Artificial Intelligence and Machine Learning at IMECE 2024

We are pleased to announce the winners of the 2024 IMECE "Best Paper Competition" within one of ASME's Emerging Strategic Areas, "Artificial Intelligence". Papers submitted under topics 01-06, 01-10, 03-16, 05-16, 17-17, 08-06, 09-10, 09-12, 11-03, and 14-06 in the International Mechanical Engineering Congress and Exposition (IMECE) were nominated by the topic chairs. After a thorough evaluation of the originality and significance of the papers, the seven winning papers have been selected.

The winning papers (in no particular order):

• Patrick Hummel, Joachim Grimstad, Yuchen Xia, and Andrew Morozov. "Generation of MATLAB Simscape Models Using Large Language Models for Training Reliability Evaluation Methods," IMECE2024-144344.


• Alice M. Agogino, Goldstein Adam, Ian Yijun Chen, Lily Hu, Roy Huang, Douglas Hutchings, Christiana Kang, Angeline Ying Kee Lee, Yuxin Miao, Jeffrey Daniel Millan, and Vivek Rao. "Methane Detection and Characterization with AI Sensor Fusion and Decision-Analytic Placement of Rapidly Deployable Sensors," IMECE2024-145130


• Mayank Jha, Amal Chulliyat Jose, Joachim Grimstad, and Andrey Morozov. "Dynamic Fault Tree Games and Reinforcement Learning for System Reliability," IMECE2024-145309.


• Olympio Belli, Helio Fiori de Castro, and Stephen Ekwaro-Osire, "Fault Parameter Quantification with a Bayesian Surrogate Model for Coupling Misalignment in a Rotor System," IMECE2024-145434.


• Amaninder Singh Gill, Ankit Agarwal, Vijayanth Tummala, Seung-Jin Lee, and Laine Mears. "Comparison of Explainable AI for Image Classification to Human Perception: A Case Study of Threaded Fasteners," IMECE2024-146133.


• Camilo Lopez-Salazar, Stephen Ekwaro-Osire, Henry Ekwaro-Osire, and Stephan Hopfmüller. "A Reinforcement Learning Approach for Production Scheduling in Industry 4.0 Considering Limited Data," IMECE2024-146180.


• Tsan-Hung Fu, Ting-Yuan Huang, and Dian-Ru Li. “Machine Learning-Enabled Process Monitoring and Error Detection in Material Extrusion-based Additive Manufacturing,” IMECE2024-147155.

---

ASME AI / Deep Learning Best Paper Honors Committee

---

Track 1: Acoustics, Vibration, and Phononics

01-06: AI and Machine Learning in Acoustics and Vibrations
This topic encompasses the integration of artificial intelligence and machine learning techniques with the study of sound and vibration. This interdisciplinary field focuses on employing AI algorithms for predictive modeling, signal processing, and system control in acoustics and vibrational systems. Applications range from noise reduction and enhanced signal processing in various environments to the design of materials with specific acoustic properties, and predictive maintenance through vibration analysis in machinery. This convergence of AI with acoustics and vibrations offers innovative solutions in numerous sectors, including automotive, aerospace, environmental monitoring, and human-computer interaction.

01-10: Machine Learning, Artificial Intelligence, and Deep Learning in Dynamics, Vibrations, and Control
Machine Learning and Artificial Intelligence are both emerging as invaluable tools for studying a wide variety of research problems. In the area of dynamical systems, these tools are being applied to problems in traffic dynamics, neural dynamics, fluid dynamics, molecular dynamics, multi-agent system dynamics, weather forecasting, and many others. This symposium seeks papers addressing applications of, and theoretical developments in, Machine Learning, Artificial Intelligence, and Deep Learning as applied to the fields of dynamical systems, vibrations, and control. Topics in which these tools are used could include the prediction of dynamical states in complex systems, system identification for linear and nonlinear systems, control of complex systems, and others. Acoustic and vibratory responses of dynamic systems are commonly used to gain insight about the system. Machine learning, Artificial Intelligence and data analytics are merging areas and tools that commonly used in science and engineering to take advantage of large amount data available given the recent advances in different engineering and data science fields. This symposium is a platform to discuss and share the recent theoretical and empirical advancements in Machine Learning (ML), Artificial Intelligence (AL) and Data Analytics (DA) as applied to the fields of acoustics, vibrations, active and passive noise and vibration control.

