Recent Advances in Electrical & Electronic Engineering - Volume 18, Issue 3, 2025

The image processing technology-can be adopted in the power transmission incident detection system, when it is combined with artificial intelligence and machine learning academic knowledge of power transmission surveillance video analysis system, it can automatically detect abnormal objects in the power transmission system. It can quickly and accurately detect abnormal objects, known as environmental object feature detection necessary for the safety of power transmission system.

In order to improve the object detection ability of the power transmission system, it adopts artificial intelligence and machine learning knowledge in the power transmission surveillance system and it can automatically detect abnormal events or objects.

Compared with differential binary target detection technique, it proposes a new adaptive background subtraction threshold algorithm to adapt the complex power transmission monitoring environment. Meanwhile, it takes special recognition algorithm for power transmission monitoring environment to ensure the accuracy and stability of the detection system.

The proposed method can be used in the monitoring system and the accuracy and stability of the detection system have been verified through experiments.

Through adopting the special recognition algorithm for power transmission monitoring environment, it can ensure the accuracy and stability of the detection system, in the detection experiments, it can analyze the objects more easily than before.

The rise of ultra-high voltage AC grids creates corona noise, which is crucial for assessing transmission line environments.

This paper analyzes corona noise distribution around AC transmission lines using a 3D model for quantitative assessment. We employ the Finite Element Method, and factors like electric field intensity, conductor splitting, and sag are considered. Corona noise is calculated using CEPRI prediction equations and validated with field data.

We found strong corona noise concentrating within a 20 m lateral and 240 m vertical radius. Within 50 m, lateral attenuation is 3.6%, and longitudinal attenuation is 3.3%.

This research provides insights for monitoring and controlling corona noise in transmission line design and operation.

The accurate locating of fault sections in a distribution network can lay an effective foundation for the rapid processing of faults. However, the waveform of high-resistance grounding faults is relatively weak, which increases the difficulty of fault feature extraction and localization. In addition, the complex operating conditions and interference factors of the actual distribution network can affect the fault section localization method, leading to incorrect location problems.

In order to overcome the limitations of existing fault section localization methods on fault resistance values and application scenarios, a fault section localization method for distribution networks based on synchronous phasor measurement is proposed in this paper.

Firstly, the transient zero sequence equivalent network of single-phase to ground faults in the distribution network is analyzed, revealing the differences in zero-sequence current within different sections of the faulty line. At the same time, based on the zero-sequence current waveform recorded by the waveform measurement device in actual distribution network, the characteristics of the waveform in different sections in the time and frequency domains are analyzed. Furthermore, a fault feature extraction method based on wavelet packet transform is proposed to construct fault differential features for different sections. Then, the grey correlation analysis method is adopted to calculate the correlation coefficients between different sections to construct locating criteria, thereby achieving accurate locating of fault sections in distribution network.

The experimental results using field data indicate that the localization accuracy can reach 98.90%, and the calculation time is about 102.65 ms, which has high localization accuracy and localization efficiency.

Through analysis and relevant experiments, it is concluded that the proposed method can accurately locate faults in actual distribution networks, and still has correct locating results for high resistance grounding faults. The effectiveness of the method has been verified.

Linear fractional differential equations of the commensurable order, specifically those related to fractional trigonometry, pose challenges in terms of analytical solutions.

The purpose of this article is to present a novel approximate analytical technique to solve linear fractional differential equations of the commensurable order, which are related to fractional trigonometry. This method is used to obtain approximate solutions by forming linear combinations of appropriate fractional basic functions, for which Laplace transforms are irrational functions. This approximation technique enables us to represent these functions using time-invariant linear system models. Also, the implementation of analog circuits of these basic fractional order systems can be obtained using approximation of rational functions.

The research demonstrates the efficacy and precision of this method through illustrative examples, showcasing its effectiveness in solving linear fractional systems.

The newly introduced approximate analytical method presents a promising approach to solving linear fractional differential equations of the commensurable order, providing accurate solutions and possibly offering applications in various fields.

Breast cancer (BRCA) is the most frequently diagnosed cancer in women, with a rise in occurrences and fatalities. The field of BRCA prediction and diagnosis has witnessed significant advancements in recent years, particularly emphasizing enhanced computer-aided digital imaging techniques, and has emerged as a powerful ally in the prediction of BRCA through histopathology image analysis. A number of approaches have been suggested in recent years for the categorization of histopathology BRCA images into benign and malignant as it examines the images at cellular level. The histopathology slides must be manually analysed which is time consuming and tiresome and is prone to human error. Additionally, different laboratories occasionally have different interpretation of these images.

This paper focuses on implementing a framework for Computer-Aided digital imaging technique that can serve as a decision support. With recent advancements in computing power the analysis of BRCA histopathology image samples has become easier. Stain normalization (SN), segmentation, feature extraction and classification are the steps to categorize the cancer into benign and malignant. Nuclei segmentation is a crucial step that needs to be taken into account in order to establish malignancy. These are considered essential for early diagnosis of BRCA. A unique method proposed for BRCA prediction is put forward. To maximize the prediction accuracy, the suggested method is integrated with machine learning (ML) techniques and clinical data is used to evaluate the suggested approach.

