Key Technology of Embedded System Implementation for Software-based CNC System  

作　　者：WAN Jiafu LI Di ZHANG Ping 

机构地区：[1]College of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China [2]School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640, China [3]Department of Computer, Guangdong College of Mechanical and Electrical Technology, Guangzhou 510515, China

出　　处：《Chinese Journal of Mechanical Engineering》2010年第2期217-224,共8页中国机械工程学报（英文版）

基　　金：supported by National Natural Science Foundation of China(Grant No.50875090,Grant No.50905063);National Hi-tech Research and Development Program of China(863 Program,Grant No.2009AA4Z111);China Postdoctoral Science Foundation (Grant No.20090460769)

摘　　要：The software-based computer numerical control（CNC） system includes three types of tasks： periodic real-time tasks, aperiodic real-time tasks, and non-real-time tasks. The tasks are characterized by concurrency, hybridization, and correlation, which make system implementation difficult. The conventional scheduling algorithm can not meet the demands of system implementation in the software-based CNC system completely. The uncertainty factors when running real-time tasks affect control performance by degrading manufacturing accuracy as a result of system resource and processor use restrictions. To address the technical difficulty of embedded system implementation, a novel fuzzy feedback scheduling algorithm based on output jitter of key real-time tasks for a software-based CNC system is proposed. Time characteristics, such as sampling jitter, input-output jitter, and non-schedulability are discussed, followed by quantification through simulations of the impact of time characteristics on manufacturing accuracy. On the basis of this research, the scheduler architecture is designed, and then the algorithm table is calculated. When the system resource changes, the key periodic real-time tasks meet their deadlines by means of dynamically adjusting the task period. The simulated results show that the machining precision rises by an order of magnitude for the proposed scheduler in resource-constrained software-based CNC systems. Moreover, unlike conventional feedback scheduling methods, the algorithm in this paper does not rely on the availability of task execution times and is easy to implement while incurring only a small overhead.The software-based computer numerical control（CNC） system includes three types of tasks： periodic real-time tasks, aperiodic real-time tasks, and non-real-time tasks. The tasks are characterized by concurrency, hybridization, and correlation, which make system implementation difficult. The conventional scheduling algorithm can not meet the demands of system implementation in the software-based CNC system completely. The uncertainty factors when running real-time tasks affect control performance by degrading manufacturing accuracy as a result of system resource and processor use restrictions. To address the technical difficulty of embedded system implementation, a novel fuzzy feedback scheduling algorithm based on output jitter of key real-time tasks for a software-based CNC system is proposed. Time characteristics, such as sampling jitter, input-output jitter, and non-schedulability are discussed, followed by quantification through simulations of the impact of time characteristics on manufacturing accuracy. On the basis of this research, the scheduler architecture is designed, and then the algorithm table is calculated. When the system resource changes, the key periodic real-time tasks meet their deadlines by means of dynamically adjusting the task period. The simulated results show that the machining precision rises by an order of magnitude for the proposed scheduler in resource-constrained software-based CNC systems. Moreover, unlike conventional feedback scheduling methods, the algorithm in this paper does not rely on the availability of task execution times and is easy to implement while incurring only a small overhead.

关 键 词：software-based CNC system embedded system implementation output jitter fuzzy feedback scheduling manufacturing accuracy 

分 类 号：TP316[自动化与计算机技术—计算机软件与理论] TG659[自动化与计算机技术—计算机科学与技术]