COMPARISION OF THE MULTIPLE REGRESSION, ANN, AND ANFIS MODELS FOR PREDICTION OF MOE VALUE OF OSB PANELS
WOOD RESEARCH, vol.61, no.5, pp.741-754, 2016 (SCI-Expanded, Scopus)
- Publication Type: Article / Article
- Volume: 61 Issue: 5
- Publication Date: 2016
- Journal Name: WOOD RESEARCH
- Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
- Page Numbers: pp.741-754
- Keywords: OSB, multiple regression, ANN, ANFIS, mechanical properties, NEURAL-NETWORKS
- Ondokuz Mayıs University Affiliated: Yes
Abstract
This research investigates the prediction of modulus of elasticity (MOE) properties, which is the most important properties in many applications, of the oriented strand board (OSB) produced under different conditions (pressing time, pressing pressure, pressing temperature and adhesive ratios) by multiple regression, artificial neural network (ANN) and adaptive Neurofuzzy inference system (ANFIS). Software computing techniques are now being used instead of statistical methods. It was found that the constructed ANFIS exhibited a higher performance than multiple regression and ANN for predicting MOE.Software computing techniques are very useful for precision industrial applications and, also determining which method gives the highest accurate result.