e-Prime - Advances in Electrical Engineering, Electronics and Energy最新文献

{"title":"Occluded face recognition using optimum features based on efficient preprocessing and machine learning","authors":"Rajesh H. Khobragade ,&nbsp;Dinesh B. Bhoyar ,&nbsp;Ajay Paithane ,&nbsp;Suresh Kurumbanshi","doi":"10.1016/j.prime.2025.101015","DOIUrl":"10.1016/j.prime.2025.101015","url":null,"abstract":"<div><div>Face occlusion is a major challenge for today’s face recognition system. The occlusions included in current datasets are pose, illumination, age, expressions, and natural and artificial obstacles over the face and extend to 40 such difficulties. The performance of even a robust system would fail when the occluded area is large as compared to the un-occluded region. We extracted traditional features based on an efficient preprocessing mechanism and classified them using machine learning over scarce datasets. The preprocessing stage involves obtaining two sets of images based on contrast correction and anisotropic filtering and then averaging them. Optimum quality features are then extracted from the mean color and grayscale image using diverse descriptors such as Gabor, Linear Binary Patterns based on Haar Wavelet components, Histogram of Gaussian features, Statistical global features based on first order, wavelet components, and color histograms. The proposed work outperforms state of art techniques concerning classification accuracy obtained using Support Vector Machine.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101015"},"PeriodicalIF":0.0,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A transfer learning-based graph convolutional network for dynamic security assessment considering loss of synchronism of wind turbines and unknown faults","authors":"Sasan Azad ,&nbsp;Mohammad Taghi Ameli ,&nbsp;Amjad Anvari-Moghaddam ,&nbsp;Miadreza Shafie-khah","doi":"10.1016/j.prime.2025.101012","DOIUrl":"10.1016/j.prime.2025.101012","url":null,"abstract":"<div><div>Pre-fault dynamic security assessment (DSA) is essential for the safe operation of power systems. Pre-fault DSA methods that utilize deep learning techniques have been successfully implemented and have shown promising results. However, these methods face challenges in real power systems, such as unknown faults and the increasing integration of power electronics-based units. Adding these units changes the system dynamics and introduces new stability problems, such as the loss of synchronism that current methods cannot analyze. In practical applications, new faults may arise that are not present in the training database, which can decrease the accuracy of the online DSA model. To tackle these challenges, this paper introduces a new dynamic security index that considers the effects of loss of synchronism in power electronics-based units on DSA. Also, a graph convolutional network (GCN)-based model is developed to improve DSA accuracy by incorporating the topological information of the power system in the form of an adjacency matrix. To address the issue of unknown faults, this paper uses transfer learning based on full fine-tuning to adapt a pre-trained GCN model to a different but related unknown fault. This approach eliminates the need for a large number of labeled examples for new faults and ensures efficient transfer of the model to new faults with a small database. Case studies are conducted on a modified IEEE 39-bus system to investigate the impact of power electronics-based units' penetration on dynamic security and the model's ability to transfer knowledge for unknown faults. The results from various evaluation indicators demonstrate the effectiveness of the proposed model.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101012"},"PeriodicalIF":0.0,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging Bayesian optimization and multilayer artificial neural network (MLANN) for fault prediction in oil-immersed transformers","authors":"Elahe Moradi","doi":"10.1016/j.prime.2025.101013","DOIUrl":"10.1016/j.prime.2025.101013","url":null,"abstract":"<div><div>Power transformers are crucial and high-cost equipment for the reliability and continuity of electrical systems. Consequently, regularly monitoring transformers to predict faults early based on existing parameters, is critical. The most common and well-known analysis method for fault prediction in power transformers is dissolved gas analysis, which measures the concentration of gases in the transformer oil. This research leverages a deep learning approach based on a multilayer artificial neural network with a Bayesian optimization method to enhance the accuracy of fault prediction on the dissolved gas analysis data. Following data preprocessing, which included imputation of missing values and normalization, the dissolved gas analysis dataset was divided into training, validation, and testing sets with 70 %, 15 %, and 15 % of the data, respectively. The proposed multilayer artificial neural network model, optimized using the Bayesian optimization method, achieved an outstanding accuracy of 97.99 %, pointedly outperforming benchmark machine learning classifiers. Furthermore, the model demonstrated superior performance across multiple evaluation criteria, including sensitivity, F1-score, G-mean, and Matthews Correlation Coefficient, ensuring a comprehensive assessment of predictive effectiveness. All simulations and evaluations were conducted using Python software, leveraging frameworks such as TensorFlow, Keras, Scikit-learn, Pandas, and NumPy to ensure efficient implementation. The Findings indicate that the multilayer artificial neural network classifier, which leverages the Bayesian optimization method, outperformed state-of-the-art techniques in fault prediction of oil-immersed transformers.