The regulation of functions such as respiratory or heart rate in human body as well as the control of motor movements are under the control of nervous system. As these actions and correlated tasks are directly influenced by the brain, the brain monitoring gives the possibility to differentiate the tasks, enabling at the same time the prediction of further actions. In this contribution, publicly available electroencephalography (EEG) datasets are analyzed with respect to the detection of epileptic seizure occurrence and BCI-related actions (here: cued motor imagery). For these purposes, timefrequency- based feature extraction alongside different classification methods is used. To perform the classification, Artificial Neural Network (ANN) and Support Vector Machine (SVM) are utilized and compared with previously obtained results. The feasibility of particular features for the detection of epileptic seizures and BCI-related tasks is discussed. Four different feature vectors per analyzed problem are identified. Acceptable accuracy of classification using ANN- and SVMbased classifiers is achieved using identified feature vectors.
In this paper is presented realization of integral environment which consists of software and hardware components for the purpose of programming Altera DE boards. Software component is Toolbox FPGA Real Time which enables simple use of Matlab/Simulink with DSP Builder for the purpose of realization of control structures. Hardware component are Interface cards that make connection of DE board with object of control possible. Simulation and experimental results of DC motor control indicate the usefulness of the proposed concept.
Abstract In this paper is presented architecture of the controller for controlling the base configuration of PUMA 560 robot (three axes). Developed controller (designated for student education) has hardware part based on Altera Cyclon II FPGA chip implemented on DE2 development board and software part MATLAB® with corresponding toolboxes. Matlab with installed Robotics Toolbox was used for the purposes such as generating trajectory of movement, calculating inverse kinematics, gravity compensation and simulation of manipulator movements. The control structures were which have been previously devised in Matlab/DSP Builder using FPGA Real Time Toolbox were implemented on FPGA chip. Performed experimental results showed that proposed concept of the controller design satisfied appointed requirements such as easy simulation, programming and testing controller performances, so the next objective of research will be design of the improved control algorithms of robot and design of new Teachbox.
In this paper we described realization of digital assembly for processing of output signal from incremental encoder on FPGA platform in Matlab/DSP Builder. For the purpose of realization of the design and programming of FPGA circuit on development board DE2 we used Matlab/DSP Builder. Encoder functioning principle, accepting, processing and counting of impulses and acquiring velocity information through differentiating measured position are all described in detail. Functionality of realized design was verified through simulation in Matlab/DSP Builder and velocity (acquired through differentiating of measured position) was provided in experimental result (comparison of motor rotation speed acquired from encoder and tachogenerator). Experimental result confirms that chosen concept of encoder signal processing was correct.
In paper is presented HDL Code generation of Cordic Algorithm in MATLAB/Simulink, using HDL Code generation tool, and its implementation on FPGA Altera Cyclone, using Altera Quartus II. There are also tested data types which Cordic uses, as well as time which is need for sine or cosine calculation of given angle, depending on these data types. With this information Cordic can be easily implemented in any digital system.
This paper deals with closed control loop implementation for robot single axis with DC motor on FPGA platform. Controlling algorithm is designed in Matlab/Simulink environment and its Custom Toolbox is specifically designed for the purpose of control structures development in real time. Torque is calculated on FPGA structure and brought to a motor which generates necessary PMW. On the motor axis is a pendulum which follows default trajectory. It is a stream of data obtained by calculating or recording robot axis position while moving it manually. Experimental results are also provided.
Nema pronađenih rezultata, molimo da izmjenite uslove pretrage i pokušate ponovo!
Ova stranica koristi kolačiće da bi vam pružila najbolje iskustvo
Saznaj više