Modelling of the clearance effects in the blanking process of CuZn30 sheet metal using neural network − a comparative study
| Autor: | Hakan Gürün, Emre Çelik, Onur Çavuşoğlu, Nihat Öztürk |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Artificial neural network
business.industry Mühendislik Process (computing) Feed forward Estimator General Medicine sac metal kesme kesme düzlüğü çapak boyu kesme kuvveti sinir ağı bulanık mantık tahmin Modular design Fuzzy logic sheet metal blanking smooth sheared burr height blanking force neural network fuzzy logic estimation Engineering visual_art visual_art.visual_art_medium business Sheet metal Algorithm Blanking Mathematics |
| Zdroj: | Volume: 11, Issue: 2 187-193 Bilişim Teknolojileri Dergisi |
| ISSN: | 2147-0715 1307-9697 |
| DOI: | 10.17671/gazibtd.380961 |
| Popis: | Clearanceeffects on the product quality and blanking force in sheet metal blankingprocess are initially investigated experimentally, and then modelled throughneural network (NN) approach. Using eleven different clearances from 8% to 18%with a sampling rate of 1%, blanking processes are applied to sheet materialCuZn30 with a thickness of 1mm using a modular template. During the experiments,blanking force, smooth sheared/fractured rate and burr height for the resultingproducts are measured for each of clearance value and a certain portion of themare taken as example patterns to train the developed feedforward NN. SeveralNN-based estimation results are presented which verify that a satisfactoryneural network model is attained for the concerned parameter estimations.Moreover, comparisons with a recent study that benefits from fuzzy logic as anestimator tool are also presented for the same system. We realize that estimatingperformance is improved using the NN and a significant contribution of ourproposal is that its design is much simpler than that of its counterpart whichrequires proper and sufficient expert knowledge for tuning of characteristicparameters such as numbers and shapes of membership functions, linguisticcontrol rules. Clearanceeffects on the product quality and blanking force in sheet metal blankingprocess are initially investigated experimentally, and then modelled through neuralnetwork (NN) approach. Using eleven different clearances from 8% to 18% with a samplingrate of 1%, blanking processes are applied to sheet material CuZn30 with athickness of 1mm using a modular template. During the experiments, blankingforce, smooth sheared/fractured rate and burr height for the resulting productsare measured for each of clearance value and a certain portion of them aretaken as example patterns to train the developed feedforward NN. Several NN-basedestimation results are presented which verify that a satisfactory neuralnetwork model is attained for the concerned parameter estimations. Moreover, comparisonswith a recent study that benefits from fuzzy logic as an estimator tool arealso presented for the same system. We realize that estimating performance is improvedusing the NN and a significant contribution of our proposal is that its designis much simpler than that of its counterpart which requires proper and sufficientexpert knowledge for tuning of characteristic parameters such as numbers andshapes of membership functions, linguistic control rules. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|