J Shanghai Jiaotong Univ Sci ›› 2020, Vol. 25 ›› Issue (6): 746-754.doi: 10.1007/s12204-020-2225-9

• • 上一篇    下一篇

Prediction of Formation Quality of Inconel 625 Clads Using Support Vector Regression

GUO Longlong (郭龙龙), WU Zebing (吴泽兵), HE Yutian (贺雨田), WEI Wenlan (魏文澜), XIA Shengyong (夏胜勇), JU Luyan (鞠录岩), WANG Bo (王博), ZHANG Yong (张勇)   

  1. (1. Mechanical Engineering College, Xi’an Shiyou University, Xi’an 710065, China; 2. Chongqing Engineering Technology
    Research Center for Light Alloy Materials and Processing, Chongqing 404000, China; 3. Refining and Chemical Plant of
    Yumen Oilfield Company, Jiuquan 735000, Gansu, China)

  • 出版日期:2020-12-28 发布日期:2020-11-26
  • 通讯作者: GUO Longlong (郭龙龙) E-mail: llguo@xsyu.edu.cn

Prediction of Formation Quality of Inconel 625 Clads Using Support Vector Regression

GUO Longlong (郭龙龙), WU Zebing (吴泽兵), HE Yutian (贺雨田), WEI Wenlan (魏文澜), XIA Shengyong (夏胜勇), JU Luyan (鞠录岩), WANG Bo (王博), ZHANG Yong (张勇)   

  1. (1. Mechanical Engineering College, Xi’an Shiyou University, Xi’an 710065, China; 2. Chongqing Engineering Technology
    Research Center for Light Alloy Materials and Processing, Chongqing 404000, China; 3. Refining and Chemical Plant of
    Yumen Oilfield Company, Jiuquan 735000, Gansu, China)

  • Online:2020-12-28 Published:2020-11-26
  • Contact: GUO Longlong (郭龙龙) E-mail: llguo@xsyu.edu.cn

摘要: The process parameters of pulsed tungsten inert gas (PTIG) have a significant influence on the formation quality, mechanical properties and corrosion resistance of the weld overlay. The PTIG was utilized to deposit Inconel 625 clads with various combinations of the process parameters, which were determined by the central composite design (CCD) method. Based on the experimental results, the relationship between process parameters of PTIG and formation quality of the Inconel 625 clads was established using support vector regression (SVR) with different kernel functions, including polynomial kernel function, radial basis function (RBF) kernel function, and sigmoid kernel function. The results indicate that the kernel functions have a great influence on the prediction of height, width and dilution. The models with RBF kernel function feature the best goodness of fitting and the most accurate against the other SVR models for estimating the height and the dilution. However, the model with polynomial kernel function is superior to the other SVR models for predicting the width. Meanwhile, the prediction performance of the SVR models was compared with the general regression analysis. The results demonstrate that the optimized SVR model is much better than the general regression model in the prediction performance.


关键词: pulsed tungsten inert gas (PTIG), Inconel 625, formation quality, prediction, support vector regression
(SVR)

Abstract: The process parameters of pulsed tungsten inert gas (PTIG) have a significant influence on the formation quality, mechanical properties and corrosion resistance of the weld overlay. The PTIG was utilized to deposit Inconel 625 clads with various combinations of the process parameters, which were determined by the central composite design (CCD) method. Based on the experimental results, the relationship between process parameters of PTIG and formation quality of the Inconel 625 clads was established using support vector regression (SVR) with different kernel functions, including polynomial kernel function, radial basis function (RBF) kernel function, and sigmoid kernel function. The results indicate that the kernel functions have a great influence on the prediction of height, width and dilution. The models with RBF kernel function feature the best goodness of fitting and the most accurate against the other SVR models for estimating the height and the dilution. However, the model with polynomial kernel function is superior to the other SVR models for predicting the width. Meanwhile, the prediction performance of the SVR models was compared with the general regression analysis. The results demonstrate that the optimized SVR model is much better than the general regression model in the prediction performance.


Key words: pulsed tungsten inert gas (PTIG), Inconel 625, formation quality, prediction, support vector regression
(SVR)

中图分类号: