Pub Date : 2024-10-16DOI: 10.1109/temc.2024.3466048
Michelle Pirrone, Jordan Bernhardt, Adam Wunderlich
{"title":"Assessing Directional Time-Dependent Interference Vulnerabilities in Closed-Box Wireless Systems","authors":"Michelle Pirrone, Jordan Bernhardt, Adam Wunderlich","doi":"10.1109/temc.2024.3466048","DOIUrl":"https://doi.org/10.1109/temc.2024.3466048","url":null,"abstract":"","PeriodicalId":55012,"journal":{"name":"IEEE Transactions on Electromagnetic Compatibility","volume":"4 1","pages":""},"PeriodicalIF":2.1,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A novel approach for the validation of data in signal integrity and power integrity using machine learning is proposed. This approach presents an alternative to the feature selective validation method outlined in the IEEE Standard 1597.1 for the validation of computational electromagnetics, computer modeling and simulations. The proposed approach focuses on replicating the human visual assessment by using data collected and labeled by expert engineers to train time series classification networks that predict the degree of agreement between two curves. The trained networks are then used for the systematic and automated validation of 1-D datasets. The performance and suitability of this approach for systematic data validation is evaluated and discussed. The trained network surpasses the single human subjects in predicting the expert opinion with an accuracy higher than 70%.
{"title":"Machine Learning Based Data Validation for Signal Integrity and Power Integrity Using Supervised Time Series Classification","authors":"Youcef Hassab;Til Hillebrecht;Fabian Lurz;Christian Schuster","doi":"10.1109/TEMC.2024.3474917","DOIUrl":"10.1109/TEMC.2024.3474917","url":null,"abstract":"A novel approach for the validation of data in signal integrity and power integrity using machine learning is proposed. This approach presents an alternative to the feature selective validation method outlined in the IEEE Standard 1597.1 for the validation of computational electromagnetics, computer modeling and simulations. The proposed approach focuses on replicating the human visual assessment by using data collected and labeled by expert engineers to train time series classification networks that predict the degree of agreement between two curves. The trained networks are then used for the systematic and automated validation of 1-D datasets. The performance and suitability of this approach for systematic data validation is evaluated and discussed. The trained network surpasses the single human subjects in predicting the expert opinion with an accuracy higher than 70%.","PeriodicalId":55012,"journal":{"name":"IEEE Transactions on Electromagnetic Compatibility","volume":"66 6","pages":"2150-2158"},"PeriodicalIF":2.0,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142444000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-15DOI: 10.1109/TEMC.2024.3474795
Yuan Ping;Yanming Zhang;Lijun Jiang
This article proposes a modified generative adversarial network (GAN)-based approach, namely Wasserstein GAN (WGAN), for the uncertainty quantification (UQ) in partial equivalent element circuit (PEEC) models. Initially, the stochastic PEEC is constructed to obtain the sample data of the quantities of interest (QoI). This sample data, along with the fake data from the generator, serves as input for the discriminator in WGAN. The loss function of the generator in WGAN is constructed using the Wasserstein distance to provide a more usable gradient than that in the traditional GAN. By estimating the distribution of sample data using the fake data in the discriminator, the stochastic properties of the QoI can be finally obtained. Notably, the proposed method can efficiently estimate the stochastic characteristics of the QoI without prior knowledge of its probability distribution. Two numerical examples are provided to validate the proposed method. It is demonstrated that the proposed WGAN method effectively quantifies uncertainty in PEEC models. Compared to traditional methods, the proposed WGAN achieves a remarkable 20-fold increase in computational speed. Consequently, our work offers a powerful machine learning tool for advanced UQ in complex electromagnetic simulations.
