IEEJ Transactions on Electrical and Electronic Engineering最新文献

Magnetic Flux Leakage (MFL) pipeline defect detection faces numerous challenges, with traditional manual analysis being inefficient and highly subjective, while deep learning methods struggle to balance prediction accuracy across three features. This paper proposes an innovative defect quantification framework that establishes a multimodal joint prediction mechanism, comprehensively integrating magnetic flux and image data to effectively enhance defect detection accuracy. In magnetic flux quantification, the framework designs a hybrid optimizer combining genetic algorithms and ant colony optimization. By employing a weighted objective function, it balances prediction accuracy of different output features and introduces diversified feature engineering techniques to enhance model generalizability and numerical stability. In image quantization, an improved HCFNet combined with Linear Deformable Convolution innovatively proposes a Parallelized Patch-Aware Attention module, improving small object detection precision. The introduction of the Softplus activation function and Huber Loss function further improves training stability and model convergence speed. Experimental results demonstrate that the proposed method significantly outperforms current mainstream detection models in defect quantification accuracy and feature quantification capabilities. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

With the rapid increase in the number of electric vehicles (EVs), the surge in stochastic EV charging loads poses significant challenges to the secure and stable operation of distribution networks. To address this issue, accurate EV charging load forecasting is crucial. This paper proposes a novel EV charging load forecasting method based on an improved self-organizing map (ISOM) clustering algorithm and an ECA-LSTM-SA model. First, an ISOM clustering algorithm is developed, which takes load values at different time instants as inputs, employs cosine similarity as the distance metric, and utilizes particle swarm optimization (PSO) to determine hyperparameters. This clustering method is used to segment charging loads into similar daily patterns. Then, an ECA-LSTM-SA forecasting model is constructed by integrating efficient channel attention (ECA) and soft attention (SA) mechanisms with long short-term memory (LSTM) networks to enhance feature extraction and prediction accuracy. The model is trained and used for forecasting within each clustered dataset. Finally, the prediction results from all clusters are concatenated to obtain the final forecasted charging load. Simulation results demonstrate that the proposed method significantly improves prediction accuracy and stability. © 2025 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

The flexibility of distributed energy resources (DERs) has been receiving increasing attention. One important issue to use DERs' flexibility for fast demand response, like for secondary reserves, is their full activation time (FAT) and ICT (Information communication technology) response time (IRT). Though studies have reported the inherent activation time of various DERs, time-synchronized measurement results of both ICT latency and the FAT are still lacking. We have constructed an experimental system to measure them synchronously with the local time server, excluding cloud timestamps. This paper reports on the experimental system and the characteristics of measured FATs and IRTs of the following DERs; one vehicle-to-home equipped charger (controlled both via the Internet and via the LTE-M) and one Mode 3 normal charger, as examples. This information of FAT will be useful for designing the group control and monitoring system of the electric vehicle charging for fast demand response. © 2025 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

The power system operation is becoming challenging due to growing power demand. The detection and classification of transformer faults, as the core equipment in the power system, are crucial for the stable operation of the grid. However, there is no uniform standard for transformer fault feature selection based on dissolved gas analysis (DGA). This paper proposes a transformer fault diagnosis method based on parameter migration feature extraction and improved random forest (IRF) feature selection. Firstly, the gramian angular field (GAF) is introduced to transform the one-dimensional gas sequence into a three-channel map, and the sample data are balanced using image processing methods. Next, the parameters of the pre-trained VGG16 feature extraction layer are utilized to establish a model that can extract GAF image features automatically. Then, to obtain optimal features, the IRF algorithm is improved by comprehensively considering the Pearson correlation coefficient. The results indicate that the proposed method is more effective in extracting fault features than the conventional approach. After filtering out the optimal features with IRF, the diagnostic rate of the LR, SVM, MLP, and SGD transformer fault model is improved by 4.27%, 12.2%, 6.7%, 10.97%, and F1_score is enhanced by 4.53%, 12.55%, 6.43%, and 10.92%, respectively. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

