锻压技术

模锻过程结合机理与数据的智能控制方法

英文标题：Intelligent control method combining mechanism and data in the die forging process

作者：陈宇吕文兵陆新江

单位：中南大学

关键词：大型模锻成形机理模型在线顺序极限学习机物理模型控制器数据模型控制器集成模型控制器控制律

分类号：TG315.4

出版年,卷(期):页码：2017,42(4):170-178

摘要：

大型模锻成形过程是一个复杂的非线性时变过程，包括锻件流变成形过程与液压系统驱动过程，以及还存在油液泄漏等众多不确定性因素，导致精准锻造过程控制异常困难。为此，在结合基于机理模型控制与数据控制优点的基础上，提出了基于物理模型结合在线顺序极限学习机的智能控制方法。该方法首先使用已知的系统信息推导出名义控制律；其次，针对模型不确定性部分，使用在线顺序极限学习机设计出该在线模型的补偿控制律；最后，建立了基于机理模型与数据模型的集成控制器，获得了最佳控制律。仿真结果表明，新方法能有效地控制复杂的锻造过程，且比现有的方法有更好的控制精度。

The process of large die forging forming is a complex nonlinear and time-varying forging process that includes a rheological forming process and a driving process of hydraulic system. Therefore, the accurate forging control is extremely difficult due to the existence of oil leakage and many other uncertainties. So, based on the combination of mechanism model control and advantages of data control, an intelligent control method was put forward based on the combination of physical model and online sequential extreme learning machine (OS-ELM). Firstly, the nominal model control law was deduced by the known system information. Secondly, according to the model uncertain parts, the compensation control law of the online-model method was designed by OS-ELM. Lastly, the hybrid model controller based on the physical model and the data model was built, and the best control law was obtained. The simulation results demonstrate that the new method can effectively control the complex forging process and achieve better control accuracy.

基金项目：

国家重点基础研究发展计划(“973”计划)项目(2011CB706802)；国家自然科学基金资助项目(51205420)；新世纪人才计划基金(NCET-13-0593)；湖南省自然科学基金资助项目(14JJ3011)

陈宇(1990-)，男，硕士研究生 E-mail：1546319120@qq.com 通讯作者：陆新江（1979-），男，博士，教授 E-mail：luxj@csu.edu.cn

参考文献：

[1]黄长征，李小东，谭建平. 液压机速度控制技术新发展[J]. 锻压技术，2007, 32(5): 8-11.

Huang C Z, Li X D, Tan J P. Development trends on speed control of hydraulic press[J]. Forging & Stamping Technology, 2007, 32(5): 8-11.

[2]徐其川. 大型锻件（材）锻造变形制度的研究及应用[D]. 武汉：武汉轻工大学，2014.

Xu Q C. Study and Application on System of Forging Deformation for Large Forge Pieces[D]. Wuhan: Wuhan Polytechnic University, 2014.

[3]Chalupa P, Novak J. Modeling and model predictive control of a nonlinar hydraulic system [J]. Computers & Mathematics with Applications, 2013, 66(2): 155-164.

[4]于革刚，吴定安，吴进军，等. 大型模锻压机同步控制技术研究[J]. 锻压技术，2011, 36(3): 62-66.

Yu G G, Wu D A, Wu J J, et al. Research on synchronous control technology for larger forging press[J]. Forging & Stamping Technology, 2011, 36(3): 62-66.

[5]刘新良. 巨型模锻液压机主动同步控制系统研究[D]. 长沙：中南大学, 2010.

Liu X L. Gaint Die Forging Hydraulic Press Active Control System Research[D]. Changsha：Central South University, 2010.

[6]周恩涛, 廖生行, 牟丹. 电液比例阀控系统模糊-PID 控制的研究[J]. 机床与液压, 2003, 31(6): 225-227.

Zhou E T, Liao S H, Mou D. Fuzzy-PID control in electro-hydraulic proportional valve system[J]. Machine Tool and Hydraulics, 2003,31(6): 225-227.

[7]陈晓祺. 液压锻造机非线性控制策略研究[D]. 天津：天津大学, 2010.

Chen X Q. Research on Nonlinear Control Method of Hydraulic Forging Machine System[D]. Tianjin：Tianjin University, 2010.

[8]张猛. 极低速下大型模锻压机系统建模与动态特性分析[D]. 长沙: 中南大学, 2012.

Zhang M. System Modeling and Dynamic Performance Analysis for Huge Die-Forging Press under Extremely Low Speed[D]. Changsha: Central South University, 2012.

[9]李文坚，李毅波，潘晴. 基于LuGre模型的大型模锻装备低速摩擦补偿分析[J]. 锻压技术，2015，40(1): 71-75.

Li W J, Li Y B, Pan Q. Analysis on low-velocity friction compensation of large forging equipment based on LuGre-model[J]. Forging & Stamping Technology, 2015, 40(1): 71-75.

[10]邓坎. 复杂模锻全过程锻压变形力建模及其验证[D]. 长沙：中南大学，2014.

Deng K. Deformation Force Modeling for the Whole Complex Forging Process and Its Verification[D]. Changsha: Central South University, 2014.

[11]Chen S W, Wu M H, Zhao S. Analog circuit fault diagnosis based on DEOS-ELM[J]. Seventh International Symposium on Computational Intelligence & Design, 2014, 1: 509-513.

[12]Kumar V, Gaur P, Mittal A P. Trajectory control of DC servo using OS-ELM based controller[J]. Power India Conference, 2012, 5 :1-5.

[13]Huang G B, Bai Z, Kasun L L C, et al. Local receptive fields based extreme[J]. IEEE Computational Intelligence Magazine, 2015, 10(2): 18-29.

[14]Song Y, Liò P. A new approach for epileptic seizure detection: sample entropy based feature extraction and extreme learning machine[J]. Journal of Biomedical Science and Engineering, 2010, 3(6): 556-567.

[15]Deng H, Lio H X. A novel neural approximate inverse control for unknown nonlinear discrete dynamical systems[J]. IEEE Transactions on Systems Man & Cybernetics, Part B: Cybernetics A Publication of the IEEE Systems Man & Cybernetics Society, 2005, 35(1): 115-123.

[16]Kasun L L C, Zhou H, Huang G B, et al. Representational learning with extreme learning machine for big data [J]. IEEE Intelligent System, 2013, 28(6): 1-4.

[17]Spooner J T, Maggiore M, Ordonez R, et al. Stable Adaptive Control and Estimation for Nonlinear Systems[M]. New York: Wiley Inter Science, 2002.

[18]彭德奇，罗伟，张彦宇. 基于SVM模型的快速锻压机智能控制算法[J]. 计算机测量与控制, 2012, 20(1): 88-90.

Peng D Q, Luo W, Zhang Y Y. Intelligent control based on SVM prediction for fast forging hydraulic press[J]. Computer Measurement & Control, 2012, 20(1): 88-90.

服务与反馈：

【文章下载】【加入收藏】