Applicable and Generalizable Machine Learning for Intelligent Welding, from Quality Prediction to Robotic Automation

Date: March 28, 2025; Time: 2:30 PM Location: PWEB 175

Abstract: In the last decade, the manufacturing sector has adopted Industry 4.0 innovations, including edge and cloud computing, Artificial Intelligence (AI), and Machine Learning (ML), enhancing production visibility, quality, automation, productivity, and safety. This presentation highlights novel ML applications in welding processes, through case studies in Resistance Spot Welding (RSW), laser welding, and arc welding.

The case study of RSW focuses on process sensing and modeling for quality prediction and defect detection. This study not only employs data-driven modeling but also utilizes ML to uncover physical insights into the RSW process, enhancing feature extraction and developing a more generalizable model for predicting quality and defects. It also introduces a new ML approach to create virtual signals for force and displacement using dynamic resistance measurements, addressing the lack of novel process sensing in facilities due to high costs. The case study of laser welding tackles feature engineering, i.e., from sensing data characterization to feature selection, to improve the model generalizability and decision-making efficiency in a plant production scenario. Transfer learning is also investigated to enable the ML models to adapt to dynamically changing welding conditions. The third case study targets the robotic automation of arc welding. To enable robotic operational adaptivity, a hybrid ML-based process characterization, and online adaptive control framework are developed for robotic arc welding to automatically and efficiently achieve the desired weld pool condition, given any initial conditions.  These case studies showcase significant potential for advancing welding processes to new levels of efficiency and effectiveness.

Biographical Sketch: Dr. Peng (Edward) Wang is currently an Associate Professor in the Department of Mechanical and Aerospace Engineering at Case Western Reserve University (CWRU). Dr. Wang has extensive experience in developing novel ML methodologies for machine condition monitoring and diagnosis, process modeling and quality prediction, and collaborative robots. Dr. Wang is the recipient of the CAREER award from the US National Science Foundation in 2023, Young Investigator Award from the International Symposium of Flexible Automation in 2024, Outstanding Young Manufacturing Engineer Award from the Society of Manufacturing Engineers (SME) in 2022, the Best Paper Award from the 2023 Manufacturing Science and Research Conference (MSEC), Outstanding Technical Paper Award from the SME North American Manufacturing Research Conference (NAMRC) in 2017, 2020, and 2021, and other best paper awards. Dr. Wang is an Associate Editor of the IEEE Sensors Journal and Journal of Intelligent Manufacturing.

Vetting Scaling Laws in Turbulent Reacting Flows: The Case of Damköhler’s Second Postulation

Date: March 14, 2025; Time: 2:30 PM Location: PWEB 175

Abstract: Damköhler’s second postulation has been the foundation of the development of scaling laws for turbulent premixed flames that led to the establishment of regime diagrams and has been used as the principal argument for explaining experimental and computed observables. Damköhler’s arguments are challenged based on direct numerical simulations of vortex-flame interactions and fully turbulent premixed flames under high Karlovitz number conditions. Specifically, the simulations could not prove that sub-flame thickness Kolmogorov eddies can enter the flame due to the high dissipation rate. Local analyses of both configurations showed that frequently used correlations based on the laminar flame structure could not be used to explain, among others, the reported thickening of turbulent flames under extreme turbulence levels. Additionally, laminar flame scales derived using detailed simulations resulted in a wide range of Karlovitz number values of the boundary separating the so-called thin reaction zone and broken reaction zone regimes and are not in agreement with established values in the literature, which have been derived from relatively simple theoretical arguments. Finally, the present results could not support even the existence of the thin reaction zone and broken reaction zone regimes, which have been hypothesized by Borghi and Peters and adopted in numerous computational and experimental studies.

