Key note Speaker : Enrique ZUAZUA
Topic: Control and Machine Learning
Abstract:Systems control, or cybernetics—a term first coined by Ampère and later popularized by Norbert Wiener—refers to the science of control and communication in animals and machines. The pursuit of this field dates back to antiquity, driven by the desire to create machines that autonomously perform human tasks, thereby enhancing freedom and efficiency.
The objectives of control systems closely parallel those of modern Artificial Intelligence (AI), illustrating both the profound unity within Mathematics and its extraordinary capacity to describe natural phenomena and drive technological innovation.
In this lecture, we will explore the connections between these mathematical disciplines and their broader implications. We will also discuss our recent work addressing two fundamental questions: Why does Machine Learning perform so effectively? And how can data-driven insights be integrated into the classical applied mathematics framework, particularly in the context of Partial Differential Equations (PDE) and numerical methods?
Speaker: Dr.R Vijay Aravind
Topic: Title Physics-Informed Neural Networks (PINNs) for Enhanced Modeling and Optimization of Lithium-Ion Batteries
Physics-Informed Neural Networks (PINNs) present a cutting-edge methodology for accurately modeling and optimizing lithium-ion batteries (LIBs) by integrating fundamental physical principles directly into machine learning models. By embedding the governing physical laws—such as the Butler-Volmer equation, mass conservation, and electrochemical dynamics—within the neural network architecture, PINNs offer superior accuracy and computational efficiency in solving the complex partial differential equations (PDEs) that describe LIB behavior. This approach enables precise predictions of key battery metrics, including state of charge (SoC), state of health (SoH), temperature distribution, and degradation processes. The integration of physics with neural networks not only enhances simulation precision but also reduces computational costs and data dependency, paving the way for improved LIB design, optimization, and real-time performance insights. This presentation will demonstrate how PINNs accelerate modeling, provide predictive insights into battery degradation, and contribute to the development of more reliable and efficient battery systems across various applications.
speaker Dr. Thameem Basha Hayath Basha
Topic: Machine Learning for Heat Transfer Enhancement
In recent years, machine learning (ML) has become a transformative tool in fluid dynamics, offering novel approaches to improve heat transfer processes. This presentation delves into the application of ML techniques for predicting fluid flow patterns, with a focus on optimizing heat transfer in energy storage and thermal management systems. Traditional methods for analyzing complex fluid dynamics and heat transfer are often time-consuming and computationally demanding. However, ML models streamline this process by efficiently predicting key parameters such as Nusselt number, flow patterns, and temperature distributions under various conditions, including natural, forced, and mixed convection. The talk will cover the basics of integrating ML into fluid dynamics, highlighting the development of predictive models that incorporate critical physical properties like nanoparticle volume fraction, Darcy number, and Rayleigh number. Case studies showcasing the use of ML to enhance heat exchanger performance and improve the thermal efficiency of NEPCM (nano-enhanced phase change materials) systems will be discussed. By merging numerical simulations with ML predictions, this approach paves the way for more efficient thermal energy management in a wide range of engineering applications, from electronics cooling to renewable energy systems. Attendees will gain a deeper understanding of ML's transformative impact on fluid dynamics research and its role in driving future innovations in heat transfer enhancement.