The prediction performance of …

Mesoscale Modeling And Machine Learning Studies Of Grain Boundary Segregation In Metallic Alloys, Malek Alkayyali

All Dissertations

Nearly all structural and functional materials are polycrystalline alloys; they are composed of differently oriented crystalline grains that are joined at internal interfaces termed grain boundaries (GBs). It is well accepted that GB dynamics play a critical role in many phenomena during materials processing or under operating environments. Of particular interest are GB migration and grain growth processes, as they influence many crystal-size dependent properties, such as mechanical strength and electrical conductivity.

In metallic alloys, GBs offer a plethora of preferential atomic sites for alloying elements to occupy. Indeed, recent experimental studies employing in-situ microscopy revealed strong GB solute segregation …

Machine Learning Strategies For Potential Development In High-Entropy Driven Nickel-Based Superalloys, Marium Mostafiz Mou

Graduate Theses/Dissertations

In this study, I developed Deep Learning interatomic potentials to model a multi-phase and multi-component system of Ni-based Superalloys. The system has up to three major phase constituents, namely Gamma, Gamma Prime, and Transition-metal rich Carbide. I utilized invariant scalar-based and/or equivariant, tensor-based neural network (NN) approach as implemented in DEEPMD, NEQUIP/ALLEGRO codes, respectively, and Moment Tensor Potential (MTP). For the training and validation sets, I employed the ab-initio molecular dynamics (AIMD) trajectory results and ground state DFT calculations, including the energy, force, and virial database from highly diverse compositions, temperatures, and pressures following a “High Entropy Strategy.” The Deep …

Application Of Artificial Intelligence To Lithium-Ion Battery Research And Development, Zhen-Wei Zhu, Jing-Yi Qiu, Li Wang, Gao-Ping Cao, Xiang-Ming He, Jing Wang, Hao Zhang

Journal of Electrochemistry

Lithium-ion batteries (LIBs) have become one of the best solutions to the energy storage issue in modern society. However, the battery materials and device development are both complex, and involve multivariable problems. Traditional trial-and-error approach, which relies on researchers to conduct experiments, has encountered bottlenecks in the improvement of the battery performance. Artificial intelligence (AI) is the most potential technology to deal with this issue due to its powerful high-speed and capabilities of processing massive data. In particular, the capability of machine learning (ML) algorithms in assessing multidimensional data variables and discovering patterns in the sets are expected to assist …

Physical Modeling Of Filament Growth And Resistive Switching In Metal Oxide-Based Rram, Kena Zhang

Material Science and Engineering Dissertations - Archive

Metal oxide-based resistive random-access memories (RRAM) exhibit several excellent performances, such as nanosecond switching speed, large write-erase endurance, and long retention time, and can potentially replace the traditional circuit elements for use as the fundamental units in next-generation hardware deep-learning or neuromorphic systems. The functionality of a metal oxide-based RRAM is attributed to an oxygen vacancy (V_O^(..))-rich conductive filament (CF), which initially forms, and later dissolves or regrows inside the oxide layer during the resistive switching process. However, the complicated interplays among the coexisting chemical, electrical, mechanical, and thermal effects during the formation, growth, and rupture of the CFs make …

A Fiber-Optic Sensor-Embedded And Machine Learning Assisted Smart Helmet For Multi-Variable Blunt Force Impact Sensing In Real Time, Yiyang Zhuang, Taihao Han, Qingbo Yang, Ryan O'Malley, Aditya Kumar, Rex E. Gerald, Jie Huang

Materials Science and Engineering Faculty Research & Creative Works

Early on-site diagnosis of mild traumatic brain injury (mTBI) will provide the best guidance for clinical practice. However, existing methods and sensors cannot provide sufficiently detailed physical information related to the blunt force impact. In the present work, a smart helmet with a single embedded fiber Bragg grating (FBG) sensor is developed, which can monitor complex blunt force impact events in real time under both wired and wireless modes. The transient oscillatory signal "fingerprint" can specifically reflect the impact-caused physical deformation of the local helmet structure. By combination with machine learning algorithms, the unknown transient impact can be recognized quickly …

