David Močnik (Author), Matej Paulič (Author), Simon Klančnik (Author), Jože Balič (Author)

Abstract

As manufacturing companies pursue higher-quality products, they spend much of their efforts monitoring and controlling dimensional accuracy. In the present work for dimensional deviation prediction of workpiece in turning 11SMn30 steel, the conventional deterministic approach, such as multiple linear regression and two artificial intelligence techniques, back-propagation feed-forward artificial neural network (ANN) and particle swarm optimization (PSO) have been used. Spindle speed, feed rate, depth of cut, pressure of cooling lubrication fluid and number of produced parts were taken as input parameters and dimensional deviation of workpiece as an output parameter. Significance of a single parameter and their interactive influences on dimensional deviation were statistically analysed and values predicted from regression, ANN and PSO models were compared with experimental results to estimate prediction accuracy. A predictive PSO based model showed better predictions than two remaining models. However, all three models can be used for the prediction of dimensional deviation in turning.

Keywords

umetna inteligenca;optimizacija z rojem delcev;inteligenca rojev;regresija;artificial neural network;dimensional dviation;particle swarm optimization;regression;

Data

Language: English
Year of publishing:
Typology: 1.01 - Original Scientific Article
Organization: UM FS - Faculty of Mechanical Engineering
UDC: 004.89:621.9
COBISS: 17628438 Link will open in a new window
ISSN: 1330-3651
Views: 713
Downloads: 129
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: Croatian
Secondary title: Predviđanje dimenzionalnih devijacija obratka primjenom regresijskih, ANN i PSO modela u postupku tokarenja
Secondary abstract: Budući da proizvodna poduzeća traže kvalitetnije proizvode, mnogo svojih napora troše na praćenje i reguliranje dimenzionalne točnosti. U ovom je radu za predviđanje dimenzionalne devijacije obratka pri tokarenju 11SMn30 čelika, primijenjen konvencionalni deterministički pristup, na primjer metoda višestruke linearne regresije i dvije metode umjetne inteligencije, "back-propagation feed-forward" umjetna neuronska mreža (ANN) i optimizacija roja čestica (PSO). Kao ulazni parametri uzeti su brzina osovine, brzina napajanja, dubina rezanja, tlak rashladnog fluida za podmazivanje i broj proizvedenih dijelova , a dimenzijska devijacija obratka kao izlazni parameter. Značaj pojedinih parametara i njihovi međusobni utjecaji na dimenzionalnu devijaciju su statistički analizirani, a vrijednosti predviđene regresijskim, ANN i PSO modelima uspoređene su s eksperimentalnim rezultatima kako bi se ocijenila točnost predviđanja. Model predviđanja zasnovan na PSO pokazao se boljim od druga dva modela. Međutim, sva se tri modela mogu koristiti za predviđanje dimenzionalnih devijacija kod tokarenja.
Secondary keywords: umetna inteligenca;optimizacija z rojem delcev;inteligenca rojev;regresija;
URN: URN:SI:UM:
Type (COBISS): Scientific work
Pages: Str. 55-62
Volume: ǂVol. ǂ21
Issue: ǂno. ǂ1
Chronology: 2014
ID: 10847611