As distributed energy resources (DERs) penetration increases, complex power flows lead to challenges such as voltage violations, system congestion, and increase of distribution loss. To effectively address these issues and enhance energy efficiency, an hourly dynamic system configuration optimization method is essential, as traditional annual and seasonal approaches fail to respond to the rapid fluctuations in power flow driven by weather conditions. In this paper, we present a dynamic system configuration optimization method from the perspective of a distribution system operator. Utilizing mixed-integer linear programming, the proposed method optimizes both the configuration and timing of reconfigurations while satisfying the reconfiguration frequency constraint to respond to the fluctuating power output from photovoltaic sources. This approach aims to minimize distribution losses and avoid system congestion and voltage violations. Through numerical experiments conducted on a three-feeder distribution system model, we demonstrate that by considering the average lifespan of switch devices to be three times per day on average, the proposed method can avoid system congestion and voltage violations. Moreover, it can reduce the distribution loss by 5.7% compared to the current method during the system period. This approach offers a cost-effective alternative to traditional infrastructure upgrades, supports the integration of renewable energy sources, and enhances grid efficiency. © 2025 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Dynamic multi-objective optimization problems (DMOPs) are one of the most challenging problems in real-world systems. This paper proposes a multi-swarm dynamic crow search algorithm (CSA) to solve DMOPs effectively and advance the application of CSA for DMOPs. Three components are introduced in the algorithm. The multi-swarm co-evolution mechanism creates a distinct swarm for each optimization objective, while a memory time-based archive update strategy is introduced. A complex behavior strategy is developed to adaptively adjust the key parameters and guide the swarms for fast convergence. The dynamism handling mechanism uses random re-evaluation for change detection, proposes a split selection method, and a memory reuse strategy to choose old solutions with good diversity, and considers random re-initialization and prediction-based approaches to respond to the change. Extensive experiments demonstrate that the proposed algorithm is competitive in both optimization performance and computational cost when compared with state-of-the-art methods. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

With the widespread adoption of electric vehicles (EVs), the demand for charging facilities is expected to grow rapidly. Rational planning of charging infrastructure has become a key factor in the development of EVs. This study comprehensively considers the impact of existing charging stations in the region. It integrates the perspectives of both charging investors and electric vehicle users to establish a public charging facility planning model to minimize the total annual social cost. The weighted Voronoi diagram is employed to divide the service areas of charging stations, and the planning model is solved using an improved particle swarm optimization (IPSO) algorithm. Case analysis demonstrates that the weighted Voronoi diagram can more effectively allocate charging station service areas, and the coordinated planning of fast and slow charging piles can significantly reduce the total social cost compared to the exclusive deployment of fast charging piles. This method meets the charging demand of EVs while achieving the optimal capacity allocation of charging piles within each charging station. It provides an optimal solution for the siting and capacity determination of charging stations, offering valuable references and insights for the practical construction of public charging stations. © 2025 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

The Mekong River estuaries in Vietnam are significant contributors to global plastic waste emissions entering the ocean, yet research on plastic debris impacts in the East Sea is limited. Specifically, studies on microplastics (MPs) transport affected by the complex hydrodynamic conditions in the Mekong estuary are scarce. The study aims to understand the movement of MPs from the Hau estuaries (a branch of the Mekong River) to the East Sea during the Northeast and Southwest Monsoons (January 2024 and July 2023, respectively). Using the OpenDrift trajectory model with the DNORA dynamic downscaling tool, findings reveal that the monsoon climate significantly influences MP transport. Wave action primarily affects MPs dispersion near estuaries and coastal zones, while current dynamics are key to MP movement to the East Sea. A one-month simulation indicates that MPs accumulate in various locations, including the Ca Mau coast, Hon Khoai Island, Phu Quy Island, Do Lon Island, and the Truong Sa Archipelago, with notable concentrations along the Malaysian coast. Additionally, neighboring countries like Thailand and the Philippines face a substantial risk of MPs pollution from the Hau estuaries. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

In early 2024, the Mekong Delta in Vietnam faced significant saltwater intrusion, exceeding average levels. Between February and March, the region experienced three periods of increased saltwater intrusion, primarily driven by the El Niño phenomenon, which resulted in a striking lack of rainfall (60%–95% below normal levels). Extended sunny days led to considerable evaporation from fields, canals, rivers, and lakes. Concurrently, reduced upstream water flow into the Delta and heightened spring tide levels pushed saltwater deeper into rice fields, severely impacting local livelihoods and agriculture. To address this issue, the study aims to predict evapotranspiration and water demand using the CROPWAT 8.0 model in combination with simulating the growth and development of rice crops in An Giang province by utilizing the ORYZA model. This research will focus on the three main rice growing seasons: Winter–Spring, Summer-Autumn, and Autumn-Winter, utilizing a rice variety with a growth duration of 95–100 days. Forecasts for 2024 will rely on drought data from 2019, projecting continuous high temperatures (0.5 °C above 2019 levels) and no rainfall from January to May in 2024. It can be seen that agricultural activities in 2024, particularly during the Summer-Autumn season, could face severe consequences. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Aiming at the problems of wind and light curtailment, reverse transmission, and over-limit of feeder power caused by the access of distributed generation (DG) in high-permeability active distribution network (ADN), this paper proposes a bi-level optimal configuration method of energy storage system (ESS) based on flexible interconnection of rotating power flow controller (RPFC). First, a bi-level framework is presented, where the objective is to minimize the payback period of the RPFC and energy storage combined system in the outer planning layer, and the objective is to minimize the annual operation cost in the inner operation layer. Second, the hybrid optimization of the genetic algorithm and Gurobi solver is used to solve the optimal configuration model. Finally, the optimal configuration model is verified on the example of IEEE 33-node. The results verify the applicability of the proposed optimal configuration scheme of the RPFC and energy storage combined system, which can effectively promote the new energy consumption and improve the flexibility and economy of the system. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.