The global transition toward sustainable energy and electrified mobility demands smarter, faster and more efficient design as well as control of electric drive systems. These systems, which encompass electric machines, drives and storage elements like batteries and supercapacitor, constitute the core of electric vehicles (EVs) and renewable energy infrastructure. Machine design and modeling related to electric, on the other hand, are geared toward the conception and simulation of machines converting electrical energy into mechanical energy. Modeling encompasses mathematical representation of these machines for predicting their behavior under varying operating conditions, optimization in electric vehicles signifies the process of improving different aspects of vehicle design, operation and performance toward maximum functionality, sustainability and efficiency. These processes constitute the application of mathematical models, engineering principles and algorithms to tackle energy consumption, enhance storage systems, battery and supercapacitor management as well as overall vehicle performance in turn.

The use and development of renewable energy has been identified globally as one of the effective means of combating environmental concerns and threats such as global warming, climate change and pollution. This orientation has been reflected onto the significant advancements achieved in machinery and industrial applications concerning energy management systems, transportation systems, energy generation, power systems, renewable energy systems, manufacturing, building systems, urban settings,  infrastructure, hydroelectric systems, marine and aerospace, automation, power plants, among many others.

Given the developments in evolving landscape, the special session focuses on the orientation of Artificial Intelligence (AI) and data-driven modeling to improve the accuracy, performance and adaptability of these components. Techniques such as machine learning, neural networks, genetic algorithms and reinforcement learning enable  advanced control and optimization of machines and energy systems in real time. In parallel fashion, data-driven modeling method such as Dynamic Mode Decomposition (DMD), Sparse Identification of Nonlinear Dynamical Systems (SINDy) and Koopman operator theory have been revolutionizing how engineers model and simulate complex, nonlinear systems without relying exclusively on first principles. To put it differently, from electric machine design to drive system control and energy storage management, AI and data-driven tools can support predictive maintenance, fault diagnosis, parameter estimation, and optimization under variable and uncertain operating conditions. These developments are particularly impactful for real-world applications in EVs, hybrid systems, microgrids as well as smart cities.

In view of these concerns, design novelties, models and applications, we aim to provide a platform for exploring and discussing recent developments, current and future challenges particularly concerned with electrical machine design and modeling, electric drives, energy conversion and modes of renewable energy, among others. In brief, this session welcomes contributions exploring theory, simulations, experiments and real-world applications, which integrate AI and data-driven modeling with traditional engineering design to enhance sustainability, reliability and efficiency. Consequently, we hope to pave new directions toward criticality, multiple modality and versatility of these notions and applications for advancing technology further, encouraging sustainability and finding solutions to pressing global challenges.

The topics include but are not limited to: