IEEE Canadian Journal of Electrical and Computer Engineering最新文献

{"title":"An Adaptive Pilot Protection for Wind Farm Transmission Line Employing Multiscale Morphological Gradient","authors":"An Li;Yingjun Zhuo;Siyu Lu;Luliang Zhang;Yujie Zhang;Lingteng Zeng;Baorong Zhou","doi":"10.1109/ICJECE.2026.3716247","DOIUrl":"https://doi.org/10.1109/ICJECE.2026.3716247","url":null,"abstract":"The complex fault-currents and prominent harmonic components of doubly-fed induction generators (DFIGs) pose significant sensitivity and mal-operation risks for traditional pilot protection on long-distance transmission lines. To address these issues, this article proposes a novel adaptive time-domain pilot protection scheme based on multiscale morphological gradients. This method uses morphological gradient with multiscale structural elements for robust fault-current characterization, extracting transient fault current features at both ends of the line, balancing computational efficiency with detailed waveform preservation. Fault detection is achieved through kurtosis of morphological gradients within a sliding window, complemented by an adaptive weighted sum of energy differences criterion to distinguish internal from external faults. The proposed method was validated using a wind farm transmission line model in power systems computer aided design (PSCAD)/electromagnetic transients, including DC (EMTDC). Extensive PSCAD/EMTDC simulations demonstrate that the proposed scheme achieves ultrafast fault detection within 1.5 ms and requires a minimal computational load of only 11 core operations (COps) per data point. Furthermore, by extracting and transmitting only scalar feature values via an adaptive alignment mechanism, it completely eliminates the reliance on strict time synchronization. The energy index maintains a distinct selective margin even under extreme boundary conditions, proving its superior practical reliability for wind farm export lines.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"49 4","pages":"605-616"},"PeriodicalIF":1.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877939","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 Novel Fusion Pipeline of Foundational and Deep Learning Models for Footwear Slip Resistance Evaluation","authors":"Shaghayegh Chavoshian;Michael Brudno;Atena Roshan Fekr","doi":"10.1109/ICJECE.2026.3701534","DOIUrl":"https://doi.org/10.1109/ICJECE.2026.3701534","url":null,"abstract":"Slips and falls remain a major public health concern, especially in winter conditions and among older adults. Using slip resistance footwear is a major factor in reducing slip risk, but this feature is typically assessed in laboratories and is not accessible to the public. In this article, we presented a novel AI-driven pipeline that estimates footwear slip resistance scores directly from the images of outsole. Our approach fused foundational models with domain-adapted deep learning techniques, comprising four core stages: 1) fine-tuned segmentation using segment anything model (SAM) to detect contact regions of the outsole; 2) tile-based material classification using convolutional neural networks (CNNs) and vision transformers (ViTs) trained on a curated dataset of footwear materials; 3) visual overlay construction for interpretability; and 4) multioutput CNN regression to estimate slip resistance scores. We evaluated our system on 150 footwear images with experimentally validated slip resistance scores and achieved a mean absolute percentage error (MAPE) between 18.56% and 31.04%. This work enables accessible, image-based slip risk evaluation and represents a significant step toward AI-powered injury prevention in real-world settings.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"49 4","pages":"592-604"},"PeriodicalIF":1.6,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877946","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":"Permanent Magnet Synchronous Motor Drive Controller With Optimum Regenerative Braking for Electric Vehicles","authors":"P. K. Prathibha;Elizabeth Rita Samuel","doi":"10.1109/ICJECE.2026.3697845","DOIUrl":"https://doi.org/10.1109/ICJECE.2026.3697845","url":null,"abstract":"The proposed work presents the design and implementation of a permanent magnet synchronous motor (PMSM) drive using field-oriented control (FOC) for electric vehicles (EVs), with a detailed evaluation of its regenerative braking capability. Experimental investigations conducted on a 2-kW PMSM test bench demonstrate regenerative power peaks approaching 30 kW, charging currents up to 20 A, and an 18%–22% improvement in recovered braking energy under optimized 60% braking conditions, thereby validating the proposed short-circuit switching strategy (SCSS). The adaptive switching strategy dynamically regulates the braking torque based on the vehicle speed and braking demand, enabling enhanced energy recovery during regenerative braking without the use of additional power converters. The regenerated power is experimentally evaluated across a range of operating speeds; under optimal braking scenarios, simulation models are also employed to analyze the system behavior. The MATLAB/Simulink environment is employed to simulate and analyze the proposed system. This work presents an energy-efficient strategy for modern EV propulsion systems, contributing to extended driving range and improved system longevity.