This study introduces the concept of decision tree (DT) classification, a new approach to power transformer differential protection. The proposed technique is based on processing the differential current. The suggested method detects winding insulation failures and distinguishes them from magnetising inrush and sympathetic inrush conditions with classification accuracies of 100% for simulations and 95% for real‐time studies. The internal faults can be accurately recognised from inrush current conditions in a few sampling cycle after the occurrence of a disturbance. Another advantage of the proposed method is that the fault detection algorithm does not depend on the selection of thresholds. Performance analysis of the DT is achieved by the simulation of different faults and switching conditions on a power transformer in power system computer aided design/electromagnetic transients including DC (PSCAD/EMTDC). Furthermore, the proposed method is also tested in laboratory environment. The accuracy of DT is also compared with support vector machine. Both experimental and simulation results are presented and discussed.

Over the last 20 years, lithium-ion batteries have become widely used in many fields due to their advantages such as ease of use and low cost. However, there are concerns about the lifetime and reliability of these batteries. These concerns can be addressed by obtaining accurate capacity and health information. This paper proposes a method to predict the capacity of lithium-ion batteries with high accuracy. Four key features were extracted from current and voltage data obtained during charge and discharge cycles. To enhance prediction accuracy, the Pearson correlation coefficient between these features and battery capacities was analyzed and eliminations were made for some batteries. Using a genetic algorithm (GA), the parameter optimization of Convolutional Neural Network (CNN), Backpropagation (BP), and Recurrent Neural Network (RNN) algorithms was performed. The parameters that provide the best performance were determined in a shorter time using GA, which includes natural selection and genetic processes instead of a trial-and-error method. The study employed five metrics—Mean Square Error (MSE), Root Mean Square Error (RMSE), Normalized Root Mean Square Error (NRMSE), Mean Absolute Error (MAE), and Squared Correlation (R²)—to evaluate prediction accuracy. Predictions based on NASA experimental data were compared with the existing literature, demonstrating superior accuracy. Using 100 training data, 68 data predictions were made with a Root Mean Square Error (RMSE) of 0.1176%. This error rate represents an accuracy level 2.5 times higher than similarly accurate studies in the literature.

In many Wireless Sensor Network (WSN) applications, the location of the nodes in the network is required. A logical method to find Unknown Nodes (UNNs) in the network is to use one or several mobile anchors (MAs) equipped with GPS units moving between UNNs and periodically broadcast their current location. The main challenge at this stage is to design an optimum path to estimate the locations of UNNs as accurately as possible, reach all nodes in the network, and complete the localization process as quickly as possible. This article proposes a new path planning approach for MA-based localization called Nested Hexagon Curves (NHexCurves). The proposed model’s performance is compared with the performance of five existing static path planning models using Weighted Centroid Localization (WCL) and Accuracy Priority Trilateration (APT) localization techniques in the obstacle-presence scenario. With the obstacle-handling trajectories used for the models, the negative impact of the obstacle on the localization is reduced. The proposed model provides full coverage and high localization accuracy in the obstacle-presence scenario. The simulation results show the advantages of the proposed path planning model with the H-curve model over existing schemes.

In this paper, we develop a methodology to obtain medium-order electrical equivalent circuits (ECs) of the thermal behavior of electronic systems. The method combines several elements: 1) the use of detailed finite-element (FE) simulations of steady-state thermal behavior; 2) graph partitioning of FE meshes to decompose the geometry at intermediate levels of detail; and 3) physically guided estimation of the parameters of the EC. To obtain richer training datasets, we also develop a method to include fictitious heat sources inside the FE model. This approach yields modular medium-order models for extensive and complicated geometries, such as a power-electronic chip. Moreover, representing the thermal behavior with an EC enables coupled simulations of electrothermal behavior, which are important in power electronics. We test our algorithms on a multimaterial pole of a dc motor and electronic chip. Excellent agreement in modeling both steady-state and transient behaviors was obtained.