Biographical Sketch: Fokion N. Egolfopoulos is a William E. Leonhard Professor of Engineering in the Department of Aerospace and Mechanical Engineering at the University of Southern California. He obtained his Diploma Degree in 1981 from the National Technical University of Athens, and his PhD in 1990 from the University of California at Davis after spending the last two years of his doctoral research at Princeton University. He is a recipient of the Silver Medal of the Combustion Institute at the Twenty-Second International Combustion Symposium, a Fellow of the Combustion Institute, a Fellow of the American Society of Mechanical Engineers (ASME), and an Associate Fellow of the American Institute of Aeronautics and Astronautics (AIAA). He has authored and co-authored one hundred and fifty-six (156) archival journal publications, eleven (11) editorial comments, three (3) book chapters, one hundred and sixty-two (162) conference proceedings and reports, and has given one hundred and seventy-two (172) invited and contributed scholarly addresses. Since 2009 he has been the Editor in Chief of Combustion and Flame, after serving as an Associate Editor of the journal from 2003 until 2008.

Exploring Modularity for Advancing Space Exploration and Supporting Crew Health

Date: March 7, 2025; Time: 2:30 PM Location: PWEB 175

Abstract: In the quest for exploring new frontiers in space, the design of modular systems has emerged as a potential solution that not only could enhance exploration capabilities but also support crew health and performance. A system is considered modular when its components are designed to function independently, each capable of performing its specific role without reliance on the entire system. At the same time, these components can seamlessly integrate to work collectively, forming a unified whole. This dual capability allows for flexibility, scalability, and adaptability, enabling the system to be customized, expanded, or reconfigured as needed to meet evolving requirements and adapt to different situations. Within a modular system, modules are designed to connect, interact, and exchange resources—either physically or virtually—through standardized interfaces or mechanisms. From modular robotic systems for exploration in unknown environments to modular systems for spacecraft habitats that can support crew health and activities.

Biographical Sketch: He is an Associate Professor in the Department of Engineering at Texas A&M University-Corpus Christi (TAMU-CC), USA. His research interests include the development and integration of Modular Robots and Modular mechatronic systems across different domains such as in Unmanned Autonomous Systems, Space, Agriculture, Industry, HealthCare, and Education. Dr. Baca has worked in the Autonomous Systems and Modular Robotics fields for over a decade and his work has led to multiple publications in leading conferences and journals, as well as organized and co-chaired international conferences and workshops. He has been involved in projects funded by federal agencies such as DoD, NSF, NASA, ED, and USDA-NIFA. He is co-founder of CORAL (Collaborative Robots and Agents Lab), and Faculty member of the NSF CREST-GEIMS (Center for Geospatial and Environmental Informatics, Modeling and Simulation) and the IUCRC (Industry-University Cooperative Research Center) Center for Growing Ocean Energy Technologies and the Blue Economy (GO Blue) at TAMU-CC.

Statistical Mechanics of Light- and Field- Responsive Soft Materials

Date: February 28, 2025; Time: 2:30 PM Location: PWEB 175

Abstract: Light- and electric field- responsive polymeric materials are important for emerging technologies in fields ranging from soft robotics to biomedical devices. However, engineering models of these materials are largely phenomenological, which inhibits systematic materials design. I will present our recent work on formulating statistical mechanical models that account for the coupling between light and electric fields to entropic polymer elasticity. First, we study polymers with photo-responsive mesogens that show spontaneous deformation when illuminated, due to a trans-cis bending of the mesogens. A statistical mechanical model that exploits a separation of energy scales between entropic elasticity and photoswitching is developed and shows the emergence of a broken symmetry in the coupling between light and deformation, which agrees with our experimental measurements of photoswitching and shape evolution. Second, we study the role of nonlocal electrical interactions in polymer chains. We develop a consistent non-perturbative model of electrical fields interacting with polymer chains, and show that the nonlocal nature of the dipolar self-interactions drives the collapse of a polymer chain above a critical field, providing a pathway to understand instabilities and failure mechanisms in polymer chains subjected to large electric fields.

Biographical Sketch: Kaushik Dayal is a professor in the Department of Civil and Environmental Engineering at Carnegie Mellon University. Dayal’s research interests are in the area of theoretical and computational multiscale methods applied to problems in materials science, with particular focus on bridging from atomic to continuum scales in the context of functional behavior, non-equilibrium response, and electromagnetic effects.

Dayal received his B.Tech. degree from the Indian Institute of Technology Madras (Chennai) in 2000. He earned his M.S. and Ph.D. in Mechanical Engineering at the California Institute of Technology in 2007.