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101013"},"PeriodicalIF":0.0,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data-driven modelling of a commercial cold storage system using subspace system identification","authors":"Adesola Temitope Bankole,&nbsp;Muhammed Bashir Mu’azu,&nbsp;Habeeb Bello-Salau,&nbsp;Zaharuddeen Haruna","doi":"10.1016/j.prime.2025.101011","DOIUrl":"10.1016/j.prime.2025.101011","url":null,"abstract":"<div><div>This study presents subspace system identification of a cold storage system incorporating external temperature as input. The proposed model presents a holistic view of the whole system with each subsystem cohesively linked together. A high-fidelity simulation benchmark model of a supermarket refrigeration system from Aalborg University, Denmark was modified by removing open display cases due to their inefficient operation. The modified benchmark model consists of a cold storage room represented as a closed display case, the suction manifold and the compressor rack. A fourteen-day outdoor temperature between 8.9 °C and 32.8 °C that depicts the temperature of a tropical climate was extracted from a weather profile for Phoenix, Arizona, USA to simulate realistic outdoor temperature for the modified model to generate synthetic data for the estimation and validation of a linear state-space model. The data of the expansion valve, suction pressure, compressor capacity, heat transfer rate and the ambient temperature were taken as inputs while the data of the air and goods temperatures were taken as outputs to achieve a holistic picture of the entire system. Results show that the best identified model has a goodness of fit of 98.66 % and 90.42 % for both outputs, final prediction error of 4.11e-15 and mean square error of 0.0005660. It also has a model order of 7, thereby giving the best trade-off between accuracy and complexity. The proposed model is stable, robust and suitable for testing linear control algorithms.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101011"},"PeriodicalIF":0.0,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative study of feedback linearization control for IM taking into account magnetic saturation effects","authors":"Mustapha Es-Semyhy ,&nbsp;Abdellfattah Ba-Razzouk ,&nbsp;Mustapha El haroussi ,&nbsp;Abdelilah Hilali","doi":"10.1016/j.prime.2025.101008","DOIUrl":"10.1016/j.prime.2025.101008","url":null,"abstract":"<div><div>This study examines how the nonlinear characteristics of the magnetic core, where the magnetic material in an induction machine (IM) exhibits a nonlinear relationship between magnetizing current and resulting flux, affect the performance of control systems. In typical IM operation, these nonlinearities lead to noticeable changes in inductance values, complicating accurate flux estimation. To address this, we develop a nonlinear observer (NLO) that explicitly incorporates the effects of the magnetic core's nonlinearity for rotor flux estimation. The observer gain is designed using a Lyapunov stability framework to ensure exponential convergence of the estimation error under varying flux conditions. This approach is compared with a conventional full-order Luenberger observer (LO) that assumes a simple, linear magnetization characteristic. Within the FOC framework, two feedback linearization strategies are evaluated. The FL sat takes into account the non-linear variations in machine inductances caused by saturation, enabling a more accurate representation of IM dynamics. However, this approach is more complex to calculate because of the nonlinear terms. The FL unsat simplifies control design by neglecting the effects of magnetic saturation, thus reducing computational requirements. Despite its simplified structure, FL unsat delivers comparable performance over the nominal speed and flux operating range. The results highlight a trade-off between dynamic modeling fidelity and control accuracy, offering valuable insights for the design of controllers and observers for IM. While FL sat is well suited to scenarios requiring high accuracy and dynamic tracking, FL unsat emerges as a pragmatic alternative for applications favoring simplicity and real-time implementation. Quantitative measurements further support these results: under constant resistances, the proposed NLO achieves an absolute integral error (IAE) of 0.0133 in rotor magnetization current tracking compared to 1.026 with LO, underlining the robustness and accuracy advantages of explicit magnetic saturation modeling.