Rule-based supervisory control of a two-link flexible manipulator

In this paper, we propose a two level hierarchical control strategy to achieve accurate end-point position of a planar two-link flexible manipulator. The upper level consists of a feedforward rule-based supervisory controller that incorporates fuzzy logic, whereas the lower level consists of conventional controllers that combine shaft position-endpoint acceleration feedback for disturbance rejection properties and shaping of the (joint) actuator inputs to minimize the energy transferred to the flexible modes during commanded movements. The effectiveness of this hierarchical control strategy is verified by experimental results for various movements of the links, in various configurations. In particular, we illustrate how the hierarchical intelligent control strategy performs better than conventional control techniques for endpoint position control in the presence of flexure effects.     

Experimental study for trajectory tracking of a two-link flexible manipulator

In this paper, the dynamical equations of a two-link flexible manipulator moving in the vertical plane are derived. The system is divided into a fast subsystem and a slow subsystem via the singular perturbation method. Considering the characteristics of a flexible manipulator, a compensated controller is designed for each joint angle. A combined robust control algorithm is proposed, which includes a sliding mode variable structure for the slow subsystem and H infinity control strategy for the fast subsystem. Experimental results of this combined robust controller are compared with those of the standard PID controller and a significant performance is well demonstrated.     

Adaptive manipulator trajectory control using neural networks

A unified study of adaptive control and neural network based control schemes for the trajectory tracking problem of robot manipulators is presented. Efficacy of parametrized adaptive algorithms in compensating the structured uncertainties in robot dynamics is verified through extensive simulation. The ability of neural networks to provide a robust adaptive framework in the presence of both structured and unstructured uncertainties is investigated. A case study is carried out in support of a parametrized adaptive scheme using neural networks. Simulation results clearly indicate that the neural network based adaptive controller achieves better tracking in the presence of parametric uncertainties as well as unmodelled effects compared to the simple direct adaptive scheme.     

Unconstrained and constrained motion control of a planar two-link structurally flexible robotic manipulator

Unconstrained and constrained motion control of a planar two-link structurally-flexible robotic manipulator are considered in this study. The dynamic model is obtained by using the extended Hamilton's principle and the Galerkin criterion. A method is presented to obtain the linearized equations of motion in Cartesian space for use in designing the control system. The approach to solving the control problem is to use feedforward and feedback control torques. The feedforward torques maneuver the flexible manipulator along a nominal trajectory and the feedback torques minimize any deviations from the nominal trajectory. The feedforward and feedback torques are obtained by solving the inverse dynamics problem for the rigid manipulator and designing linear quadratic Gaussian with loop transfer recovery (LQG/LTR) compensators, respectively. The LQG/LTR design methodology is exploited to design a robust feedback control system that can handle modeling errors and sensor noise, and operate on Cartesian space trajectory errors. Computer simulated results are presented for an example planar, two-link, structurally flexible robotic manipulator. © 1994 John Wiley & Sons, Inc.     

Noise analysis of robot manipulator using neural networks

Due to a lot of robot manipulators application in industry, low noise degree is very important criteria for robot manipulator's joints. In this paper, joint noise problem of a robot manipulator with five joints is investigated both theoretically and experimentally. The investigation is consisted of two steps. First step is to analyze the noise of joints using a hardware and software. The hardware is a part of noise sensors. The second step; according to experimental results, some neural networks are employed for finding robust neural noise analyzer. Five types of neural networks are used to compare each other. From the results, it is noted that the proposed RBFNN gives the best results for analyzing joint noise of the robot manipulator.     

Modelling the movement of a two-link manipulator

An algorithm for optimizing the control signal for simple movements of a two-link manipulator with four degrees of freedom is described. Based on the typical movement and functions of upper human extremities, the manipulator (so-called anthropomorphic manipulator) is composed of two links. The motion of the links is developed by four driving motors. The mathematic model is based of the Lagrange equations of the IInd king. The minimization of the time of movement with initial limitation of accuracy is obtained and the error of the final position is minimized without changing the time-optimal criterion. The relations connected with minimalization of both quality factors are considered. At the same time, the algorithm optimizes the torque distribution between the actuators which drive each link of manipulator. As well the manipulator as its activity are modelled on the digital computer. The results of the computer simulation of the algorithm, and the modelling of the time and accuracy optimal control, are presented.     

