基于指令滤波的机械臂有限时间输出约束阻抗控制

提出一种基于指令滤波的机械臂有限时间输出约束阻抗控制方法.通过阻抗控制技术来解决机械臂与环境之间的相互作用,使机械臂跟踪期望轨迹.通过有限时间控制提高机械臂控制的响应速度,缩小跟踪误差,并引入障碍Lyapunov函数对机械臂末端输出状态进行约束.采用模糊自适应技术处理机械臂系统中的未知摩擦量和外部扰动量.仿真结果表明:该方法实现了对期望轨迹的有效跟踪控制,并且使机械臂输出状态都限制在预定义的约束空间中,具有更快的响应速度和更好的跟踪效果.     

基于自适应神经网络控制的机械臂运动轨迹跟踪误差研究

针对机械臂受到外界干扰时运动不稳定、轨迹跟踪误差较大等问题,提出了自适应神经网络控制方法。给出了机械臂动力学方程式,利用正反馈神经网络研究机器臂的动力学特性。设计了自适应神经网络控制系统,通过李雅普诺夫函数证明了该闭环系统的稳定性和收敛性。建立了机械臂模型简图,采用Matlab/Simulink软件对机械臂动力学参数进行仿真。同时,与PID控制系统仿真结果进行对比和分析。仿真结果显示,机械臂运动轨迹在受到外界干扰情况下,采用自适应神经网络控制运动轨迹跟踪误差较小,输入转矩波动较小。机械臂采用自适应神经网络控制方法,可以提高运动轨迹的控制精度,削弱了机械臂运动的抖动现象。     

具有未建模动态机械臂的自适应神经网络控制

对于具有未建模动态机械臂系统,基于神经网络对非线性函数的拟合特性,用径向基神经网络来补偿机械臂系统中的未建模动态,同时提出的自适应神经网络控制器,可以保证具有未建模动态的非线性机械臂系统的渐进稳定特性.仿真结果验证了这种控制策略的有效性.     

无模型机械臂BP神经网络状态观测及反演跟踪控制

针对摩擦阻尼及模型参数不确定的情况,运用反演控制设计策略,针对多连杆机械臂提出了一种基于神经网络观测器的无模型轨迹跟踪控制方法。运用带有修正项的自适应BP神经网络观测器对不可测状态量进行观测,同时对系统模型进行在线逼近。在此基础上设计了基于观测状态和逼近模型的反演跟踪控制器, Lyapunov稳定性理论证明了该控制器能够保证跟踪误差的有界和闭环系统中所有信号的有界。跟踪给定轨迹的仿真实验证明了该方法的有效性。     

具有状态约束的电液伺服系统模型参考鲁棒自适应控制

针对电液伺服系统中的模型不确定性和状态约束问题,设计了一种模型参考鲁棒自适应控制(MRRAC)方法。将电液伺服系统的近似模型作为模型预测控制(MPC)的设计对象,在设计过程中考虑状态约束,并生成受约束的状态期望,作为后续伺服控制方法的参考指令。为了克服液压系统中的模型不确定性,基于反步法设计了鲁棒自适应控制器(RAC),实现了兼顾模型不确定性和状态约束的伺服控制。基于Lyapunov稳定性理论证明了所设计控制策略的闭环渐近稳定性,且系统所有信号均有界。仿真结果表明,控制器对于系统模型不确定性具有较强的鲁棒性,且可实现对指定状态的有效约束,充分验证了该控制策略的有效性。     

漂浮基空间柔性机械臂基于神经网络的逆模控制

针对传统控制方法对强耦合柔性空间机械臂难以有效控制的问题,提出基于神经网络的逆模控制策略。建立了非线性空间柔性机器人的动力学模型,根据增广变量输入法推得其控制律;利用具有良好逼近能力的前馈神经网络来自适应补偿柔性臂的未知非线性逆模型;采用Kalman滤波算法来保证网络权值在线实时调整(系统的误差代价函数由PID控制器提供)。仿真证明了所提出的控制方案的有效性,具有较高工程应用价值。     

