Next-Generation Control of Multilevel Inverters and Electrical Machines: AI, Nonlinear Techniques, and Real-Time Validation

Dear Colleagues,

The increasing demand for high-performance, efficient, and reliable energy conversion systems has accelerated the development of advanced control methodologies for power electronic converters and electrical machines. Among these approaches, nonlinear control techniques and artificial intelligence (AI) have demonstrated significant potential in addressing the complex dynamics, uncertainties, and operational constraints encountered in modern electrical drive and power conversion systems. This Topic aims to present the latest theoretical, computational, and experimental advances in the application of nonlinear control and AI-based techniques to multilevel inverters and electrical machines. It provides a platform for researchers and industry practitioners to explore innovative solutions that enhance system performance, robustness, efficiency, fault tolerance, and adaptability in emerging applications such as renewable energy systems, electric vehicles, smart grids, and industrial automation. Particular attention is given to advanced nonlinear control strategies, including sliding mode, adaptive, robust, backstepping, and predictive control methods, as well as AI-driven approaches based on machine learning, deep learning, reinforcement learning, fuzzy systems, and digital twins. The Topic also addresses the design, modeling, optimization, and control of multilevel inverter topologies and electrical drive systems operating under challenging and uncertain environments. In addition to highlighting recent scientific achievements, this Topic discusses the major challenges facing the widespread adoption of intelligent and nonlinear control technologies, including computational complexity, real-time implementation constraints, reliability, cybersecurity, and industrial scalability. Furthermore, it explores future research directions toward autonomous energy systems, explainable AI, edge intelligence, and next-generation smart power conversion technologies. A distinguishing feature of this Topic is its emphasis on experimental validation and practical implementation. Contributions presenting hardware prototypes, real-time control platforms, Hardware-in-the-Loop (HIL) testing, FPGA/DSP implementations, and industrial case studies are particularly encouraged to bridge the gap between theoretical developments and real-world applications. By bringing together leading researchers from the fields of power electronics, control engineering, artificial intelligence, and electrical machines, this Topic seeks to advance the development of intelligent, efficient, and resilient energy conversion systems for future sustainable technologies.

Prof. Dr. Habib Benbouhenni
Dr. Alin Gheorghita Mazare
Topic Editors