Prediction of surface roughness with genetic programming

Brezočnik, Miran; Kovačić, Miha; Ficko, Mirko

doi:10.1016/j.jmatprotec.2004.09.004

Cited by 155 publications

(59 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to the extensive usage of evolutionary methods (e.g., [25][26][27]) the authors used genetic algorithm for optimal solution search.…”

Section: Introductionmentioning

confidence: 99%

A Universal CAD System for Cutting Stock Problem

Kovačić¹,

Brezočnik²

2017

Int. j. simul. model.

Self Cite

View full text Add to dashboard Cite

In this research the universal system using CAD geometry for solving of cutting stock problem is proposed. The system consists of the three main modules: geometry definition module, objective definition module, and the search strategy module. In the first module the reference points and orientation of parts and stock are defined. In the second module some constraints such as the quantity of the desired type of parts to be placed on the stock can be taken into account. The third module contains the search strategy. For the purpose of this research, the genetic algorithm was used as the search method. For illustration of the generality of the proposed approach, three practical examples for solving orthogonally and irregularly-shaped cutting stock problems are presented. The parts which are to be cut from stock-material with minimal loss and also the stock-material itself are presented as CAD geometries without any kind of geometrical constraints (i.e., concavity, convexity, sections, and holes). In the presented approach the AutoCAD environment was used. The AutoLISP in-house developed system for cutting stock problem was integrated into the AutoCAD. The developed system is without any kind of geometrical constraints and thus highly applicable in the practice. The presented approach can be developed also in other CAD systems where the application programming interfaces (API) are available.

show abstract

“…Due to the extensive usage of evolutionary methods (e.g., [25][26][27]) the authors used genetic algorithm for optimal solution search.…”

Section: Introductionmentioning

confidence: 99%

A Universal CAD System for Cutting Stock Problem

Kovačić¹,

Brezočnik²

2017

Int. j. simul. model.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The relevant cutting parameters must be selected in order to prepare a CNC program, allowing optimum machining according to given machining requirements. To that end, in the past research dealing with the optimisation of cutting parameters [15,16] with respect to machining duration [17], machining costs [18], maximum extent of removed material [19], tool resistance to wear [20][21][22][23] and machined surface roughness [24][25][26][27][28] has been carried out.…”

Section: Introductionmentioning

confidence: 99%

Intelligent CAD/CAM System for Programming of CNC Machine Tools

Klančnik¹,

Brezočnik²,

Balič³

2016

Int. j. simul. model.

Self Cite

View full text Add to dashboard Cite

This paper suggests the automated programming of CNC-machine tools with the help of artificial intelligence. Based on a CAD-model of the product, the system, without any help from an expert, automatically prepares a CNC program, so that the machining is safe, accurate and time-efficient. The developed CAD/CAM system uses NSGA-II multi-objective optimisation and swarm intelligence. The system consists of a prediction and evaluation module. In a prediction module artificial intelligence suggests solutions that include information about tool path, selected tools and suggested cutting parameters. The evaluation module estimates the suggested solutions by considering the geometrical, technological and time criteria, and the criterion of efficiency of machining. A simulation model was developed for searching optimal solutions. In this paper, the developed system is experimentally tested using a test case of manufacturing. The test results confirmed that with the help of this method of artificial intelligence, machine tools can be automatically programmed.

show abstract

“…and with the goal of cost-efficient processing and shortening of time. The set goals are achieved by improving the conditions of machining by applying neural networks (NN) and genetic programming [10,11], as well as the approaches that use other methods [12÷14]. In the optimization of machining parameters, NN are often combined with GA.…”

Section: Introductionmentioning

confidence: 99%

Use of soft computing technique for modelling and prediction of CNC grinding process

et al. 2016

View full text Add to dashboard Cite

Original scientific paper Due to the complexity of grinding process of multilayer ceramics, and the need for a specific product quality, the choice of optimal technological parameters is a challenging task for the manufacturers. The main aim of investigation is to secure the demanded final product quality (plane parallelism) in the function of input parameters (machine, machine operator, foil and production line). "Soft computing techniques" are becoming more interesting to the researchers for the modelling of processing parameters of complex technological processes. In this paper, a soft computing technique, known as the Artificial Neural Networks (ANN), is used for the modelling and prediction of parameters of technological process of CNC grinding of multilayer ceramics. The results show that the ANN with the back-propagation algorithm justifies the application also to this problem. By designing different architectures of ANN (learning rules, transfer functions, number and structure of hidden layers and other) on the set of data from the productiontechnological process, the best result of RMS error (10,76 %) in the process of learning and 12,07 % in the process of validation was achieved. The achieved results confirm the acceptability and the application of this investigation in the technological and operational preparation of production. Keywords: grinding, neural networks, prediction, soft computing Uporaba tehnike mekog računalstva za modeliranje i predviđanje postupka CNC brušenjaIzvorni znanstveni rad Zbog složenosti procesa brušenja višeslojne keramike te osiguranja zahtijevane kvalitete proizvoda, odabir optimalnih tehnoloških parametara je izazovan zadatak za proizvođače. Osigurati traženu izlaznu kvalitetu proizvoda (paralelnost površina) u funkciji ulaznih parametara (stroj, operater stroja, folija i proizvodna linija) predstavlja glavni cilj istraživanja. "Tehnike mekog računalstva" dobivaju pozornost istraživača za modeliranje procesnih parametara složenih tehnoloških procesa. U ovom radu koristi se tehnika mekog računalstva poznata kao umjetne neuronske mreže (ANN) za modeliranje i predviđanje parametara tehnološkog procesa CNC brušenja višeslojne keramike. Rezultati su pokazali da ANN s algoritmom širenja unazad potvrđuje primjenu i na ovaj problem. Oblikovanjem različitih arhitektura ANN (pravila učenja, prijenosne funkcije, broj i strukture skrivenih slojeva i drugi) na setu podataka iz proizvodno -tehnološkog procesa ostvaren je najbolji rezultat RMS greške od 10,76 % u procesu učenja i 12,07 % u procesu validacije. Ostvareni rezultati potvrđuju prihvatljivost i primjenu ovog istraživanja u tehnološkoj i operativnoj pripremi proizvodnje.

show abstract

Prediction of surface roughness with genetic programming

Cited by 155 publications

References 17 publications

A Universal CAD System for Cutting Stock Problem

A Universal CAD System for Cutting Stock Problem

Intelligent CAD/CAM System for Programming of CNC Machine Tools

Use of soft computing technique for modelling and prediction of CNC grinding process

Contact Info

Product

Resources

About