This paper introduces a novel method that leverages artificial neural networks to estimate magnetic flux density in the proximity of overhead transmission lines. The proposed method utilizes an artificial neural network to estimate the parameters of a mathematical model that describes the magnetic flux density distribution along the lateral profile for various configurations of overhead transmission lines. The training target data is acquired using the particle swarm optimization algorithm. A performance comparison between the proposed method and the Biot-Savart law-based method is conducted using an extensive test dataset. The resulting coefficient of determination and mean square error values demonstrate the successful application of the proposed method for a range of different spatial arrangements of phase conductors. Furthermore, the performance of the proposed method is thoroughly assessed on multiple test cases. The practical relevance of the proposed method is highlighted by contrasting its results with the field measurements obtained in the proximity of a 400 kV overhead transmission line.

This paper introduces a novel chaotic strategy for controlling the acceleration coefficients within the particle swarm optimization (PSO) algorithm. The PSO algorithm with chaotic exponential-based acceleration coefficients is developed to enhance the exploration of the search space and avoid premature convergence, a common issue associated with the standard PSO algorithm. The PSO algorithm with chaotic exponential-based acceleration coefficients is applied to multilevel image thresholding. The attained experimental results demonstrate that the PSO algorithm utilizing the chaotic strategy to control the cognitive and social acceleration coefficients can be successfully utilized for the selection of image thresholds across a variety of images.

Abstract This paper presents an artificial neural network (ANN) based method for overhead lines magnetic flux density estimation. The considered method enables magnetic flux density estimation for arbitrary configurations and load conditions for single-circuit, multi-circuit, and also overhead lines that share a common corridor. The presented method is based on the ANN model that has been developed using the training dataset that is produced by a specifically designed algorithm. This paper aims to demonstrate a systematic and comprehensive ANN-based method for simple and effective overhead lines magnetic flux density estimation. The presented method is extensively validated by utilizing experimental field measurements as well as the most commonly used calculation method (Biot - Savart law based method). In order to facilitate extensive validation of the considered method, numerous magnetic flux density measurements are conducted in the vicinity of different overhead line configurations. The validation results demonstrate that the used method provides satisfactory results. Thus, it could be reliably used for new overhead lines’ design optimization, as well as for legally prescribed magnetic flux density level evaluation for existing overhead lines.

Abstract The methodology for the evaluation of long-term exposure to the overhead line magnetic field is presented, in this paper. The developed methodology is based on the ambient temperature measurements and phase conductors’ height measurements to find a linear regression model to determine phase conductors’ height changes for different ambient temperatures. Based on the overhead transmission line geometry, and datasets about historical overhead line phase current intensity values and ambient temperatures long-term magnetic field exposure can be determined. For magnetic flux density determination, a method based on artificial neural networks is used. The methodology is applied to the case study of overhead line that connect substations Sarajevo 10 and Sarajevo 20. A period of one year is analyzed and magnetic flux density values are determined. The obtained results indicate that during the analyzed period for significant amounts of time magnetic flux density values surpass the recommended values for long-term exposure.

Multilevel image thresholding based on the exhaustive search for the optimal thresholds is computationally expensive. To overcome this drawback this paper investigates the use of the particle swarm optimization (PSO) algorithms with time-varying acceleration coefficients in multilevel image thresholding. Specifically, two multilevel image thresholding methods based on Kapur's entropy and PSO algorithm with time-varying acceleration coefficients are considered. The two methods use different strategies to vary cognitive and social acceleration coefficients within the PSO algorithm. The considered thresholding methods are assessed on five test images. The multilevel image thresholding performance is assessed for varying numbers of thresholds. The performance of the methods under consideration is compared to that of the thresholding method based on the PSO algorithm with constant acceleration coefficients. The experimental results show that the thresholding methods based on the PSO algorithm with time-varying acceleration coefficients can be successfully used to obtain image thresholds across different test images.

The principal challenge addressed in this paper is modifying the standard particle swarm optimization algorithm to achieve improved multilevel image thresholding performance. In this paper, a multilevel image thresholding method that relies on Kapur's entropy and the improved particle swarm optimization algorithm is presented. The improved particle swarm optimization algorithm employs a particular nonlinearly decreasing inertia weight strategy and Gaussian mutation. The performance of the considered multilevel image thresholding method is assessed on five test images. The experimental results demonstrate the successful utilization of the improved particle swarm optimization algorithm for determining image thresholds across different images. This algorithm is shown to enhance the multilevel image thresholding performance over the standard particle swarm optimization algorithm.

In this paper, the multilevel image thresholding methods based on the particle swarm optimization algorithm and different chaotic inertia weight strategies are considered. The performance of each chaotic inertia weight strategy is evaluated using a set of standard test images. Different numbers of image classes are considered. In addition, the paper also considers the multilevel thresholding performance based on commonly employed linear decreasing inertia weight and random inertia weight. All considered multilevel thresholding methods are based on Kapur’s entropy. The experimental results demonstrate that the particle swarm optimization with chaotic inertia weight can be successfully used for multilevel image thresholding.

In this paper, a multilevel thresholding method for image segmentation based on Otsu’s between-class variance and multi-swarm particle swarm optimization algorithm with dynamic learning strategy is presented. The considered multilevel image thresholding method is assessed on various standard test images and for different numbers of thresholds. For each test image and a considered number of thresholds, the mean and the standard deviation of Otsu’s objective function over a number of independent runs are evaluated. The experimental results showcased that this method can be successfully employed in multilevel image thresholding.

This paper presents a comparative analysis of two different natural exponent inertia weight strategies for particle swarm optimization in multilevel image thresholding. The considered multilevel image thresholding methods are based on Otsu’s between class variance. The multilevel thresholding methods are evaluated on different test images and for varying numbers of thresholds. The experimental results have demonstrated that the particle swarm optimization algorithm with the natural exponent inertia weight can be successfully employed to obtain threshold levels for different test images.

This paper presents a multilevel thresholding method based on the multi-swarm particle swarm optimization with dynamic learning strategy and chaotic random inertia weight. This multilevel thresholding method is implemented using Kapur’s entropy. The performance of the presented method is validated on a set of standard test images. For each image and each considered number of threshold levels, the mean and standard deviation of Kapur’s entropy values are determined based on 30 independent applications of the thresholding method. The reported experimental results show that the presented method can be successfully applied across different images.