1. Approach to optimization of cutting conditions by using artificial neural networksFranc Čuš, Uroš Župerl, 2006, izvirni znanstveni članek Opis: Optimum selection of cutting conditions importantly contribute to the increase of productivity and the reduction of costs, therefore utmost attention is paid to this problem in this contribution. In this paper, a neural network-based approach to complex optimization of cutting parameters is proposed. It describes the multi-objective technique of optimization of cutting conditions by means of the neural networks taking into consideration the technological, economic and organizational limitations. To reach higher precision of the predicted results, a neural optimization algorithm is developed and presented to ensure simple, fast and efficient optimization of all important turning parameters. The approach is suitable for fast determination of optimum cutting parameters during machining, where there is not enough time for deep analysis. To demonstrate the procedure and performance of the neural network approach, an illustrative example is discussed in detail. Ključne besede: optimization, cutting parameter optimization, genetic algorithm, cutting parameters, neural network algorithm, machining, metal cutting Objavljeno: 30.05.2012; Ogledov: 964; Prenosov: 11 Celotno besedilo (0,00 KB) |
2. Intelligent programming of CNC turning operations using genetic algorithmJože Balič, Miha Kovačič, Boštjan Vaupotič, 2006, izvirni znanstveni članek Opis: CAD/CAM systems are nowadays tightly connected to ensure that CAD data can be used for optimal tool path determination and generation of CNC programs for machine tools. The aim of our research is the design of a computer-aided, intelligent and genetic algorithm(GA) based programming system for CNC cutting tools selection, tool sequences planning and optimisation of cutting conditions. The first step is geometrical feature recognition and classification. On the basis of recognised features the module for GA-based determination of technological data determine cutting tools, cutting parameters (according to work piece material and cutting tool material) and detailed tool sequence planning. Material, which will be removed, is split into several cuts, each consisting of a number of basic tool movements. In thenext step, GA operations such as reproduction, crossover and mutation are applied. The process of GA-based optimisation runs in cycles in which new generations of individuals are created with increased average fitness of a population. During the evaluation of calculated results (generated NC programmes) several rules and constraints like rapid and cutting tool movement, collision, clamping and minimum machining time, which represent the fitness function, were taken into account. A case study was made for the turning operation of a rotational part. The results show that the GA-based programming has a higher efficiency. The total machining time was reduced by 16%. The demand for a high skilled worker on CAD/CAM systems and CNC machine tools was also reduced. Ključne besede: CNC programming, genetic algorithm, intelligent CAM, turning, tool path generation Objavljeno: 30.05.2012; Ogledov: 963; Prenosov: 15 Celotno besedilo (0,00 KB) |
3. Using of acoustic models in mechanical diagnosticsMateja Ploj Virtič, Boris Aberšek, Uroš Župerl, 2008, izvirni znanstveni članek Opis: This paper presents an acoustical model for control and diagnostics of single stage gear wheels. The model is based on various methods and procedures that as a result provide information about the generatorćs condition, the gear in particular. The acoustical model is part of a complex system that units' different models to meet diagnostics of single stage gear wheels as precise as possible. Using the adaptive FIR filter, acoustical model enables the calculation of impulse response for different notch lengths between 0 and ac. The acoustical model consists of digital FIR filter, modified by LMS algorithm, used to calculate impulse responses in non-linear systems, the model for the calculation of any impulse response and the frequency analysis with the use of FFT for the simulation of frequency spectrums. Frequency spectrum of the simulated sound signal enables an analysis of the error that can be used for calculating the remaining service life and/or determining the control cycle of maintenance. Ključne besede: mechanical fault diagnostics, acoustic models, impulse response, adaptive algorithm Objavljeno: 31.05.2012; Ogledov: 651; Prenosov: 6 Celotno besedilo (0,00 KB) |
4. A hexahedral mesh connectivity compression with vertex degreesSebastian Krivograd, Mladen Trlep, Borut Žalik, 2008, izvirni znanstveni članek Opis: This paper introduces a new algorithm for the compression of manifold hexahedral meshes topology, using vertex degree. The topology compression consists of two parts-the meshćs boundary consisting of quadrilaterals is compressed first, and then the hexahedra are processed by the help of six commands. The topology compression algorithm has been matched against the best-known method to-date, and shows itself to be competitive. Ključne besede: hexahedral meshes topology, FEM, compression, topology compression algorithm, geometry, algorithms Objavljeno: 31.05.2012; Ogledov: 764; Prenosov: 5 Celotno besedilo (0,00 KB) |