Study On Predictive Maintenance Of V-Belt In Milling Machines Using Machine Learning, Reza Aulia Rahman, Mohammad Faishol Erikyatna, Achmad Fauzan Hery Soegiharto

Journal of Mechanical Engineering Science and Technology (JMEST)

Towards industry 4.0, monitoring the degradation of machine tools’ components becomes a key feature so that smooth productivity is achieved. To preserve the functionality and performance of the machine tools, proper maintenance activities must be planned and carried out. V-belt is important component in machine tools that transmits power from the electric motor spindle in order to machine to work and cut desired material properly. The purpose of this research is to develop a predictive maintenance system for v-belt milling machine Krisbow 31N2F using machine learning. The machine learning algorithm models using multiple and simple linear regression algorithm was developed …

Additive Manufacturing Of Complexly Shaped Sic With High Density Via Extrusion-Based Technique – Effects Of Slurry Thixotropic Behavior And 3d Printing Parameters, Ruoyu Chen, Adam Bratten, Joshua Rittenhouse, Tian Huang, Wenbao Jia, Ming-Chuan Leu, Haiming Wen

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Additive manufacturing of dense SiC parts was achieved via an extrusion-based process followed by electrical-field assisted pressure-less sintering. The aim of this research was to study the effect of the rheological behavior of SiC slurry on the printing process and quality, as well as the influence of 3D printing parameters on the dimensions of the extruded filament, which are directly related to the printing precision and quality. Different solid contents and dispersant- Darvan 821A concentrations were studied to optimize the viscosity, thixotropy and sedimentation rate of the slurry. The optimal slurry was composed of 77.5 wt% SiC, Y2O3 and Al2O3 …

Machine Learning Mosa Monitoring System, Aditya G. Manjunath, Sabahudin Vrtagic, Fatih Dogan, Milan Dordevic, Mileta Zarkovic, Jasmin Kevric, Goran Dobric

Materials Science and Engineering Faculty Research & Creative Works

This research paper deals with the problem of Metal-Oxide Surge Arrester (MOSA) condition monitoring and a new methodology in surge arrester monitoring and diagnostics is presented. A machine learning algorithm (back propagation regression) is used to estimate the non-linearity coefficient of the surge arrester, based on operating voltage and leakage current of the arrester. Using a simulated system, this research investigates the possibility of application and efficiency of machine learning. It is shown that the applied learning algorithm results are competitive with the model results parameters calculated as R2 = 0.999 and mean absolute real error computed as 0.005 which …

Predicting Compressive Strength Of Alkali-Activated Systems Based On The Network Topology And Phase Assemblages Using Tree-Structure Computing Algorithms, Rohan Bhat, Taihao Han, Sai Akshay Ponduru, Arianit Reka, Jie Huang, Gaurav Sant, Aditya Kumar

Electrical and Computer Engineering Faculty Research & Creative Works

Alkali-activated system is an environment-friendly, sustainable construction material utilized to replace ordinary Portland cement (OPC) that contributes to 9% of the global carbon footprint. Moreover, the alkali-activated system has exhibited superior strength at early ages and better corrosion resistance compared to OPC. The current state of analytical and machine learning models cannot produce highly reliable predictions of the compressive strength of alkali-activated systems made from different types of aluminosilicate-rich precursors owing to substantive variation in the chemical compositions and reactivity of these precursors. In this study, a random forest model with two constraints (i.e., topological network and thermodynamic constraints) is …

Data-Driven And Multiscale Modeling Of Dna-Templated Dye Aggregates, Austin Biaggne, Lawrence Spear, German Barcenas, Maia Ketteridge, William B. Knowlton, Bernard Yurke, Lan Li

Materials Science and Engineering Faculty Publications and Presentations

Dye aggregates are of interest for excitonic applications, including biomedical imaging, organic photovoltaics, and quantum information systems. Dyes with large transition dipole moments (μ) are necessary to optimize coupling within dye aggregates. Extinction coefficients (ε) can be used to determine the μ of dyes, and so dyes with a large ε (>150,000 M⁻¹) should be engineered or identified. However, dye properties leading to a large ε are not fully understood, and low-throughput methods of dye screening, such as experimental measurements or density functional theory (DFT) calculations, can be time-consuming. In order to screen large datasets of molecules …

