Search Results (111)

In transmission lines, the discharge characteristics of long air gaps significantly influence the design of external insulation. Existing machine learning models for predicting breakdown voltage are typically limited to single gaps and do not account for the combined effects of complex factors. To address this issue, this paper proposes a novel prediction model based on the Improved Sparrow Search Algorithm-optimized XGBoost (ISSA-XGBoost). Initially, a comprehensive dataset of 46-dimensional electric field eigenvalues was extracted for each gap using finite element simulation software and MATLAB. Subsequently, the model incorporated a comprehensive set of input variables, including electric field eigenvalues, gap distance, waveform and polarity of the switching impulse voltage, temperature, relative humidity, and atmospheric pressure. After training, the ISSA-XGBoost model achieved a Mean Absolute Percentage Error (MAPE) of 7.85%, a Root Mean Squared Error (RMSE) of 56.92, and a Coefficient of Determination (R²) of 0.9938, indicating high prediction accuracy. In addition, the ISSA-XGBoost model was compared with traditional machine learning models and other optimization algorithms. These comparisons further substantiated the efficacy and superiority of the ISSA-XGBoost model. Notably, the model demonstrated exceptional performance in terms of predictive accuracy under extreme atmospheric conditions. Full article

The rapid growth of solar photovoltaic (PV) installations worldwide has increased the need for the effective monitoring and maintenance of these vital renewable energy assets. PV systems are crucial in reducing greenhouse gas emissions and diversifying electricity generation. However, they often experience faults and damage during manufacturing or operation, significantly impacting their performance, while thermal infrared imaging provides a promising non-invasive method for detecting common defects such as hotspots, cracks, and bypass diode failures, current deep learning approaches for fault classification generally rely on computationally intensive architectures or closed-source solutions, constraining their practical use in real-time situations involving low-resolution thermal data. To tackle these challenges, we introduce SlantNet, a lightweight neural network crafted to classify thermal PV defects efficiently and accurately. At its core, SlantNet incorporates an innovative Slant Convolution (SC) layer that utilizes slant transformation to enhance directional feature extraction and capture subtle thermal gradient variations essential for fault detection. We complement this architectural advancement with a thermal-specific image enhancement augmentation strategy that employs adaptive contrast adjustments to bolster model robustness under the noisy and class-imbalanced conditions typically encountered in field applications. Extensive experimental validation on a comprehensive solar panel defect detection benchmark dataset showcases SlantNet’s exceptional performance. Our method achieves a 95.1% classification accuracy while reducing computational overhead by approximately 60% compared to leading models. Full article

Artificial intelligence (AI) models have demonstrated their capabilities across various fields by performing tasks that are currently handled by humans. However, the training of these models faces several limitations, such as the need for sufficient data. This study proposes the use of acoustic signals as training data as this method offers a simpler way to obtain a large dataset compared to traditional approaches. Acoustic signals contain valuable information about the process behavior. We investigated the ability of extracting useful features from acoustic data expecting to predict labels separately by a multilabel classifier rather than as a multiclass classifier. This study focuses on electrical discharge turning (EDT) as a hybrid process of electrical discharge machining (EDM) and turning, an intricate process with multiple influencing parameters. The sounds generated during EDT were recorded and used as training data. The sounds underwent preprocessing to examine the effects of the parameters used for feature extraction prior to feeding the data into the ANN model. The parameters investigated included sample rate, length of the FFT window, hop length, and the number of mel-frequency cepstral coefficients (MFCC). The study aimed to determine the optimal preprocessing parameters considering the highest precision, recall, and F1 scores. The results revealed that instead of using the default set values in the python packages, it is necessary to investigate the preprocessing parameters to find the optimal values for the maximum classification performance. The promising results of the multi-label classification model depicted that it is possible to detect various aspects of a process simultaneously receiving single data, which is very beneficial in monitoring. The results also indicated that the highest prediction scores could be achieved by setting the sample rate, length of the FFT window, hop length, and number of MFCC to 4500 Hz, 1024, 256, and 80, respectively. Full article