Innovative Synergy: The Power of Design-Engineering Teams

Date: February 21, 2025; Time: 2:30 PM Location: PWEB 175

Abstract: In today’s fast-paced product development landscape, collaboration between engineers and industrial designers is more crucial than ever. However, misaligned goals, communication gaps, and process inefficiencies often hinder progress. In this talk, Robert explores practical strategies to bridge the divide between design and engineering, enabling teams to work faster and smarter without sacrificing creativity or functionality. Drawing from real-world case studies, he’ll discuss tools and methodologies—such as iterative prototyping, cross-functional workflows, and shared digital platforms—that foster synergy and streamline the product development process. Attendees will leave with actionable insights to enhance collaboration, reduce time-to-market, and create innovative, user-focused products. Whether you’re a designer, an engineer, or a product manager, this session offers a fresh perspective on building better products together.

Biographical Sketch: Robert is a distinguished Principal Industrial Designer of irwindesigned LLC, founded in 2007. He also works for Eureka in R&D as a Sr. Industrial Design Engineer in Advanced Development. Renowned for his expertise in sustainable product development and industrial design strategy, Robert has collaborated with leading clients like Amazon, Hoover, PepsiCo, and Hershey’s. His work spans user research, CAD modeling, prototyping, and environmental impact assessment. Beyond his firm, he has led groundbreaking projects, including the Amazon Dash Cart and net-zero energy homes, and secured numerous patents for his inventions. Robert is also an educator, founding the Learn Industrial Design platform for on-demand courses, and hosts the “Designing In The Wild” podcast. With a Bachelor of Arts in Industrial Design from The Art Institute of Colorado and certifications in sustainability and design thinking, he is a recognized thought leader in circular systems and life cycle thinking. His accolades include Consumer Product of the Year at the Colorado Inventor Showcase and features in prominent publications and media.

Self-Adaptive Materials and Structures for Resilient and Healthy Future

Date: January 31, 2025; Time: 2:30 PM Location: PWEB 175

Abstract: Adaptability is one of the hallmarks of living systems that provide resilience in a dynamically changing environment. I will present our efforts to study coupled mechanical systems toward mechanically adaptive materials and structures. I will start with the overview of my research, then focus on two recent efforts.

First, I will present self-adaptive materials that can change their mechanical properties depending on loading conditions by the coupling between stress and material synthesis [1]. Nature produces outstanding materials for structural applications, such as bone and wood, that can adapt to their surrounding environment. For instance, bone regulates mineral quantity proportional to the amount of stress. It becomes stronger in locations subjected to higher mechanical loads. This capability leads to the formation of mechanically efficient structures for optimal biomechanical and energy-efficient performance. However, it has been challenging for synthetic materials to change and adapt their structures and properties to address the changing loading condition. To address the challenge, we are inspired by the findings that bones are formed by mineralizing ions from blood onto collagen matrices. I will present a material system that triggers proportional mineral deposition from electrolytes on piezoelectric matrices upon mechanical loadings so that it can self-adapt to mechanical loadings. For example, the mineralization rate could be modulated by controlling the loading condition, and a 30-180% increase in the modulus of the material was observed upon cyclic loadings whose range and rate of the property change could be modulated by varying the loading condition. I will also present our approach for reprogrammable self-configurable structures based on the material by controlling the modulus distribution through the applied loading [2]. Our findings can contribute to new strategies for dynamically changing mechanical environments, with potential applications including healthcare, infrastructure, and vehicle.

Second, I will present adaptive energy-absorbing “materials” with extreme energy dissipation and improving energy absorption with increasing strain rate by the coupling between viscoelastic properties of materials and nonlinear geometrical effects [3]. An architected material (or metamaterial) is a class of materials that provide new properties not observed in natural materials or from a bulk material that its constituent is made of. We utilize energy dissipation mechanisms across different length scales by using architected liquid crystalline elastomers. As a result, our energy-absorbing materials show about an order of magnitude higher energy absorption density at a quasi-static condition compared with the previous studies and even higher energy dissipation at faster strain rates with power-law relation, whose exponent can be tuned by controlling the mesoscale alignment of molecules using a simple strain control-based approach. Thus, the material exhibits up to a 5 MJ/m3 energy absorption density at a strain rate of 600 s-1, which is comparable to the dissipation from irreversible plastic deformation exhibited by denser metals. Our findings have the potential to realize extremely lightweight and high energy-dissipating materials, which will be beneficial for a wide range of applications, including automotive, aerospace, and personal protection.

