Control model of Laser Cutting Quality based on Simulated Annealing and Neural Network
In processing of laser cutting metal sheet, there is the complex correspondence between crafts parameter.and surface quality. This paper proposed a control model of laser cutting quality based on BackPropagetion(BP) neural networks, which indicated the relationship between craft parameters and surface roughness of laser cutting. By the use of the simulated annealing, the fitting accuracy and convergence of the network would been improved. Experimental design with the Central Composite Design could increase the amount of information and reliability of network trainning samples. After the concrete manufacturing of stainless steel sheet, it was seen from the results the developed method gained better reliability and significance of application.
Laser cutting surface quality neural network simulated annealing
Gui Tong Hong Xu Hanqi Yu
Engineering Practice and Trainning Center.Nanjing institute of technology, theHongJingRoad,211167,Ji Engineering Practice and Trainning Center,Nanjing institute of technology, the HongJing Road,211167,
国际会议
大连
英文
206-211
2011-10-19（万方平台首次上网日期，不代表论文的发表时间）