本文提出了一种改进的基于生成对抗网络（GAN）的方法，即Wasserstein GAN (WGAN)，用于部分等效元件电路（PEEC）模型的不确定性量化（UQ）。首先，构造随机PEEC以获得感兴趣量（qi）的样本数据。该样本数据与来自生成器的假数据一起作为WGAN中鉴别器的输入。WGAN中生成器的损失函数使用Wasserstein距离来构建，以提供比传统GAN中更可用的梯度。利用鉴别器中的假数据估计样本数据的分布，最终得到qi的随机性质。值得注意的是，该方法可以在不知道qi概率分布的情况下有效地估计其随机特征。给出了两个数值算例，验证了该方法的有效性。结果表明，该方法能有效地量化PEEC模型中的不确定性。与传统方法相比，WGAN的计算速度提高了20倍。因此，我们的工作为复杂电磁模拟中的高级UQ提供了强大的机器学习工具。
{"title":"Uncertainty Quantification for PEEC Based on Wasserstein Generative Adversarial Network","authors":"Yuan Ping;Yanming Zhang;Lijun Jiang","doi":"10.1109/TEMC.2024.3474795","DOIUrl":"10.1109/TEMC.2024.3474795","url":null,"abstract":"This article proposes a modified generative adversarial network (GAN)-based approach, namely Wasserstein GAN (WGAN), for the uncertainty quantification (UQ) in partial equivalent element circuit (PEEC) models. Initially, the stochastic PEEC is constructed to obtain the sample data of the quantities of interest (QoI). This sample data, along with the fake data from the generator, serves as input for the discriminator in WGAN. The loss function of the generator in WGAN is constructed using the Wasserstein distance to provide a more usable gradient than that in the traditional GAN. By estimating the distribution of sample data using the fake data in the discriminator, the stochastic properties of the QoI can be finally obtained. Notably, the proposed method can efficiently estimate the stochastic characteristics of the QoI without prior knowledge of its probability distribution. Two numerical examples are provided to validate the proposed method. It is demonstrated that the proposed WGAN method effectively quantifies uncertainty in PEEC models. Compared to traditional methods, the proposed WGAN achieves a remarkable 20-fold increase in computational speed. Consequently, our work offers a powerful machine learning tool for advanced UQ in complex electromagnetic simulations.","PeriodicalId":55012,"journal":{"name":"IEEE Transactions on Electromagnetic Compatibility","volume":"66 6","pages":"2048-2055"},"PeriodicalIF":2.0,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The overvoltages generated in low-voltage equipment in a building struck by direct lightning are greatly affected by the electromagnetic phenomena caused by the currents flowing in the building structure and grounding lines. Therefore, it is necessary to estimate the current to evaluate such overvoltages accurately. In this article, we investigate a method for evaluating the currents flowing in the building structure and the protective earth line using a mathematical formula based on the electromagnetic phenomenon of the Faraday cage effect.
{"title":"Calculation Method Using Faraday Cage Effects on Currents in Buildings Struck Directly by Lightning","authors":"Qianling Liu;Hisyo Nakamura;Shinji Yasui;Masaya Nakagawa;Tatsuya Yamamoto","doi":"10.1109/TEMC.2024.3467129","DOIUrl":"10.1109/TEMC.2024.3467129","url":null,"abstract":"The overvoltages generated in low-voltage equipment in a building struck by direct lightning are greatly affected by the electromagnetic phenomena caused by the currents flowing in the building structure and grounding lines. Therefore, it is necessary to estimate the current to evaluate such overvoltages accurately. In this article, we investigate a method for evaluating the currents flowing in the building structure and the protective earth line using a mathematical formula based on the electromagnetic phenomenon of the Faraday cage effect.","PeriodicalId":55012,"journal":{"name":"IEEE Transactions on Electromagnetic Compatibility","volume":"66 6","pages":"1858-1867"},"PeriodicalIF":2.0,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10718725","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-15DOI: 10.1109/temc.2024.3468270
Adrian T. Sutinjo, Scott Haydon
{"title":"Increasing Plane Wave Coupling to a Microstrip on a GTEM Cell Wall in Radiated Susceptibility Measurement","authors":"Adrian T. Sutinjo, Scott Haydon","doi":"10.1109/temc.2024.3468270","DOIUrl":"https://doi.org/10.1109/temc.2024.3468270","url":null,"abstract":"","PeriodicalId":55012,"journal":{"name":"IEEE Transactions on Electromagnetic Compatibility","volume":"10 1","pages":""},"PeriodicalIF":2.1,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-15DOI: 10.1109/TEMC.2024.3476489
Yu-Ying Cheng;Tzong-Lin Wu
This article presents the first comprehensive investigation into the crosstalk mechanism within a three-wire (four-conductor) C-PHY transmission channel based on mixed-mode theory ( X , Y , and C modes). The phase difference between X and Y modes is identified as a primary contributor to crosstalk, leading to signal integrity (SI) degradation. A tab-routing design is first specifically applied to enhance SI in three-wire (four-conductor) C-PHY channels. Additionally, an artificial neural network (ANN) based surrogate model is developed to map tab-routing parameters to eye-opening metrics efficiently. By combining the particle swarm optimization (PSO) algorithm with the ANN-based surrogate model, optimal geometrical parameters for the tab-routing C-PHY channel with enhanced SI performance can be quickly determined. The optimized three-wire tab-routing C-PHY channel, fabricated on a two-layer printed circuit board (PCB), demonstrates a 17.2% improvement in eye-opening and an 8.5% reduction in the occupied area compared to a typical 50 Ω three-wire channel. This article also represents the first application of machine learning (ANN, PSO) to C-PHY SI research, significantly improving design process efficiency. The feasibility and accuracy of the ANN-based surrogate model applied to the tab-routing C-PHY channel are thoroughly validated.