Nonlinear control with end-point acceleration feedback for a two-link flexible manipulator: Experimental results

Experimental results for end-point positioning of multi-link flexible manipulators through end-point acceleration feedback are presented in this article. The advocated controllers are implemented on a two-link flexible arm developed at the Control/Robotics Research Laboratory at Polytechnic University. The advocated approach in this article is based on a two-stage control design. The first stage is a nonlinear (1) feedback linearizing controller corresponding to the rigid body motion of the manipulator. Because this scheme does not utilize any feedback from the end-point motion, significant vibrations are induced at the end effector. To this effect, and to enhance the robustness of the closed-loop dynamics to parameter variations, the inner loop is augmented with an outer loop based on a linear output LQR design that utilizes an end-point acceleration feedback. The forearm of the manipulator is significantly more flexible as compared with the upper arm. Experimental and simulation results validate the fact that the end-effector performance is significantly better with the proposed (1) feedback linearizing control as compared with the linear independent joint PD control. In addition, the nonlinear control offers other advantages in terms of smaller and smoother actuator torques and reducing the effects of nonlinearities. Close conformation between simulation and experimental results validates the accuracy of the model.     

Experiments on a floating underwater robot with a two-link manipulator

This article concerns experiments with a free-floating underwater robot with a two-dimensional, horizontal planar, two-link manipulator. Some dynamic models of underwater manipulators have been proposed, but only a few experiments have been carried out. Here, we derive a dynamic model for a free-floating underwater robot with a two-link manipulator, including the hydrodynamic forces, and validate the effectiveness of the model by simulation and experiment. We also show an experimental result using a resolved acceleration control method. These experimental results show the effectiveness the model and the control method. This work was presented in part at the 5th International Symposium on Artificial Life and Robotics, Oita, Japan, January 26–28, 2000     

Vibration control of a two-link flexible robot arm

Analysis and experimentation is described for a two-link apparatus in which both members are very flexible. Attention is focused on endpoint position control for point-to-point movements, assuming a fixed reference frame for the base, with two rotary joints. Each link is instrumented with acceleration sensing and is driven by a separate motor equipped with velocity and position sensing. The control perspective adopted is to implement a two-stage control strategy in which the vibration control problem for fine-motion endpoint positioning is considered separate from the gross-motion, large-angle slew problem. In the first stage the control law shapes the actuator inputsfor the large-angle movement in such a way that minimal energy is injected into the flexible modes, while in the second phase an endpoint acceleration feedback scheme is employed in independent joint controlfor vibration suppression at the link endpoints.     

Identification of nonlinear dynamical systems using multilayered neural networks

A novel multilayer discrete-time neural net paradigm is presented for the identification of multi-input multi-output (MIMO) nonlinear dynamical systems. The major novelty of this approach is a rigorous proof of identification error convergence that reveals a requirement for a new identifier structure and nonstandard weight tuning algorithms. The NN identifier includes modified delta rule weight tuning and exhibits a learning-while-functioning feature instead of learning-then-functioning, so that the identification is on-line with no explicit off-line learning phase needed. The structure of the neural net (NN) identifier is derived using a passivity aproach. Linearity in the parameters is not required and certainty equivalence is not used. The notion of persistency of excitation (PE) and passivity properties of the multilayer NN are defined and used in the convergence analysis of both the identification error and the weight estimates.     

小波和神经网络在心音识别中的应用

提出一种心音的特征提取和分类方法,用离散小波变换分解、重构产生信号的细节包络,进而用于提取特征,从预处理的信号中提取统计特性,作为心音分类的特征。多层感知器用于心音的分类,并通过250个心动周期得到验证,算法识别率达到92%。     

Fast virus detection by using high speed time delay neural networks

This paper presents an intelligent approach to detect unknown malicious codes by using new high speed time delay neural networks. The entire data are collected together in a long vector and then tested as a one input pattern. The proposed fast time delay neural networks (FTDNNs) use cross correlation in the frequency domain between the tested data and the input weights of neural networks. It is proved mathematically and practically that the number of computation steps required for the presented time delay neural networks is less than that needed by conventional time delay neural networks (CTDNNs). Simulation results using MATLAB confirm the theoretical computations.     

