机械臂的CONN控制与CMAC控制的比较研究

由于正交神经网络算法简单，学习收敛速度快，具有线性、非线性逼近精度高等优异特性，取得了较好的应用效果，但在机器人动态建模与实时控制问题上研究较少。为此在机械臂的神经网络控制中，该文提出复合正交神经网络(CONN)与PID并行控制方法，并对小脑模型(CMAC)与PID并行控制作一比较研究。仿真结果表明，当阶跃输入与正弦输入时CONN与CMAC实现的前馈控制具有相同的控制效果，但CONN算法比CMAC算法更简单，这充分地体现了复合正交神经网络的特点。     

Implementation of real-time distributed control for discrete event robotic systems using Petri nets

This article presents a systematic method of modeling and implementing real-time control for discrete-event robotic systems using Petri nets. Because, in complex robotic systems such as flexible manufacturing systems, the controllers are distributed according to their physical structure, it is desirable to realize real-time distributed control. In this article, the task specification of robotic processes is represented as a system control-level net. Then, based on the hierarchical approach, it is transformed into detailed subnets, which are decomposed and distributed into the local machine controllers. The implementation of real-time distributed control through communication between the system controller and the machine controllers on a microcomputer network is described for a sample robotic system. The proposed implementation method is sufficiently general, and can be used as an effective prototyping tool for consistent modeling, simulation, and real-time control of large and complex robotic systems.     

机器人视觉伺服中CMAC学习控制系统研究

根据小脑模型关联控制器（CMAC）收敛速度快,适于实时控制系统的特点,设计了一种基于CMAC学习控制方法的机器人视觉伺服系统。在该系统中,CMAC被用作前馈视觉控制器对常规反馈控制器进行补偿。所提出的CMAC控制器替代图像雅可比矩阵来获得目标图像特征和机器人关节运动之间2D/3D变换关系,通过其在线学习,可以使系统对摄像机标定误差不敏感,从而提高系统的鲁棒性。实验证明了所设计控制系统的有效性。     

一种自适应CMAC在交流励磁水轮发电系统中仿真研究

在分析常规CMAC结构的基础上,针对一类非线性、参数时变和不确定的控制系统,提出了一种自适应CMAC神经网络的控制器．该控制器以系统动态误差和给定信号量作为CMAC的激励信号,并与自适应线性神经元网络相结合构成系统的复合控制．为了验证其有效性,将其应用到交流励磁水轮发电机系统的多变量非线性控制中,并与常规的PID控制效果进行了比较．仿真结果表明,该控制器具有较强鲁棒性和自适应能力,控制品质优良。     

基于FPGA的CMAC-PID控制器的研究

CMAC是一种局部学习神经网络，结构简单，收敛速度快；PID是目前应用最为广泛的控制算法。结合二者的优点，采用并行方式形成CMAC-PID控制器，进行了Matlab仿真实验。基于VHDL设计该控制器，重点在于CMAC的在线学习算法实现和控制器模块的闭环仿真测试。在FPGA上实现了该控制器，实验结果表明，该控制器运算速度快、精度高，具有较强的抗干扰性，是实现IP控制模块或单片智能控制的一种新的有效途径。     

基于CMAC网络的迭代学习初始控制策略

针对传统迭代学习控制在面临新的环境或控制任务时学习时间长、收敛速度慢的问题,首先引入迭代学习初始控制算法,并给出了算法收敛的充分必要条件;然后,利用小脑模型连接控制网络(CMAC)与反馈PID网络进行综合,在系统的历史控制经验基础上,估计系统的期望控制输入,作为迭代学习控制器的初始控制输入,再由开闭环P型迭代学习律逐步改善控制效果,从而避免了对初始控制输入量的盲目选择,使得系统的实际输出只需较少的迭代次数就能达到跟踪的精度要求。机器人系统的仿真结果表明了该算法的可行性与有效性。     

基于RBF辨识的CMAC在淀粉生产线中的控制研究

针对淀粉生产线中淀粉乳罐的液位控制精度问题,本文在分析了CMAC神经网络、单神经元和RBF辨识工作原理的基础上,设计了基于RBF辨识的自适应CMAC神经网络控制器调节淀粉生产线中乳液的液位。对自适应CMAC神经网络和基于RBF辨识的CMAC两种控制器进行了设计与仿真。防真结果表明,基于BRF辨识的自适应CMAC具有更好的跟踪效果和较快的响应速度,该系统具有很大的应用价值,不仅可以应用于淀粉生产线而且也为工业控制提供了更为精确的控制。     

