Predicting Mixing: A Strategy for Integrating Machine Learning and Discrete Element Method

被引:0
作者
Kumar, Sunil [1 ]
Garg, Yavnika [1 ]
Khatoon, Salma [1 ]
Dubey, Praveen [1 ]
Kumari, Kiran [1 ]
Anand, Anshu [1 ]
机构
[1] Indian Inst Technol Roorkee, Dept Chem Engn, Roorkee 247667, India
关键词
ROTATING DRUM; RADIAL SEGREGATION; GRANULAR MIXTURES; PARTICLE-SHAPE; SIMULATION; BEHAVIOR; DENSITY; SOLIDS; FLOW; DYNAMICS;
D O I
10.1021/acs.iecr.4c02147
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Segregation, the opposite of mixing, poses a common challenge in granular systems. Using a rotating drum as the basic mixing equipment, the fundamental focus of this study is to quantify undesirable segregation. The impact of particle level parameters (size, density, their combination, mass fraction) and system parameters (filling %, rotational speed, and baffle) on the segregation index within the rotating drum is first assessed using the discrete element method (DEM). Later, the machine learning (ML) model is applied in conjunction with DEM to expand and fill in the parameter space for particle-level parameters in a computationally efficient way, providing accurate predictions of segregation in less time. The DEM results are validated by comparing them with experimental data, ensuring their accuracy and reliability. The results show that optimal mixing is achieved when the total filling percent in a system is 36.3% while maintaining an equal proportion of particles. The highest level of mixing occurs at 60 rotations per minute, with fine particles concentrating near the drum's core and coarser particles distributed around the periphery. The presence of 3-4 baffles optimally enhances mixing performance. Four ML models-linear regression, polynomial regression, support vector regression, and random forest (RF) regression-are trained using data from DEM simulations to predict the segregation index (SI). An error analysis is performed to pick the best model out of the four ML models. The analysis reveals that the RF model accurately predicts the SI. Using the RF model, the SI can be reliably predicted for any value of the seven features studied using DEM. An example 3D surface plot is generated by considering just two (out of 7) of the most important particle level parameters: size and density. The result shows that while both particle size and density contribute to segregation, variations in particle size appear to have a more pronounced effect on the SI compared to particle density.
引用
收藏
页码:19640 / 19661
页数:22
相关论文
共 50 条
  • [21] Longitudinal and transverse mixing in rotary kilns: A discrete element method approach
    Finnie, GJ
    Kruyt, NP
    Ye, M
    Zeilstra, C
    Kuipers, JAM
    CHEMICAL ENGINEERING SCIENCE, 2005, 60 (15) : 4083 - 4091
  • [22] Investigation of mixing behaviors in a spouted bed with different density particles using discrete element method
    Ren, Bing
    Shao, Yingjuan
    Zhong, Wenqi
    Jin, Baosheng
    Yuan, Zhulin
    Lu, Yong
    POWDER TECHNOLOGY, 2012, 222 : 85 - 94
  • [23] Modeling of shield machine tunneling experiment by discrete element method
    Wu, Li
    Liu, Chang
    MECHATRONICS ENGINEERING, COMPUTING AND INFORMATION TECHNOLOGY, 2014, 556-562 : 1200 - 1204
  • [24] DESIGN OF SIMULATION STRATEGY FOR CORN CLEANING ON DISCRETE ELEMENT METHOD
    Li, Hua
    Gong, Hongju
    Yin, Wenqing
    COMPUTER AND COMPUTING TECHNOLOGIES IN AGRICULTURE II, VOL 1, 2009, 293 : 603 - 611
  • [25] Predicting breakage of high aspect ratio particles in an agitated bed using the Discrete Element Method
    Guo, Y.
    Wassgren, C.
    Hancock, B.
    Ketterhagen, W.
    Curtis, J.
    CHEMICAL ENGINEERING SCIENCE, 2017, 158 : 314 - 327
  • [26] Application of Positron Emission Particle Tracking (PEPT) to validate a Discrete Element Method (DEM) model of granular flow and mixing in the Turbula mixer
    Marigo, M.
    Davies, M.
    Leadbeater, T.
    Cairns, D. L.
    Ingram, A.
    Stitt, E. H.
    INTERNATIONAL JOURNAL OF PHARMACEUTICS, 2013, 446 (1-2) : 46 - 58
  • [27] Numerical study of particle mixing in a lab-scale screw mixer using the discrete element method
    Qi, Fenglei
    Heindel, Theodore J.
    Wright, Mark Mba
    POWDER TECHNOLOGY, 2017, 308 : 334 - 345
  • [28] Simulation of effect of internals on particulate mixing and heat transfer in downer reactor using discrete element method
    Liu, Bing
    Li, Yongwang
    POWDER TECHNOLOGY, 2016, 297 : 89 - 105
  • [29] Numerical study of the mixing efficiency of a batch mixer using the discrete element method
    Basinskas, Gytis
    Sakai, Mikio
    POWDER TECHNOLOGY, 2016, 301 : 815 - 829
  • [30] Machine-learning-enabled discrete element method: Contact detection and resolution of irregular-shaped particles
    Lai, Zhengshou
    Chen, Qiushi
    Huang, Linchong
    INTERNATIONAL JOURNAL FOR NUMERICAL AND ANALYTICAL METHODS IN GEOMECHANICS, 2022, 46 (01) : 113 - 140