This paper summarizes the main results and contributions of the MagNet Challenge 2023, an open-source research initiative for data-driven modeling of power magnetic materials. The MagNet Challenge has (1) advanced the stateof-the-art in power magnetics modeling; (2) set up examples for fostering an open-source and transparent research community; (3) developed useful guidelines and practical rules for conducting data-driven research in power electronics; and (4) provided a fair performance benchmark leading to insights on the most promising future research directions. The competition yielded a collection of publicly disclosed software algorithms and tools designed to capture the distinct loss characteristics of power magnetic materials, which are mostly open-sourced. We have attempted to bridge power electronics domain knowledge with state-of-the-art advancements in artificial intelligence, machine learning, pattern recognition, and signal processing. The MagNet Challenge has greatly improved the accuracy and reduced the size of data-driven power magnetic material models. The models and tools created for various materials were meticulously documented and shared within the broader power electronics community.

Polyether ether ketone (PEEK), polytetrafluoroethylene (PTFE), and polyimide (PI) are widely used in aerospace due to their excellent properties. Understanding their aging behavior is essential for long‐term performance in extreme environments. This study examines the effects of thermal oxidative aging (at 250°C over varying periods) under humid conditions on their chemical, structural, thermal, mechanical, and dielectric properties. In PEEK, aging led to solidification and crosslinking phenomenon which resulted in increased tensile strength and storage modulus, while elongation at break and tan δ decreased. Dielectric permittivity, polarization charge density, and leakage current also declined with aging, while AC breakdown strength increased by 1.6% in PEEK. PTFE exhibited surface oxidation, thermal degradation, and a decrease in storage modulus, with an increase in loss tangent. Breakdown strength slightly decreased, while dielectric loss and leakage current increased over aging time. PI underwent severe mechanical degradation, with tensile strength reduced by 54% and elongation by 16%, along with oxidation‐induced discoloration. Low‐mass polar molecules generated in PI during thermal degradation which contributed to the deterioration of its dielectric properties, lead to increased permittivity, polarization, leakage current, and a lower breakdown strength observed after aging. These findings provide insights into degradation mechanisms, aiding aerospace material selection for extreme environments.

Pre-stretching membranes in dielectric elastomer actuator (DEA) systems is a widely known technique to improve the dielectric’s breakdown strength and therefore enhance the overall device performance. The impact of this approach on the long-term reliability of DEAs is, however, still unknown. In the present work, it is investigated how the elastomer lifetime is affected by the mechanical pre-stretch. Silicone membrane samples with different pre-stretch ratios were prepared and the respective DC dielectric strengths were measured for both short and prolonged tests using methodologies inherited from high voltage assessment technology. It is shown that, despite an absolute beneficial increase of the dielectric strength for the tensioned membranes, pre-stretching has a detrimental effect on the system’s useful life. In all the studied cases, the pre-stretched specimens showed a shorter expected lifetime compared to new, relaxed membranes. The results suggest a careful selection of the relative electric field to be applied to DEAs system for long and reliable lifetime.

In the production of green hydrogen, electrolyzers draw power from renewable energy sources. In this paper, the design of SST (Solid State Transformer) for large-scale H ₂ electrolyzers is benchmarked. The three most promising topologies are chosen for design and comparison, including Modular Multi-level Converter (MMC) based SST, Modular Multi-level Resonant (MMR) based SST, and Input-Series-Output-Parallel (ISOP) based SST. The distance between converter towers for insulation and maintenance, the insulation system of the transformer, and the cooling system are designed with practical considerations in order to have an accurate estimation of the volume and weight of the SST. Losses in the switches are calculated based on equations, and losses in passive components are calculated based on FEM simulation. The operating frequency for each topology is optimized to minimize loss, weight, and volume. The best of each topology is then compared with each other to identify the most suitable one for large-scale H ₂ electrolyzers.

Traditional methods such as Steinmetz's equation (SE) and its improved variant (iGSE) have demonstrated limited precision in estimating power loss for magnetic materials. The introduction of Neural Network technology for assessing magnetic component power loss has significantly enhanced accuracy. Yet, an efficient method to incorporate detailed flux density information—which critically impacts accuracy—remains elusive. Our study introduces an innovative approach that merges Fast Fourier Transform (FFT) with a Feedforward Neural Network (FNN), aiming to overcome this challenge. To optimize the model further and strike a refined balance between complexity and accuracy, Multi-Objective Optimization (MOO) is employed to identify the ideal combination of hyperparameters, such as layer count, neuron number, activation functions, optimizers, and batch size. This optimized Neural Network outperforms traditionally intuitive models in both accuracy and size. Leveraging the optimized base model for known materials, transfer learning is applied to new materials with limited data, effectively addressing data scarcity. The proposed approach substantially enhances model training efficiency, achieves remarkable accuracy, and sets an example for Artificial Intelligence applications in loss and electrical characteristic predictions with challenges of model size, accuracy goals, and limited data.