硅锰铁合金埋弧炉三相电极功率在线估计  

An On-line Prediction Model of Three-phase Electrode Effective Power for Silicon-manganese Smelting Process

作　　者：唐春霞 阳春华[2] 桂卫华[2] 贺建军[2] 王红霞[3] 

机构地区：[1]长沙民政学院教务处,长沙410004 [2]中南大学信息科学与工程学院,长沙410083 [3]中国航空综合技术研究所标准化中心,北京100028

出　　处：《控制工程》2015年第5期969-974,共6页Control Engineering of China

基　　金：湖南省科技支撑计划(2011GK3177);国家自然科学基金项目(60843002)

摘　　要：针对硅锰合金埋弧炉三相电极功率不可测、难以实现三相熔池有效功率平衡的问题,提出了基于电源中心点和熔池中心点的三相电极功率在线估计方法,通过构造电源中心点,实现对电炉变压器高压侧各相电压、相电流、相有功功率的在线测量;通过构造熔池中心点,实现了变压器低压侧三相熔池电压的在线测量,基于能量守恒原理建立了硅锰铁合金埋弧炉电极有功功率机理模型。考虑到建模过程中各种假设和简化引起的估计误差较大,采用BP神经网络对机理模型进行在线补偿。将该方法应用于某铁合金厂12500k VA硅锰铁合金埋弧炉三相电极功率在线测量,结果表明其有效性。Considering the difficulty in the measurement of three-phase electrode effective power and the difficulty in balance of three phase electrode effective power, an on-line prediction method of three-phase electrode effective power was proposed. Firstly, an electrical zero in the primary circuit and a neutral point in the melting pool bottom were designed, where the phase voltage, phase current, phase active power in the primary side of transformer as well as the melting pool phase voltage can be measured. Then, a mechanism model of three-phase electrode effective power was proposed based on Energy Conservation Method and a BP neural network based model was applied to compensate its estimated error. At last, applying this method to estimate the three-phase electrode effective power of a 12500kVA submerged arc furnace, the results show that the proposed method has good performance.

关 键 词：硅锰铁合金埋弧炉 供电系统 功率估计 神经网络 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]