An ocean target electric field signal is an effective approach for analyzing the ocean environment and is widely used for detecting ocean targets, extracting their features, and tracking them. Low-frequency analysis and recording (LOFAR) is a commonly used time–frequency analysis tool that provides the time–frequency spectrum of a signal; however, its reliance on the Fourier transform (FT) results in a low frequency resolution and signal-to-noise ratio (SNR), which limits its target detection capabilities. To address this problem, we propose a method called low-frequency analysis and recording based on basis pursuit (LOFAR-BP) for analyzing and detecting ocean target electric field signals. LOFAR-BP uses basis pursuit (BP) with the L1 norm for frequency analysis, whereas LOFAR utilizes the FT. We demonstrate that the FT is the L2 norm mathematically. LOFAR-BP generates the time–frequency spectrum in the same way that LOFAR does. By extracting characteristic values from the time–frequency spectrum, targets can be detected using an appropriate threshold. Both simulation and ocean experiments showed that LOFAR-BP effectively enhances target signals and suppresses noise. Compared with LOFAR, LOFAR-BP improved the frequency resolution by 60% in both experiments and increased the SNR by 54.82 dB in the simulation experiment and by 39.59 dB in the ocean experiment. When applied to target detection, LOFAR-BP can detect targets 6 s earlier than LOFAR can. Full article

In this paper, the Efficient Channel Attention (ECA) mechanism is incorporated at the terminal layer of the YOLOv10 backbone network to enhance the feature expression capability. In addition, Transformer is introduced into the C3 module in the feature extraction process to construct the C3TR module to replace the original C2F module as the deepening network extraction module. In this study, both the ECA mechanism and the self-attention mechanism of Transformer are thoroughly analyzed and integrated into YOLOv10. The C3TR module is used as an important part to deepen the effect of network extraction in backbone network feature extraction. The self-attention mechanism is used to model the long-distance dependency relationship, capture the global contextual information, make up for the limitation of the local sensory field, and enhance the feature expression capability. The ECA module is added to the end of the backbone to globally model the channels of the feature map, distribute channel weights more equitably, and enhance feature expression capability. Extensive experiments on the electrical equipment dataset have demonstrated the high accuracy of the method, with a mAP of 89.4% compared to the original model, representing an improvement of 3.2%. Additionally, the mAP@[0.5, 0.95] reaches 61.8%, which is 5.2% higher than that of the original model. Full article

Tree-related high-impedance faults (THIFs) in medium voltage distribution systems represent a typical fault, especially where an overhead line crosses a forested area. The arc caused by THIFs could ignite nearby combustibles, significantly increasing the risk of forest fires. THIF detection remains a significant challenge because this type of fault has weak characteristics, as the fault impedance can reach hundreds of kΩ. Many previous studies have investigated reducing the risk of wildfires caused by THIFs. This paper reviews the existing literature on THIF modeling, detection, and ignition risk assessment. The modeling focuses on the distinctions and connections among electrical models of tree structures, traditional high-impedance fault (HIF) models, and THIF models. Detailed reviews and comparisons are conducted on THIF detection methods, encompassing fault analysis, fault feature extraction, and fault identification. The experiments and methods for assessing THIF ignition risk are also introduced and discussed. The review reveals critical research gaps. In modeling, there is a lack of frameworks that simultaneously elucidate underlying mechanisms and support detection algorithms. In detection algorithms, the existing methods have not been adequately validated under complex environmental conditions. In ignition risk assessment, current studies do not account for a comprehensive range of influencing variables. Finally, this paper proposes future research directions for THIF, aiming to provide a comprehensive reference for researchers and practitioners in this field. Full article

