摘要
在LABVIEW的平台上进行焊接电流信号的采集,为减小外界因素的影响,对采集数据通过小波滤波、数据归一化、均值滤波处理后得到初始运算数据。将处理后的数据在MATLAB中通过构造核函数与决策函数实现支持向量回归机的运算,得到焊缝偏差值。通过对比分析得出,使用该方法能有效提高电弧传感焊缝偏差识别系统的精度,满足实际焊接作业中的需要。
The welding current signal acquisition based on LABVIEW platform,then in order to reduce the influence of external factors,the acquisition data by wavelet filtering,data normalization,mean filtering processing initial data.The processed data in MATLAB by constructing the kernel function and the decision function of the realization of support vector regression machine operation,the final weld seam deviation. Finally ,through the contrast analysis,using this method can effectively improve the arc sensor seam bias recognition accuracy of the system,to meet the actual needs of the welding operation.
出处
《电焊机》
北大核心
2014年第10期52-55,共4页
Electric Welding Machine
关键词
向量回归机
计算机仿真
焊缝偏差识别
vector regression machines
computer simulations
recognition of seam bias