Accuracy assessment of the models for the prediction of flexural performance of particleboard made out of poplar (Populus alba)

سال انتشار: 1400
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 198

متن کامل این مقاله منتشر نشده است و فقط به صورت چکیده یا چکیده مبسوط در پایگاه موجود می باشد.
توضیح: معمولا کلیه مقالاتی که کمتر از ۵ صفحه باشند در پایگاه سیویلیکا اصل مقاله (فول تکست) محسوب نمی شوند و فقط کاربران عضو بدون کسر اعتبار می توانند فایل آنها را دریافت نمایند.

این مقاله در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

CNRE05_370

تاریخ نمایه سازی: 10 مرداد 1400

چکیده مقاله:

This study was targeted to evaluate the accuracy of the prediction models including multiple linear regression, artificial neural network and Taguchi method was used to predict modulus of rupture and modulus of elasticity of particleboard. Therefore, particleboards were produced by poplar particles in three level of density (۰.۶۵, ۰.۷, and ۰.۷۵ g/cm۳), three levels of slenderness ratios (۴۷, ۳۰, and ۱۳) and three levels of adhesive percent (۸, ۹.۵, and ۱۱%). After doing the experimental and preparing the data, density, particle size and adhesive showed statistically significant effects on Modulus of Rupture (MOR) and Modulus of Elasticity (MOE) of particleboard. Mean absolute percentage error (MAPE) and coefficient of determination (R۲) was used to assess the model performances. MAPE of lower than ۱۰ percent and R۲ of higher than ۰.۹ is satisfactory and acceptable for the prediction of models in most industrial works. The results showed that MAPE for the prediction of MOR and MOE were ۹.۱۳ and ۹.۰۶%, respectively. R۲ of them were ۰.۶۸۵ and ۰.۷۷۳, respectively. Artificial neural network model could predict MOR and MOE of the particleboard with a MAPE of ۷.۷۲% and ۷%, and a R۲ of ۰.۷۷ and ۰.۸۶, respectively. MAPE of the multiple regression model for the prediction of MOR and MOE were ۸.۳% and ۹.۰۶%, and their corresponding R۲ were ۰.۷۴ and ۰.۷۸, respectively. The higher performance was obtained in ANN model.

نویسندگان

Akbar Rostampour Haftkhani

Assistant prof. of Wood Science and Technology, department of natural resources, Faculty of agriculture and natural resources, University of Mohaghegh Ardabili, Ardabil, Iran.