Abstract
This study sets up the corresponding relation between product modeling elements and style semantics based on neural network. First, establish matrices of office chair modeling elements and style semantics by questionnaire method respectively. Then, build standard Back Propagation Neural Network (BPNN), BPNN on Levenberg-Marquardt (L-M) algorithm, standard Radial Basis Function (RBF) neural network and RBFNN on K-means clustering algorithm by MATLAB software and compare the simulating results on two kinds of BPNN and RBFNN. Finally, choose the RBFNN on Kmeans clustering algorithm as the best model to guide product modeling design. The effectiveness and applicability of this method are demonstrated by experimental results on the office chair design. It is shown that this method not only improves the efficiency of existing products style semantics judgment but also can be used to evaluate the style semantics of each design candidate.
Paper version not known (
Free)
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call