| Application of Principal Component Analysis and BP Artificial Neural Network in Prediction of Abrasion Resistance of Rubber Materials |
| |
| DOI： |
| Key Words: SBR；neural network；principal component analysis；abrasion resistance；sensitivity analysis |
| Author Name | Affiliation | | XIANG Ke－lu | Beijing University of Chemical Technology | | LUO Jin－lian | Beijing University of Chemical Technology | | XIE Peng | Beijing University of Chemical Technology | | WU You－ping | Beijing University of Chemical Technology |
|
| Hits: 592 |
| Download times: 375 |
| Abstract: |
| A back propagation(BP) neural network model based on sensitivity analysis was established to predict abrasion of SBR composites.The data of eight kinds of mechanical properties of SBR composites were dimensionally reduced through principal component analysis(PCA)，and the PCA data were utilized as the input vectors while abrasion as the output vector of the BP network.Meanwhile，the sensitivity matrix of the input vector was calculated in order to analyze the influence of mechanical properties on abrasion.The results demonstrated that the co－linearity between the network input vectors could be eliminated by PCA and the network was simplified at the same time.The prediction error was within the allowable range，indicating that the BP network was suitable for SBR abrasion prediction.Sensitivity analysis indicated that the abrasion resistance of SBR was remarkably influenced by modulus，elongation at break and permanent deformation at break. |
|
View Full Text
View/Add Comment Download reader |
| Close |