The transient electromagnetic (TEM) method is a crucial tool for subsurface exploration, providing essential insights into the electrical resistivity structures beneath the Earth’s surface. Traditional forward modeling approaches, such as the finite-difference time-domain (FDTD) method and the finite-element method (FEM), are computationally intensive, limiting their practicality for real-time, high-resolution, or large-scale investigations. To address these challenges, we present Deep-TEMNet, an advanced deep learning framework specifically designed for two-dimensional TEM forward modeling. Deep-TEMNet integrates the U-Net architecture with a tailored two-dimensional long short-term memory (2D LSTM) module, allowing it to effectively capture complex spatial-temporal relationships in TEM data. The U-Net component enables high-resolution spatial feature extraction, while the 2D LSTM module enhances temporal modeling by processing spatial sequences in two dimensions, thereby optimizing the representation of electromagnetic field dynamics over time. Trained on high-fidelity FEM-generated datasets, Deep-TEMNet achieves exceptional accuracy in reproducing electromagnetic field distributions across diverse geological scenarios, with a mean squared error of 0.00000134 and a root mean square percentage error of 0.002373019. The framework offers over 150 times the computational speed of traditional FEMs, with an average inference time of just 3.26 s. Extensive validation across varied geological conditions highlights Deep-TEMNet’s robustness and adaptability, establishing its potential for efficient, large-scale subsurface mapping and real-time data processing. By combining U-Net’s spatial resolution capabilities with the sequential processing strength of the 2D LSTM module, Deep-TEMNet significantly advances computational efficiency and accuracy, positioning it as a valuable tool for geophysical exploration, environmental monitoring, and other applications requiring scalable, real-time TEM analyses that are easily integrated into remote sensing workflows. Full article

Beyond data transmission, antennas have recently been utilized as sensors, offering the advantage of reducing hardware requirements and power consumption compared to systems where sensors are separate from antennas. Patch antennas, in particular, are widely used across various applications, including sensing, due to their attractive features like compact size and conformability. In addition, they can be easily designed in different ways to sense variations in certain variables. Adding a slot to the patch antenna introduces several advantages, including multiband, wideband operation, and improved impedance bandwidth. Slots also provide a concentrated region of electromagnetic fields, which increases the antenna’s sensitivity for sensing and detection purposes. In this paper, a rectangular patch antenna with a cross slot is designed and proposed for water, ice, and frost detection. Detection is achieved by measuring variations in the resonant frequency in response to water, ice accumulation, and frost. The results indicate that the proposed antenna can detect both water and ice accretion with a frequency shift of up to 1.538, 0.358, and 0.056 GHz, respectively, which reflects good sensitivity levels of the antenna. The effect of the slot on strengthening the near electric field and antenna sensitivity is discussed in this paper. The antenna is fabricated and measured and the indicators of each detection scale have been extracted. The proposed antenna has a simple structure and a small size of (40 × 40 × 1.53 m³). In addition, it can be precisely used to sense different environmental parameters such as frost and ice. Thus, it can serve as a strong candidate for detecting natural disasters like frost damage. Furthermore, the findings in this paper offer valuable insights into how the presence and structure of slots influence the sensitivity response of patch antennas, supporting ongoing research in this field. Full article

In this study, we address the critical issue of accurately detecting series AC arc faults, which are often challenging to identify due to their small fault currents and can lead to devastating electrical fires. We propose an intelligent diagnosis method based on the extreme learning machine (ELM) model to enhance detection accuracy and real-time monitoring capabilities. Our approach involves collecting high-frequency current signals from 23 types of loads using a self-developed AC series arc fault data acquisition device. We then extract 14 features from both the time and frequency domains as candidates for arc fault diagnosis, employing a random forest to select the most significantly changed features. Finally, we design an ELM classifier for series arc fault diagnosis, achieving an identification accuracy of 99.00% ± 0.26%. Compared to existing series arc fault diagnosis methods, our ELM-based method demonstrates superior recognition performance. This study contributes to the field by providing a more accurate and efficient diagnostic tool for series AC arc faults, with broad implications for electrical safety and fire prevention. Full article