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"49 3","pages":"485-494"},"PeriodicalIF":1.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512592","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":"Analyzing Patterns of Consumption on Distributed Units Location and Costs in Electrical Systems","authors":"Meisam Mahdavi;S. M. Muyeen;Abdullah G. Alharbi;Francisco Jurado","doi":"10.1109/ICJECE.2026.3710423","DOIUrl":"https://doi.org/10.1109/ICJECE.2026.3710423","url":null,"abstract":"The growing adoption of distributed generation (DG) has made it important to improve the performance of distribution networks. While numerous studies have focused on optimal DG siting and sizing for loss minimization, most approaches rely on peak load or static demand assumptions, overlooking the temporal variability of electricity consumption. However, load patterns directly influence power losses, energy procurement from the main grid, and the operational and investment costs associated with DG deployment. Ignoring these variations may lead to inaccurate cost estimation and suboptimal allocation decisions. This article investigates the impact of hourly certain and uncertain load profiles on the renewable DG allocation in radial systems through a mixed-integer conic linear programming (MICLP) model that minimizes the total annualized system cost, including energy loss costs, DG investment and operating costs, and energy purchase expenses. Four representative load profiles are incorporated into the optimization framework to evaluate their influence on DG placement decisions. The model is implemented in AMPL using CPLEX and validated on benchmark distribution systems ranging from 7 to 69 buses. Simulation results confirm that incorporating load variability and uncertainty significantly influences the DG placement and improves the accuracy of cost and loss evaluation compared with constant-load planning approaches. The findings demonstrate the importance of considering realistic consumption patterns in achieving more reliable and economically efficient DG allocation solutions.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"49 3","pages":"558-568"},"PeriodicalIF":1.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148780987","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":"Exploring YOLO Architectures for Radar-Based Flying Object Classification Using Micro-Doppler Signatures","authors":"Megha Kataria;Brejesh Lall","doi":"10.1109/ICJECE.2026.3686010","DOIUrl":"https://doi.org/10.1109/ICJECE.2026.3686010","url":null,"abstract":"The increasing use of unmanned aerial vehicles (UAVs) across civilian and defense applications has created a need for reliable, real-time drone classification methods. Radar-based micro-Doppler signatures provide distinctive motion patterns that enable effective target identification under various environmental conditions. While deep learning has been applied to radar spectrograms, most studies use conventional classifiers that lose spatial detail critical for interpreting micro-Doppler features. This article presents the first systematic benchmarking of the You Only Look Once (YOLO) family (YOLOv1–YOLOv8) for radar-based UAV classification. Each model was adapted from its detection architecture by redesigning the detection head for classification and trained using the DIAT–μSAT dataset containing six aerial target classes. Models were evaluated across multiple metrics, including accuracy, precision, recall, F1-score, model size, and inference speed. Grad-CAM visualization was used to analyze spatial attention across YOLO versions. Results show that YOLOv8 achieves the best balance between accuracy (93.1%) and efficiency, outperforming both earlier YOLO models and standard CNN-based classifiers. The study establishes a unified benchmark for YOLO architectures on radar data and demonstrates their potential for efficient real-time radar classification.