Khalil El Khamlichi Drissi

Artificial intelligence (AI) is increasingly pivotal in modernizing the lifecycle of power electronic systems (PESs). Extending the discussion on the design and control phases presented in Part-I of the survey, Part II focuses on the transformative role of AI in the maintenance and forecasting phases of PES. Specifically, we analyze how AI techniques are applied to power electronic components, power electronic converters (PECs), and their emerging applications. This survey analyzes how AI techniques monitor PES’s health by detecting faults/anomalies, and estimating the remaining useful life (RUL), and in turn enable fault prevention before complete failure. Distinct from prior surveys, it also discusses soft-fault detection in complex wired networks such as aircraft, representing a system-of-systems application. In the context of forecasting, AI enables accurate prediction of PES parameters, such as power efficiency, thermal behavior, components’ lifetime, load demand, and energy generation. This survey identifies open challenges and provides forward-looking insight to guide researchers and engineers in developing robust, efficient, and autonomous maintenance and forecasting solutions for PES.

Artificial intelligence (AI) has become essential in dealing with the growing complexities of modern power electronic systems (PESs). In the context of Industries 4.0, 5.0, and especially 6.0, which are considered as ultra-large-scale systems, AI is becoming essential in addressing the multidimensional challenges of PES design, energy management, and control in complex interconnected systems. This part I of our two-part survey provides a comprehensive overview of AI techniques applied to the design and control stages across the lifecycle of PES. In this survey, we consider an energy conversion chain incorporating energy sources, converters, controllers, sensors, and loads as a complex or a large system with several subsystems by integrating the AI part for several objectives among others: design, control, optimization, maintenance, fault detection, etc. Our unique contributions include: first, a complete lifecycle-oriented perspective for power electronics systems, second, structured tabular summaries emphasizing experimental validation versus simulation-only studies, third, focus on design automation and AI-integrated converter control, and fourth, identification of research gaps in hardware implementation and model interpretability. This survey also identifies open challenges and offers forward-looking insights into design automation, and AI-integrated converter control for smart grids, electric vehicles, and power systems. This article aims to serve as a roadmap for both researchers and engineers seeking to adopt AI in next-generation power electronics. Part II of this survey will focus on the maintenance and forecasting phases of the lifecycle of PES.

Dynamic Wireless Power Transfer (DWPT) is a revolutionary technology for developing an autonomic electromobility transport system. A robust control method is essential for maximum power transfer with high efficiencies and the safe operation of the DWPT systems. This paper developed a frequency domain model of a series-series wireless power transfer system to thoroughly analyze how different control parameters affect the system performances under dynamic situations. For the first time, the power triangle phenomenon associated with the proposed optimum frequencies of a DWPT system is discovered to reveal the causal relationship between frequency, phase shift, and power. The theoretical performances of the proposed optimum frequencies are well aligned with the results of simulation and experiments, with 83% of the normalized root mean square errors less than 2%.

Analytical methods are significantly useful tools for engineers in computational modeling. These methods provide fast simulations, while preserving physical meaning. In this paper, a full analytical formulation is developed based on the circuit approach, also known as Intermediate Level Circuit Model (ILCM), to evaluate the shielding effectiveness (SE) of metallic structures. The proposal focuses on rectangular enclosures containing apertures of complex geometrical shape, illuminated by an external plane wave. The enclosure is taken as a short-circuited waveguide. The aperture is treated as a transmission line with an intrinsic impedance that depends on the aperture polarizability, according to Bethe’s theory of small holes. The formulation easily takes into account high-order resonant modes and different apertures, such as circular, elliptical, round-ended and cross-shaped apertures. The ILCM technique reveals good agreement with a numerical full-wave method for various configurations of enclosures, covering a large range of frequencies from 0.5 GHz to 2.5 GHz, thus offering perspectives for parametric and/or optimization SE studies.