刘晓飞,姚建涛,赵永生.基于模型的冗余驱动并联机构神经网络同步协调控制[J].农业机械学报,2018,49(2):367-375.
LIU Xiaofei,YAO Jiantao,ZHAO Yongsheng.Model-based Synchronous Control of Redundantly Actuated Parallel Manipulator with Neural Network[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(2):367-375.
摘要点击次数: 1872
全文下载次数: 984
基于模型的冗余驱动并联机构神经网络同步协调控制   [下载全文]
Model-based Synchronous Control of Redundantly Actuated Parallel Manipulator with Neural Network   [Download Pdf][in English]
投稿时间:2017-06-26  
DOI:10.6041/j.issn.1000-1298.2018.02.048
中文关键词:  并联机构  冗余驱动  驱动力同步协调  力位混合驱动  动力学模型  神经网络
基金项目:国家自然科学基金项目(51675458、51675459)、河北省自然科学基金项目(E2017203387)和河北省高等学校青年拔尖人才计划项目(BJ2017060)
作者单位
刘晓飞 燕山大学 
姚建涛 燕山大学 
赵永生 燕山大学 
中文摘要:冗余驱动并联机构驱动数目大于自由度数目,其各驱动关节间需要具有更高的驱动协调性。为了解决冗余驱动并联机构的驱动协调问题,本文提出了一种基于模型的驱动力同步协调控制方法。以冗余驱动并联机构6PUS+UPU为研究对象,在力位混合驱动的基础上,提出了一种驱动力同步协调控制策略;结合神经网络设计了驱动力同步控制器,并基于机构动力学模型设计了神经网络自学习算法。模型仿真与样机实验分别验证了本文方法的有效性。
LIU Xiaofei, YAO Jiantao and ZHAO Yongsheng
Yanshan University,Yanshan University and Yanshan University
Key Words:parallel manipulator  redundantly actuated  driving force synchronous control  force-position hybrid control  dynamic model  neural network
Abstract:Redundantly actuated parallel manipulator demands higher actuation coordination than the non-redundantly actuated one, thanks to its degree of actuation exceeding its degree of freedom. To improve the actuation coordination of redundantly actuated parallel manipulator, a novel model-based driving force synchronous control method with neural network was proposed. With 6PUS+UPU parallel manipulator as object, dynamic model was derived based on virtual work principle. To improve the actuation coordination of redundantly actuated parallel manipulator, a novel driving force synchronous control method was proposed on basis of force-position hybrid actuation. The synchronous control method was based on the driving force error of actuated joints and driving force adjustment was calculated by the synchronous controller. The synchronous controller was designed with neural network. What’s more, the learning law of neural network controller was derived with manipulator’s dynamic model to improve the learning efficiency. Model simulation and prototype experiment were carried out, and a performance comparison analysis with traditional force-position hybrid actuation method was made to verify the proposed control method. Comparison analysis revealed that, comparing with the traditional force-position hybrid actuation method, driving force synchronous control with neural network proposed could effectively improve the actuation coordination of redundantly actuated parallel manipulator. The results revealed that the synchronous control method reduced the driving force errors of whole manipulator by properly magnifying the control error of force actuated joint.

Transactions of the Chinese Society for Agriculture Machinery (CSAM), in charged of China Association for Science and Technology (CAST), sponsored by CSAM and Chinese Academy of Agricultural Mechanization Science(CAAMS), started publication in 1957. It is the earliest interdisciplinary journal in Chinese which combines agricultural and engineering. It always closely grasps the development direction of agriculture engineering disciplines and the published papers represent the highest academic level of agriculture engineering in China. Currently, nearly 8,000 papers have been already published. There are around 3,000 papers contributed to the journal each year, but only around 600 of them will be accepted. Transactions of CSAM focuses on a wide range of agricultural machinery, irrigation, electronics, robotics, agro-products engineering, biological energy, agricultural structures and environment and more. Subjects in Transactions of the CSAM have been embodied by many internationally well-known index systems, such as: EI Compendex, CA, CSA, etc.

   下载PDF阅读器