---

Track 3: Advanced Manufacturing

03-16: AI Integration in Mechanical Engineering and Smart Manufacturing
The call for papers in Artificial Intelligence (AI) within the realm of manufacturing and mechanical engineering signifies a pivotal opportunity for researchers, academicians, and industry experts to contribute cutting-edge insights to the rapidly evolving intersection of technology and industry. This call invites scholarly contributions that explore innovative applications of AI in manufacturing processes, energy domain, machine condition monitoring, process control, Generative AI for Manufacturing, Deep Learning, robotics, automation, and smart systems within the mechanical engineering domain. Topics may span from intelligent control systems and predictive maintenance leveraging machine learning algorithms to the integration of AI in supply chain management for enhanced efficiency. Researchers are encouraged to submit papers that delve into the challenges and opportunities presented by the integration of AI, addressing issues such as ethical considerations, scalability, and the real-world implementation of AI-driven solutions in manufacturing. This call serves as a catalyst for fostering dialogue and collaboration, aiming to advance the knowledge base and promote the adoption of intelligent technologies in the manufacturing and mechanical engineering sectors.

Topics Include:
1. AI approaches to support the shop floor manufacturing integration;
2. AI Integration in the Energy Sector: Enhancing Battery Management, Fuel Cells, and Renewable Energy Systems;
3. Predictive maintenance/process control using machine learning in mechanical engineering;
4. Robotics and automation powered by artificial intelligence and deep learning;
5. Smart systems and their applications in manufacturing processes;
6. AI-driven solutions for supply chain management in the manufacturing sector;
7. Scalability challenges and opportunities in AI applications for mechanical engineering;
8. Integration of AI in quality control and assurance processes in manufacturing;
9. Generative AI applications influencing and innovating manufacturing practices;
10. Ethical considerations in the integration of AI in manufacturing.

---

Track 5: Advances in Aerospace Technology

05-16: Applications of Artificial Intelligence/Machine Learning in Aerospace Engineering
Data science including artificial intelligence and machine learning has started making significant impact in academia and industry. Aerospace engineering field has unique opportunities and challenges to incorporate data intensive analysis techniques. This topic covers a wide range of applications of artificial intelligence and machine learning in aerospace engineering such as inspection, design, manufacturing and performance of aerospace structures, anomaly detection, autonomous exploration, power or fuel consumption prediction, satellite image analysis, etc.

---

Track 7: Dynamics, Vibration, and Control

07-17: Machine Learning and Artificial Intelligence in Dynamics, Vibrations and Control
Machine Learning and Artificial Intelligence are both emerging as invaluable tools for studying a wide variety of research problems. In the area of dynamical systems, these tools are being applied to problems in traffic dynamics, neural dynamics, fluid dynamics, molecular dynamics, multi-agent system dynamics, weather forecasting, and many others. This symposium seeks papers addressing applications of, and theoretical developments in, Machine Learning, Artificial Intelligence, and Deep Learning as applied to the fields of dynamical systems, vibrations, and control. Topics in which these tools are used could include the prediction of dynamical states in complex systems, system identification for linear and nonlinear systems, control of complex systems, and others.

---

Track 8: Energy

08-06: AI for Energy Systems
The purpose of this to topic is to provide a forum for information and innovation considering the advances in Artificial Intelligence (A.I.) and Machine Learning Applications in Energy Systems. Papers and technical presentations are solicited in areas including but not limited to:

• Energy Grid management and analysis with A.I.
• Sustainable Energy and Energy Distribution analysis
• Modelling and Simulations of energy systems (engines, refrigerators, mechanical parts) using A.I.
• A.I. analysis of Energy Trading and Energy Economics
• Smart Energy Storage Systems
• Predictive Analysis of Energy demand through A.I. systems
• Energy System Security (blockchain energy contracts, cybersecurity of energy resources)
• Automation in Energy Production and Distribution Systems
• Thermodynamic Analysis through A.I. and Machine Learning (analysis and design of thermodynamic cycles, working media, physical phenomena etc.)
• Application of A.I. in statistical and stochastic thermodynamic systems

---

Track 9: Engineering Education

09-10: Teaching Laboratories, Hands-on lab Experiences, Online Laboratory Teaching, Virtual Lab Simulation, Use of AI in Laboratory Experiments, Laboratory Equipment, Laboratory Safety Practices, Technology-Aided Lecturing, Novel Manufacturing Processes in ME Programs
This topic focuses on teaching laboratories, hands-on experiences, online laboratory teaching, virtual lab simulation, use of AI in laboratory experiments, laboratory equipment and safety. The topic also focuses on innovative teaching methods and novel tools used in class lecturing. It also includes topics such as machine shop experiences, teaching of novel manufacturing processes, and the use of additive manufacturing in research, laboratories, and capstone projects. Authors are welcomed to submit papers or presentations in the above mentioned topics describing their educational experiences, instructional practices, and pedagogical methods.

