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

Članak prikazuje savijanje lima u dvije faze i predviđanje konačnog kuta savijanja pomoću usmjerene neuronske mreže. Glavni cilj je bio istražiti tehnološke parametre savijanja lima u dvije faze i razviti inteligentan način, koji će omogućiti predviđanje tih tehnoloških parametara. Prikazan je proces savijanja lima u dvije faze, gdje se prikazuju i razni tehnološki parametri i ispitni alati sa kojima su provedena ispitivanja i mjerenja. Rezultati ispitivanja i mjerenja su bili ključ u donošenju procjene pojedinih tehnoloških parametara. Opisano je predviđanje konačnog kuta savijanja lima korištenjem usmjerene neuronske mreže, koja prima signale na ulazu. Ti signali tada prolaze kroz skrivenu razinu do izlaza, gdje dobiju odgovor na ulazne signale. Za ulaz u neuronsku mrežu upotrebljavaju se podaci koji utječu na odabir kuta konačnog savijanja. Za neuronsku mrežu se koristi pet različitih inputa. Odabirom željenog kuta savijanja pomoću neuronske mreže, može se doprinijeti optimizaciji savijanja lima u dvije faze.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