Release Time:2019-03-11  Hits:

Indexed by: Conference Paper

Date of Publication: 2011-11-04

Included Journals: Scopus、CPCI-S、EI

Volume: 501

Page Number: 27-+

Key Words: artificial neural network; composites; ANN

Abstract: Using a feed-forward artificial neural network (ANN), the tensile strength of a series of poly(phthalazinone ether sulfone ketone)(PPESK) blended with different contents of polyetheretherketone(PEEK), polysulfone(PSF), polyphenylene sulide (PPS) and reinforced with various amounts of whisker(TK) composites has been predicted based on a measured database. Compared with the experimental results, the maximum error obtained is not more than 0.8%. It is concluded that the predicted data are well acceptable. A well-trained ANN is expected to be very helpful mathematical tool in the structure-property analysis of polymer composites. Finally, using ANN modeling data and experimental data, the tensile strength properties related to whisker weight percent were established.