The data-driven machine-learning approach has significantly advanced the development of computational electromagnetics. This study introduces the Kolmogorov-Arnold network (KAN) as a novel method to overcome the limitations of traditional multilayer perceptron-based physics-informed neural networks (MLP-PINNs), which often struggle with fixed activation functions and high computational costs. In terms of accuracy, KAN outperforms traditional PINNs with a 13.47% improvement in estimated accuracy. For efficient convergence, KAN achieves stable training with only 175 steps, significantly reducing computational overhead compared to PINNs, which require over 15000 steps. Additionally, KAN demonstrates superior generalizability and flexibility, achieving an average 5.03% accuracy improvement over PINN in transfer learning scenarios. These results highlight KANs potential in computational electromagnetics.

This paper proposes a multiport energy management system (EMS) and its rule-based expert control strategy for a 150 kW range-extended towing vessel (RETV). The system integrates a diesel generator system, a permanent magnet synchronous motor, a lithium battery, and supercapacitors. To verify its feasibility and effectiveness, the proposed multiport EMS was modelled and tested through MATLAB/Simulink. Simulation results demonstrate that the designed multiport EMS works efficiently under the five typical operating conditions of the 150 kW RETV. In addition, two case studies were conducted and compared to investigate the impact of the battery’s initial state of charge (SoC) on the system’s energy efficiency. It was found that an overall 85% energy efficiency can be achieved for the RETV when the initial SoC is either 75% or 15%. The battery consistently operates within the optimal SoC range of 20% to 80%, and the supercapacitors effectively meet the instantaneous high-power demand.

This study investigates a large language model driven (LLM) framework for intelligent preprocessing and short-term electricity price forecasting in the Australian National Electricity Market (NEM). By integrating unstructured news features, weather signals, and cyclical calendar variables, the model captures both physical and informational drivers of price volatility. A hybrid approach combining quantile regression with conformal calibration achieves statistically significant improvements in accuracy and uncertainty calibration. The framework demonstrates the potential of integrating LLMs into operational forecasting pipelines to support electricity market decision-making and risk management.

Open-boundary 2-D magnetostatic field problems are computationally challenging for traditional numerical methods. This work proposes MagOpenNet, a physics-informed neural network (PINN) framework that introduces the concept of the 1-D and 2-D Astley Infinite Element Method (IEM), along with a self-adaptive weighting strategy, to address the complexities of predictions for both interior and exterior domains. Benchmark tests on circular geometry show that MagOpenNet attains at least 73.2 % reduction compared to the Finite Element Method (FEM) in computation time, 15.58 % reduction compared to IEM and 73.42 % reduction compared to the Finite Difference Method (FDM), with an average of 98.6 % accuracy. The transfer learning-based bus duct, C-core, and U-core benchmarks yield a similar outcome. Compared to traditional PINNs, MagOpenNet achieves up to 36.61 % time reduction in training. These results demonstrate that MagOpenNet provides an alternative for high computational efficiency, high accuracy, strong generalisation ability and stable convergence for open boundary magnetostatic analyses.

The Permanent Magnet Linear Motor (TPMLM) is widely used in different industrial fields. TPMLMs with slots and iron cores have high power density, but their thrust fluctuations and copper losses are significant. Due to the nonlinearity and saturation of magnetic circuits, their electromagnetic models are complex and the accuracy of numerical methods is very inferior. Substantially accurate modelling is crucial for motor optimisation design. In this paper, a data‐driven modelling method based on Bayesian optimisation deep neural network (DNN) is proposed to improve the accuracy of the electromagnetic field. The finite element (FE) modelling under different structural parameters is analysed and provides a training dataset for DNN. Then, a multi‐objective optimisation problem for the slotted TPMLM is carried out based on the multi‐objective black hole algorithm. Compared to the original design, the average thrust of TPMLM increased by 49.37%, the thrust fluctuation percentage decreased by 9.59%, and the coil copper consumption percentage decreased by 2.64%. The results show that the improved DNN model has very high modelling accuracy, providing a new way for motor design and optimisation.