5. Intelligent process planning for competitive engineeringValentina Gečevska, Franc Čuš, 2010, izvirni znanstveni članek Opis: Process planning is one of the key activities for product design and manufacturing. The impact of process plans on all phases of product design and manufacture requires high level of interaction of different activities and close integration of them into a coherent system. This paper presents a process model of product development with manufacturing approach based on intelligent process planning techniques with focus on optimal selection of manufacturing parameters. Some derivations of the computing model for analysis of machining conditions by optimal determination of the cutting parameters in multi-pass NC machining activities are made with implementation of new evolutionary computation techniques. Genetic Algorithm (GA) based optimization method and deterministic optimization method (DO) are developed and then implementations into real manufacturing process planning for new product developed are analyzed. The results showed that both the developed optimization methods (GA and DO), especially GA, are effective methods for solving multi-objective optimization problems during the manufacturing process planning and cutting parameters selection. Ključne besede: genetic algorithm, intelligent manufacturing systems, process planning Objavljeno: 31.05.2012; Ogledov: 804; Prenosov: 3 Celotno besedilo (0,00 KB) |
6. Use of genetic algorithm for fitting Sovova's mass transfer modelDejan Hrnčič, Marjan Mernik, Maša Knez Hrnčič, 2010, izvirni znanstveni članek Opis: A genetic algorithm with resizable population has been applied to the estimation of parameters for Sovovaćs mass transfer model. The comparison of results between a genetic algorithm and a global optimizer from the literatureshows that a genetic algorithm performs as good as or better than a global optimizer on a given set of problems. Other benefits of the genetic algorithm, for mass transfer modeling, are simplicity, robustness and efficiency. Ključne besede: Sovova's mass transfer model, genetic algorithm, parameter estimation Objavljeno: 31.05.2012; Ogledov: 755; Prenosov: 11 Celotno besedilo (718,52 KB) |
7. |
8. 2-local 3/4-competitive algorithm for multicoloring hexagonal graphsPetra Šparl, Janez Žerovnik, 2005, izvirni znanstveni članek Opis: An important optimization problem in the design of cellular networks is to assign sets of frequencies to transmitters to avoid unacceptable interference.A cellular network is generally modeled as a subgraph of the infinite triangular lattice. Frequency assignment problem can be abstracted asa multicoloring problem on a weighted hexagonal graph, where the weights represent the number of calls to be assigned at vertices. In this paper we present a distributed algorithm for multicoloring hexagonal graphs using only the local clique numbers ▫$omega_1(v)$▫ and ▫$omega_2(v)$▫ at each vertex v of the given hexagonal graph, which can be computed from local information available at thevertex. We prove the algorithm uses no more than ▫$4omega(G)/3$▫ colors for any hexagonal graph G, without explicitly computing the global clique number ▫$omega(G)$▫. We also prove that our algorithm is 2-local, i.e., the computation at a vertex v ▫$in$▫ G uses only information about the demands of vertices whose graph distance from v is less than or equal to 2. Ključne besede: mathematics, graph theory, graph colouring, 2-local distributed algorithm, cellular networks, frequency planning Objavljeno: 01.06.2012; Ogledov: 996; Prenosov: 4 Celotno besedilo (0,00 KB) |
9. An almost distribution-independent incremental Delaunay triangulation algorithmMirko Zadravec, Borut Žalik, 2005, izvirni znanstveni članek Opis: This paper presents a new incremental insertion algorithm for constructing a Delaunay triangulation. Firstly, the nearest point is found in order to speed up the location of a triangle containing a currently inserted point. A hash table and 1-3 deterministic skip lists, combined with a walking strategy, are used for this task. The obtained algorithm is compared with the most popular Delaunay triangulation algorithms. The algorithm has the following attractive features: it is fast and practically independent of the distribution of input points, it is not memory demanding, and it is numerically stable and easy to implement. Ključne besede: Delaunay triangulation, incremental algorithm, computational geometry, skip list, hash table Objavljeno: 01.06.2012; Ogledov: 924; Prenosov: 15 Celotno besedilo (0,00 KB) |
10. ACTLW - an action-based computation tree logic with unless operatorRobert Meolic, Tatjana Kapus, Zmago Brezočnik, 2008, izvirni znanstveni članek Opis: Model checkers for systems represented by labelled transition systems are not as extensively used as those for systems represented by Kripke structures. This is partially due to the lack of an elegant formal language for property specification which would not be as raw as, for example, HML yet also not as complex as, for example, -calculus. This paper proposes a new action-based propositional branching-time temporal logic ACTLW, which enhances popular computation tree logic (CTL) with the notion of actions in a similar but more comprehensive way than action-based CTL introduced by De Nicola and Vaandrager [R. De Nicola, F.W. Vaandrager, Action versus logics for transition systems, in: Semantics of Systems of Concurrent Processes, Proceedings LITP Spring School on Theoretical Computer Science, LNCS 469, 1990, pp. 407-419]. ACTLW is defined by using temporal operators until and unless only, whereas all other temporal operators are derived from them. Fixed-point characterisation of the operators together with symbolic algorithms for globalmodel checking are shown. Usage of this new logic is illustrated by an example of verification of mutual-exclusion algorithms. Ključne besede: formal verification, model checking, action-based temporal logic, fixed point, mutual-exclusion algorithm Objavljeno: 01.06.2012; Ogledov: 1048; Prenosov: 8 Celotno besedilo (0,00 KB) |