水下机械臂运动空间分析与轨迹跟踪算法优化

针对水下机械臂动力学模型不确定和未知外界干扰问题,采用基于HJI理论的径向基函数神经网络自适应控制算法对水下机械臂进行控制。首先,以水下六自由度机械臂为例,基于D-H法则对水下机械臂的运动学进行分析,通过仿真验证该方法的正确性;接着,基于蒙特卡洛法构建水下六自由度机械臂的运动空间云图,真实反映水下机械臂的运动空间;然后,以二自由度水下机械臂为例,设计基于HJI理论的RBF神经网络自适应控制器,利用神经网络的万能逼近原理逼近不确定干扰项,考虑到神经网络逼近存在误差,将逼近误差看作外界干扰项并通过HJI理论对逼近误差在线评价,评价系统对干扰项的抑制能力,并采用自适应算法在线估计网络权值,加快系统收敛;最后,通过仿真可知,该机械臂能较好地完成轨迹跟踪。     

基于最优拉丁Widrow-Hoff网络的变负载机械臂自适应鲁棒控制

为了进一步提高机械臂在变负载下控制精度,设计了一种基于最优拉丁Widrow-Hoff网络的变负载机械臂自适应鲁棒控制方法。采用模态分解法创建关于机械臂的动力学状态方程,再以最优拉丁神经网络为基础提出具备自适应性能的鲁棒控制器,有利于加强机械臂在变负载情况下的系统鲁棒性以及控制精准度。仿真结果表明,利用最优拉丁Widrow-Hoff网络针对系统非线性实施估计,通过观测器系统总干扰实施补偿与估计,可以适应各种负载工况。试验验证文中所设计控制器具备较强的鲁棒性;可以全面考虑系统干扰以及系统非线性等各类因素,更契合控制的现实应用场景,具有更高的跟踪精准度。该研究有助于提高机器人的动作精度,为后续的特种环境的是适应性起到一定的推进作用。     

存在振动的某机械臂控制研究

针对火炮自动装填系统机械臂的控制问题,建立了整个机械臂的简化模型,并推导存在振动的机械臂的动力学方程,以便在实验室进行研究。使用ADAMS与Matlab机电联合仿真系统对机械臂进行仿真。通过使用传统的PID控制方案和模糊自适应PID控制方案分别对机械臂进行仿真,对2种方案的结果进行对比。结果表明:模糊自适应PID控制的抗干扰能力较强,能够满足存在振动和变负载条件下机械臂的控制。     

机械臂反演非奇异终端的神经滑模控制

为了解决具有外部干扰以及建模误差的多关节机械臂的轨迹跟踪问题,提出了一种机械臂反演非奇异终端的神经滑模控制方法。采用非奇异终端的滑模面,基于反演方法以及滑模控制的原理,设计了反演滑模控制器。针对由于外部干扰以及建模误差引起的反演滑模控制系统中不确定的因素上界,设计了径向基(radial basis function,简称RBF)神经网络的自适应律,对不确定因素上界进行了在线估计,并对控制系统的稳定性使用了Lyapunov定理进行证明。仿真分析结果表明,所提出的方法不仅可以减少系统中存在的抖振现象,而且具有较好的轨迹跟踪性能和较强的鲁棒性。     

基于CNN-GRU的遥操作机器人操作者识别与自适应速度控制方法

传统空间遥操作系统中从端机械臂的运动速度完全取决于操作者的操作速度.为了提高空间遥操作系统的安全性,提出了一种基于操作者操作速度识别的自适应速度控制方法.结合深度学习的理论,提出了一种基于卷积神经网络(CNN)和门控循环单元(GRU)神经网络的融合模型来对操作者的速度进行识别分类.选取了九位受试者构建操作者速度样本库,...     

采摘机械臂的PSO-RBF神经网络自适应控制

针对采摘机械臂系统的不确定性为控制带来的问题,设计一种PSO-RBF神经网络自适应控制方法.该方法使用径向基函数神经网络来逼近并补偿系统模型误差,用粒子群优化算法来优化RBF的权值参数,确保PSO-RBF控制性能更好.MATLAB仿真结果表明:与RBF神经网络控制相比,PSO-RBF神经网络控制精度和性能更好.     

