Conference Logo ProgramMaster Logo
Conference Tools for TMS Specialty Congress 2024
Login
Register as a New User
Help
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools

About this Abstract
Meeting TMS Specialty Congress 2024
Symposium 2nd World Congress on Artificial Intelligence in Materials & Manufacturing (AIM 2024)
Presentation Title An Insight Into Predictive Modelling of NiTi Shape Memory Alloys
Author(s) Sina Hossein Zadeh, Amir Behbahanian, John Broucek, Mingzhou Fan, Guillermo Vazquez, Mohammad Noroozi, William Trehern, Xiaoning Qian, Ibrahim Karaman, Raymundo Arroyave
On-Site Speaker (Planned) Sina Hossein Zadeh
Abstract Scope Nickel-titanium (NiTi) shape memory alloys have become increasingly pivotal across various industries, primarily recognized for their exceptional mechanical properties and corrosion resistance amalgamation. These unique properties of NiTi alloys have extended their usage, opening a diverse range of applications that have shifted the paradigm in material science and engineering. This comprehensive study demonstrates how the generation, restriction, and employment of compositional and processing features aid in the advanced development of predictive models. These multifaceted models, devised with meticulous precision, have surpassed expectations and proven to be highly effective, with an average accuracy rate of 95%. This significant rate underpins the successfully predicted transformation properties; it opens the avenue for a revolutionary procedure in controlling alloy transformation properties based on the model predictions. This innovative methodology, merging materials science thinking and data-driven studies, helps shape our future toward an even more material-efficient society.
Proceedings Inclusion? Definite: Other

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Data-driven Laplacian-penalized Non-rigid iterative Closest Point Reverse Deformation Model for Net-shape Investment Castings
A FAIR-framework for Integrating Advanced Manufacturing Multimodal Data Sets
A FAIRification Framework for Synchrotron High Energy X-ray Diffraction Datasets
A Manufacturing Technology Roadmap for AI-enhanced Multimodal Sensing of Materials and Processes for Complete Product Lifecycle Performance
A Materials Data Segmentation Benchmark (MDSB)
A Materials Data Segmentation Garden for Benchmarking Segmentation Models
A Surrogate-assisted Uncertainty Quantification and Sensitivity Analysis of a Ni-base Superalloy Hot Isostatic Pressing Finite Element Mode
A Texture Synthesis Approach for Generating Synthetic Microstructural Images for Training ML Models in a Low-data Regime
A Unified Microstructure Segmentation Approach Through Incorporating Domain Knowledge Into Machine Learning
Accelerated Development of Materials Using High-throughput Strategies and AI/ML
AI-driven Topology Optimization of Photonic Structures With Manufacturing Constraints
AI-simulation Workflow to Accelerate Computational Screening of Metal-organic Framework Structures
AI for Science: Data-centric AI by Utilizing D/HPC and FAIRified Scientific Analysis Workflows
An Insight Into Predictive Modelling of NiTi Shape Memory Alloys
Analyzing the Impact of Design Factors on Solar Module Thermomechanical Durability Using Interpretable Machine Learning
Application of Data-driven Digital Twins in Advanced Manufacturing
Assessing the Performance of Machine Learning Universal Interatomic Potentials on Intermetallic Systems
Assessment of an Intelligent System for Additive Manufacturing Product Evaluation
Autonomous Learning of Atomistic Structural Transitions via Physics-inspired Graph Neural Networks
Bayesian SegNet for Semantic Segmentation With Improved Interpretation of Microstructural Evolution During Irradiation of Materials
Capturing AM Process Defects on Fatigue Fracture Surfaces Through Machine Learning Segmentation
Classification of 2D Diffractograms Into “Spotty” and “Continuous” Patterns Using Deep Neural Networks Trained By ab-Initio Simulations
