Milorad BOŽIĆ, Igor KRČMAR, Jasmin IGIĆ
In contrast to usually applied Neural Network (NN) based controllers where the structure and fixed parameters of NN were obtained off line, here we present a fully adaptive Internal Model-based Neural Control design aimed to unknown nonlinear industrial processes with stable dynamics. The internal model of the control plant is implemented by the NN provided with a Stochastic Gradient Descent (SGD) learning algorithm. To cope with a high variability of process gain at different operational points and possible high errors in estimation of the corresponding sensitivities of nonlinear process model we proposed one practical solution to eliminate offset in a steady state at constant system inputs. Some illustrations and performance testing of the proposed adaptive NN controller are given by using an example.
This paper gives an overview of the separable two dimensional transposed Farrow structure. We analyze a separable transposed implementation structure in terms of complexity. We also present a straightforward procedure to design the separable 2-D Farrow structure. The procedure is to apply the best known one dimensional frequency domain design method for polynomial-based filters in each dimension. In this way, all frequency domain requirements, such as passband ripple, stopband attenuation, passband and stopband edges are defined independently for each dimension.
Suad IBRAHIMKADIĆ, Slobodan LUBURA
Since the safety has always been an important part of a control system, the new international standard EN ISO 13849-1 for safety of machinery is an important document that needs to be thoroughly read and applied in new projects. This paper provides some basic information about the standard and the way how it is used. The control system from a real project will be used as an example for design of some safety functions.
Using simulation tools to design and evaluate suitable function of industrial robot systems, is an easy and low-priced technique to shape multipart robot applications. At the current software market, all name-like robot manufacturers offer proprietary robot simulation software. This concerns simulations referred to the industrial robot systems as well as to the mobile or other kind of robot systems. Which software application is appropriate for use for educational purposes, depends on different factors and especially the circumstances on-site. In this work, based on experiences and diverse decisive factors at Rheinische Fachhochschule Köln gGmbh, a University of Applied Sciences, such a selection processes has been analyzed, explained and vindicated.