基于MATLAB的多级离心泵性能预测建模的研究

发布时间：2018-10-09 14:00

【摘要】：多级离心泵是一种将机械能转化成输出液体动能的机械装置,其性能建模的准确性对机泵系统的耦合匹配效率有着直接影响。对于多级离心泵而言,目前还没有成熟的建模方法。伴随着计算机水平的迅猛发展,MATLAB软件被广泛应用于未知模型的建立和预测。因此,本文基于MATLAB仿真平台,采用黑箱建模的方法对多级离心泵进行性能预测建模。本文的主要研究工作如下：1)首先,简要介绍基于最小二乘法的曲线拟合原理,在此基础上采用实测数据分别得到多级离心泵的扬程、功率、效率与流量的关系,并利用GUI界面创建性能曲线拟合界面窗口。2)然后,以上述流量、扬程、效率数据作为输入量,功率作为输出量,建立多级离心泵的BP神经网络性能预测模型,并对预测结果进行分析。3)最后,采用遗传算法对上述模型进行优化。仿真对比实验证实：相较于上述的BP神经网络性能预测模型,经过遗传函数优化后的多级离心泵性能预测模型更加精确。本论文的研究工作得到国家科技支撑计划课题“大型流体机械节能技术研究与应用”(2013BAF01B02)的资助。
[Abstract]:Multistage centrifugal pump is a kind of mechanical device which converts mechanical energy into output liquid kinetic energy. The accuracy of its performance modeling has a direct impact on the coupling matching efficiency of the pump system. For multi-stage centrifugal pump, there is no mature modeling method. With the rapid development of computer, MATLAB software is widely used in the establishment and prediction of unknown models. Therefore, based on MATLAB simulation platform, the black box modeling method is used to predict the performance of multistage centrifugal pump. The main research work of this paper is as follows: (1) first of all, the principle of curve fitting based on the least square method is briefly introduced. On this basis, the relations among the lift, power, efficiency and flow rate of the multistage centrifugal pump are obtained by using the measured data, respectively. Using the GUI interface to create the performance curve fitting interface window .2) then, the performance prediction model of multistage centrifugal pump based on BP neural network is established with the data of flow, head and efficiency as input and power as output. Finally, genetic algorithm is used to optimize the model. The simulation results show that the performance prediction model of multistage centrifugal pump based on genetic function optimization is more accurate than the BP neural network model mentioned above. The research work of this thesis is supported by the research and application of energy saving technology of large fluid machinery (2013BAF01B02).
【学位授予单位】：安徽大学
【学位级别】：硕士
【学位授予年份】：2015
【分类号】：TH311

【相似文献】