This strategy is adaptable to many cancer types and imaging techniques. The suggested technique is applied to clinical data and is integrated with logistic regression and K-Nearest Neighbor resulting in accuracy of 92.10% and 86.89% respectively for BRCA histopathology images.

The objective of this work is to validate the proposed model which takes input as feature pattern for a given label. For the collected clinical samples, the model is able to classify the input as benign or malignant. The proposed model worked efficiently for different BC datasets and performed classification task successfully. Integrating mathematical model (MM) with ML model for interpreting histopathology BRCA is a potential area of research in the field of digital pathology.

The global transition to green energy and the rapid development of Electric Vehicle (EV) technology, along with falling component costs, have fueled the growing popularity of electric vehicles. To support the widespread adoption of EVs, an efficient and user-friendly charging infrastructure is crucial.

This work aims to propose a comprehensive EV charging system that addresses the rising demand for charging stations, streamlines the charging process, and empowers EV drivers with essential information. The primary focus is on an economical and effective booking system, enabling users to locate nearby charging stations and make informed choices about their charging preferences.

We suggest developing a EVs Charging Finder App, serving as a central platform for EV users to find nearby charging stations. The app will provide vital details, including ratings, reviews, available time slots, charging duration estimates, and more. Users can also contribute new charging station data, fostering app growth. Additionally, an alert system will notify users when nearby charging slots become available, enhancing convenience for EV drivers.

The EVs Charging Finder App is anticipated to significantly enhance the accessibility and convenience of EV charging. Users can effortlessly locate charging stations, assess quality through reviews and ratings, and plan charging sessions based on real-time availability. The battery voltage of 45.2 V is a critical parameter for monitoring the health and performance of the battery, influencing the accuracy of state of charge (SoC) estimations and potentially impacting the efficiency of the electric vehicle. The 47.7 km driven is a key factor in assessing energy consumption and vehicle efficiency, which can affect the remaining state of charge in the battery. The battery's state of charge (SOC) is at 85%, indicating a relatively high charge level. Knowing that the charging station is available is crucial for planning charging activities, allowing users to proceed without concerns about station availability. The booking time at 10:00 AM is essential for efficiently managing charging infrastructure, especially in scenarios with high demand for charging services. These data points collectively contribute to optimizing the charging experience and ensuring the effective utilization of electric vehicle resources.

The proposed EVs Charging Finder App offers a practical and efficient solution to address the surging demand for charging stations. By providing comprehensive information and real-time alerts, this system aims to make EV charging more accessible, user-friendly, and environmentally sustainable.

Accurate prediction of offshore wind power is the basis for promoting the safe and economic operation of offshore wind farms.

This paper proposes an uncertainty prediction learning model based on outlier processing, synchronous wavelet denoising and attention mechanism optimization to achieve accurate prediction of offshore wind power.

Firstly, the isolated forest is adopted to filter the outliers of offshore wind power data and delete the error data caused by equipment or humans. Secondly, a syn-chrosqueezing wavelet neural network (SWT) is applied to denoise historical wind power data, improve data quality, and lay a foundation for accurate prediction. Next, the offshore wind power prediction method based on IP-SO-LSTM-Attention is constructed to realize offshore wind power prediction, in which the attention mechanism is applied to focus on the influence of important features on the output of offshore wind power, and the improved particle swarm optimization algorithm is adopted to find the best network structure of LSTM-Attention to optimize the prediction effect. After predicting the point prediction results based on the SWT-IPSO-LSTM-Attention model, this paper sets MAPE, RMSE, MAE and other indicators to evaluate the prediction effect.

The prediction error MAPE of the proposed model is 4.12%. It is 63.21% higher than the benchmark model (SWT-BP) and 56.35% higher than the benchmark model (SWT-LSTM).

Based on the point prediction results, this paper uses KDE (Gaussian) prediction results to calculate the out-put curve under different confidence levels and provides decision-making reference information for accurate decision-making.

Circular antenna arrays are widely used in 5G, IoT, and beamforming applications of next-generation communications, however attaining the subsidiary lobes along with directivity is still a challenge. The array parameters could be estimated in real-time using a variety of standard approaches, but these methods would tends to lag in maintaining appropriate directivity and even a low side lobe level.

To suppress the subsidiary lobe, achieve the required primary lobe direction, and enhance directivity, an optimization problem is applied in this study. Also with the circular antenna array problem, an artificial hummingbird algorithm (AHA) is used to accurately determine the regulating parameters.

Simulations are performed, and the outcomes are analyzed with those achieved using other accepted techniques. The results indicated that the artificial hummingbird technique significantly reduces side lobes while preserving acceptable directivity.

In this work based on the dimensional analysis, it is also possible to achieve high directivity values alongside low side lobe levels using reduced antenna elements.