Abstract:
Metal forming processes involve complex material behavior, nonlinear deformation, and interactions among multiple process parameters, making accurate modeling, prediction, and process optimization challenging. Physics-based modeling and numerical simulations provide essential insights into deformation mechanisms, but their practical applications are often limited by the complexity of material characterization, computational cost, and the need for extensive experimental validation. Machine learning (ML) offers complementary capabilities by extracting meaningful relationships from experimental and simulation data, enabling efficient predictions and supporting informed decision-making.
This seminar explores how mechanics-based approaches and machine learning can be integrated to address challenges across different aspects of metal forming, from material characterization to process design and optimization. By leveraging heterogeneous deformation fields, numerical simulations, and experimental observations, data-driven models can be developed to identify complex material parameters, predict and compensate for geometric inaccuracies, and guide the design of forming processes under competing constraints such as wrinkling and fracture. These applications demonstrate how physical understanding can guide the development of ML models, while ML can enhance the efficiency and practical applicability of conventional mechanics-based approaches.
The seminar will highlight the opportunities and challenges of combining mechanics and machine learning, with perspectives on extending these approaches toward more intelligent, adaptive, and autonomous metal forming systems.
Bio:
Jinjin Ha is an Assistant Professor in the Department of Mechanical Engineering at the University of New Hampshire, USA. She received her Ph.D. from Pohang University of Science and Technology (POSTECH), South Korea, in 2016. Before joining UNH in 2020, she conducted postdoctoral research at the University of New Hampshire and The Ohio State University. In 2024, she was an Alexander von Humboldt Research Fellow at TU Dortmund University, Germany.
Her research lies at the intersection of material mechanics, metal forming technologies, and intelligent manufacturing. By integrating experimental characterization, advanced computational modeling, and machine learning, she seeks to understand and control material deformation, enhance formability, and develop innovative and sustainable manufacturing processes. Her recent work emphasizes advanced constitutive modeling, flexible and robotic forming technologies, and data-driven approaches to process prediction and optimization.
Dr. Ha serves as an Associate Editor of the International Journal of Material Forming and on the editorial boards of the International Journal of Plasticity and the International Journal of Precision Engineering and Manufacturing. She actively contributes to international research collaborations and scientific communities in metal forming, material mechanics, and manufacturing engineering.
Persons with disabilities have the right to request and receive reasonable accommodation. Please call the Department of Mechanical Engineering at 517-355-5131 at least one day prior to the seminar; requests received after this date will be met when possible.