基于RBF神经元网络的漂浮基空间机械臂关节运动自适应控制方法

讨论了栽体位置、姿态均不受控制情况下,漂浮基空间机械臂关节运动的控制问题.由拉格朗日第二类方法及系统动量、动量矩守恒关系,建立了漂浮基空间机械臂完全能控形式的系统动力学方程.以此为基础,借助于RBF神经网络技术、Ge-Lee(GL)矩阵及其乘积算子定义,对漂浮基空间机械臂进行了神经网络系统建模;针对空间机械臂系统所有惯性参数均未知的情况,设计了漂浮基空间机械臂关节运动的自适应神经网络控制方案.提出的控制方案不要求系统动力学方程具有通常的关于惯性参数的线性性质,且无需预知系统惯性参数的任何信息,也无需对神经网络进行离线训练、学习,此外,由于充分利用了空间机械臂的系统动力学特性,因此在控制过程中不需要反馈、测量漂浮基的位置、移动速度、移动加速度以及姿态转角的角速度、角加速度.一个平面两杆漂浮基空间机械臂的系统数值仿真证实了该方案的有效性.     

Diagonal recurrent neural network based adaptive control of nonlinear dynamical systems using lyapunov stability criterion

In this paper adaptive control of nonlinear dynamical systems using diagonal recurrent neural network (DRNN) is proposed. The structure of DRNN is a modification of fully connected recurrent neural network (FCRNN). Presence of self-recurrent neurons in the hidden layer of DRNN gives it an ability to capture the dynamic behaviour of the nonlinear plant under consideration (to be controlled). To ensure stability, update rules are developed using lyapunov stability criterion. These rules are then used for adjusting the various parameters of DRNN. The responses of plants obtained with DRNN are compared with those obtained when multi-layer feed forward neural network (MLFFNN) is used as a controller. Also, in example 4, FCRNN is also investigated and compared with DRNN and MLFFNN. Robustness of the proposed control scheme is also tested against parameter variations and disturbance signals. Four simulation examples including one-link robotic manipulator and inverted pendulum are considered on which the proposed controller is applied. The results so obtained show the superiority of DRNN over MLFFNN as a controller.     

Development of an adaptive radial basis function neural network estimator-based continuous sliding mode control for uncertain nonlinear systems

In this paper an adaptive neural network (NN)-based nonlinear controller is proposed for trajectory tracking of uncertain nonlinear systems. The adopted control algorithm combines a continuous second-order sliding mode control (CSOSMC), the radial basis function neural network (RBFNN) and the adaptive control methodology. First, a second-order sliding mode control scheme (SOSMC), which is published recently in literature for linear uncertain systems, is extended for nonlinear uncertain systems. Second, an adaptive radial basis function neural network estimator-based continuous second order sliding mode control algorithm (CSOSMC-ANNE) is adopted. In CSOSMC-ANNE control methodology, a radial basis function neural network with adaptive parameters is exploited to approximate the unknown system parameters and improve performance against perturbations. Also, the discontinuous switching control of SOSMC is supplanted with a smooth continuous control action to completely eliminate the chattering phenomenon. The convergence and global stability of the closed-loop system are proved using Lyapunov stability method. Numerical computer simulations, with dynamical model of the nonlinear inverted pendulum system, are presented to demonstrate the effectiveness and advantages of the presented control scheme.     

Intelligent phase plane switching control of a pneumatic muscle robot arm with Magneto-Rheological Brake

Pneumatic cylinders are one kind of low cost actuation sources which have been applied in industrial and robotics field, since they have a high power/weight ratio, a high-tension force and a long durability. To overcome the shortcomings of conventional pneumatic cylinders, a number of newer pneumatic actuators have been developed such as McKibben Muscle, Rubber Actuator and Pneumatic Artificial Muscle (PAM) Manipulators. However, some limitations still exist, such as the air compressibility and the lack of damping ability of the actuator bring the dynamic delay of the pressure response and cause the oscillatory motion. In addition, the nonlinearities in the PAM manipulator still limit the controllability. Therefore, it is not easy to realize motion with high accuracy and high speed and with respect to various external inertia loads. To overcome these problems, a novel controller which harmonizes a phase plane switching control method (PPSC) with conventional PID controller and the adaptabilities of neural network is newly proposed. In order to realize satisfactory control performance a variable damper, Magneto-Rheological Brake (MRB), is equipped to the joint of the robot. The mixture of conventional PID controller and an intelligent phase plane switching control using neural network (IPPSC) brings us a novel controller. The experiments were carried out in a robot arm, which is driven by two PAM actuators, and the effectiveness of the proposed control algorithm was demonstrated through experiments, which had proved that the stability of the manipulator can be improved greatly in a high gain control by using MRB with 1PPSC and without regard for the changes of external inertia loads.     

