IEEJ Transactions on Electrical and Electronic Engineering最新文献_第10页

Data-Driven Temperature Deviation Estimation of a Proton Exchange Membrane Water Electrolyzer Stack from Electrochemical Impedance Using Machine Learning 基于电化学阻抗的质子交换膜水电解槽堆数据驱动温度偏差估计

IF 1.1 4区工程技术

IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2025-03-08 DOI: 10.1002/tee.70009

Noboru Katayama, Ryoma Iki, Xing-Xing Chen, Ka-Hong Loo

{"title":"Data-Driven Temperature Deviation Estimation of a Proton Exchange Membrane Water Electrolyzer Stack from Electrochemical Impedance Using Machine Learning","authors":"Noboru Katayama, Ryoma Iki, Xing-Xing Chen, Ka-Hong Loo","doi":"10.1002/tee.70009","DOIUrl":"https://doi.org/10.1002/tee.70009","url":null,"abstract":"We developed a method to analyze temperature variations in proton exchange membrane water electrolysis stacks by using machine learning to interpret electrochemical impedance spectroscopy (EIS) data. To train the machine learning model, we artificially generated impedance data at various temperature differences by merging data from uniformly heated stacks. The impedance data were collected using a dual active bridge DC/DC converter to apply a range of DC currents and an AC current through phase shift fluctuations. These data were then sampled for impedance analysis. A deep neural network was employed to correlate the real and imaginary components of impedance across frequencies with the stack's average temperatures and temperature variances. Our model, evaluated with actual thermal condition data, successfully predicted average temperatures and temperature differences within 2°C and 5°C accuracy, respectively, showing its potential for monitoring and managing temperature and other parameters in electrolysis stacks only by EIS and a deep neural network. © 2025 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"20 9","pages":"1488-1496"},"PeriodicalIF":1.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/tee.70009","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144767578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Theoretical Analysis and Demonstration of LCL-Circuit and Linearization of Dielectric Barrier Discharge lcl电路的理论分析与论证及介质阻挡放电的线性化

IF 1 4区工程技术

IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2025-03-07 DOI: 10.1002/tee.70003

Ryota Nagata, Taichiro Tamida

引用次数: 0

Reward Design Using Large Language Models for Natural Language Explanation of Reinforcement Learning Agent Actions 基于大语言模型的奖励设计用于强化学习智能体行为的自然语言解释

IF 1 4区工程技术

IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2025-03-06 DOI: 10.1002/tee.70005

Shinya Masadome, Taku Harada

{"title":"Reward Design Using Large Language Models for Natural Language Explanation of Reinforcement Learning Agent Actions","authors":"Shinya Masadome, Taku Harada","doi":"10.1002/tee.70005","DOIUrl":"https://doi.org/10.1002/tee.70005","url":null,"abstract":"Reinforcement learning (RL) has found applications across diverse domains; however, it grapples with challenges when formulating reward functions and exhibits low exploration efficiency. Recent studies leveraging large language models (LLMs) have made strides in addressing these issues. However, for RL agents to be practically deployable, elucidating their decision-making process is crucial for enhancing explainability. We introduce a novel RL approach aimed at alleviating the burden of designing reward functions and facilitating natural language explanations for actions grounded in the agent's decisions. Our method employs two types of agents: a low-level agent responsible for concrete action selection and a high-level agent tasked with setting abstract action goals. The high-level agent undergoes training using a hybrid reward function framework, which incentivizes its actions by comparing them with those generated by an LLM across discretized states. Meanwhile, the training of the low-level agent is guided by a reward function designed using the EUREKA algorithm. We applied the proposed method to the cart-pole problem and demonstrated its ability to achieve a learning convergence rate while reducing human effort. Moreover, our approach yields coherent natural language explanations elucidating the rationale behind the agent's actions. © 2025 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"20 8","pages":"1203-1211"},"PeriodicalIF":1.0,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/tee.70005","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144573585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Parameter Selection of General Signal Delay Superposition Operator Used for Real-Time Detection of Single-Phase Fundamental and Harmonics 用于单相基频和谐波实时检测的通用信号延迟叠加算子参数选择

IF 1 4区工程技术

IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2025-02-25 DOI: 10.1002/tee.24270