Closing the Loop in Direct-chill Casting of Aluminium Alloys, a Deep Learning Approach
CRowdsourced Materials Data Engine for Unpublished X-ray Diffraction
Data Driven Modeling for Yield Improvement in Gas Atomization Process
Dataset Generation and Verification for Additive Manufacturing Using Explainable AI
Deep Material Network Trained With Local Field Information: Predictions of Homogenized and Local Field Distribution
Development for an Intelligent System for Controlling the Peripheral Temperature of the Blast Furnace
Development of a Machine Learning Based Tool for Defect Detection in Cold Spray Aluminum
Digital Twin for In-situ Process Monitoring and Control of Aerosol Jet Printing
Electronic Structure Prediction of Multi-million Atom Systems Through Uncertainty Quantification Enabled Transfer Learning
Empowering Non-Destructive Powder Evaluation with Accessible AI Tools
Enhancing Machine Learning Classification of Microstructures: A Workflow Study on Joining Image Data and Metadata in CNN
Equivariant Neural Networks for Controlling Dynamic Spatial Light Modulators
Exploring Graph Neural Network Surrogates for Microstructure Analysis
Extreme Value Statistics Analysis of Process Defects in Additive Manufacturing Materials
FAIRification of Data-centric AI: Programmatic JSON-LD Creation and OWL Generation
Federated Learning Approaches: Data-decentralized Analysis on Synchrotron X-ray Diffraction Data
Flexible Robotic Assembly through Human-Interpretable State Machine Synthesis
Fluoroelastomers Genome: Analysis of Fluoroelastomers Growth Behavior Based on Spatio-temporal Scene Graphs
Fracture Toughness and Fatigue Life Prediction of Additively Manufactured Al 2024 Alloy Using Machine Learning Models
Generative Super-resolution for Inexpensive In-situ Layerwise Optical Imaging
Graph-based Machine Learning to Assess Particle Growth Kinetics From Image Sequences
High-throughput In-silico Multi-objective Materials Screening for Accelerated Polymer Design and Discovery
High-throughput Microstructural-based Remnant Life Assessment of High-temperature Steels
High Performance Computing and Artificial Intelligence Enabled Materials Characterization and Experimental Automation
HotSpotNet: A Deep Learning Approach to Predicting Stress Hot Spots in Materials Based on Microstructural Features
Hybrid Denoising Diffusion Models for Statistically Conditioned Generation
Identification of Binder Jet Spreading Anomalies Through Semantic Segmentation
Image Analysis of Fractography: Defect Feature Comparisons
Impact of Different Training Datasets on Machine Learning Based Grain Growth Model and Grain Growth Kinetics
Improved Deep Learning Image Classification of Rare Material Defects in Non-destructive-testing Processes by Utilizing Data Imbalance Methods and Synthetic Data
Improved Methods to Predict the Mixing Enthalpy of Liquid Alloys for CALPHAD Databases With Artificial Neural Networks
In-situ Melt Pool Morphology Estimation From Thermal Imaging via Vision Transformers
Integrating Machine Learning Into Constitutive Material Modeling for the Creep Age Forming Process
Intelligent Data Sampling for Autonomous Parameterization: A Gaussian-Process-Ensemble Approach
Intrinsic Dimensionality Estimates for Microstructural Data
Inverse Design of High-temperature Al-alloys Using Hybrid CALPHAD-based ICME Techniques
Learning a Reliable Compression of In-situ, High-speed Camera Data for Additive Manufacturing
Learning Full-rank Elastic Tensors With Equivariant Neural Networks
Leveraging Segmentation Models for Platinum Particle Identification on BWR Nuclear Reactor Components
Machine Learning-enhanced Prediction of Surface Smoothness for Inertial Confinement Fusion Target Polishing Using Limited Data
Machine Learning Approach to Phase Recognition and Prediction of Mechanical Properties
Machine Learning Assisted Discovery of Deposition Conditions for Binary Metallic Alloys
