Process prediction model for wood plastic composites pencil boards based on BP neural network

Author

BU, Chiwu

Author_Institution

Sch. of Light Ind., Harbin Univ. of Commerce, Harbin, China

fYear

2011

fDate

15-17 July 2011

Firstpage

533

Lastpage

535

Abstract

Corn straw fiber powder and high-density polyethylene as the main raw materials, polystyrene, silane and paraffin as adhesives, coupling agents and lubricants, respectively, plant fiber composite materials were prepared for the replacement osf basswood pencil board. How the mass ratios of the corn straw powder, high density polyethylene and polystyrene influence the performance of the composite pencil boards were analyzed. The process prediction model for composite pencil boards based on BP neural network was designed, whose accuracy is up to 6%.

Keywords

adhesives; backpropagation; ecocomposites; filled polymers; joining processes; lubricants; natural fibres; neural nets; polymer fibres; production engineering computing; raw materials; wood; wood products; BP neural network; adhesives; basswood pencil board; composite pencil boards; corn straw fiber powder; coupling agents; high-density polyethylene; lubricants; paraffin; plant fiber composite materials; polystyrene; process prediction model; raw materials; silane; wood plastic composites pencil boards; Composite materials; Optical fiber networks; Powders; Predictive models; Rough surfaces; Surface roughness; Surface treatment; BP neural network; Composite materials; Pencil boards; Plant fiber;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechanic Automation and Control Engineering (MACE), 2011 Second International Conference on

Conference_Location

Hohhot

Print_ISBN

978-1-4244-9436-1

Type

conf

DOI

10.1109/MACE.2011.5986978

Filename

5986978