Title :
The Combination of Grey System and BP Neural Network
Author :
Shuhai, Fan ; Yexiang, Fang ; Wenping, Li ; Yungao, Ma ; Tianyuan, Xiao
Author_Institution :
Nanjing Univ. of Technol., Nanjing
Abstract :
Many problems existed in the current grey system model-building, such as the rough exponential model, unsatisfied precision and the poor parallel computation ability. So it was very important to expand the current grey theory and find out an appropriate model building method. There were several ways to combine grey system with neural network, such as "Simple Combination", "Serial Combination", "Strengthening Grey System with Neural Network", "Building Neural Network with the Aid of Grey System" and "Grey Neural Network". For the grey neural network, three model building methods (crosswise method, lengthwise method and hybrid method) were given out. Finally, an example of a typical grey BP neural network was given where the crosswise method was used and successfully applied to mass customization manufacturing quality control.
Keywords :
backpropagation; grey systems; neural nets; BP neural network; crosswise method; grey system; hybrid method; lengthwise method; mass customization manufacturing; model building; quality control; rough exponential model; serial combination; simple combination; Automation; Computer industry; Concurrent computing; Mechatronics; Neural networks; Prediction methods; Predictive models; Quality control; Temperature; Uncertainty; grey system; neural network; quality control;
Conference_Titel :
Mechatronics and Automation, 2007. ICMA 2007. International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-0828-3
Electronic_ISBN :
978-1-4244-0828-3
DOI :
10.1109/ICMA.2007.4303731