As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
A PCA-BPNN model is proposed and simulated which aims to resolve the difficulties faced by the product quality prediction in the modern industry which is brought by the high dimension of production parameters generated in the complex and nonlinear production process. The PCA algorithm is introduced into the BPNN model to realize the dimension reduction without vital information loss which can simplify the architecture of the neural network. The PCA-BPNN model is illustrated and simulated. Experimental results show that this model is superior over the BPNN which achieves a stable prediction performance with a rapid convergence and can overcome the problem, oscillation of MSE, occurred in the BPNN.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.