赵嘉乐1，童 昕1,2，李占福2,3，崔德海1
(1.华侨大学 机电及自动化学院，福建 厦门 361021；2.福建工程学院 福建省数控装备产业研究院，福建 福州 350118；3.中建海峡建设发展有限公司，福建 福州 350000)
DOI:10.13732/j.issn.1008-5548.2022.04.014
收稿日期： 2022-02-23， 修回日期：2022-06-01，在线出版时间：2022-06-22。
基金项目：福建省自然科学基金项目，编号：2020J01870。
第一作者简介：赵嘉乐(1997—)，男，硕士研究生，研究方向为计算机辅助设计与工程。E-mail:19013080048@stu.hqu.edu.cn。
通信作者简介：童昕(1964—)，男，教授，博士生导师，研究方向为计算机辅助设计。E-mail:Tongxin_hqu_fjut@163.com。
摘要：为了提高振动筛的筛分效率，采用离散元法对振动筛的筛分过程进行仿真模拟，分析筛分过程中颗粒触筛与透筛概率对筛分效率的影响，利用随机森林算法建立了筛机参数与颗粒触筛、透筛概率的数据模型，分析各筛机参数对颗粒触筛、透筛概率的影响权重及规律，结果表明：颗粒触筛概率主要受振动频率、振动幅度和振动方向角的影响；颗粒透筛概率主要受筛网倾角及筛孔孔径的影响。利用布谷鸟寻优算法进行参数优化，寻优得到振动频率为15 Hz,振动幅度为2 mm,振动方向角为50°,筛网倾角为20°,筛网长度为160 mm,筛孔孔径为1.0 mm,筛丝直径为0.7 mm为筛机参数的最优组合参数。
关键词：离散元法；触筛概率；透筛概率；随机森林算法；参数优化
Abstract：In order to improve the screening efficiency of the vibrating screen, the discrete element method was used to simulate the screening process of vibrating screen, and analyzed the impact of the particle contact probability and particle penetration probability on screening efficiency. The data model of sieve machine parameters and particle contact probability and particle penetration probability was established by random forest algorithm, and analyzed the weight and rule of the influence of the parameters of each vibration screen parameters on the particle contact probability and particle penetration probability. The results show that the particle contact probability is mainly influenced by vibration frequency, vibration amplitude and vibration direction angle. The particle penetration probability is mainly influenced by screen inclination angle and screen aperture size. The cuckoo search algorithm was used to optimized parameters, and the optimal combination of vibrating screen parameters is obtained as follows that vibration frequency is 15 Hz, vibration amplitude is 2 mm, vibration direction angle is 50°, screen inclination angle is 20°, screen length is 160 mm, screen aperture size is 1.0 mm, and screen wire diameter is 0.7 mm.
Keywords：discrete element method; particle contact probability; particle penetration probability; random forest algorithm; parameter optimization
参考文献（References）：
[1]JIANG H S,ZHAO Y M,QIAO J P,et al.Process analysis and operational parameter optimization of a variable amplitude screen for coal classification[J].Fuel,2017,194:329-338.
[2]DAVOODI A,ASBJÖRNSSON G,HULTHÉN E,et al.Application of the discrete element method to study the effects of stream characteristics on screening performance[J].Minerals,2019,9(12):788.
[3]SHEN G L,TONG X.Particle stratification of a vibrating screen with translation-swing composite motion[J].Journal of Vibroengineering,2020,22(3):498-508.
[4]LI Z F,JIA P Y,LI K Y,et al.Study on screening performance and parameter optimization of vibrating-dewatering screen[J].Advances in Mechanical Engineering,2021,13(9):97-100.
[5]CHEN Z Q,TONG X,LI Z F.Numerical investigation on the sieving performance of elliptical vibrating screen[J].Processes,2020,8(9):1151.
[6]CHEN B,YAN J,MO W,et al.DEM simulation and experimental study on the screening process of elliptical vibration mechanical systems[J].Journal of Vibroengineering,2019,21(8):2025-2038.
[7]李占福,童昕,周广涛.基于离散单元法的平摆筛设计及其透筛机理分析[J].机械设计与研究,2016,32(1):145-149.
[8]DAVOODI A,BENGTSSON M,HULTHÉN E,et al.Effects of screen decks’ aperture shapes and materials on screening efficiency[J].Minerals Engineering,2019,139(1):105699.
[9]温鹏飞,乔金鹏,段晨龙,等.变振幅等厚筛分过程物料透筛行为及分布研究[J].煤矿机械,2020,41(4):165-167.
[10]韦鲁滨,陈清如.煤用概率分级筛数学模型的研究[J].煤炭学报,1995(1):57-62.
[11]陈涛,童昕.基于DEM的筛分触筛机理的探究[J].矿山机械,2014,42(9):93-97.
[12]王翠,宁水根,王桂锋,等.基于摆动筛面设计的进料速率对分层和透筛的影响研究[J].机械设计,2021,38(4):117-122.
[13]PENG L P,FENG H H,WANG Z Q,et al.Screening mechanism and properties of a cantilevered vibrating sieve for particles processing[J].Applied Sciences,2019,9(22):4911.
[14]ASBJÖRNSSON G,BENGTSSON M,HULTHÉN E,et al.Model of banana screen for robust performance[J].Minerals Engineering,2016,91:66-73.
[15]DONG K,ESFANDIARY A H,YU A B.Discrete particle simulation of particle flow and separation on a vibrating screen:effect of aperture shape[J].Powder Technology,2016,314:195-202.
[16]FENG X,GONG Z P,WANG L J,et al.Behavior of maize particle penetrating a sieve hole based on the particle centroid in an air-screen cleaning unit[J].Powder Technology,2021,385:501-516.
[17]王奕森,夏树涛.集成学习之随机森林算法综述[J].信息通信技术,2018,12(1):49-55.
[18]李占山,刘兆赓.基于XGBoost的特征选择算法[J].通信学报,2019,40(10):101-108.
[19]GANDOMI A H,YANG X S,ALAVI A H.Cuckoo search algorithm:a metaheuristic approach to solve structural optimization problems[J].Engineering with Computers,2013,29(1):17-35.
