Simon Klancnik

Modeling and Design of Experiments of Laser Cladding Process by Genetic Programming and Nondominated Sorting

Laser deposition of materials represents a modern additive technology that has a number of advantages over remaining technologies for depositing metallic materials. Besides a low-energy input, a quality bond, and minimal heat-affected zone, this technology is also characterized by the good mechanical properties of the deposited material that is a result of rapid cooling. Despite the prospects, this technology is still at the developing phase. New materials and techniques for determining optimal process parameters are being introduced. In this article, we developed a system for modeling (predicting) the properties of the deposited material and used design of experiments (DOE) for the laser cladding process parameter selection. Based on the experimental data obtained during cladding process, models were made for predicting the volume and roughness of the deposited material. Genetic programming was used for modeling the process. Then, a set of several thousand possible combinations (settings) of the machine parameters was produced on the basis of the obtained model. The most appropriate machine (process) parameters were selected in terms of deposition speed, powder efficiency, and surface roughness. These parameters were determined by nondominated sorting. The results offer the operator of the machine a set of appropriate process parameters that enable the production of high-quality products.

Programming of CNC Milling Machines Using Particle Swarm Optimization

This article proposes asystem for theautomatic programming of a CNC milling machine by particle swarm optimization (PSO). In the presented research, each individual swarm particle presents a possible numerical control (NC) program. Voxel representation of machining area was used. Bresenhams algorithm was implemented, for the rasterization of the cuts. Optimisation with PSO was carried out within a voxelized machining area. The system automatically finds the NC program for optimal machining. The NC program guarantees an optimal selection of tools, the shortest possible work and rapid motions, and minimization of the manufacturing time, thus achieving a reduction in machining costs and increased productivity. Testing using test workpieces and 2.5 D milling confirmed the efficiency of the proposed approach. The proposed intelligent system is easily adaptable for programming other types of CNC machines by PSO.

Intelligent design of an unconstrained layout for a flexible manufacturing system

The presented research removes common constraints regarding the design of layout of flexible manufacturing system, and the subsequent search for a good solution is left solely to artificial intelligence. The proposed system is composed of a creative subsystem which can use different evolutionary optimization methods, and a subsystem for evaluating layouts. In the presented work the subsystem for creation uses a particle swarm optimization method for the creation/modification of solution sets. Evaluation of solution quality is made using intelligent search of the shortest travel paths within the layout. This system has proved to be innovative since it proposes very good solutions which are oriented to the main task of the system and are not simplified because of human limitations.

Inteligentni sustav za predviđanje mehaničkih svojstava materijala na osnovu metalografskih slika

This article presents developed intelligent system for prediction of mechanical properties of material based on metallographic images. The system is composed of two modules. The first module of the system is an algorithm for features extraction from metallographic images. The first algorithm reads metallographic image, which was obtained by microscope, followed by image features extraction with developed algorithm and in the end algorithm calculates proportions of the material microstructure. In this research we need to determine proportions of graphite, ferrite and ausferrite from metallographic images as accurately as possible. The second module of the developed system is a system for prediction of mechanical properties of material. Prediction of mechanical properties of material was performed by feed-forward artificial neural network. As inputs into artificial neural network calculated proportions of graphite, ferrite and ausferrite were used, as targets for training mechanical properties of material were used. Training of artificial neural network was performed on quite small database, but with parameters changing we succeeded. Artificial neural network learned to such extent that the error was acceptable. With the oriented neural network we successfully predicted mechanical properties for excluded sample.

Modelling of intelligent robot system by reverse engineering and swarm intelligence

The paper proposes the design of the intelligent robot system by reverse engineering and optimisation of the resistance welding application. Building of the system starts with the design of the virtual robot model by reverse engineering method. By that method, the user programme interface of the older robot ACMA XR701 is modernised. Building of the system continues with the incorporation of the TCP/IP-RS232 communication interface ensuring the control of the robot through internet. In the end, superstructuring of the robot system with the optimisation module, based on the swarm intelligence, is proposed.

Prediction of technological parameters of sheet metal bending in two stages using feed forward neural network

This paper describes sheet metal bending in two stages as well as predicting and testing of the final bend angle by means of a feed-forward neural network. The primary objective was to research the technological parameters of bending sheet metal in two stages and to develop an intelligent method that would enable the predicting of those technological parameters. The process of bending sheet metal in two stages is presented by demonstrating the various technological parameters and the test tool used to carry out tests and measurements. The results of the tests and measurements were of decisive guidance in the evaluation of individual technological parameters. Developed method for prediction of the final bend angle is based on a feed-forward neural network that receives signals at the input level. These signals then travel through the hidden level to the output level, where the responses to input signals are received. The input to the neural network is composed of data that affect the selection of the final bend angle. Only five different inputs are used for the total neural network. By choosing the desired final bend angle by means of the trained neural network, bending sheet metal in two stages is optimised and made more efficient.

Intelligent Optimization Methods for Industrial Storage Systems

The presented chapter introduces intelligent methods, which can be used for designing and managing of modern warehouses. Because of the ever-increasing complexity of such systems, the traditional methods cannot assure optimal or near-optimal solutions in design and operation. Demands for high utilization, flexibility, and the capacity to work reliably, even in changeable environments, can be met by adding intelligence to artificial system. The most promising intelligent methods are evolutionary computation and swarm intelligence which are unique methods of non-deterministic solving and optimizing. They proved to be effective and robust for planning and management of real systems. Evolutionary computation and swarm intelligence are methods, which were obtained from the observation of nature. Nature has some of the best answers to the problem of design and management. Therefore, this chapter tries to present intelligent methods to wider audience, and especially to experts and students of warehousing design and management.

Milling Strategy Prediction with SOM Neural Network

Abstract In this paper we present how with Artificial Neural Network (ANN) the prediction of milling tool-path strategy could be made, according to set technological aim. In our case the best possible surface quality of machined surface was taken as the primary technological aim. This paper shows how feature extraction from 3D CAD model and classification with self-organization neural network are done. The experimental results presented in this paper suggest that the prediction of milling strategy with self-organization neural network (SOM) is effective.