Adrian Olaru

Adaptive Control System for Drill Machine

The paper shows an adaptive system for drilling. To drill diameter measure video optical method with USB camera was used. Rotation of drill tool was controlled using an inverter. Adaptive system was controlled by PC using special software made in C++.

Control of Articulated Manipulator Model Using ATMEGA16

The paper presents a model for the construction of an articulated manipulator with 3 degrees of freedom (DOF). It is made from lightweight metal. To drive was used the stepper motors. Manipulator control system was made using a ATMEGA16 microcontroller. The control software was elaborated in BASCOM. Manipulator were tested using a manually control by joystick and in automation mode using a data file in array form. Presented solution is useful for didactics. By using more powerful motors and more complicated design it can be used to implementation in industrial conditions.

Proper Assisted Research Method Solving of the Robots Inverse Kinematics Problem

Finding the better solution of the inverse kinematics problem, with the minimum of the trajectory errors, is very difficult because there are many variable parameters and many redundant solutions. The presented paper show the assisted solving of the inverse kinematics with the goal to minimize the final end-effector trajectory errors, by optimizing the distance between the and-effector final position and the target. All obtained results were been verified by applying the proper forward kinematics virtual LabVIEW instrumentation. The paper tries to answer at the inverse kinematics problem for one known mathematical trajectory and identifying the cinematic errors after the establishing and applying the proper assisted solving method using the Cycle Coordinate Descent Method coupled to the proper Neural Network Sigmoid Bipolar Hyperbolic Tangent (CCDM-SBHTNN). We were shown one complete study case to obtain one circle space trajectory using one arm type robot fixed on the ceiling. The presented method is general and can be used in all other robots types and in all other conventional and unconventional space curves.

Assisted Research of the Neural Network

In the optimization of the trajectory or of the guidance of mobile robots one of the more important things is to assure one small difference between the output data of the system and the target. This paper show how on-line will be possible to establish one convergence way to the target without any influences of the input data or initial conditions of the weights or biases. The paper show the general components and the mathematical model of some more important neurons and one numerical simulation of the linear neural network. In the paper was used the least mean square (LMS) error algorithm for adjusting the weights and biases and incremental training by different training rate, finally to obtain one minimum error to the target.

Assisted Research and Optimization of the Proper Neural Network Solving the Inverse Kinematics Problem

Finding the better solution of the neural network design to solve the inverse kinematics problem with the minimum of the trajectory errors is very difficult, because there are many variable parameters and many redundant solutions. The presented paper show the assisted research of the influences of some more important parameters to the final end-effector trajectory errors of the proposed neural network model solving the inverse kinematics problem. We were been studied the number of neurons in each layers, the sensitive function for the first and second layer, the magnifier coefficient of the trajectory error, the variable step of the time delay and the position of this block, the different cases of target data and the case when the hidden target data were adjusted. All obtained results were been verified by applying the proper direct kinematics virtual LabVIEW instrumentation. Finally we were obtained one optimal Sigmoid Bipolar Hyperbolic Tangent Neural Network with Time Delay and Recurrent Links (SBHTNN(TDRL)) type, what can be used to solve the inverse kinematics problem with maximum 4% of trajectory errors.

Assisted Research of the Neural Network with LabVIEW Instrumentation

The paper open the way to the assisted choose of the optimal neural network. There are shown some important neurons type, transfer functions, weights and biases of neurons, and some complex layers with different type of neurons in a static and dynamic networks. By using the proper virtual LabVIEW instrumentation were established some influences of the network parameters to the number of iterations till canceled the mean square error to the target. Were presented the simulation of some different neural network types like linear, sigmoid, sigmoid bipolar and radial. For some of more important, were presented the complex mathematical models and numerical simulation using the proper teaching law.

On the Controlling of Spherical Ultrasonic Motor

Research team of Prof. Shigeki TOYAMA has developed at Tokyo University of A&T a new type of ultrasonic motor. Its spherical shape confer 2 or 3 degree of freedom in a single joint which makes it suitable for mechatronics field. In order to control the Spherical Ultrasonic Motor a new method by using Hall sensors and a residual magnetic field induced in rotor was implemented. Present paper is dealing with the command and the control of a SUM by using Hall elements and a residual magnetic field induced in rotor. In this way the approach of controlling problem is by using the inverse kinematics and neuronal networks.

Static Balancing of Mechanical Systems Used in Medical Engineering Field – Continuous Balancing

In medical field are used many categories of mechanical systems, from simple mechanisms to the complex mechatronic systems. Present paper is focused to those mechanical systems that are working in vertical plane by supporting loads or by lifting weights. The targets are both patients and medical workers. Paper is proposing some new devices and mechanisms for supporting the weights that are hanged to the ceiling. These mechanical systems are called too with zero-stiffness because the balancing force does not depend to elongation of elastic system. For all the presented solutions the balancing of the weight forces will be done by using the elastic forces of torsion spiral springs and cylindrical helical springs with straight characteristics. The balancing is made exactly for all positions throughout the work field.

Increase the Space Trajectory Precision by Using the Proper Assisted Research Method for Inverse Kinematics Problem

Inverse kinematics model of the industrial robot is used in the control of the end-effecter trajectory. The solution of the inverse kinematics problem is very difficult to find, when the degree of freedom increase and in many cases this is impossible. In these cases is used the numerical approximation or other method with diffuse logic. The paper showed one new method for optimization of the inverse cinematic solution by applying the proper assisted Iterative Pseudo Inverse Jacobian Matrix Method coupled with proper Sigmoid Bipolar Hyperbolic Tangent Neural Network with Time Delay and Recurrent Links Method (IPIJMM-SBHTNN-TDRLM). In the paper was shown one case study to obtain one space circle curve by using one arm type robot and the proposed method. The errors of the space coordinates of the circle, after applying the proposed method, was less than 0.001. The study has contained the determining the internal coordinates corresponding to the external coordinates of the circle space curve, by solving the inverse kinematics with the proposed method and after that, by applying the forward kinematics to this coordinates, were obtained the external coordinates, what were compared with the theoretical one. The presented method is general and it can be used in all other robots types and for all other conventional and unconventional space curves.

Modeling and Simulation of the Multiple Robot’s Applications

This paper explains and demonstrates how can designed one multi robots application with many tasks and some different type of modular collaborative robots. Was described the general mathematical model for the direct and inverse kinematics to controlling the robots and how can solve the inverse kinematics of multiple tasks by using the priority of tasks or serial tasks composed by sum of the weighted several tasks. Some collaborative multi robots applications with parallel, serial or composed robots configurations were shown. The general mathematical matrix model of the robot application point with three translations and three rotations to the world Cartesian coordinates of the application map was defined. The designed method, the animation programs and the used LabVIEW proper virtual instruments open the way to easily define the multi robots application map, establish the constraints of the used robots and of the environment to avoid the singular points and tests the manipulation programs for collaborative application.