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"49 3","pages":"285-298"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148141552","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 Novel Stabilizer-Based Interface Algorithm for Power Hardware-in-the-Loop Simulation","authors":"Fajar Kurnia Al Farisi;Jian-Hong Liu;Na-De Yang;Kuo-Lung Lian;Zhi-Kai Fan","doi":"10.1109/ICJECE.2026.3696455","DOIUrl":"https://doi.org/10.1109/ICJECE.2026.3696455","url":null,"abstract":"Power hardware-in-the-loop (PHIL) is a type of real-time simulation (RTS) in which power hardware under test (PHUT) interacts with a simulated power system through an interface algorithm (IA). A variety of IAs for PHIL have been proposed and investigated in the literature. Due to its straightforward implementation, the ideal transformer model (ITM) is the most widely used IA in PHIL simulations. Building upon the ITM framework, several IAs, including two representative extended models—the partial circuit duplication (PCD) and the damping impedance method (DIM)—have been developed and implemented. These extended models require maintaining a predefined impedance ratio between the PHUT and the remainder of the simulated system, making their application labor-intensive and technically challenging. Moreover, these models inherently suffer from critical stability issues, leading to unstable interactions between the simulated system and the PHUT. To enhance PHIL stability, some advanced IAs adopt a Smith predictor (SP); however, such approaches rely heavily on the fidelity of the system model, thereby limiting their effectiveness in stabilizing PHIL simulations. To fully address stability in PHIL simulations, this article proposes a novel stabilizer-based IA to enhance PHIL simulation stability. The proposed stabilizer-based IA demonstrates a significant enhancement in PHIL simulation stability, particularly under the integration of passive devices or active components such as inverter-based resources (IBRs), compared to existing IAs. In addition, under harmonic injection conditions in PHIL simulations, the proposed method provides enhanced simulation fidelity by improving the reproduction of distorted interface voltage and current waveforms between the simulated system and the PHUT. PHIL simulations conducted on the PHIL system are presented to validate the effectiveness of the proposed approach.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"49 3","pages":"510-524"},"PeriodicalIF":1.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148627847","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":"Development of a Secure Hybrid Deep Learning Model for Honeypot Security and Monitoring System Using Quantum Dilated Convolutional–Fuzzy–Maxout Network","authors":"Rajasekar Kaniappan;V. Jamuna","doi":"10.1109/ICJECE.2026.3689042","DOIUrl":"https://doi.org/10.1109/ICJECE.2026.3689042","url":null,"abstract":"Due to the rise of computing techniques and their prevalent applications, cloud computing (CC) has been considered as a significant approach for secure data storage. Network firewalls protect the servers from harmful traffic and unauthorized access. Still, security solutions like intrusion detection and prevention systems (IDPSs) and antivirus (AVs) are complex and consume more time. For solving such issues, a honeypot is considered a popular technique for attaining network security. The discovery of honeypots, which are deliberately created as decoy systems to draw attention to and identify malicious behavior or illegal access, is an essential component of cybersecurity. Honeypots work as bait to help detect security flaws, learn attack patterns, and mitigate possible risks before they have a substantial impact on actual systems. This is essential because honeypots can identify undiscovered dangers, aid in the prevention of future assaults, and enhance network security by giving real-time information on possible intrusions. In CC, identifying honeypots is essential because they provide another line of protection by spotting complex threats that might elude traditional security procedures. Cloud administrators may strengthen intrusion detection, improve data security, and increase the overall resilience of the system by locating and evaluating honeypots. In this research, a novel quantum dilated convolutional–fuzzy–maxout network (QDCFMNet) is developed for honeypot identification in cloud environments. The prime process is the simulation of cloud nodes. The input log files are subjected to data preprocessing using a linear normalization approach. The features from the normalized log files are fused using the deep Kronecker network (DKN) with Kulczynski similarity. The synthetic minority oversampling technique (SMOTE) augments the dimension of the log file. The proposed QDCFMNet is employed for honeypot identification. In addition, SHapley Additive exPlanations (SHAP) is incorporated to analyze the contribution of input features and to improve the interpretability of the proposed model. Furthermore, the metrics like precision, recall, and 1-score are used to compute the efficiency of the QDCFMNet-based honeypot identification, which attains the finest values of 90.59%, 91.72%, and 91.15%, respectively.