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101008"},"PeriodicalIF":0.0,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143908237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Single source switched capacitor boosting nine-level inverter for PV applications","authors":"Lakshmi Prasanna ,&nbsp;T.R. Jyothsna ,&nbsp;Allam Venkatesh ,&nbsp;CH. Nayak bhukya","doi":"10.1016/j.prime.2025.101009","DOIUrl":"10.1016/j.prime.2025.101009","url":null,"abstract":"<div><div>Switched-Capacitor-Based Multilevel Inverters (SCMLIs) are evaluated using a \"cost function\" (CF) that takes into consideration important factors such the number of devices, total standing voltage (TSV), and source demands. In this study, a nine-level inverter is constructed to improve its boosting capabilities while minimizing its CF value and switch count. The proposed SCMLI uses a single DC source and two capacitors to achieve a voltage boosting of four. Peak Inverse Voltage (PIV) is lower than the output voltage peak amplitude for all working switches. Using a level-shifted pulse width modulation technique, the suggested architecture is examined. First, the performance of the suggested design is examined using MATLAB/Simulink simulations that allow for various kinds of parameter variations. It also takes into account the design of switching capacitors and the assessment of device power losses. PLECS software based thermal modelling is used to evaluate efficiency and power losses. The enhanced performance of the proposed structure in addressing key areas is demonstrated by a detailed comparative examination of existing topologies. Following that, hardware-in-loop (HIL) tests are carried out to validate the feasibility of the study and the functionality of the suggested topology.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101009"},"PeriodicalIF":0.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of multiple faults in induction motor using machine learning techniques","authors":"Puja Pohakar ,&nbsp;Ravi Gandhi ,&nbsp;Surender Hans ,&nbsp;Gulshan Sharma ,&nbsp;Pitshou N. Bokoro","doi":"10.1016/j.prime.2025.101007","DOIUrl":"10.1016/j.prime.2025.101007","url":null,"abstract":"<div><div>Studying simultaneous faults in three-phase induction motors guarantees reliability, reduces unplanned downtime, and minimizes maintenance expenses in industrial settings. Induction motors have concurrent faults, including stator winding, rotor faults, unbalanced voltages, load fluctuations, and overvoltages. These make fault diagnosis difficult and can result in disastrous failures if not detected. Traditional diagnostic methods are expert judgment-based and pre-threshold-based and, therefore, less efficient when dealing with vast industrial processes. Based on key operating parameters like voltage, current, and speed, this article describes how machine learning (ML) algorithms like Random Forest (RF), K-Nearest Neighbors (KNN), Gradient Boosting Machine (GBM), Support Vector Machines (SVM), and Extreme Gradient Boosting with Feature Interaction (XGBoost + FIS) are used to detect different motor faults. Due to their limits, machine learning algorithms outperform traditional methods in real-time fault diagnosis, predictive maintenance, and multi-fault categorization. Through ensemble learning and feature selection, the models cope well with big data sets with enhanced fault classification accuracy and robustness against noise. In addition, ML fault analysis minimizes reliance on human experience and presents a computerized, scalable industrial motor condition monitoring method. Experimental outcomes show that excellent classification accuracy is achieved in ML models; hence, active maintenance and effective motor operation are feasible. The outcomes point to the potential of AI-based predictive maintenance to enhance safety, energy efficiency, and process continuity in industrial applications. Traditional fault detection methods rely on pre-established thresholds or expert-provided rules and may not perform effectively for concurrent multiple faults. In order to surpass these limitations, a new approach by using state-of-the-art machine learning algorithms such as Extreme Gradient Boosting (XGBoost) combined with Fuzzy Inference Systems (FIS) presents a new perspective towards improved accuracy and comprehensibility in fault detection. This method takes advantage of the ability of XGBoost to learn intricate relationships and utilizes FIS's rule-based reasoning for explainability. The incorporation of FIS in XGBoost enhances the precision of fault classification, handles uncertainty, and encourages interpretability.