摘要
将熔化极气体保护焊(GMAW)焊接电参数概率密度分布(PDD)和时间频数分布(CFD)数值信息进行进一步的处理,用其平均值、方差和标准方差等统计参数,构成12维矢量S12,描述不同工艺条件下的GMAW焊接过程。综合神经网络和模糊技术的优点,建立了模糊神经网络系统FKCN,对8种工艺条件下24个GMAW焊接试验的识别成功率达到了100％。
The test data of probability density distribution (PDD) and class frequency distribution (CFD) of electrical parameters in GMAW are further processed, and their statistical values of mean, variance and standard deviation are used to set up a 12-dimensional vector S12 for describing GMAW processes under different welding conditions. The merits of neural network and fuzzy logic technology are combined together to develop a neuro-fuzzy system FKCN, which can automatically recognize 24 test cases under 8 kinds of welding conditions with a correct rate of 100%.
出处
《机械工程学报》
EI
CAS
CSCD
北大核心
2004年第1期151-154,共4页
Journal of Mechanical Engineering
基金
德意志研究联合会(DFG)资助项目(2001[059])。