Passivity analysis for neural networks with a time-varying delay

This paper deals with the problem of passivity analysis for neural networks with both time-varying delay and norm-bounded parameter uncertainties by employing an improved free-weighting matrix approach. Some useful terms have been retained, which were used to be ignored in the derivative of Lyapunov-Krasovskii functional. Furthermore, the relationship among the time-varying delay, its upper bound and their difference is taken into account. As a result, for two types of time-varying delays, less conservative delay-dependent passivity conditions are obtained in terms of linear matrix inequalities (LMIs), respectively. Finally, a numerical example is given to demonstrate the effectiveness of the proposed techniques.     

Identification of probe request attacks in WLANs using neural networks

Any sniffer can see the information sent through unprotected ‘probe request messages’ and ‘probe response messages’ in wireless local area networks (WLAN). A station (STA) can send probe requests to trigger probe responses by simply spoofing a genuine media access control (MAC) address to deceive access point (AP) controlled access list. Adversaries exploit these weaknesses to flood APs with probe requests, which can generate a denial of service (DoS) to genuine STAs. The research examines traffic of a WLAN using supervised feed-forward neural network classifier to identify genuine frames from rogue frames. The novel feature of this approach is to capture the genuine user and attacker training data separately and label them prior to training without network administrator’s intervention. The model’s performance is validated using self-consistency and fivefold cross-validation tests. The simulation is comprehensive and takes into account the real-world environment. The results show that this approach detects probe request attacks extremely well. This solution also detects an attack during an early stage of the communication, so that it can prevent any other attacks when an adversary contemplates to start breaking into the network.     

Identification of nonlinear dynamic systems using functional linkartificial neural networks

We have presented an alternate ANN structure called functional link ANN (FLANN) for nonlinear dynamic system identification using the popular backpropagation algorithm. In contrast to a feedforward ANN structure, i.e., a multilayer perceptron (MLP), the FLANN is basically a single layer structure in which nonlinearity is introduced by enhancing the input pattern with nonlinear functional expansion. With proper choice of functional expansion in a FLANN, this network performs as good as and in some cases even better than the MLP structure for the problem of nonlinear system identification.     

Nonlinear control with acceleration feedback for a two-link flexible robot

In this paper, a three-loop control strategy is applied to each link of a two-link flexible robot. In the first loop feedback linearization is applied to the rigid and motor dynamics. The second loop consists of a simple proportional-derivative (PD) control law for accurate rigid body angle tracking. The third loop uses endpoint accelearation feedback to account for flexure effects. The overall scheme is relatively simple in order to facilitate easy implementation; experimental results are provided to verify the effectiveness of the developed schemes.     

基于深度强化学习的二连杆机械臂运动控制方法

针对二连杆机械臂的运动控制问题,提出了一种基于深度强化学习的控制方法.首先,搭建机械臂仿真环境,包括二连杆机械臂、目标物与障碍物;然后,根据环境模型的目标设置、状态变量和奖罚机制来建立三种深度强化学习模型进行训练,最后实现二连杆机械臂的运动控制.对比分析所提出的三种模型后,选择深度确定性策略梯度(DDPG)算法进行进一...     

Feedback control of a flexible cylindrical manipulator

Flexible robotic manipulators have been the subject of numerous studies in the past few years. Past studies, however, have concentrated on flexible manipulators with only revolute joints. This paper considers the case of a structurally flexible manipulator with prismatic and revolute joints; specifically, an algorithm for controlling a structurally flexible three-degree-of-freedom cylindrical manipulator is presented. The control algorithm involves two steps. Using nonlinear feedback, the equations of motion are first decoupled into three subsystems representing the three rigid degrees of freedom together with their associated ‘flexible equations’, if any. Then, using linear optimal control theory, controllers are designed for the three subsystems independently. Computer simulated results for an example system are presented.