基于神经元网络的大功率等离子体电弧加热器建模  

Modeling of High-power Plasma Arc Hearter Based on Neural Network

作　　者：马建平[1] 袁修荣 郝瑞祥[2] MA Jianping;YUAN Xiurong;HAO Ruixiang(China Academy of Aerospace Aerodynamics,Beijing 100074 China;School of Electrical Engineering,Beijing Jiaotong University,Beijing 100044 China)

机构地区：[1]中国航天空气动力技术研究院,北京100074 [2]北京交通大学电气工程学院,北京100044

出　　处：《高压电器》2021年第10期141-145,157,共6页High Voltage Apparatus

摘　　要：针对等离子体电弧加热器的电气特性进行研究,建立了一种基于电弧电流、电弧电压和气流量的等离子体电弧神经网络模型。该模型主要考虑了电弧电流以及气流量对电弧电压的作用。利用MATLAB软件的Simulink模块建立大功率等离子体电弧模型,并与搭建的大功率晶闸管整流电源电路进行联合仿真。仿真得到的数据与实验数据进行对比分析,仿真结果表明:该模型可以准确模拟等离子体电弧的伏安特性,能够为后续等离子体电弧电源系统控制系统的参数优化,改善动态特性,实现电弧加热器实验系统参数匹配优化等,提供重要支撑。The characteristics of the plasma arc heater is studied,and a plasma arc neural network model based on arc current,arc voltage and gas flow rate is established.The model mainly considers the effect of arc current and gas flow rate on arc voltage.The Simulink module of MATLAB software is used to establish a high-power plasma arc model,and a joint simulation is carried out with the constructed high-power thyristor rectifier power supply circuit.The data obtained from the simulation are compared with the experimental data.The simulation results show that the model can accurately simulate the volt-ampere characteristics of the plasma arc,which provides important support for the parameters optimization design of the control system of the plasma arc power system,improvement of dynamic performance,parameters matching optimization of plasma arc experiment system.

关 键 词：电弧模型 电弧加热器 RBF神经网络 MATLAB/SIMULINK 

分 类 号：V416.8[航空宇航科学与技术—航空宇航推进理论与工程] TP183[自动化与计算机技术—控制理论与控制工程]