Title :
On-line prediction of surface roughness in cylindrical traverse grinding based on BP+GA algorithm
Author :
Li, Guofa ; Liu, Jia ; Yang, Shuxiang
Author_Institution :
Dept. of Mech. Eng., Jilin Univ., Changchun, China
Abstract :
Artificial neural networks are introduced in the area of grinding. There are some disadvantages in BP (Back Propagation) algorithm, such as low rate of convergence speed, easily falling into local minimum point and weak global search capability. In order to solve these problems, this paper presents a new learning algorithm that uses GA (Genetic Algorithm) to train BP neural networks. The prediction model of surface roughness in cylindrical traverse grinding based on evolutionary neural networks is proposed in detail. The experimental and the simulating results shows that the combination of BP and GA can effectively overcome the problem of easily falling into local minimum point, and this method can get higher accuracy of prediction. By controlling the grinding parameters, this method can realize the prediction for the roughness of the workpiece.
Keywords :
backpropagation; genetic algorithms; grinding; grinding machines; neural nets; production engineering computing; surface roughness; BP neural network training; artificial neural networks; back propagation algorithm; cylindrical traverse grinding; evolutionary neural networks; genetic algorithm; global search capability; local minimum point; on-line surface roughness prediction; workpiece roughness; Genetic algorithms; Neural networks; Prediction algorithms; Rough surfaces; Surface roughness; Surface treatment; Wheels; BP+GA neural networks; Cylindrical traverse grinding; On-line Prediction; Surface roughness;
Conference_Titel :
Mechanic Automation and Control Engineering (MACE), 2011 Second International Conference on
Conference_Location :
Hohhot
Print_ISBN :
978-1-4244-9436-1
DOI :
10.1109/MACE.2011.5987221