煤泥输送管道压力分布模型研究

摘要

In view of nonlinear characteristic of pressure distribution of high viscous materials like coal slurry in slurry pipeline,the paper put forward a kind of modeling method based on BP neural network optimized by quantum genetic algorithm after analysis of relationship of pipeline pressure and main influence factors based on experimental data.The method optimizes weights and thresholds of BP neural network by quantum genetic algorithm,and uses the optimized BP neural network to approximate nonlinear characteristics of the pipeline pressure of coal slurry,then gets mathematical model.The simulation results show that the pressure distribution model of coal slurry pipeline based on optimized BP neural network has good stability,its error is 0.063 2,which can satisfy engineering requirement,and it is better than the model based on BP neural network in optimization time and accuracy.%针对煤泥高浓度黏稠物料在煤泥输送管道中压力分布的非线性特性,通过实验数据分析管道压力与主要影响因素的关系,并提出一种基于量子遗传算法的BP神经网络建模方法.该方法采用量子遗传算法优化BP神经网络的权值和阈值,再用优化后的BP神经网络来逼近煤泥输送管道中压力分布的非线性特性,从而得到其数学模型.仿真结果表明,采用该方法建立的煤泥输送管道压力分布模型稳定性好,误差仅为0.063 2,满足了实际工程要求,且在寻优时间和准确性等方面均优于采用BP神经网络建立的模型.