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"49 3","pages":"312-320"},"PeriodicalIF":1.9,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148141581","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 Development of 11-Level Boost Multilevel Inverter With New Switching Scheme","authors":"Karunakaran Eddu;Suresh Yellasiri;Bhukya Nageswar Rao;Anup Kumar Panda","doi":"10.1109/ICJECE.2026.3693574","DOIUrl":"https://doi.org/10.1109/ICJECE.2026.3693574","url":null,"abstract":"This article proposes a novel 11-level boost multilevel inverter (BMLI) in combination with a novel fuzzy switching scheme. The proposed inverter is composed of a reduced number of components, with 12 switches, 2 diodes, 3 capacitors, and a single-DC source, operating with a self-voltage balancing mechanism without additional sensors. The proposed fuzzy switching scheme integrates both high frequency and fundamental frequency with rule-based membership functions (MFs) by completely eliminating the complex logic gate design, high-memory lookup tables, and enhancing the output waveform quality. Furthermore, MFs are derived from the optimized firing angles, which are generated by utilizing an enhanced selective harmonic elimination pulsewidth modulation (SHEPWM) and sine quantizer methods. The proposed BMLI offers a distinct advantage, in which selected switches operate at high frequency, while the remaining switches operate at the fundamental frequency, thereby enhancing waveform quality, reducing harmonic distortion, and minimizing switching losses. Power loss and thermal stress analyses are conducted to demonstrate the performance capability of the proposed inverter. A quantitative comparison of the proposed inverter with former multilevel inverters has been carried out to address its potential. The effectiveness and performance of the proposed BMLI are validated through experimental verification on a scale-down hardware prototype.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"49 3","pages":"406-417"},"PeriodicalIF":1.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512595","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":"Induced L∞-Norm Bounded Stability of Linear Systems With Time-Varying Delay and Application to DC Motor Control","authors":"Hilal Bingöl;Gökhan Soysal;Klaus Werner Schmidt","doi":"10.1109/ICJECE.2026.3707925","DOIUrl":"https://doi.org/10.1109/ICJECE.2026.3707925","url":null,"abstract":"This article develops a controller-synthesis method for induced <inline-formula> <tex-math>${mathcal {L}}_{infty } $ </tex-math></inline-formula>-norm bounded stability of time-delay systems under disturbances. First, a general sufficient bounded-stability condition is derived using a Lyapunov–Krasovskii functional. Next, this condition is specialized to linear systems with time-varying input delay and expressed as linear matrix inequalities (LMIs) for state-feedback controller synthesis. The applicability of the proposed framework is illustrated through a DC motor control example with various input/output configurations. In addition, comparative results are provided for constant-delay, time-varying-delay, and delay-free controller designs, including a comparison with an <inline-formula> <tex-math>${mathcal {H}}_{infty } $ </tex-math></inline-formula>-based controller.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"49 3","pages":"536-544"},"PeriodicalIF":1.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148749111","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":"Small-Signal Stability of Hybrid Grid-Forming and Grid-Following Converter Systems: Grid Strength Effect","authors":"Xing Yao;Meng Zhan;Yutao Pan","doi":"10.1109/ICJECE.2026.3697739","DOIUrl":"https://doi.org/10.1109/ICJECE.2026.3697739","url":null,"abstract":"As the penetration of renewable energy continues rising and the grid conditions become increasingly complicated, the instability phenomena have happened more frequently, but their mechanisms remain uncovered. This article investigates the small-signal stability of a 100% hybrid grid-forming (GFM) and grid-following (GFL) converter system and uncovers the general role of grid strength. A general state-space model is developed, which is easily applicable to any multiconverter system. Based on the state-space matrix, root locus, and participation factor analyses, the stable and unstable parameter domains characterized by different instability modes are obtained, which reveal that they occur as either a pure single-converter instability behavior or a superposition of different instability types. A detailed parametric analysis is conducted to clarify these distinct instability modes. In addition, it is found that the stiff-grid-instability of the GFM is a local effect, determined largely by the grid strength along the interconnection path between any two GFM converters. In contrast, the weak-grid-instability of either GFM or GFL converter is a global effect, which is triggered when the overall grid strength is weakened. All these findings are broadly supported by theoretical analysis and time-domain simulations and they can provide improved insights in the grid-strength effects on the stability of large-scale power system dominated by converters.","PeriodicalId":100619,"journal":{"name":"IEEE Canadian Journal of Electrical and Computer Engineering","volume":"49 3","pages":"472-484"},"PeriodicalIF":1.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509754","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}