Surface electromyography (sEMG) signals reflect the local electrical activity of muscle fibers and the synergistic action of the overall muscle group, making them useful for gesture control of myoelectric manipulators. In recent years, deep learning methods have increasingly been applied to sEMG gesture recognition due to their powerful automatic feature extraction capabilities. sEMG signals contain rich local details and global patterns, but single-scale convolutional networks are limited in their ability to capture both comprehensively, which restricts model performance. This paper proposes a deep learning model based on multi-scale feature fusion—MS-CLSTM (MS Block-ResCBAM-Bi-LSTM). The MS Block extracts local details, global patterns, and inter-channel correlations in sEMG signals using convolutional kernels of different scales. The ResCBAM, which integrates CBAM and Simple-ResNet, enhances attention to key gesture information while alleviating overfitting issues common in small-sample datasets. Experimental results demonstrate that the MS-CLSTM model achieves recognition accuracies of 86.66% and 83.27% on the Ninapro DB2 and DB4 datasets, respectively, and the accuracy can reach 89% in real-time myoelectric manipulator gesture prediction experiments. The proposed model exhibits superior performance in sEMG gesture recognition tasks, offering an effective solution for applications in prosthetic hand control, robotic control, and other human–computer interaction fields. Full article

This paper presents a new approach in the field of probability-informed machine learning (ML). It implies improving the results of ML algorithms and neural networks (NNs) by using probability models as a source of additional features in situations where it is impossible to increase the training datasets for various reasons. We introduce connected mixture components as a source of additional information that can be extracted from a mathematical model. These components are formed using probability mixture models and a special algorithm for merging parameters in the sliding window mode. This approach has been proven effective when applied to real-world time series data for short- and medium-term forecasting. In all cases, the models informed by the connected mixture components showed better results than those that did not use them, although different informed models may be effective for various datasets. The fundamental novelty of the research lies both in a new mathematical approach to informing ML models and in the demonstrated increase in forecasting accuracy in various applications. For geophysical spatiotemporal data, the decrease in Root Mean Square Error (RMSE) was up to $27.7\%$, and the reduction in Mean Absolute Percentage Error (MAPE) was up to $45.7\%$ compared with ML models without probability informing. The best metrics values were obtained by an informed ensemble architecture that fuses the results of a Long Short-Term Memory (LSTM) network and a transformer. The Mean Squared Error (MSE) for the electricity transformer oil temperature from the ETDataset had improved by up to $10.0\%$ compared with vanilla methods. The best MSE value was obtained by informed random forest. The introduced probability-informed approach allows us to outperform the results of both transformer NN architectures and classical statistical and machine learning methods. Full article

In the context of digitization and automation, extracting relevant information from business documents remains a significant challenge. It is typical to rely on machine-learning techniques to automate the process, reduce manual labor, and minimize errors. This work introduces a new model for extracting key values from electricity invoices, including customer data, bill breakdown, electricity consumption, or marketer data. We evaluate several machine learning techniques, such as Naive Bayes, Logistic Regression, Random Forests, or Support Vector Machines. Our approach relies on a bag-of-words strategy and custom-designed features tailored for electricity data. We validate our method on the IDSEM dataset, which includes 75,000 electricity invoices with eighty-six fields. The model converts PDF invoices into text and processes each word separately using a context of eleven words. The results of our experiments indicate that Support Vector Machines and Random Forests perform exceptionally well in capturing numerous values with high precision. The study also explores the advantages of our custom features and evaluates the performance of unseen documents. The precision obtained with Support Vector Machines is 91.86% on average, peaking at 98.47% for one document template. These results demonstrate the effectiveness of our method in accurately extracting key values from invoices. Full article

Substations, as critical nodes for power transmission and distribution, play a pivotal role in ensuring the stability and security of the entire power grid. With the ever-increasing demand for electricity and the growing complexity of grid structures, traditional manual inspection methods for substations can no longer meet the requirements for efficient and safe operation and maintenance. The advent of automated inspection systems has brought revolutionary changes to the power industry. These systems utilize advanced sensor technology, image processing techniques, and artificial intelligence algorithms to achieve real-time monitoring and fault diagnosis of substation equipment. Among these, the recognition of cable-to-terminal connection relationships is a key task for automated inspection systems, and its accuracy directly impacts the system’s diagnostic capabilities and fault prevention levels. However, traditional methods face numerous limitations when dealing with complex power environments, such as inadequate recognition performance under conditions of significant perspective angles and geometric distortions. This paper proposes a cable-to-terminal connection relationship recognition method based on the YOLOv8-pose model. The YOLOv8-pose model combines object detection and pose estimation techniques, significantly improving detection accuracy and real-time performance in environments with small targets and dense occlusions through optimized feature extraction algorithms and enhanced receptive fields. The model achieves an average inference time of 74 milliseconds on the test set, with an accuracy of 92.8%, a recall rate of 91.5%, and an average precision mean of 90.2%. Experimental results demonstrate that the YOLOv8-pose model performs excellently under different angles and complex backgrounds, accurately identifying the connection relationships between terminals and cables, providing reliable technical support for automated substation inspection systems. This research offers an innovative solution for automated substation inspection systems, with significant application prospects. Full article