{"title":"Signal Integrity Optimization for C-PHY Channel Using Surrogate Model of Tab-Routing Structure","authors":"Yu-Ying Cheng;Tzong-Lin Wu","doi":"10.1109/TEMC.2024.3476489","DOIUrl":"10.1109/TEMC.2024.3476489","url":null,"abstract":"This article presents the first comprehensive investigation into the crosstalk mechanism within a three-wire (four-conductor) C-PHY transmission channel based on mixed-mode theory (\u0000<italic>X</i>\u0000, \u0000<italic>Y</i>\u0000, and \u0000<italic>C</i>\u0000 modes). The phase difference between \u0000<italic>X</i>\u0000 and \u0000<italic>Y</i>\u0000 modes is identified as a primary contributor to crosstalk, leading to signal integrity (SI) degradation. A tab-routing design is first specifically applied to enhance SI in three-wire (four-conductor) C-PHY channels. Additionally, an artificial neural network (ANN) based surrogate model is developed to map tab-routing parameters to eye-opening metrics efficiently. By combining the particle swarm optimization (PSO) algorithm with the ANN-based surrogate model, optimal geometrical parameters for the tab-routing C-PHY channel with enhanced SI performance can be quickly determined. The optimized three-wire tab-routing C-PHY channel, fabricated on a two-layer printed circuit board (PCB), demonstrates a 17.2% improvement in eye-opening and an 8.5% reduction in the occupied area compared to a typical 50 Ω three-wire channel. This article also represents the first application of machine learning (ANN, PSO) to C-PHY SI research, significantly improving design process efficiency. The feasibility and accuracy of the ANN-based surrogate model applied to the tab-routing C-PHY channel are thoroughly validated.","PeriodicalId":55012,"journal":{"name":"IEEE Transactions on Electromagnetic Compatibility","volume":"66 6","pages":"2133-2141"},"PeriodicalIF":2.0,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-14DOI: 10.1109/temc.2024.3466089
Xiangrui Su, Wenchang Huang, Junghee Cho, Joonki Paek, Chulsoon Hwang
{"title":"A Method for Measuring the Transfer Function Inside a Compact Metallic Enclosure Using a Slot Antenna","authors":"Xiangrui Su, Wenchang Huang, Junghee Cho, Joonki Paek, Chulsoon Hwang","doi":"10.1109/temc.2024.3466089","DOIUrl":"https://doi.org/10.1109/temc.2024.3466089","url":null,"abstract":"","PeriodicalId":55012,"journal":{"name":"IEEE Transactions on Electromagnetic Compatibility","volume":"1 1","pages":""},"PeriodicalIF":2.1,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-14DOI: 10.1109/TEMC.2024.3465538
Bingheng Li;Da Li;Ling Zhang;Zheming Gu;Ruifeng Xu;Yan Li;Er-Ping Li
With the rapid increase in the operating frequency and integration density of ball grid array packages, pin assignment (pinmap) significantly impacts electromagnetic interference (EMI). However, the previous deep reinforcement learning (DRL) approaches required time-consuming evaluation and training procedures. In this article, we propose a novel design methodology for predicting and optimizing the EMI of pinmaps. First, we present a deep learning-based predictor that can accurately and quickly evaluate the EMI levels of pinmaps, thereby supporting fast pinmap design. Furthermore, transfer learning achieves excellent predictor performance with less training data, resulting in effective data savings. Based on the presented predictors, an enhanced genetic algorithm is developed to optimize the EMI and can quickly find better solutions compared with the DRL approaches. As a result, this article proposes a detailed guideline for predicting and optimizing the EMI of pinmaps, and the proposed methodology can be further developed for promising intelligent system-level packaging design.