We envision that our research can contribute to intelligent, resilient and sustainable mechanical systems, with applications including healthcare, infrastructure, and defense [4].

References

[1] S. Orrego, Z. Chen, U. Krekora, D. Hou, S.-Y Jeon, M. Pittman, C. Montoya, Y. Chen, S. H. Kang*, “Bioinspired materials with self-adaptable mechanical properties,” Advanced Materials, 32, 1906970 (2020).

[2] B. Sun, G. Kitchen, D. He, D. K. Malu, J. Ding, Y. Huang, A. Eisape, M. M. Omar, Y. Hu, S. H. Kang*, “A material dynamically enhancing both load-bearing and energy-dissipation capability under cyclic loading,” Science Advances, in press.

[3] S.-Y. Jeon, B. Shen, N. A. Traugutt, Z. Zhu, L. Fang, C. M. Yakacki, T. D. Nguyen, S. H. Kang*, “Synergistic energy absorption mechanisms of a bistable architected liquid crystal elastomers,” Advanced Materials, 2200272 (2022).

[4] G. Kitchen, B. Sun, S. H. Kang, “Bioinspired Nanocomposites with Self-Adaptive Mechanical Properties,” Nano Research, 17, 633 (2024).

Biographical Sketch: Sung Hoon Kang is an Associate Professor in the Department of Materials Science and Engineering at Korea Advanced Institute of Science and Technology (KAIST). He earned a Ph.D. degree in Applied Physics at Harvard University and M.S. and B.S. degrees in Materials Science and Engineering from MIT and Seoul National University, respectively. Before joining KAIST, he was an Assistant Professor in the Department of Mechanical Engineering, Hopkins Extreme Materials Institute and Institute for NanoBioTechnology at Johns Hopkins University. Sung Hoon has been investigating solutions to address current challenges in engineering materials, structures and devices with applications including resiliency, sensing, energy, and healthcare. In particular, he investigates behaviors of coupled mechanical systems by numerical modeling, nano/micro/macro fabrication, 3D printing, 3D structural/material/mechanical characterizations, and in vitro/in vivo testing. His research has been supported by AFOSR, NSF, NIH, ARO, ONR, State of Maryland, and private foundations. Throughout his career, Sung Hoon has co-authored 70 papers, has given over 230 presentations (including over 160 invited talks), and has eight patents and three pending patents. His honors include 2024 National Research Foundation of Korea Brain Pool Plus Fellowship, 2023 Young Innovator Award by Nano Research, Invitee for First US-Africa Frontiers of Science, Engineering, and Medicine Symposium, 2022 Hanwha Non-Tenured Faculty Award, 2021, 2020 Air Force Summer Faculty Fellowship, 2020 Johns Hopkins University Catalyst Award, 2019 Johns Hopkins University School of Engineering Research Lab Excellence Award, Invitee for 2019 China-America Frontiers of Engineering Symposium, FY 2018 Air Force Office of Scientific Research Young Investigator Program Award, Invitee for 2016 National Academy of Engineering US Frontiers of Engineering Symposium, and 2011 Materials Research Society Graduate Students Gold Award. He served as an editorial board member of Scientific Reports and a guest editor of Materials Research Society Bulletin. Currently, he serves as an editorial board member of Journal of Physics: Materials and Sensors, respectively. He has been co-organizing ~35 symposia on bioinspired materials, 3D printing, and mechanical metamaterials at international conferences. He is a member of American Society of Mechanical Engineers (ASME), American Physical Society (APS), Materials Research Society (MRS), Electrochemical Society (ECS), and Society of Engineering Science (SES). He served as the Chair, Vice Chair, Secretary, and Editor of ASME Technical Committee on Mechanics of Soft Materials.