Electric vehicle accidents on the road occur frequently, and head injuries are often the cause of serious casualties. However, most electric vehicle riders seldom wear helmets. Therefore, combining target detection algorithms with road cameras to intelligently monitor helmet-wearing has extremely important research significance. Therefore, a helmet-wearing detection algorithm based on the improved YOLOv8n model, PRE-YOLO, is proposed. First, we add small target detection layers and prune large target detection layers. The sophisticated algorithm considerably boosts the effectiveness of data manipulation while significantly reducing model parameters and size. Secondly, we introduce a convolutional module that integrates receptive field attention convolution and CA mechanisms into the backbone network, enhancing feature extraction capabilities by enhancing attention weights within both channel and spatial aspects. Lastly, we incorporate an EMA mechanism into the C2f module, which strengthens feature perception and captures more characteristic information while maintaining the same model parameter size. The experimental outcomes indicate that in comparison to the original model, the proposed PRE-YOLO model in this paper has improved by 1.3%, 1.7%, 2.2%, and 2.6% in terms of precision P, recall R, mAP@0.5, and mAP@0.5:0.95, respectively. At the same time, the number of model parameters has been reduced by 33.3%, and the model size has been reduced by 1.8 MB. Generalization experiments are conducted on the TWHD and EBHD datasets to further verify the versatility of the model. The research findings provide solutions for further improving the accuracy and efficiency of helmet-wearing detection on complex traffic roads, offering references for enhancing safety and intelligence in traffic. Full article

As electric vehicles (EVs) are becoming more common and the need for sustainable energy practices is growing, better management of EV charging station loads is a necessity. The simple act of folding renewable power from solar or wind in an EV charging system presents a huge opportunity to make them even greener as well as improve grid resiliency. This paper proposes an innovative EV charging station energy consumption forecasting approach by incorporating integrated renewable energy data. The optimization is achieved through the application of SARLDNet, which enhances predictive accuracy and reduces forecast errors, thereby allowing for more efficient energy allocation and load management in EV charging stations. The technique leverages comprehensive solar and wind energy statistics alongside detailed EV charging station utilization data collected over 3.5 years from various locations across California. To ensure data integrity, missing data were meticulously addressed, and data quality was enhanced. The Boruta approach was employed for feature selection, identifying critical predictors, and improving the dataset through feature engineering to elucidate energy consumption trends. Empirical mode decomposition (EMD) signal decomposition extracts intrinsic mode functions, revealing temporal patterns and significantly boosting forecasting accuracy. This study introduces a novel stem-auxiliary-reduction-LSTM-dense network (SARLDNet) architecture tailored for robust regression analysis. This architecture combines regularization, dense output layers, LSTM-based temporal context learning, dimensionality reduction, and early feature extraction to mitigate overfitting. The performance of SARLDNet is benchmarked against established models including LSTM, XGBoost, and ARIMA, demonstrating superior accuracy with a mean absolute percentage error (MAPE) of 7.2%, Root Mean Square Error (RMSE) of 22.3 kWh, and R² Score of 0.87. This validation of SARLDNet’s potential for real-world applications, with its enhanced predictive accuracy and reduced error rates across various EV charging stations, is a reason for optimism in the field of renewable energy and EV infrastructure planning. This study also emphasizes the role of cloud infrastructure in enabling real-time forecasting and decision support. By facilitating scalable and efficient data processing, the insights generated support informed energy management and infrastructure planning decisions under dynamic conditions, empowering the audience to adopt sustainable energy practices. Full article