Wenjun Tian, Mingxing Tian, Hongsheng Su, Zhiqiang Sun

{"title":"Parameter Selection of General Signal Delay Superposition Operator Used for Real-Time Detection of Single-Phase Fundamental and Harmonics","authors":"Wenjun Tian, Mingxing Tian, Hongsheng Su, Zhiqiang Sun","doi":"10.1002/tee.24270","DOIUrl":"https://doi.org/10.1002/tee.24270","url":null,"abstract":"To acquire quickly and accurately the real-time information of fundamental waves and specified harmonics is a prerequisite for harmonic control. Generalized delayed signal superposition operator (GDSS) is a numerical detection method for fundamental and harmonic real-time information, and its detection accuracy and real-time performance are closely related to the GDSS operator parameters. Based on the basic principles of the GDSS operator, this paper proposes a formula method and a search method for the selection of operator parameters and reveals the quantitative relationship between detection accuracy and real-time performance. According to the signal harmonic distribution characteristics, the formula method and the search method are employed respectively to obtain the GDSS operator parameters that reduce the computational complexity and improve real-time performance while meeting the requirements of detection accuracy. The simulation example shows that the proposed method is feasible and effective, and provides a further theoretical basis for the actual use of GDSS. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"20 7","pages":"1089-1096"},"PeriodicalIF":1.0,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144256560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simplified Algorithm for Multi-Step Model Predictive Control of Permanent Magnet Synchronous Motors for Ship Propulsion 舰船推进用永磁同步电机多步模型预测控制的简化算法

IF 1 4区工程技术

IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2025-02-17 DOI: 10.1002/tee.24278

Xiangjun Wang, Haichuan Cao, Hao Sun, Pengxiang Wang

{"title":"Simplified Algorithm for Multi-Step Model Predictive Control of Permanent Magnet Synchronous Motors for Ship Propulsion","authors":"Xiangjun Wang, Haichuan Cao, Hao Sun, Pengxiang Wang","doi":"10.1002/tee.24278","DOIUrl":"https://doi.org/10.1002/tee.24278","url":null,"abstract":"A simplified voltage vector multi-step model predictive control algorithm is proposed to address the practical problems of excessive dependence on system parameters for vector control of permanent magnet synchronous motors for ship propulsion, poor steady state control performance of single-step model predictive control algorithm, and large computational volume of traditional multi-step model predictive control algorithm. First, by analyzing the operation and implementation process of traditional vector control, this paper applies the single-step current model predictive control algorithm with a double closed-loop structure to establish a finite control set model predictive control model for ship propulsion permanent magnet synchronous motor, which has the advantages of reducing the dependence of the control algorithm on the system parameters, and simple calculation. Second, considering the prediction conservatism problem and prediction delay problem of single-step model predictive control in one control cycle, this paper proposes an SVVM-MPC algorithm, which can utilize delay compensation, streamlining the voltage vector and increasing the prediction step size to ensure the controller is lighter computational load while obtaining better steady-state control results. Finally, the simulation and experimental results show that the computation of SVVM-MPC algorithm is only 37.5% of the traditional multistep current prediction algorithm under the variation of speed and load torque of ship propulsion permanent magnet synchronous motors, meanwhile, the torque pulsation is effectively suppressed and reduced by about 25%, which improves the quality of three-phase currents and enhances the steady-state control performance. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"20 8","pages":"1268-1281"},"PeriodicalIF":1.0,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144573878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modeling Techniques for Light Distribution of White LEDs 白光led光分布的建模技术

IF 1 4区工程技术

IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2025-02-16 DOI: 10.1002/tee.70000

Tomoaki Kashiwao, Kenji Ikeda, Masaru Tsumori, Kanji Bando

引用次数: 0

An End-to-End Pillar Feature Based Neural Network Improved by Attention Modules for Object Detection of Autonomous Vehicles 基于关注模块改进的端到端支柱特征神经网络自动驾驶汽车目标检测

IF 1 4区工程技术

IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2025-02-05 DOI: 10.1002/tee.24276

Bin Zhang, Congzhi Ren, Hun-ok Lim

{"title":"An End-to-End Pillar Feature Based Neural Network Improved by Attention Modules for Object Detection of Autonomous Vehicles","authors":"Bin Zhang, Congzhi Ren, Hun-ok Lim","doi":"10.1002/tee.24276","DOIUrl":"https://doi.org/10.1002/tee.24276","url":null,"abstract":"The development of 3D object detectors for dealing with 3D point clouds generated by LiDAR sensors is facing a significant challenge in real-world autonomous driving scenarios. Current research mainly focuses on Voxel-based detectors, which use sparse convolution for training and inference. These models often require substantial computational resources for training, making them hard to be applied to real autonomous vehicles. Among these models, two models called PointPillars and CenterPoint (pillar-version) are noticed since they are based on 2D Pillar encoding, making the inferencing process fast. However, in comparison to other models, they exhibit relatively lower detection accuracy performances. In this paper, to enhance the detection accuracy of Pillar encoding models without significantly increasing computational complexity, attention modules added within the Pillar encoder are proposed. These modules adopt the attention mechanism while reducing input dimensions. Simultaneously, the attention modules are also added to the CNN backbone network to increase the detection accuracy. The inference time increases from 16 to 17 ms, compared with the fastest PointPillar model. The effectiveness of the proposed network is proven by experiments. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"20 8","pages":"1212-1218"},"PeriodicalIF":1.0,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144573284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modeling and Optimal Design of Magnetic Drive for High-Voltage Nanosecond Marx Generator 高压纳秒马克思发电机磁力传动建模与优化设计

