PSO-ELM的浆体管道临界淤积流速预测模型研究  

Study on prediction model of critical deposition velocity in slurry pipeline based on PSO-ELM

作　　者：汪明先[1] 吴建德[1,2] 王晓东[1,2] WANG Ming-xian WU Jian-de WANG Xiao-dong(Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China Engineering Research Center for Mineral Pipeline Transportation of Yunnan, Kunming 650500, China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500 [2]云南省矿物管道输送工程技术研究中心,云南昆明650500

出　　处：《传感器与微系统》2017年第3期66-69,共4页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(51169007);云南省科技计划项目(2013DH034);云南省中青年学术和技术带头人后备人才培养计划项目(2011CI017)

摘　　要：针对浆体管道临界淤积流速预测难度大、精度低等问题,提出了粒子群优化—极限学习机(PSOELM)的临界淤积流速预测模型。利用PSO算法对ELM模型参数输入权值和隐元偏置进行优化,应用优化得到的ELM模型对预测集进行预测。通过实验仿真得到预测结果的最大误差为5.73%,预测效果优于常规的ELM模型和反向传播(BP)神经网络模型。Aiming at problems of great difficulties and low precision in predicting critical deposition velocity of slurry pipeline,a prediction model for critical deposition velocity based on particle swarm optimization and extreme learning machine（ PSO-ELM） is proposed. The method using PSO algorithm to optimize the ELM model parameters such as the input weight and hidden element bias,the optimized ELM model is used to predict prediction set. The maximum error of predicted result is 5. 73 % by experimental simulation,which shows that the prediction effect is superior to the conventional ELM and back propagation（ BP） neural network model.

关 键 词：浆体管道 临界淤积流速 粒子群优化算法 极限学习机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] X936[自动化与计算机技术—计算机科学与技术]