Piotr Gierlak

Hybrid position/force control of the SCORBOT-ER 4pc manipulator with neural compensation of nonlinearities

The problem of the manipulator hybrid position/force control is not trivial because the manipulator is a nonlinear object, whose parameters may be unknown, variable and the working conditions are changeable. The neural control system enables the manipulator to behave correctly, even if the mathematical model of the control object is unknown. In this paper, the hybrid position/force controller with a neural compensation of nonlinearities for the SCORBOT-ER 4pc robotic manipulator is presented. The presented control law and adaptive law guarantee practical stability of the closed-loop system in the sense of Lyapunov. The results of a numerical simulation are presented.

Hybrid Position/Force Control in Robotised Machining

The article presents an application of the neural hybrid position/force control of the robotic manipulator. Realisation of many machining processes requires an application of the hybrid position/force control in order to perform the desired robot trajectory, which results from the machined surface geometry, and the desired tool downforce. The application of the robotic manipulator for realisation of the machining process enables to elimination of human handwork and ensures greater accuracy and repeatability of products. In the article is presented mainly the application of the hybrid position/force control system, in which a multilayer neural network is applied in order to manipulator nonlinearities compensation.

Conventional and fuzzy force control in robotised machining

This article presents an application of the hybrid position-force control of the robotic manipulator with use of artificial neural networks and fuzzy logic systems in complex control system. The mathematical description of the manipulator and a closed-loop system are presented. In the position control were used the PD controller and artificial neural networks, which compensate nonlinearities of the manipulator. The paper presents mainly the application of various strategies of the force control. The force control strategies using conventional controllers P, PI, PD, PID and fuzzy controllers are presented and discussed. All of the control methods were verified on the real object in order to make a comparison of a control quality.

Discrete dual-heuristic programming in 3DOF manipulator control

In this paper we propose a discrete tracking control system for 3 degrees of freedom (DOF) robotic manipulator control. The control system is composed of Adaptive Critic Design (ACD), a PD controller and a supervisory term derived from the Lyapunov stability theory. ACD in Dual-Heuristic Programming (DHP) configuration consists of two structures realized in a form of neural networks (NN): actor - generates a control signal and critic approximates a derivative of the cost function with respect to the state. The control system works on-line, does not require a preliminary learning and uses the 3DOF manipulator dynamicsmodel for a state prediction in ACD structure. Verification of the proposed control algorithm was realized on a SCORBOT 4PC manipulator.

Verification of Multilayer Neural-Net Controller in Manipulator Tracking Control

In this paper a multilayer neural-net (NN) controller is applied for tracking control of robotic manipulator, which is a nonlinear object having unknown and changeable parameters. Dynamics equations of a rigid manipulator are presented. The NN controller is used for compensating manipulator nonlinearities. The controller is realized in a form of a multilayer NN, which is nonlinear in the weights. The standard delta rule using backpropagation tuning is inadequate, so a term correcting the delta rule as well as a robustifying term is added. The presented control law and tuning algorithm are derived from the Lyapunov’s direct method. Results of the experiment are presented in this paper.

Adaptive position/force control for robot manipulator in contact with a flexible environment

The subject of the article is the adaptive position and force control of a robotic manipulator in interaction with flexible environment. The aim of the study is to provide a solution that takes into account the essential aspects of operation of the manipulator with the environment and at the same time can be actually implemented. A manipulatorenvironment system model taking into account motion resistance and environment elasticity. The position and force control task has been defined considering the manipulator and environment models. Asymptotic stability of the control system has been demonstrated considering the adaptation of parameters of the manipulator and the environment. Practical stability of the system has been demonstrated in the case of interference with the guaranteed stability of the adaptation of parameters without requiring persistence of excitation. Numerical analysis and experimental study of the issue has been presented. An interaction of robot manipulator with flexible environment is considered.A force/position tracking controller is proposed.No information on robot parameters is required.Practical stability is guaranteed by the adaptive controller.System stability is proved by using Lyapunov stability theory.

CNC Milling Tool Head Imbalance Prediction Using Computational Intelligence Methods

In this paper, a mechanical imbalance prediction problem for a milling tool heads used in Computer Numerical Control (CNC) machines was studied. Four classes of the head imbalance were examined. The data set included 27334 records with 14 features in the time and frequency domains. The feature selection procedure was applied in order to extract the most significant attributes. Only 3 out of 14 attributes were selected and utilized for the representation of each signal. Seven computational intelligence methods were applied in the prediction task: K–Means clustering algorithm, probabilistic neural network, single decision tree, boosted decision trees, multilayer perceptron, radial basis function neural network and support vector machine. The accuracy, sensitivity and specificity were computed in order to asses the performance of the algorithms.

The Manipulator Tool Fault Diagnostics Based on Vibration Analysis in the Frequency Domain

The issues presented in the article, relate to the detection of damage of a cutting tool used in robotised machining. Due to the time saving requirements, it is desirable to carry out the current control of the tool mounted in the holder of the robotic manipulator. The tool is a ceramic fiber brush used for grinding. A typical damage of the brush is fiber breakage, which leads to an unbalance of the tool and vibrations. The phenomenon of vibrations and parameters of the vibratory motion of the tool have been used as a carrier of information about the state of the tool. On the basis of the measurement data, obtained during tests of tools with varying degrees of damage, classifiers of the tool state were built. Two types of classifiers were tested: decision trees and artificial neural networks. The results confirm that it is possible to build a classifier of the tool state with high effectiveness reaching up to 99,875%.

Globalized Dual Heuristic Dynamic Programming in Control of Robotic Manipulator

The article focuses on the implementation of the globalized dual-heuristic dynamic programming algorithm in the discrete tracking control system of the three degrees of freedom robotic manipulator. The globalized dual-heuristic dynamic programming algorithm is included in the approximate dynamic programming algorithms family, that bases on the Bellman’s dynamic programming idea. These algorithms generally consist of the actor and the critic structures realized in a form of artificial neural networks. Moreover, the control system includes the PD controller, the supervisory term and an additional control signal. The structure of the supervisory term derives from the stability analysis, which was realized using the Lyapunov stability theorem. The control system works on-line and the neural networks’ weight adaptation process is realized in every iteration step. A series of computer simulations was realized in Matlab/Simulink software to confirm performance of the control system.

Tracking Control of Manipulator

Abstract In this paper a neural-net (NN) controller for tracking control of a manipulator is used. A manipulator is a nonlinear object which usually has unknown and changeable parameters. Dynamics equations of a rigid manipulator are presented. A NN controller is used for compensating manipulators nonlinearities. The controller is realized in a form of a linear NN in the weights. The NN is learned by using backpropagation tuning. The presented control law and tuning algorithm are derived from the Lyapunov direct method. In this paper results of simulation and experiment are presented.