IF 1 4区工程技术

IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2025-02-04 DOI: 10.1002/tee.24274

Ruitian Wang, Qingqing Liu, Xin Li, Xinsheng Zhang, Beichao Yang, Xin Chen

{"title":"Modeling and Optimal Design of Magnetic Drive for High-Voltage Nanosecond Marx Generator","authors":"Ruitian Wang, Qingqing Liu, Xin Li, Xinsheng Zhang, Beichao Yang, Xin Chen","doi":"10.1002/tee.24274","DOIUrl":"https://doi.org/10.1002/tee.24274","url":null,"abstract":"All-solid-state high-voltage pulse generators are widely used in many applications, such as medical lasers and plasma generators. The rise time is a crucial parameter for the generator. This paper focuses on the modeling and optimal design of Marx pulse generator based on silicon carbide (SiC) MOSFETs and magnetic drive. First, based on the model of toroidal transformer and the equivalent circuit model of SiC MOSFETs, the electromagnetic transient model of the Marx generator with the magnetic drive is established to analyze the influence of circuit parameters on the rise time. Then, the toroidal transformer with shell-type coil structure is proposed, which has a lower leakage inductance. Furthermore, a leakage inductance model is established for the novel transformer structure, and the optimal design is carried out. Finally, the Marx generator test platform is built to validate the model and optimization method. The test results indicate that the pulse generator proposed in this paper has a pulse rise time of 20 ns under the condition of 2 kV/20 A, which represents a 33.3% increase in performance compared to the proposed Marx generator. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"20 7","pages":"976-990"},"PeriodicalIF":1.0,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144256390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Piecewise Logarithmic Fitting-Based Ant Lion Optimizer 基于分段对数拟合的蚁狮优化器

IF 1 4区工程技术

IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2025-01-31 DOI: 10.1002/tee.24275

Cheng-ze Li, Geng-song Li, Yi Liu, Qi-bin Zheng

引用次数: 0

Design and Analysis of Double-Sided U-Shaped Linear Primary Permanent Magnet Vernier Motor 双面u型直线一次永磁游标电机的设计与分析

IF 1 4区工程技术

IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2025-01-29 DOI: 10.1002/tee.24269

Hualin Huang, Xiaojian Lu, Chi Zhang, Wenyuan Yan, Jie Zhang, Jie Zhou, Guilin Yang

{"title":"Design and Analysis of Double-Sided U-Shaped Linear Primary Permanent Magnet Vernier Motor","authors":"Hualin Huang, Xiaojian Lu, Chi Zhang, Wenyuan Yan, Jie Zhang, Jie Zhou, Guilin Yang","doi":"10.1002/tee.24269","DOIUrl":"https://doi.org/10.1002/tee.24269","url":null,"abstract":"This paper introduces a new double-sided U-shaped linear primary permanent magnet Vernier (U-LPPMV) motor, whose most important feature is a U-shaped Halbach structure in which the magnetization direction of five permanent magnets is concentrated at the center point, which provides more than twice the thrust density compared with existing single-sided motors. The secondary stage adopts a convex pole structure consisting of laminated silicon steel sheets, which has the advantages of a simple structure and low cost. The no-load counter-electromotive force and magnetic chain are made more sinusoidal by changing the side end structure at both ends of the primary. Next, the air-gap magnetic density of the motor is analyzed analytically by establishing the magnetomotive force potential-magnetic conductance model, and the accuracy is verified by simulation analysis. In addition, a global optimization of the motor is performed to increase the average thrust and improve the electromagnetic performance based on the optimized structural parameters. Finally, the accuracy of the theory is demonstrated by prototype design and fabrication as well as by building a test platform, and the motor is more suitable for long-stroke, high-load, and high-precision application scenarios. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"20 7","pages":"1080-1088"},"PeriodicalIF":1.0,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144256487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0