Open AccessOptimal Design of Product Culture Image Modeling Based on FNN Model and PSO Algorithms
Author(s) -
Li Lin,
Yanzhe Zhao
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/573/1/012025
Subject(s) - product (mathematics) , computer science , product design , image (mathematics) , genetic algorithm , artificial neural network , population , mathematical optimization , artificial intelligence , mathematics , machine learning , geometry , demography , sociology
In order to solve the problem of strong subjectivity of cultural image modeling design in today’s market and single optimization result caused by product cultural image transformation design method, the evaluation method of product cultural image modeling based on FNN model and the optimization design method of product cultural image modeling based on PSO algorithm were both proposed. Firstly, the representative samples were determined, and the cultural images were sorted out and classified to quantify the shape parameters of the samples; then, the membership function of the product shape parameters was established to fuzzify them, and the mapping relationship between the “product shape parameters-cultural image fitness” was obtained by using three-layer BP neural network, and the evaluation method of the product cultural image modeling was established; By updating the speed and position of representative sample population, adjusting its modeling parameters based on PSO algorithm, the optimization design mechanism of product cultural image modeling was established. Finally, taking the design optimization design of Miao embroidery products in Songtao area of Guizhou Province as an example, the results showed that the optimization design method could well adapt to the optimization design of cultural image modelling and had injected new vitality into cultural creative design.