Jia Liu

Associate Professor University of Florida

Gainesville FL

Jia Liu's research focuses on physics-informed big data analytics, machine learning and AI with applications in smart manufacturing.

Contact

University of Florida
View more experts managed by University of Florida

View all Experts

Biography

Jia “Peter” Liu is an associate professor and the Trey Lauderdale Industrial and Systems Engineering fellow in the Herbert Wertheim College of Engineering. His research interests encompass statistical learning, machine learning and LLM with applications in advanced manufacturing. He works to integrate physics knowledge and interpretable data-driven modeling for a variety of complex manufacturing processes involving heterogeneous sensors, with a primary focus on understanding the fatigue performance of laser powder bed fusion, which has critical applications in aerospace, defense and automotive sectors. He is also interested in developing novel federated learning to enable privacy-preserving information sharing among distributed manufacturers for secure manufacturing.

Areas of Expertise

AI in Manufacturing

Smart Manufacturing

Additive Manufacturing

Machine Learning

Social

Articles

Benchmarking Machine Learning Methods Against Finite Element and Empirical Models for Predicting Solder Joint Characteristic Life

IEEE Xplore

Alavi, et al.

2025-09-25

Accurate prediction of solder joint characteristic life is crucial for ensuring the reliability of electronic assemblies, especially under severe environmental conditions. This study benchmarks the predictive capabilities of machine learning (ML) methods against traditional empirical power-law models and finite element analysis (FEA) performed using ANSYS, employing a comprehensive dataset comprising 185 experimental test results.

Determining critical surface features affecting fatigue behavior of additively manufactured Ti-6Al-4V

Taylor & Francis

Ahmad, et al.

2025-08-01

This study utilized a fracture mechanics based approach to identify the key surface features influencing the fatigue performance of laser powder bed fused (L-PBF) Ti-6Al-4V. X-ray computed tomography was employed to detect surface and sub-surface flaws, and a new method to capture and quantify the geometry of surface micro-notches—such as width, depth, opening angle, and radius of curvature—was proposed.

Nondestructive fatigue life prediction for additively manufactured metal parts through a multimodal transfer learning framework

ScienceDirect

Li, et al.

2024-10-09

Understanding the fatigue behavior and accurately predicting the fatigue life of laser powder bed fusion (L-PBF) parts remain a pressing challenge due to complex failure mechanisms, time-consuming tests, and limited fatigue data. This study proposes a physics-informed data-driven framework, a multimodal transfer learning (MMTL) framework, to understand process-defect-fatigue relationships in L-PBF by integrating various modalities of fatigue performance, including process parameters, XCT-inspected defects, and fatigue test conditions.