Application of RVM for prediction of bead shape in underwater rotating arc welding

作者：Du, Jianhui^*; Shi, Yonghua; Wang, Guorong; Huang, Guoxing

来源：China Welding, 2010, 19(4): 40-43.

• Maximum error
• Mean errors
• Prediction model
• Prediction precision
• Relevance Vector Machine
• Rotating arc sensor
• Rotating arcs
• Rotational frequency
• Small size
• Training data sets
• Weld bead
• Welding current
• Welding parameters

Bead shape in underwater rotating arc welding was affected by several welding parameters. RVM(relevance vector machine) was used to build a model to predict weld bead shape. The training data set of RVM consists of the welding parameters which are rotational frequency, rotational radius, height of torch and welding current and the features of the bead shape. The maximum error and mean error for prediction of width are 0.10 mm and 0.09 mm, respectively, and the maximum error and mean error for prediction of penetration are 0.31 mm and 0.12 mm, respectively, which are showed that the prediction model can achieve higher prediction precision at reasonably small size of training data set.

• 出版日期2010-12
• 单位华南理工大学