多层感知机神经网络在SF6密度监测中的应用研究  

Research on the Application of Multi-Layer Perceptron Neural Network in SF6 Density Monitoring

在线阅读下载全文

作  者:程英哲 赵鑫成 李升晖 陈洁昊 潘威 林秋凯 CHENG Ying-zhe;ZHAO Xin-cheng;LI Sheng-hui;CHEN Jie-hao;PAN Wei;LIN Qiu-kai(Ultra High Voltage Branch,State Grid Fujian Electric Power Co.,Ltd.,Fuzhou 350011)

机构地区:[1]国网福建省电力有限公司超高压分公司,福州350011

出  处:《环境技术》2024年第10期81-86,共6页Environmental Technology

基  金:国网福建省电力有限公司科技项目资助(基于自校验智能式SF6气体密度继电器的技术研究及应用),项目编号:52130A24000C。

摘  要:电力系统柔性、稳定性和可靠性的进一步提高,不仅对设备本体智能化提出了更高的要求,而且对监控单元的智能化同样提出了更高的要求。六氟化硫(SF6)气体因其卓越的绝缘和灭弧特性,在高压电气设备中得到了广泛应用。然而,SF6气体只有在一定密度下才能保持其优良的电气性能。因此,SF6气体的密度监测对于电力系统的稳定运行至关重要。基于SF6气体监控系统智能化的迫切发展需求,本文提出了一种基于多层感知机(MLP)神经网络的SF6气体密度监测方法,旨在通过学习温度、压力等参数的变化规律,实现对SF6密度的准确预测,并通过网格搜索优化了网络架构和训练参数。仿真实验结果表明,所提出的MLP模型具有较高的拟合优度,验证了模型在SF6气体密度监测中的有效性。未来研究将致力于进一步优化模型,提高实时响应能力,为电力系统的智能化监测提供技术支撑。With the increasing global demand for electricity,the stability and reliability of power systems have become a focus of attention.Sulfur hexafluoride(SF6)gas is widely used in high-voltage electrical equipment because of its excellent insulation and arc extinguishing properties.However,SF6 gas can only maintain its excellent electrical properties at a certain density.Therefore,density monitoring of SF6 gas is crucial for the stable operation of power systems.In this paper,a SF6 gas density monitoring method based on multilayer perceptron(MLP)neural network is proposed,aiming to achieve accurate prediction of SF6 density by learning the changing law of temperature,pressure and other parameters,and optimizing the network architecture and training parameters through grid search.The results of simulation experiments show that the proposed MLP model has a high goodness of fit,which verifies the effectiveness of the model in SF6 gas density monitoring.Future research will be devoted to further optimizing the model,improving the real-time response capability,and providing technical support for intelligent monitoring of power systems.

关 键 词:SF6 密度监测 温度补偿 多层感知机 仿真实验 

分 类 号:TP29[自动化与计算机技术—检测技术与自动化装置]

 

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