模锻过程结合机理与数据的智能控制方法

发布时间：2018-12-12 23:42

【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。
[Abstract]:Large-scale die forging process is a complex nonlinear time-varying process, including forging rheological forming process and hydraulic system driving process, as well as the existence of oil leakage and many other uncertain factors, resulting in the precision forging process control is extremely difficult. Based on the advantages of mechanism-based model control and data control, an intelligent control method based on physical model and on-line sequential learning machine is proposed. Firstly, the nominal control law is derived by using the known system information, secondly, the compensation control law of the online model is designed by using the on-line sequential limit learning machine for the uncertain part of the model. Finally, an integrated controller based on mechanism model and data model is established, and the optimal control law is obtained. The simulation results show that the new method can effectively control the complex forging process and has better control precision than the existing methods.
【作者单位】： 中南大学机电工程学院高性能复杂制造国家重点实验室;
【基金】：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)
【分类号】：TG316.3
，

本文编号：2375454