基于神经网络的超声波轻质燃油质量流量测量方法研究

摘要

The relationship between the light fuel ultrasonic velocity, its density and temperature is studied on the basis of a large amount of experimental data.The artificial neural network model is established to predict light fuel density of various batches and various manufactures, the predicting error of the density is less than 0.24%.A method of mass flow measurement by a ultrasonic flow meter has been given.With no need for the fuel standard density, the ultrasonic flow meter can measure the light liquid fuel mass measurement, the repeatability error of mass flow of a prototype proved to be less than 0.35%.%在对不同油品进行实验的基础上,分析了轻质燃油超声波传播速度、温度和密度之间的关系,建立了不同油品密度与温度和超声波传播速度之间人工神经网络模型.利用该模型,通过超声波速和温度测量,实现超声波流量计的直接质量计量,而不考虑油品批次和标准密度不同造成的影响.其密度测量误差小于0.24％,原理样机质量流量测量误差优于0.35％.