{"title":"EMI Prediction and Optimization for Pinmap Design Using Deep Transfer Learning and an Enhanced Genetic Algorithm","authors":"Bingheng Li;Da Li;Ling Zhang;Zheming Gu;Ruifeng Xu;Yan Li;Er-Ping Li","doi":"10.1109/TEMC.2024.3465538","DOIUrl":"10.1109/TEMC.2024.3465538","url":null,"abstract":"With the rapid increase in the operating frequency and integration density of ball grid array packages, pin assignment (pinmap) significantly impacts electromagnetic interference (EMI). However, the previous deep reinforcement learning (DRL) approaches required time-consuming evaluation and training procedures. In this article, we propose a novel design methodology for predicting and optimizing the EMI of pinmaps. First, we present a deep learning-based predictor that can accurately and quickly evaluate the EMI levels of pinmaps, thereby supporting fast pinmap design. Furthermore, transfer learning achieves excellent predictor performance with less training data, resulting in effective data savings. Based on the presented predictors, an enhanced genetic algorithm is developed to optimize the EMI and can quickly find better solutions compared with the DRL approaches. As a result, this article proposes a detailed guideline for predicting and optimizing the EMI of pinmaps, and the proposed methodology can be further developed for promising intelligent system-level packaging design.","PeriodicalId":55012,"journal":{"name":"IEEE Transactions on Electromagnetic Compatibility","volume":"66 6","pages":"2123-2132"},"PeriodicalIF":2.0,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-14DOI: 10.1109/TEMC.2024.3474431
Chang-Sheng Mao;Da-Wei Wang;Wen-Sheng Zhao;Yue Hu
In this article, a pseudolabeling (PL) based semisupervised learning method is proposed to identify the eye diagram distortion for accurately locating the signal integrity (SI) problems of high-bandwidth memory (HBM) silicon interposer channels. First, four main factors influencing the eye diagrams are presented, and 12 different eye diagram distortions are considered. The proposed convolutional neural network (CNN) and four different models are trained to identify these eye diagram distortions, and it is demonstrated that the proposed CNN exhibits good performance. Then, the PL method is applied to further improve the model performance. Finally, with the combination of the proposed CNN and PL method, the accuracy reaches up to 97.5% and becomes 32.3% higher than LeNet. Simultaneously, the graphic processing unit memory usage of the proposed model is 39.2% less than that of AlexNet. The proposed method provides an effective way for fast and accurately localizing the source of the SI problems for HBM interposer.
{"title":"Pseudo-Labeling Based Semi-Supervised Learning for Signal Integrity Analysis of High-Bandwidth Memory (HBM) Interposer","authors":"Chang-Sheng Mao;Da-Wei Wang;Wen-Sheng Zhao;Yue Hu","doi":"10.1109/TEMC.2024.3474431","DOIUrl":"10.1109/TEMC.2024.3474431","url":null,"abstract":"In this article, a pseudolabeling (PL) based semisupervised learning method is proposed to identify the eye diagram distortion for accurately locating the signal integrity (SI) problems of high-bandwidth memory (HBM) silicon interposer channels. First, four main factors influencing the eye diagrams are presented, and 12 different eye diagram distortions are considered. The proposed convolutional neural network (CNN) and four different models are trained to identify these eye diagram distortions, and it is demonstrated that the proposed CNN exhibits good performance. Then, the PL method is applied to further improve the model performance. Finally, with the combination of the proposed CNN and PL method, the accuracy reaches up to 97.5% and becomes 32.3% higher than LeNet. Simultaneously, the graphic processing unit memory usage of the proposed model is 39.2% less than that of AlexNet. The proposed method provides an effective way for fast and accurately localizing the source of the SI problems for HBM interposer.","PeriodicalId":55012,"journal":{"name":"IEEE Transactions on Electromagnetic Compatibility","volume":"66 6","pages":"2056-2064"},"PeriodicalIF":2.0,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-14DOI: 10.1109/temc.2024.3462928
Madhawa Ranasinghe, Venkata Dinavahi
{"title":"Massively Parallel Hybrid TLM-PEEC Solver and Model Order Reduction for 3D Nonlinear Electromagnetic Transient Analysis","authors":"Madhawa Ranasinghe, Venkata Dinavahi","doi":"10.1109/temc.2024.3462928","DOIUrl":"https://doi.org/10.1109/temc.2024.3462928","url":null,"abstract":"","PeriodicalId":55012,"journal":{"name":"IEEE Transactions on Electromagnetic Compatibility","volume":"66 1","pages":""},"PeriodicalIF":2.1,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：