CMAC(小脑模型)神经计算与神经控制

CMAC神经网络是局部学习网络,结构简单,收敛速度快,易于软件和和硬件实现 ,具有广泛的应用前景．本文综述了CMAC神经网络结构和算法,以及在控制中的应用,指出 了CMAC神经计算和神经控制发展方向及在实际应用中需解决的问题．     

作业型飞行机器人抓取后重心偏移的轨迹跟踪控制

作业型飞行机器人是指能够对环境施加主动影响的飞行机器人, 它通常由旋翼飞行器与机械臂组合而成. 本文针对作业型飞行机器人在动态飞行抓取后, 重心位置变化产生的系统控制难题, 设计了有效的跟踪控制策略. 首先, 在系统建模时引入重心偏移系统参数和重心偏移控制参数, 并考虑惯性张量不为常数, 提高了系统建模的精度. 然后, 在姿态解算时, 考虑重心偏移对系统性能的影响, 构建包含重心偏移系统参数的解算方法, 得到更高精度的期望翻滚角和期望俯仰角. 接着, 设计了基于滑模控制的重心偏移补偿位置控制器, 实现了有效的位置跟踪控制. 同时, 在姿态反演控制器的基础上, 加入自适应律估计重心偏移控制参数和变化的惯性张量, 再通过小脑神经网络逼近惯性张量的真实值, 提高姿态控制器的精度. 最后, 给出了所设计控制器的稳定性证明, 并在仿真环境下验证了所提出的方法的有效性和优越性.     

Gait Pattern Based on CMAC Neural Network for Robotic Applications

The main goal of this paper is to provide a general methodology and a practical approach for the design of gait pattern for biped robotic applications directly usable by researchers and engineers. This approach, which is based on CMAC neural network, is an alternative way in comparison to the traditional Central Pattern Generator. In the proposed method, the CMAC neural networks are used to learn basic motions (e.g. reference gait) and a Fuzzy Inference System allows to merge these reference motions in order to built more complex gaits. The results of our biped robotic applications show how to design a self-adaptive gait pattern according to average velocity and external perturbations.     

液位控制系统中混沌运动的小脑模型控制

一般的控制系统可能会因为一些非线性故障转变为混沌动力学系统.液位控制系统中的比例反馈回路中存在非线性环节,使液位控制系统的运动成为混沌运动.针对这种情况下的混沌数学模型,通过仿真验证小脑模型神经元网络控制方法,仿真图说明控制方法对混沌模型进行有效控制,可以将稳态值控制到与期望值一致.同时小脑模型神经元网络具有计算速度快的优点,这种控制方法在实际工程领域中的应用值得研究.     

Adaptive CMAC-based supervisory control for uncertain nonlinear systems.

An adaptive cerebellar-model-articulation-controller (CMAC)-based supervisory control system is developed for uncertain nonlinear systems. This adaptive CMAC-based supervisory control system consists of an adaptive CMAC and a supervisory controller. In the adaptive CMAC, a CMAC is used to mimic an ideal control law and a compensated controller is designed to recover the residual of the approximation error. The supervisory controller is appended to the adaptive CMAC to force the system states within a predefined constraint set. In this design, if the adaptive CMAC can maintain the system states within the constraint set, the supervisory controller will be idle. Otherwise, the supervisory controller starts working to pull the states back to the constraint set. In addition, the adaptive laws of the control system are derived in the sense of Lyapunov function, so that the stability of the system can be guaranteed. Furthermore, to relax the requirement of approximation error bound, an estimation law is derived to estimate the error bound. Finally, the proposed control system is applied to control a robotic manipulator, a chaotic circuit and a linear piezoelectric ceramic motor (LPCM). Simulation and experimental results demonstrate the effectiveness of the proposed control scheme for uncertain nonlinear systems.     

基于MATLAB的新型CMAC控制器的设计与仿真

在小脑神经网络(CMAC)与PID并行控制的基础上,提出了一种新型的CMAC控制器,即FCMAC控制器。这种把小脑神经网络与模糊控制(Fuzzy)结合起来的控制方法,具有两种控制方法的优点。本文中以某交流伺服电机作为控制对象,用MATLAB进行了仿真。仿真结果表明,FCMAC控制器具有较高的控制精度、良好的自适应特性。     

提高小脑模型神经网络精度的算法及仿真应用

CMAC(cerebella model articulation controller)神经网络的局部结构使得学习非线性函数更快.然而,在许多应用领域,CMAC的学习精度不能满足应用要求.该文提出了一种改进CMAC学习精度的联想插补算法,同时给出了一个仿真实验.其结果表明,使用此算法,改进的CMAC的学习精度比改进前提高了10倍,学习收敛也更快.     

