摘要
针对浆体管道的临界淤积流速存在预测难度高且计算较为复杂的问题,本文引入改进的人工蜂群算法(ABC)优化最小二乘支持向量机的方法对其做出了预测.为平衡算法的局部搜索和全局搜索性能,改进后的算法中的蜜蜂参考了雇佣蜂全局当前最优解和个体当前最优解的搜寻方式来展开寻优.通过实验仿真,结果表明:利用所提出的方法相比常规预测方法得到的预测效果更加精确,其均方根误差、平均相对误差以及平均绝对误差值仅分别为3.05%、1.00%和2.06%.同时,优于传统的临界淤积流速经验计算公式.
Aiming at the difficulty of predicting the critical deposition velocity in slurry pipeline and the complexity of calculation,this paper introduced the improved artificial bee colony algorithm(ABC)to optimize the least squares support vector machine(LSSVM)for predicting the critical deposition velocity.In order to balance the local search and global search performance of the algorithm,the bees in the improved algorithm refer to the global current optimal solution of hired bees and the individual current optimal solution.The simulation results show that the proposed method is more accurate than the conventional method.The mean square root error,average relative error and average absolute error are only 3.05%,1.00%and 2.06%respectively.Meanwhile,it is superior to the traditional empirical formula for calculating critical deposition velocity.
作者
杨静宗
杨天晴
周成江
潘安宁
Yang Jingzong;Yang Tianqing;Zhou Chengjiang;Pan Anning(School of Information,Baoshan University,Baoshan 678000,China;School of Information Engineering and Automation Chemistry,Kunming University of Technology,Kunming 650500,China)
出处
《南京师大学报（自然科学版）》
CAS
CSCD
北大核心
2020年第1期136-142,共7页
Journal of Nanjing Normal University(Natural Science Edition)
基金
国家自然科学基金项目(61563024)
保山学院科学研究基金项目(BYBS201802).
