电磁暂态仿真模型敏捷生成方法研究  被引量:1

Research on agile generation method of electromagnetic transient simulation model

在线阅读下载全文

作  者:黄淼[1] 李韬 文旭 钟浩[3] HUANG Miao;LI Tao;WEN Xu;ZHONG Hao(College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;Southwest Subsection of State Grid, Chengdu 610041, China;Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station, Three Gorges University, Yichang 443002, China)

机构地区:[1]重庆邮电大学自动化学院,重庆400065 [2]国家电网公司西南分部,成都610041 [3]三峡大学梯级水电站运行与控制湖北省重点实验室,湖北宜昌443002

出  处:《重庆理工大学学报(自然科学)》2022年第2期191-196,共6页Journal of Chongqing University of Technology:Natural Science

基  金:国家自然科学基金项目(52007022);湖北省梯级水电站运行与控制重点实验室(三峡大学)开放基金项目(2019KJX05)。

摘  要:大型工业企业电网开展仿真建模时,根据描述电网结构的图形文件搭建仿真模型。针对这种情况,为提升仿真建模的效率,避免繁琐的手动建模过程,提出了一种电磁暂态仿真模型敏捷生成的新方法。首先,构建一种基于卷积神经网络(convolutional neural networks,CNN)的识别模型,用于识别图形文件中的电力元件;其次,基于矢量缓冲区提出一种判断电力元件连接关系的方法,用于识别元件之间的电气连接关系;最后,利用计算机程序生成相应的电磁暂态仿真数据文件。算例测试结果验证了所提方法的有效性。For modeling and simulation of large industrial enterprises powergrid,modeling based on the grid structure described by graphic files is the most basic and critical step.In order to improve the efficiency of simulation modeling and avoid tedious manual work,a novel agile generation method of electromagnetic transient simulation model is proposed.Firstly,a recognition model based on convolutional neural networks is constructed to identify electrical components in graphic files.Secondly,a method for judging the connection relationship between power components is proposed based on vector buffer,which is used to identify the electrical connection relationship.Finally,a computer program written by authors is used to generate the corresponding simulation data file.The simulation results on a test case show that the proposed method is effective.

关 键 词:电力系统 电磁暂态仿真 敏捷建模 卷积神经网络 

分 类 号:TM732[电气工程—电力系统及自动化]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象