Improvement of the control performance of pneumatic artificial muscle manipulators using an intelligent switching control method

Problems with the control, oscillatory motion and compliance of pneumatic systems have prevented their widespread use in advanced robotics. However, their compactness, power/weight ratio, ease of maintenance and inherent safety are factors that could be potentially exploited in sophisticated dexterous manipulator designs. These advantages have led to the development of novel actuators such as the McKibben Muscle, Rubber Actuator and Pneumatic Artificial Muscle Manipulators. However, some limitations still exist, such as a deterioration of the performance of transient response due to the changes in the external inertia load in the pneumatic artificial muscle manipulator. To overcome this problem, a switching algorithm of the control parameter using a learning vector quantization neural network (LVQNN) is newly proposed. This estimates the external inertia load of the pneumatic artificial muscle manipulator. The effectiveness of the proposed control algorithm is demonstrated through experiments with different external inertia loads.     

Adaptive Real-time Predictive Compensation Control for 6-DOF Serial Arc Welding Manipulator

Because of long driving chain and great system load inertia, the serial manipulator has a serious time delay problem which leads to significant real-time tracking control errors and damages the welding quality finally. In order to solve the time delay problem and enhance the welding quality, an adaptive real-time predictive compensation control(ARTPCC) is presented in this paper. The ARTPCC technique combines offline identification and online compensation. Based on the neural network system identification technique, the ARTPCC technique identifies the dynamic joint model of the 6-DOF serial arc welding manipulator offline. With the identified dynamic joint model, the ARTPCC technique predicts and compensates the tracking error online using the adaptive friction compensation technique. The ARTPCC technique is proposed in detail in this paper and applied in the real-time tracking control experiment of the 6-DOF serial arc welding manipulator. The tracking control experiment results of the end-effector reference point of the manipulator show that the presented control technique reduces the tracking error, enhances the system response and tracking accuracy efficiently. Meanwhile, the welding experiment results show that the welding seam turns more continuous, uniform and smooth after using the ARTPCC technique. With the ARTPCC technique, the welding quality of the 6-DOF serial arc welding manipulator is highly improved.     

基于多传感器的工业机械臂精细化操作远程控制方法

为实现远程控制工业机械臂时的精细化操作,使其关节轨迹具有连续、平稳、光滑的控制效果,提出基于多传感器的工业机械臂精细化操作远程控制方法。优化传感器的布局,以便采集信息;利用新息变化野值检测方法消除工业机械臂精细化操作中存在的野值,提高关节角度与速度信息的完整性和精度;将滑模控制与神经网络结合,消除因非线性、摩擦非线性和未知参数等不确定性因素对机械臂精细化操作的影响,构建工业机械臂操作远程控制器,实现工业机械臂精细化操作的远程控制。实验结果表明,所提方法可精准控制工业机械臂的关节角度与速度,具有较高的灵活性和高效性。     

基于神经网络PID的冗余伺服系统自适应控制

建立冗余直接驱动式电液伺服系统的数学模型。针对电液伺服系统时变、强非线性的特点以及冗余伺服系统在余度降级过程中的故障瞬态现象和余度降级后的性能降级现象,考虑传统PID控制器自适应能力不强、鲁棒性差等缺陷,提出神经网络自适应控制方案。根据冗余电液伺服系统的特点和目前神经网络控制的发展水平,采用基于径向基函数神经网络的智能PID控制器实现冗余伺服系统的自适应控制。研究结果表明：该控制器能够根据控制指令、被控对象结构参数等因素的变化实时调整控制器参数,和传统PID控制器相比具有控制精度高、鲁棒性强的特点,可以有效地克服冗余伺服系统余度切换时的故障瞬态现象和余度降级后的性能降低现象。