摘要
双弯管法是以单弯管流量计为基础发展起来的一种固相质量流量测量方法,测量结果与其影响因素之间存在复杂的非线性关系,直接影响测量精度。在双弯管法测量原理的基础上,利用人工神经网络优良的非线性映射能力,建立了一个4层BP神经网络的软测量模型,以实验数据为样本对该模型进行训练,然后测试其测量精度。测试结果与实验数据一致性较好,最大误差在10%以内,该模型为固相质量流量的测量提供了一种有效的方法。
Double-elbow method is a kind of solid phase mass flow measuremwnt which is developed from the single-elbow tube flowmeter,the nonlinear relationship between measured results and its influencing factors is complex,which affect the accuracy of measurement directly. Based on the principle of double-elbow method,using the powerful nonlinear mapping ability of artificial neural network,a four layer BP neural network soft measurement model was established,with the experimental data as samples training for this model and test its accuracy of measurement. Test results are in good consistency with the experimental data,the maximum error is within 10%,the model provides an effective method for the solid mass flow measurement.
出处
《仪表技术与传感器》
CSCD
北大核心
2014年第7期103-105,共3页
Instrument Technique and Sensor
基金
国家自然科学基金项目(61271402)
河北省自然科学基金项目(F2010001970)
关键词
双弯管法
固相质量流量
BP神经网络
软测量
double-elbow method
solid phase mass flow rate
BP neural network
soft measurement