Research on Multi-method Optimization and Fusion Control of Ball Mill Pulverizing System

Journal of Chuxiong Normal University ›› 2020, Vol. 35 ›› Issue (3): 20-25.

• Mathematics • Previous Articles Next Articles

Research on Multi-method Optimization and Fusion Control of Ball Mill Pulverizing System

MU Haifang^1,2, HAN Jun^1,2, LI Ming¹

1. School of Mechanical and Electronic Engineering,Suzhou University,Suzhou,Anhui Province 234000;
2. Coal Mine Electrical Engineering Eechnology Research Center,Suzhou University,Suzhou,Anhui Province 234000

Received:2019-11-22 Online:2020-05-20 Published:2020-12-28

Abstract

Abstract: The pulverizing system of ball mill is nonlinear,strong coupling and time-varying,making it a complex problem to realize its good control.Based on the existing control methods,the idea of multi-method hybrid optimization is put forward for its production process control.Firstly,the structure of the controller is established;secondly,the structure of the neural network,the back-propagation algorithm and the particle swarm optimization is optimized to complete the PID algorithm parameters adaptive adjustment;and finally,the system is controlled.The simulation results of a ball mill system show that,compared with general control methods,this method has better control quality because it has the characteristics of small overshoot,fast tracking and strong robustness.

Key words: ball mill, fuzzy, neural network, particle swarm optimization

CLC Number:

TG74

MU Haifang, HAN Jun, LI Ming. Research on Multi-method Optimization and Fusion Control of Ball Mill Pulverizing System[J]. Journal of Chuxiong Normal University, 2020, 35(3): 20-25.

References

[1] 郭伟,陈琛,王汉杰,等.一种改进的多变量广义预测控制在球磨机制粉系统中的应用[J].控制工程,2016
Guo W,Chen S,Wang H J,et al.Applications of an improved multivariable generalized predictive control in ball mill pulverizing system[J].Control Engineering of China,2016,23(1):48–53.
[2] 董君伊,孙立,李东海.球磨机制粉系统的线性自抗扰控制[J].工程科学学报,2015,37(4):509–516.
Dong J Y,Sun L,Li D H.Linear active disturbance rejection control for ball mill coal-pulverizing systems[J].Chinese Journal of Engineering,2015,37(4):509–516.
[3] 石硕,刘彦华,江溢洋,等.基于逆向解耦的球磨机系统的PID控制[J].计算机仿真,2013,30(8):384–388.
Shi S,Liu Y H,Jiang Y Y,et al.PID control for ball mill system based on inverted decoupling design[J].Computer Simulation,2013,30(8):384–388.
[4] 肖恭伟,欧吉坤,刘国林,等.基于改进的BP神经网络构建区域精密对流层延迟模型[J].地球物理学报,2018,61(8):3139–3148.
Xiao G W,Ou J K,Liu G L,et al.Construction of a regional precise tropospheric delay model based on improved BP neural network[J].Chinese Journal of Geophysics,2018,61(8):3139–3148.
[5] 宋召运,刘波,程昊,等.基于改进粒子群算法的串列叶型优化设计[J].推进技术,2016,37(8):1469–1476.
Song S Y,Liu B,Cheng H,et al.Optimization of tandem blade based on modified particle swarm algorithm[J].Journal of Propulsion Technology,2016,37(8):1469–1476.
[6] 司景萍,马继昌,牛家骅,等.基于模糊神经网络的智能故障诊断专家系统[J].振动与冲击,2017,36(4):164–171.
Si J P,Ma J C,Niu J H,et al.An intelligent fault diagnosis expert system based on fuzzy neural network[J].Journal of Vibration and Shock,2017,36(4):164–171.
[7] 王文中,张树生,余隋怀.基于粒子群优化的BP神经网络图像复原算法研究[J].西北工业大学学报,2018,36(4):709v714.
Wang W Z,Zhang S S,Yu S H.Image restoration by BP neural based on PSO[J].Journal of Northwestern Polytechnical University,2018,36(4):709–714.
[8] 许荣斌,王业国,王福田,等.基于改进PSO-BP算法的快递业务量预测[J].计算机集成制造系统,2018,24(7):1871–1879.
Xu R B,Wang Y G,Wang F T,et al.Prediction of package volume based on improved PSO-BP[J].Computer Integrated Manufacturing Systems,2018,24(7):1871–1879.
[9] 孙灵芳,孙晶淼.球磨机制粉系统建模及广义预测控制的研究与应用[J].系统仿真学报,2015,27(6):1329–1337.
Sun L F,Sun J M.Study of improved generalized predictive control in ball mill application[J].Journal of System Simulation,2015,27(6):1329–1337.
[10] 程启明,程尹曼,汪明媚,等.球磨机混合优化前向神经网络PID解耦控制系统[J].电力系统及其自动化学报,2010,22(2):54–59.
Cheng Q M,Cheng Y M,Wang M M,et al.Feed-forward neural network PID decoupling control system based on hybrid optimization algorithm for ball mill[J].Proceedings of the CSU-EPSA,2010,22(2):54–59.

Research on Multi-method Optimization and Fusion Control of Ball Mill Pulverizing System

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 0

Recommended Articles

Metrics

Comments