Conference Tools for 2025 TMS Annual Meeting & Exhibition

Help

About this Abstract
Meeting	2025 TMS Annual Meeting & Exhibition
Symposium	Verification, Calibration, and Validation Approaches in Modeling the Mechanical Performance of Metallic Materials
Presentation Title	Physics-Informed Neural Networks with LuGre Model for Friction Force Analysis in Tribological Systems
Author(s)	Huajing Song, Andrew Boyne
On-Site Speaker (Planned)	Huajing Song
Abstract Scope	This study introduces an innovative approach to friction force prediction in tribological systems using Physics-Informed Neural Networks (PINNs) integrated with the LuGre friction model. By combining these methods, we simultaneously optimize LuGre model parameters and predict friction forces, addressing challenges in fitting the LuGre model to experimental data. The PINN is trained using a composite loss function balancing data fidelity and physical constraints. We present the theoretical framework of the LuGre-PINN model and demonstrate its application through a case study using laboratory tribological test data on engine-relevant materials. This research advances friction modeling in aerospace applications, potentially enhancing the design and reliability of tribological systems, where accurate friction force modeling is crucial for component performance
Proceedings Inclusion?	Planned:
Keywords	Machine Learning, Mechanical Properties, Modeling and Simulation

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Constitutive Framework for Modeling Dynamic Recrystallization in Pure Copper

A Critical Analysis on the Predictive Capabilities of Different Criteria for Ductile Failure Initiation in Metallic Materials

Advanced Calibration of the GTN Damage Model for Aluminum Alloy AA6111 via Bayesian Inference and Digital Image Correlation Techniques

An Open-Source Framework for Data Augmentation and Emulation: Application to Process Optimization in AM

Bayesian Calibration and Validation of a Physics-Based Crystal Plasticity and Damage Model for Shock Compression and Spall

Computational Materials for Qualification and Certification Steering Group and Community Vision Roadmap

Digital Twins to Accelerate AM Qualification: Defining Challenge Problems to Validate Model Performance

Establishing Temperature-Based Relationships for Mechanical Properties and Crystal Plasticity Parameters of Additively Manufactured Haynes-214 Alloy

Experiment and Crystal Plasticity Model-Based Investigation of Surface Roughness Influence in the Fatigue Life of Additive Manufactured Nickel-Supperalloys

Experiments and Methods to Calibrate and Validate Defect-Sensitive Fatigue Models

Explicit Finite Element Model of Composite Metal Foam’s Mechanical Response During Quasi-Static & Dynamic Compression

Improved Representation of Grain-Level Microstructures to Support Advanced In-Situ Mechanical Testing

Investigating Reduced Order and Surrogate Models of Crystal Plasticity Finite Element Models for Calibration Against Strain Field Data

Micromechanical Model Verification of Additively Manufactured Inconel 625 Informed by In Situ High-Energy X-Ray Diffraction

Microstructure Dependence of Spall Failure in Mg-Al Alloys at Extreme Strain Rates

Non-Uniqueness in Crystal Plasticity Fitting Parameters: Effects on Intragranular Mechanical Behavior

Physics-Informed Neural Networks with LuGre Model for Friction Force Analysis in Tribological Systems

Predicting Mechanical Properties of Ti-6Al-4V Alloy Using a Physics-Informed Neural Network (PINN) for Crystal Plasticity Modeling

Predicting the Variability in Performance of Zircaloy in Nuclear Reactors

Probabilistic Global-Local Calibration of Crystal Plasticity Parameters for Additively Manufactured Metals Using Synthetic Data

Quantifying Error in Machine Learning Predictions of Macroscopic Yield Surfaces of Polycrystalline Materials

Quantifying Uncertainties Using Crystal Plasticity Modeling of Microstructural Clones

Strain-Gradient Crystal Plasticity Finite Element Modeling of Phenomena Pertaining to the Sequential Strain Path Changes in AA6016-T4

Substructure-Sensitive Crystal Plasticity: A Consistent Approach Across Materials, Loading Conditions and Temperatures

Synchrotron-Based Experiments and Microstructure-Sensitive Modeling

Uncertainty-Aware Validation in Modeling of Metal Plasticity: Beyond Mean Squared Error

Uncertainty Quantification of Crystal Plasticity Parameters Using ExaConstit

Uncertainty Quantified Parametrically Upscaled Constitutive Models for Fatigue Nucleation in Polycrystalline Metallic Materials

Questions about ProgramMaster? Contact programming@programmaster.org