Manufacturing for Good – Experiences in Bangladesh

Date: February 14, 2025; Time: 2:30 PM Location: PWEB 175

Abstract: This seminar will describe design and manufacturing activities that are part of USAID’s $27MM, 6.5-year CSISA-MEA (Cereal Systems Initiative for South Asia – Mechanization Extension Activity).  The goal of this project is to improve the agricultural mechanization and agricultural-based light engineering companies in Bangladesh, thereby improving the lives of millions of people who depend on agriculture for their livelihoods.  The objectives of the CSISA-MEA project will be presented, its impact on Bangladesh, examples of the various activities, – training, women, machinery design and fabrication, factory design, foundries, materials processing, energy and the environment – and finally a deep dive into rice seedling transplantation and the proposed improved manufacturing processes for a critical spare part for the rice transplanter – its plucking fork.

Biographical Sketch: Prof. Jonathan Colton holds the Eugene C. Gwaltney, Jr. Professorship in Manufacturing and is Professor of Mechanical Engineering, of Industrial Design, and of International Affairs at Georgia Tech.  He received his S.B., S.M., and Ph.D. in Mechanical Engineering from Massachusetts Institute of Technology.  His research and teaching interests are at the intersections of global/international development and design and manufacturing.  Dr. Colton directs the Georgia Tech -U.S. Department of State Diplomacy Lab.  For over a decade, he served as a member of the World Health Organization’s Immunization Practices Advisory Committee.  He led an international team that designed a Net-Zero Energy Warehouse for Drugs and Vaccines in Tunis for the government of Tunisia that was funded by the Gates Foundation.  In 2013-2024, Prof. Colton served as a U.S. Department of State Jefferson Science Fellow at the USAID Bureau for Food Security where he supported the scaling up of agricultural technologies in the Feed the Future program.  He currently helps to lead the USAID-funded CSISA-MEA (Cereal Systems Initiative for South Asia – Mechanization Extension Activity), a $27 million project to increase agricultural mechanization and manufacturing capacities in Bangladesh.  Prof. Colton’s composites research studies the design and fabrication of the next generation of aircraft with emphasis on continuous fiber reinforced materials and the conversion of post-industrial use materials for high performance transportation usage.  A current Department of Energy project seeks to apply machine learning and artificial intelligence to reduce the energy required to cure advanced aerospace thermosetting composite structures, such as airplane wings, airframes and wind mill blades.  His research has been funded by NSF, NIH, US CDC, TRW, United Technologies, Lockheed Martin, Boeing, U.S. Navy, Westinghouse, Ford, General Motors, General Electric, Philips Petroleum, NIST, NATO, Schlumberger, Gates Foundation, NASA, and Kodak, among others.

Enabling Intelligent Decision-Making in Manufacturing through Data-driven Methods

Date: February 7, 2025; Time: 2:30 PM Location: PWEB 175

Abstract: Future manufacturing envisions cyber manufacturing services that cater to on-demand production of discrete engineered products. These services are expected to be enabled by recent advances in digital manufacturing spanning the factory floor and the supply chain through Industry 4.0+ concepts and technologies. Critical to the realization of this vision are computational tools that enable intelligent and, where possible, automated decision-making. This talk will discuss the role of data-driven and, where possible, physics-driven computational tools in enabling automated decision-making at various stages of the design-to-manufacturing translation of discrete engineered products. Specifically, it will address the use of modern AI/ML and physics-based computational capabilities to automate key manufacturing decision-making including manufacturability assessment, process selection and sequencing, supplier selection, and other aspects of process planning with a focus on material removal and hybrid manufacturing processes.

Biographical Sketch: Shreyes Melkote holds a Morris M. Bryan, Jr. Professorship for Advanced Manufacturing Systems in Mechanical Engineering at Georgia Tech. He also serves as Executive Director of the Novelis Innovation Hub at Georgia Tech and Associate Director of the Georgia Tech Manufacturing Institute. His research spans many areas of manufacturing including precision machining, surface modification methods, hybrid manufacturing, industrial robotics, and application of AI/ML to solve complex decision-making problems in manufacturing. His honors include the 2024 ASME Milton C. Shaw Manufacturing Research Medal, the 2023 SME Gold Medal, and the ASME Blackall and Machine Tool Gage Award, among others. He has served as President of NAMRI/SME and as ASME Foundation Swanson Fellow at the Interagency Advanced Manufacturing National Program Office at NIST. He is a Fellow of ASME, SME, and CIRP.