Simulation Of Li Dendrite Inhibition In Lithium Battery By Phase-Field Method, Yao Ren

Material Science and Engineering Dissertations - Archive

Lithium (Li) dendrite growth poses serious challenges for the development of Li metal batteries which also stops the footsteps of human utilizing the environment-friendly new power source. Replacing liquid electrolyte with solid electrolyte can not only inhibit the dendrite growth by mechanical suppression, but also introduce more possibilities to the electrochemistry of battery. However, the underlying mechanism is still not fully understood, and most theoretical works focus on pure liquid electrolyte, ignoring the mechanical strain effects. Here we developed a phase-field model which simulates the Li dendrite growth to study the competition between diffusion and deposition rates, the pure elastic …

Machine Learning Assisted Discovery Of Shape Memory Polymers And Their Thermomechanical Modeling, Cheng Yan

LSU Doctoral Dissertations

As a new class of smart materials, shape memory polymer (SMP) is gaining great attention in both academia and industry. One challenge is that the chemical space is huge, while the human intelligence is limited, so that discovery of new SMPs becomes more and more difficult. In this dissertation, by adopting a series of machine learning (ML) methods, two frameworks are established for discovering new thermoset shape memory polymers (TSMPs). Specifically, one of them is performed by a combination of four methods, i.e., the most recently proposed linear notation BigSMILES, supplementing existing dataset by reasonable approximation, a mixed dimension (1D …

Prediction Of Concrete Strengths Enabled By Missing Data Imputation And Interpretable Machine Learning, Gideon A. Lyngdoh, Mohd Zaki, N.M. Anoop Krishnan, Sumanta Das

Faculty Publications - Biomedical, Mechanical, and Civil Engineering

Machine learning (ML)-based prediction of non-linear composition-strength relationship in concretes requires a large, complete, and consistent dataset. However, the availability of such datasets is limited as the datasets often suffer from incompleteness because of missing data corresponding to different input features, which makes the development of robust ML-based predictive models challenging. Besides, as the degree of complexity in these ML models increases, the interpretation of the results becomes challenging. These interpretations of results are critical towards the development of efficient materials design strategies for enhanced materials performance. To address these challenges, this paper implements different data imputation approaches for enhanced …

Recent Advances In Electrochemical Kinetics Simulations And Their Applications In Pt-Based Fuel Cells, Ji-Li Li, Ye-Fei Li, Zhi-Pan Liu

Journal of Electrochemistry

Theoretical simulations of electrocatalysis are vital for understanding the mechanism of the electrochemical process at the atomic level. It can help to reveal the in-situ structures of electrode surfaces and establish the microscopic mechanism of electrocatalysis, thereby solving the problems such as electrode oxidation and corrosion. However, there are still many problems in the theoretical electrochemical simulations, including the solvation effects, the electric double layer, and the structural transformation of electrodes. Here we review recent advances of theoretical methods in electrochemical modeling, in particular, the double reference approach, the periodic continuum solvation model based on the modified Poisson-Boltzmann …

Moisture Content Prediction In Polymer Composites Using Machine Learning Techniques, Partha Pratim Das, Monjur Morshed Rabby, Vamsee Vadlamudi, Rassel Raihan

Institute of Predictive Performance Methodologies (IPPM-UTARI)-Archive

The principal objective of this study is to employ non-destructive broadband dielectric spectroscopy/impedance spectroscopy and machine learning techniques to estimate the moisture content in FRP composites under hygrothermal aging. Here, classification and regression machine learning models that can accurately predict the current moisture saturation state are developed using the frequency domain dielectric response of the composite, in conjunction with the time domain hygrothermal aging effect. First, to categorize the composites based on the present state of the absorbed moisture supervised classification learning models (i.e., quadratic discriminant analysis (QDA), support vector machine (SVM), and artificial neural network-based multilayer perceptron (MLP) classifier) …