Search

Your search keyword '"YAN Pengwei"' showing total 221 results
Start Over Author "YAN Pengwei"
221 results on '"YAN Pengwei"'

1. A fault current limiting control strategy for GFM converters based on directional current command

Author

WANG Nannan, ZOU Qiang, LU Yu, YAN Pengwei, TIAN Jie, and ZHAN Changjiang

Subjects
new power system, converter control, gfm control, fault current limiting, differential voltage orientation, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract

The grid-forming （GFM） control technology is instrumental in enabling converters to provide frequency and voltage support response akin to synchronous generators， thus bolstering the stability of the new power system. Nonetheless， a notable challenge lies in delivering grid support during fault current limiting. To this end， a strategy for fault current limiting in GFM converters based on measuring terminal and internal differential voltage orientation is proposed. In this approach， the angles of the positive and negative sequence current commands lag 90° behind the positive and negative sequence voltage differences. Additionally， the maximum magnitude of the synthesized vector of the current commands aligns with the converter’s overcurrent capability， which is equivalent to the generation of positive and negative sequence adaptive virtual inductance by control， respectively. This method obviates the need for direct virtual inductance value calculations and can maximize the maximum support capacity of the converter to realize the fault current characteristics resembling those of synchronous generators. The proposed fault current limiting strategy is validated by a simulation system built through PSCAD/EMTDC. The simulation outcomes affirm the strategy’s efficacy in delivering substantial grid support to the AC system while limiting fault currents.

Published
2023
Full Text
View/download PDF

2. LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model

Author

Lin, Tianqianjin, Yan, Pengwei, Song, Kaisong, Jiang, Zhuoren, Kang, Yangyang, Lin, Jun, Yuan, Weikang, Cao, Junjie, Sun, Changlong, and Liu, Xiaozhong

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Social and Information Networks
Abstract

Graph foundation models (GFMs) have recently gained significant attention. However, the unique data processing and evaluation setups employed by different studies hinder a deeper understanding of their progress. Additionally, current research tends to focus on specific subsets of graph learning tasks, such as structural tasks, node-level tasks, or classification tasks. As a result, they often incorporate specialized modules tailored to particular task types, losing their applicability to other graph learning tasks and contradicting the original intent of foundation models to be universal. Therefore, to enhance consistency, coverage, and diversity across domains, tasks, and research interests within the graph learning community in the evaluation of GFMs, we propose GFMBench-a systematic and comprehensive benchmark comprising 26 datasets. Moreover, we introduce LangGFM, a novel GFM that relies entirely on large language models. By revisiting and exploring the effective graph textualization principles, as well as repurposing successful techniques from graph augmentation and graph self-supervised learning within the language space, LangGFM achieves performance on par with or exceeding the state of the art across GFMBench, which can offer us new perspectives, experiences, and baselines to drive forward the evolution of GFMs., Comment: under review

Published
2024

3. Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration

Author

Yuan, Weikang, Cao, Junjie, Jiang, Zhuoren, Kang, Yangyang, Lin, Jun, Song, Kaisong, lin, tianqianjin, Yan, Pengwei, Sun, Changlong, and Liu, Xiaozhong

Subjects
Computer Science - Artificial Intelligence, Computer Science - Computation and Language, I.2.7
Abstract

Large Language Models (LLMs) could struggle to fully understand legal theories and perform complex legal reasoning tasks. In this study, we introduce a challenging task (confusing charge prediction) to better evaluate LLMs' understanding of legal theories and reasoning capabilities. We also propose a novel framework: Multi-Agent framework for improving complex Legal Reasoning capability (MALR). MALR employs non-parametric learning, encouraging LLMs to automatically decompose complex legal tasks and mimic human learning process to extract insights from legal rules, helping LLMs better understand legal theories and enhance their legal reasoning abilities. Extensive experiments on multiple real-world datasets demonstrate that the proposed framework effectively addresses complex reasoning issues in practical scenarios, paving the way for more reliable applications in the legal domain.

Published
2024

4. Empowering Dual-Level Graph Self-Supervised Pretraining with Motif Discovery

Author

Yan, Pengwei, Song, Kaisong, Jiang, Zhuoren, Kang, Yangyang, Lin, Tianqianjin, Sun, Changlong, and Liu, Xiaozhong

Subjects
Computer Science - Machine Learning, Computer Science - Social and Information Networks, Statistics - Methodology
Abstract

While self-supervised graph pretraining techniques have shown promising results in various domains, their application still experiences challenges of limited topology learning, human knowledge dependency, and incompetent multi-level interactions. To address these issues, we propose a novel solution, Dual-level Graph self-supervised Pretraining with Motif discovery (DGPM), which introduces a unique dual-level pretraining structure that orchestrates node-level and subgraph-level pretext tasks. Unlike prior approaches, DGPM autonomously uncovers significant graph motifs through an edge pooling module, aligning learned motif similarities with graph kernel-based similarities. A cross-matching task enables sophisticated node-motif interactions and novel representation learning. Extensive experiments on 15 datasets validate DGPM's effectiveness and generalizability, outperforming state-of-the-art methods in unsupervised representation learning and transfer learning settings. The autonomously discovered motifs demonstrate the potential of DGPM to enhance robustness and interpretability., Comment: 14 pages, 6 figures, accepted by AAAI'24

Published
2023

5. Detecting the Rumor Patterns Integrating Features of User, Content, and the Spreading Structure

Author

Yan, Pengwei, Yu, Guo, Jiang, Zhuoren, Lin, Tianqianjin, Yuan, Weikang, Liu, Xiaozhong, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Sserwanga, Isaac, editor, Joho, Hideo, editor, Ma, Jie, editor, Hansen, Preben, editor, Wu, Dan, editor, Koizumi, Masanori, editor, and Gilliland, Anne J., editor

Published
2024
Full Text
View/download PDF

50. Effect of the Fe 2 O 3 /SBA-15 Surface on Inducing Ozone Decomposition and Mass Transfer in Water.

Author

Yuan, Lei, Fang, Lele, Zhang, Jizhou, Yan, Pengwei, and Chen, Zhonglin

Subjects
FERRIC oxide, INTERFACIAL reactions, HYDROXYL group, WATER purification, MASS transfer
Abstract

Catalytic ozonation with metal oxides is of interest for advanced water treatment technology. The amount of active oxygen-containing radicals produced is a primary objective of this process. Fe2O3 is a widely used catalyst because of its high performance. In this study, Fe2O3/SBA-15 was synthesized and characterized. The results revealed that Fe2O3/SBA-15 was a nano-/mesoporous material with high-order hexagonal array structures and exhibited greater catalytic performance than Fe2O3 in ozonation processes. To investigate the role of the Fe2O3/SBA-15 surface in O3 decomposition, the kinetic constant was measured, and the interfacial reactions were discussed. Compared with Fe2O3, Fe2O3/SBA-15 significantly increased the formation of hydroxyl radicals (•OH) and the efficient utilization of O3 in the catalytic O3 decomposition process. The SBA-15 support decreased the O3 self-decomposition rate during catalytic ozonation with Fe2O3/SBA-15, which resulted in increased formation of •OH via the reaction between O3 and Fe2O3. From a practical point of view, Fe2O3/SBA-15 is an efficient green ozonation catalyst for water treatment. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results