From aerosol synthesis of materials and devices to a new kinetic theory of gases?

Date: December 6, 2024; Time: 2:00 PM Location: PWEB 175

Abstract: Recent advances in understanding of combustion and aerosol formation and growth through multiscale process design, allow now inexpensive synthesis of nanoparticles with sophisticated composition, size and morphology by spray combustion at kg/h even at academic institutions with such units now all over the world (UK, Spain, India etc.). These have led to synthesis of single noble atom heterogeneous catalysts, biomaterials and highly porous sensing films. These advances and community’s keen interest on nanoscale phenomena have motivated a closer look to the fundamentals of aerosol particles in the free molecule regime.

For eons, the kinetic theory of gases has been assuming elastic collisions between spherical gas molecules [1]. However, is this so with what we know about molecular shape and force fields today? Having reached a state of maturity now, molecular dynamics (MD) simulations can elucidate the fundamentals of basic aerosol phenomena that lead to better understanding of natural phenomena and accelerate process design and scale-up [2].

Here the mechanics of gas collisions are elucidated for plain air at room temperature by thoroughly-validated atomistic MD treating O₂ and N₂ as true diatomic molecules accounting for their shape and force field, for the first time to our knowledge. So it is revealed that their trajectories are no longer just straight (or ballistic) while collision frequencies are much higher due to the attractive component of the force field and the diatomic shape of N₂ and O₂ as will be shown by the respective videos. Frequently, colliding molecules were split from each other but soon return to collide again and again without interacting with any other molecule in between resulting in orbiting collisions as had been envisioned 60 years ago [3].

A direct result of the enhanced interactions between air molecules when treated as true diatomic ones is that their mean free path (MFP) comes out to be considerably smaller than that from the classic kinetic theory. The new MFP for air is 38.5 nm, almost 43% smaller than that in textbooks of 67.3 nm at ambient conditions [4]. Such a result is significant in aerosol synthesis of tiny (< 5 nm) nanoparticles where asymptotic (self-preserving) particle size distributions and (fractal-like) structures have not been attained yet to simplify the corresponding process design as with carbon blacks and fumed oxides today.

Most importantly, this motivates a renewed examination of aerosol dynamics in the free molecular regime. If time permits, it will be shown that accounting for the gas molecule shape and force field (in addition to that of particles) drastically decreases the diffusivity of tiny aerosol nanoparticles, up to an order of magnitude lower than that given by Epstein’s equation in all aerosol textbooks as their size approaches that of surrounding gas molecules.

1. Maxwell JCMA, The London, Edinburgh, Dublin Philos. Mag. J. Sci., 19-32 (1860).
2. Mavrantzas VG & Pratsinis SE, Curr. Opinion Chem. Eng., 23 174 – 183 (2019).
3. Hirschfelder, JO, Curtiss, CF, Bird, RB, Molecular Theory of Gases & Liquids, Wiley, 1964.
4. Tsalikis D, Mavrantzas VG, Pratsinis SE, Aerosol Sci. Technol. 58, 930 – 941 (2024).

Biographical Sketch: Dr. Pratsinis has a 1977 Diploma in Chemical Engineering from Aristotle Univ. of Thessaloniki, Greece and a 1985 PhD from Univ. of California, Los Angeles. He was in the faculty and head of ChE at the Univ. of Cincinnati, USA until 1998 when he was elected Professor of Process Engineering & Materials Science at ETH Zurich, Switzerland. He has graduated 46 PhDs, published 400+ refereed articles, filed 20+ patent families that are licensed to industry and have contributed to creation of four spinoffs. One of them (HeiQ Materials AG) was the first ever from ETH Zurich to enter the London Stock Exchange in December 2020. Another one (Alivion AG) was launched in 2022 and has sold already its devices for detection of adulterated alcohol and methanol poisoning in 26 countries. For more details on him you may glance at https://ptl.ethz.ch/people/person-detail.html?persid=79969