Machine Learning Customized Novel Metals for Energy-efficient 4D Printing
Machine Learning to Identify Composition and Heat Treatment Schedule of Low-alloyed TRIP-aided Steel Sheets With the Strength-ductility Trade-off
Managing Scientific Data in Characterization Investigations With FAIR
MatGPT™ - Accelerated Alloy Development by Combining LLMs, Machine Learning, Simulation & Validation
MICRO2D: Statistically Conditioned Deep Generative Models for Curating Big Microstructure Datasets
Microstructural Diffusional Variational Autencoder for Generation of Microstructure Ensembles
MIPAR Spotlight: Integrating Zero-Shot, Deep Learning, and Conventional Processing for Advanced Micrograph Analysis
Multiaxial Fatigue Life Prediction of Additively Manufactured Ti6Al4V Alloy Using Machine Learning Techniques
Neural Networks as Surrogate Models for Real-time Optimization of Additive Manufacturing
Not as Simple as We thought: A Rigorous Examination of Data Aggregation in Materials Informatics
Optical to Scanning Electron Microscopy Style Transfer of Steel Micrograph Using Machine Learning
Optimizing the Microstructure of Additively Manufactured Al Alloy Using Deep Learning
Overcoming Integration Barriers for Multivariate Big Geospatiotemporal Data
Patch-wise Canonical Correlation Analysis in SEM: Advancing 3D Serial Sectioning Image Registration
Persistent Homology for Microstructure Manifold Construction
Physics-constrained, Inverse Design of High-temperature, High-strength, Printable Al Alloys Using Machine Learning Methods
Physics Inspired Modelling of the Milling Process Using a Combined Deep Learning and Symbolic Regression Approach for an Efficient Production of Battery Materials
Predicting Interfacial Solute Segregation in Nanocrystalline Alloys Using Advanced Atomic Descriptors and Machine Learning Schemes
Predicting Microstructure From Process Conditions Using Multi-modal Machine Learning
PV-VISION: A Deep Learning Based Package for Automated Solar Module Inspection
Pyrometry Mapping of Segmented Porosity in Computed Tomography
Realtime In-process Monitoring of Porosity via Convolutional Neural Networks During Additive Manufacturing and Laser Welding
Reinforcement Learning Approaches to Developing Policies for Incremental Robotic Forging
Reproducible Quantification of the Microstructure of Complex Quenched and Quenched and Tempered Steels Using Modern Methods of Machine Learning
Rethinking Materials Simulations: Blending Direct Numerical Simulations With Neural Operators
Semantic Segmentation of Scanning Electron Microscopy Images for Contact Degradation Analysis in Field-aged Photovoltaic Modules
Simulation of Spray Processes to Train Machine Learning Algorithm for Autonomous Path Generation
Space Launch System Weld Process Optimization Using Informatics and Machine Learning
Spatiotemporal Scene Graph Representations for Terabyte Scale X-ray Computed Tomography Datasets of AlMg
Thermodynamically Consistent Neural Networks for Modeling of Inelastic Material Responses
Training Requirements of a Deep Learning Network With Physics-based Regularization Functions Enforcing Stress Equilibrium
Uncertainty Quantification in Machine-learning Models for Predicting β-phase Volume Fraction From Synchrotron X-ray Diffraction Patterns
Unraveling the Mechanisms of Stability in CoMoFeNiCu High Entropy Alloys via Physically Interpretable Graph Neural Networks
Unveiling Metal Additive Manufacturing Microstructure Through Data-driven Unsupervised Clustering of Crystallographic Texture
Using Large Language Models to Aid Materials Design Workflows
Using Unsupervised Learning to Cluster Fatigue Life Based on Small Crack Characteristics
Utilizing Machine Learning to Generate Representative Euler Angles for Large EBSD Datasets
Virtual Inspection of Advanced Manufacturing via Process-scale Digital Twins
Questions about ProgramMaster? Contact programming@programmaster.org | TMS Privacy Policy | Accessibility Statement