Diagnosis of concealed internal faults within power transformer is a key for high grid reliability to ensure continuity of power supply to customers. One of the urgent situations of power transformer is the faults under CT saturation and the operation under inrush currents that lead to huge failure of fault identification of the power transformer. In this paper, a fault identification scheme is designed using details and approximate coefficients obtained by discreet wavelet transform applied to a differential current signal under different situations. Also, this paper considers the impact of transformer internal faults such as turn to earth and turn to turn faults, external faults, and inrush currents. The signature of processing differential current is employed for identifying these fault conditions since such fault has a distinct differential current signature. The simulation tests are performed on a 115/22 kV power transformer using ATP-EMTP real-time simulator. Different wavelet families are assessed to show that the optimum mother wavelet, db1, has high fault detection and classification performance. The proposed scheme is verified for transformer energization conditions, and the influence of CT saturation is also considered in this study. Moreover, one of the most important proposed scheme features is simplicity with high lights aspects toward all fault conditions and fault types at different fault location and different fault resistances. Intensive simulation results are obtained to prove the improved selectivity and sensitivity of the proposed scheme for identifying internal transformer faults. Furthermore, sensitivity analysis is not only conducted in terms of transformer loading and fault resistance variation, but transformer scalability study is also verified. Finally, to evaluate the performance of the proposed scheme, an assessment study is adopted to show the accuracy and reliability of differential protection scheme.

Polymer-based composite material optimization is a key technology for achieving the desired thermal management in heat conduction sheets used in electronics and aerospace. Diamond particles are widely used as thermally conductive fillers in a liquid of poly di-methyl siloxane (PDMS) matrix because of their unique thermophysical properties. Electrical alignment is a powerful approach for filler alignment to achieve higher thermal conductivity. Meanwhile, practical experiments require substantial time, resources and consumable energy due to extensive testing. Therefore, it is essential to develop a highly robust predictive model for estimating thermal conductivity. This paper proposes a data-driven-based model that investigates a novel decision tree (DT) regression model for predicting thermal conductivity based on electrical alignment parameters, aiming to identify the optimal experimental conditions that achieve higher thermal conductivity. In this study, electrical alignment parameters, namely voltage, frequency, and rotational speed, are selected as descriptors for modelling and computing thermal conductivity. Correlation and multicollinearity analyses are conducted to evaluate the relationships among these descriptors. Three machine learning approaches, including Decision Tree, Random Forest (RF), and Gradient Boosting Decision Tree (GBDT), are investigated alongside six empirical regression models. The predictive model-based refined DT achieves high accuracy with the lowest mean square error of 0.0004 and a higher coefficient of determination (R-squared) of 0. 9751on testing data, respectively. This indicates that the model is capable of accurately predicting the thermal conductivity of hybrid nanofluids over a wide range of hybrid nanoparticle combinations with high closeness to the experimental records. This predictive model condition highlights the potential of DT-based method to precisely compute the thermal conductivity of PDMS-diamond composite based on the applied electrical alignment parameters.

Precise estimation of fuel cell parameters is critical for optimizing performance and developing energy systems. However, experimental data are often affected by outliers stemming from inaccurate measurements, transient operating conditions, or environmental variations. In this line, this study proposes a robust approach for estimating proton exchange membrane fuel cell (PEMFC) parameters. This study focuses on the steady-state current–voltage (I–V) characteristics and performs parameter extraction for a semi-empirical model. The proposed estimation framework employs the collaboration of the Huber loss function (HLF) in conjunction with adaptive hyperparameter and the metaheuristic Wild Horse Optimizer (WHO) to compute seven unknown PEMFC parameters. The impact of different hyperparameter (δ) values is examined on the performance of the HLF while estimating key fuel cell parameters. The sensitivity of the estimating process to the δ-value is explored using measured and estimated datasets, including accuracy, convergence rate, and resilience. The WHO-based approach is adopted to address and mitigate issues such as premature convergence and entrapment in local optima, which are common challenges in existing optimization strategies. The proposed model has been tested and verified through three test samples of standard commercial PEMFC units as benchmarks. The simulation results demonstrate that the WHO exhibits robust performance across the three benchmark PEMFC systems. Furthermore, the proposed model's generalization capability is validated under a range of operating conditions using polarization curves generated at different temperatures and cathode stoichiometries. A single globally specified parameter set reliably predicts fuel cell performance across these diverse conditions, as evidenced by its consistent ability to deliver high-quality solutions with an extraordinary level of precision under predefined experimental conditions. The proposed estimation framework outperforms three commercial PEMFC units (NedStack-PS6, Horizon-500 W, and BCS-500W), achieving Huber loss values of 1.03277845, 0.00562094, and 0.00584889, respectively. The adaptive HLF with hyperparameter (δ) ranging from 0.5 to 2.0 efficiently tackles outliers and improves convergence speed. While the hyperparameter (δ) in previous studies was kept constant, δ = 1. The proposed estimation framework closely matches the experimental data and offers significantly higher accuracy compared to existing competing methods in the literature. The results reveal that the suggested HLF enhances the robustness and immunity of the WHO optimizer, and it outperforms traditional approaches such as steady-state error.