09-12: Mechatronics, Robotics, Automation, Automotive, Power Electronic, Control Engineering, Packaging, Automated Storage and Retrieval, Cybersecurity in Industry, Artificial Intelligence and Machine Learning
This topic deals with innovative curriculum and pedagogical tools dealing with the fields of mechatronics, robotics, automation, automotive, power electronic, control engineering, packaging, automated Storage and retrieval, cybersecurity in Industry at the undergraduate and graduate level. In addition, Artificial Intelligence (e.g. chatGPT) and Machine Learning role in education is also added to this topic. Papers, presentations, or posters reporting on the synergistic interaction of mechanical engineering, electrical, electronic engineering, control systems, Artificial Intelligence and Machines Learning education are welcomed. Methods of teaching effectiveness in both classroom and laboratory are ideal for presenting under this topic.

---

Track 11: Heat Transfer and Thermal Engineering

11-03: Artificial Intelligence, Machine Learning and Data Science for Thermal Processes, Heat Transfer and Energy Systems
While some machine learning (ML) methods such as regression were established over two centuries ago, it was not until the last decade that the terms machine learning, artificial intelligence (AI), analytics, and data science became ubiquitous. This can be attributed to the freely available and effective algorithms and the publication of convincing success stories. These collection of tools for understanding data, making future predictions, and optimizing decision making are fundamentally changing the way thermal systems are conceived, designed, operated, and controlled. In the field of heat transfer, these methods have shown promising results for everything from basic thermo-hydraulic characterization, flow regime visualization and understanding, novel component and system design to efficient optimal control of complex systems such as data centers and buildings. This session seeks seminar presentations and manuscripts that highlight the development and application of AI/ML methods for innovation in heat transfer and heat transfer and energy systems, including, but not limited to: machine learning-accelerated design and optimization, machine learning-accelerated solution of important transport equations, new machine learning methods specifically needed for thermal transport, etc.

---

Track 12: Mechanics of Solids, Structures, and Fluids

• 12-06: Scientific Machine Learning (SciML) for Characterization, Modeling, and Design of Structures and Materials
• 12-07: Probabilistic Scientific Machine Learning and Uncertainty Quantification
• 12-08: Data-Enabled Predictive Modeling, Scientific Machine Learnin/g, and Uncertainty Quantification in Computational Mechanics
• 12-10: Advancements of Data-Driven and Differentiable Computing in Solid Mechanics
• 12-11: Scientific Machine Learning and Uncertainty Quantification Methods for Experimental Mechanics
• 12-15: Advances in Neural Operators for Scientific Machine Learning

---

Track 14: Safety Engineering, Risk and Reliability Analysis

14-06: Machine Learning and Deep Learning in Safety, Reliability, and Maintenance
Today, Machine Learning (ML) and Deep Learning (DL) supported by Big Data enhance almost every industrial sector, including safety-critical areas. ML and DL techniques are used to detect and mitigate errors during the system operation. ML and DL are used to predict and determine when the system's maintenance will be indispensable to reduce or prevent the chance of future failures, and therefore increase its availability. ML and DL-based risk and safety analysis can help to ensure that component fault will not lead to a hazardous system failure. Also, DL-based components will soon become parts of safety-critical systems. The next generation of safety standards has to define appropriate verification and validation techniques and propose adequate fault tolerance mechanisms. To promote cross-fertilization and facilitate the development of this field, we welcome papers mainly related, but not limited to: Application of ML and DL-base methods for anomaly and error detection and mitigation, predictive maintenance, and reliability and safety evaluation; Safety and risk analysis of DL components; Evaluation of the resilience of DL components; Research on fault-tolerant architectures of DL components; Remote health monitoring; Safety standardization and practical application of DL components in safety-critical industrial domains.

---

Submit Abstract