【作者】 陆宁；

【导师】 任长明；

【作者基本信息】 天津大学 ， 计算机应用技术， 2006， 硕士

【摘要】 软测量技术也称为软仪表技术。就是利用易测量过程变量(常称为辅助变量或二次变量),依据这些易测过程变量与难以直接测量的待测过程变量(常称为主导变量)之间的数学关系(软测量模型),通过各种数学计算和估计方法,从而实现对待测量过程的测量或估计。目前,软测量技术已成为过程控制领域的研究热点之一。本文介绍了BP神经网络、RBF神经网络和模糊神经网络的算法,在充分消化和吸收前人研究成果的基础上,以某炼油厂气体分馏装置为背景,根据生产装置的具体情况,在充分分析系统特性的基础上,找出非常具有代表意义的丙烯精馏塔,应用人工神经元网络的软测量技术,通过DCS的上位计算机的获得各辅助变量的实时数据为训练样本,分别用BP神经网络和RBF模糊神经网络对丙烯精制塔这一对象进行了模型辨识,将预测值和化验值进行比较,证明所辨识出的对象模型能够较好地表现出对象的动态行为,且具有较好的泛化性能。更多还原

【Abstract】 Soft measurement technology is also named soft instrument technology. It uses easy-to-measure process variable (It is also named assistant variable or secondary variable.), and bases on the relation (soft measurement model) between the easy-to-measure process variable and the need measuring process variable (It is also named main variable) which is difficult to measure directly to measure or estimate the need measuring process by all kinds of mathematic calculation and estimation methods. At present, the soft measurement technology has become one hotspot in the field of process control.In this thesis, it introduced the calculation methods of BP nerve net, RBF nerve net and blurry nerve net. Take the gas fractionation unit of one refinery as the background to find out a representative propylene fractionation tower which based on entirely digesting and absorbing the foretime study fruit, fully analyzing the system characteristic, and the details of production unit. Take the real time data of assistant variable obtained by top computer of DCS as the training sample, apply the BP nerve net and RBF blurry nerve net of manual nerve cell net soft measurement technology to the object propylene fractionation tower to conduct model identification, then compare the forecast value and the measurement to prove that the identified object model can well perform the dynamic action of the object and it has good popularization performance.更多还原