摘要
双弯管法是一种基于弯管单相流测量原理的气固两相流固相质量流量测量方法,其测量结果与输入参数间非线性关系非常复杂,直接影响其测量精度。在双弯管法固相质量流量测量原理基础上,利用人工神经网络优良的非线性映射能力,建立了一种带有附加动量项的BP神经网络软测量模型,并在气固两相流测量实验平台上进行了实验研究。以实验数据为样本对双弯管法软测量模型进行训练,仿真结果与实验数据一致性较好,测量误差小于6%,为煤粉质量流量实时在线测量提供了一种行之有效的方法。
Double-elbow method is a kind of gas-solid two phase flow solid mass flow measurement which is based on elbow single-phase flow measuring principle,the nonlinear relationship between the measurement results and the input parameters is very complex,directly affect the measurement precision. Based on the principle of doubleelbow method of measuring mass flow,using the powerful nonlinear mapping ability of artificial neural network,a BP network soft measurement model is established which with additional momentum term; on gas-solid two-phase flow measurement experimental platform study is carried out. Using the experimental datas as sample,train this model,simulation results are in good consistency with the experimental datas,measurement error is within 6 %,provides an effective method for online measuring pulverized coal mass flow.
出处
《传感器与微系统》
CSCD
2015年第5期137-139,共3页
Transducer and Microsystem Technologies
基金
国家自然科学基金资助项目(61271402)
河北省自然科学基金资助项目(F2010001970)
关键词
双弯管法
煤粉质量流量
气固两相流
BP神经网络
double-elbow method pulverized coal mass flow gas-solid two-phase flow BP neural network