基于神经网络与PID控制的挠性结构的混合控制研究

利用CMAC神经网络与PID控制算法，提出了一种针对飞行器挠性结构振动的混合控制方法．首先在给出系统动力学方程的基础上，利用CMAC神经网络的具体特点，给出了神经网络算法；进而将PID控制算法引入控制系统，形成了一种混合控制方法，该方法具有CMAC神经网络与PID控制算法两者的优点．最后针对复杂的飞行器挠性结构振动问题进行了实例仿真，说明了算法的有效性．     

基于CMAC与PID复合控制的汽轮机功率控制系统

针对汽轮机功率调节过程的非线性特征,提出了将CMAC神经网络与常规PID控制相结合的方法,并将其应用于汽轮机功率控制中。该复合控制方法可以实现前馈与反馈的联合控制,其中前馈控制由CMAC神经网络实现,反馈控制由常规PID控制器实现。通过对比分析CMAC/PID复合控制与常规PID控制的仿真结果,可以看到在不同的扰动因素存在时,CMAC/PID复合控制均能取得较好的控制效果。     

基于自组织模糊CMAC网络的非线性系统鲁棒自适应跟踪控制

基于自组织模糊CMAC(SOFCMAC)神经网络,提出了一种非线性模型参考神经网络 增广逆系统鲁棒自适应跟踪控制方法.该方法的特点是通过S0FCMAC神经网络在线修正由 于建模误差、不确定因素等引起的非线性系统逆误差,使得系统输出准确跟踪参考模型输出. SOFCMAC的权值调整规律由Lyapunov稳定性理论导出.文中证明了非线性闭环系统的稳定 性.仿真例子表明了本文方法的有效性.     

<Emphasis Type="Italic">HumanPT</Emphasis>: An Open-source,HumanPT Architecture-based,Robotic Application for Low Cost Robotic Tasks

In this paper, first HumanPT architecture for low cost robotic applications is presented. HumanPT architecture differs than other architectures because it is implemented on existing robotic systems (robot  robotic controller) and exploits the minimum communication facilities for real-time control that these systems provide. It is based on well-known communication methods like serial communication (USB, RS232, IEEE-1394) and windows sockets (server–client model) and permits an important number of different type of components like actuators, sensors and particularly vision systems to be connected in a robotic system. The operating system (OS) used is Microsoft Windows, the most widely spread OS. The proposed architecture exploits features of this OS that is not a real-time one, to ensure – in case that the robotic system provide such a facility – control and real time communication with the robotic system controller and to integrate by means of sensors and actuators an important number of robotic tasks and procedures. As implementation of this architecture, HumanPT robotic application and experimental results concerning its performance and its implementation in real tasks are provided. HumanPT robotic application, developed in Visual C++, is an integrated, but simultaneously an open-source software that can be adapted in different types of robotic systems. An important number of robotic tasks or procedures including sensors and particularly vision systems can be generated and executed. Small enterprises by means of the proposed architecture and the open source software can be automated at low cost enhancing in this way their production.     

Adaptive CMAC neural control of chaotic systems with a PI-type learning algorithm

The cerebellar model articulation controller (CMAC) has the advantages such as fast learning property, good generalization capability and information storing ability. Based on these advantages, this paper proposes an adaptive CMAC neural control (ACNC) system with a PI-type learning algorithm and applies it to control the chaotic systems. The ACNC system is composed of an adaptive CMAC and a compensation controller. Adaptive CMAC is used to mimic an ideal controller and the compensation controller is designed to dispel the approximation error between adaptive CMAC and ideal controller. Based on the Lyapunov stability theorems, the designed ACNC feedback control system is guaranteed to be uniformly ultimately bounded. Finally, the ACNC system is applied to control two chaotic systems, a Genesio chaotic system and a Duffing–Holmes chaotic system. Simulation results verify that the proposed ACNC system with a PI-type learning algorithm can achieve better control performance than other control methods.     

针对纯滞后系统神经网络Dahlin控制的研究

针对传统的基于Dahlin算法的控制器在大惯性、纯滞后、时变性、非线性对象的控制效果不佳,甚至发生不稳定现象的弱点,提出了以CMAC神经网络与Dahlia算法相结合的控制方法.以CMAC神经网络作为一个前馈控制器,实现时滞系统的自适应稳定控制.仿真实验表明,这种复合控制方法保留了Dahlin算法与CMAC神经网络的各自特长,同时具备学习速度快、适应能力强的优点,具有良好的稳定性和控制效果.