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101007"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inverted-L wideband quad-port MIMO antenna with intersecting strip parasitic for 5G new radio (n77) network systems","authors":"Phakpoom Sritongnuan ,&nbsp;Phatsakul Thitimahatthanakusol ,&nbsp;Nathapat Supreeyatitikul ,&nbsp;Jessada Konpang","doi":"10.1016/j.prime.2025.101006","DOIUrl":"10.1016/j.prime.2025.101006","url":null,"abstract":"<div><div>This research proposes a minimized-coupling and simplified inverted-L quad-port multiple-input-multiple-output (MIMO) antenna designed for 5G (n77) applications. The proposed antenna is distinguished using the characteristic mode (CM) technique, providing a unique method to analyze and optimize the antenna performance. The antenna is fabricated on a single-layer FR-4 substrate, with the upper layer consisting of a quad-port inverted-L monopole antenna and the lower layer featuring a partial ground plane. Key insights from the CM-based analysis reveal strong coupling between Ports 1&amp;3 and 2&amp;4, primarily driven by Modes 3 and 4. To mitigate this coupling, two pairs of intersecting strip parasitics are located at the center of the upper layer, serving as isolators. This design innovation is a key contribution of the research, offering an effective solution to enhance port isolation. Simulated models of the MIMO antenna were developed, and a prototype was fabricated and experimentally tested. The measured reflection coefficient at 3.5 GHz is 50 % (2.75–4.5 GHz), with a maximum gain of 4.5 dBi at 3 GHz. The antenna achieves port isolation greater than 15 dB, and the measured performance metrics include envelope correlation coefficient (ECC ≤ 0.05), diversity gain (DG ≥ 9.90 dB), mean effective gain (MEG ≤ -3 dB), total active reflection coefficient (TARC &lt; -15 dB), and channel capacity loss (CCL &lt; 0.5 dB). The novelty of this research lies in the effective use of intersecting strip parasitics to reduce coupling in the inverted-L quad-port MIMO antenna, demonstrating its potential for high-performance 5G NR (n77) applications.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101006"},"PeriodicalIF":0.0,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computer vision-based location-aware antenna system for 5G applications","authors":"Irshad Ali T K ,&nbsp;Ansal K A ,&nbsp;Sumitha Mathew ,&nbsp;Rashida K","doi":"10.1016/j.prime.2025.101004","DOIUrl":"10.1016/j.prime.2025.101004","url":null,"abstract":"<div><div>This article introduces an advanced location-aware antenna system that uses computer vision technology to monitor the real-time positions of potential users, terminals, or individuals within a given area. The system incorporates a machine learning-based computer vision algorithm, specifically the You Only Look Once (YOLO) model, and an optimisation technique for analysing visual data. This method identifies and extracts positional coordinates for potential users, allowing the antenna system—mounted on a rotating assembly—to adjust its orientation and accurately direct its beam toward the target objects determined by the algorithm. A rotated square patch antenna is designed to operate at dual frequencies of 3.7 GHz and 5.5 GHz within the sub-6 GHz range. A four-element Multi-Input, Multi-Output (MIMO) antenna is developed without additional decoupling structures, printed on an FR4 substrate of dimension 80 × 80 × 1.6 mm³. The performance metrics of the MIMO antennas demonstrate promising results, with isolation between elements exceeding 28 dB, an Envelope Correlation Coefficient (ECC) of less than 0.05, a Total Active Reflection Coefficient (TARC) below -10 dB, and the ratio of Mean Effective Gain (MEG) consistently within the specified range. This compliance indicates that the antennas can provide excellent diversity performance, which enhances signal reliability and overall communication quality. The proposed system significantly enhances wireless communication by effectively reducing interference, improving signal quality, and extending coverage range. These improvements contribute to a more reliable and efficient communication experience.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101004"},"PeriodicalIF":0.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143911963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and implementation of an ultra-high gain, soft-switching, bidirectional dc-dc converter with high efficiency","authors":"Mahdi Madadi ,&nbsp;Mostafa Jazaeri ,&nbsp;Hamed Molla-Ahmadian","doi":"10.1016/j.prime.2025.101002","DOIUrl":"10.1016/j.prime.2025.101002","url":null,"abstract":"<div><div>This paper introduces a novel ultra-high gain bidirectional design for a DC-DC converter, which integrates a high-gain interleaved DC-DC converter with a dual active half-bridge (DAHB) using a coupled inductor. The design offers several significant advantages, including high voltage gain, bidirectional power flow, and soft switching to reduce power losses. The voltage gain is higher compared to the competitors, making it particularly effective in renewable energy conversion systems. Furthermore, it maintains continuous current on the high-current (low-voltage) side, thereby improving power quality and potentially eliminating the need for additional filters in industrial applications. The use of an interleaved controller further reduces current ripple, enhancing overall power quality. In order to verify the proposed topology and also evaluate the performance and reliability of the design, a 300 W laboratory prototype is developed. The behavior of the open-loop control system in step-up mode is comprehensively analyzed and the results are presented.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101002"},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}