Study on the wire feed speed prediction of double-wire-pulsed MIG welding based on support vector machine regression

Obtaining the wire feed speed which can properly match the process parameters is difficult in double-wire-pulsed metal inert gas (MIG) welding. This work analyzed ten factors which affect the wire feed speed in reality and conducted corresponding correlation analysis. Then, four significant correlation factors, which were duty ratio, frequency, average current of leading wire, and average current of trailing wire, are selected as independent variables for establishing a double-wire feed speed prediction model. The model established by support vector machine regression used two evaluation criterions, which were the mean square error (MSE) and squared correlation coefficient (SCC), and then obtained the optimal model parameters by mesh optimization. Finally, the proposed model was validated by actual double-wire-pulsed welding experiments. This study can optimize the double-wire welding technological designing process and improve the intelligent double-wire welding industry.

[1]  J. Tušek,et al.  Mathematical modeling of melting rate in twin-wire welding , 2000 .

[2]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[3]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[4]  C. Fornell,et al.  Evaluating structural equation models with unobservable variables and measurement error. , 1981 .

[5]  N. L. Johnson,et al.  Encyclopedia of Statistical Sciences 2. , 1984 .

[6]  Kyoung-jae Kim,et al.  Financial time series forecasting using support vector machines , 2003, Neurocomputing.

[7]  Enrico Zio,et al.  Failure and reliability prediction by support vector machines regression of time series data , 2011, Reliab. Eng. Syst. Saf..

[8]  Ping-Feng Pai,et al.  Predicting engine reliability by support vector machines , 2006 .

[9]  Yunqian Ma,et al.  Comparison of Model Selection for Regression , 2003, Neural Computation.

[10]  Edward J. Wegman,et al.  Statistical Signal Processing , 1985 .

[11]  Fenggui Lu,et al.  Arc profile characteristics of Al alloy in double-pulsed GMAW , 2013 .

[12]  Sami Ekici,et al.  Support vector machines models for surface roughness prediction in CNC turning of AISI 304 austenitic stainless steel , 2012, J. Intell. Manuf..

[13]  Yang Shao,et al.  Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points , 2012 .

[14]  Yu Shi,et al.  Research on evaluation method of aluminum alloy pulse MIG welding stability base on approximate entropy , 2011, 2011 3rd International Conference on Advanced Computer Control.

[15]  Biswajeet Pradhan,et al.  A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS , 2013, Comput. Geosci..

[16]  Jiankang Huang,et al.  Wire extension with Dual freedom PID control in pulsed MIG welding process of aluminum alloy , 2011, 2011 Second International Conference on Mechanic Automation and Control Engineering.

[17]  N. Murugan,et al.  Selection of parameters of pulsed current gas metal arc welding , 2006 .

[18]  Qingsong Xu,et al.  Rate-Dependent Hysteresis Modeling and Control of a Piezostage Using Online Support Vector Machine and Relevance Vector Machine , 2012, IEEE Transactions on Industrial Electronics.

[19]  Sancho Salcedo-Sanz,et al.  Short term wind speed prediction based on evolutionary support vector regression algorithms , 2011, Expert Syst. Appl..

[20]  Xueping Ding,et al.  Arc characteristics and metal transfer process of hybrid laser double GMA welding , 2015 .

[21]  N. Murugan,et al.  Modeling and simulation of wire feed rate for steady current and pulsed current gas metal arc welding using 317L flux cored wire , 2007 .

[22]  D. W. Lyons,et al.  Experimental Approach to Selection of Pulsing Parameters in Pulsed GMAW A method for selection of process parameters in pulsed GMAW helps to efficiently develop welding procedures , 1999 .

[23]  Jungho Im,et al.  ISPRS Journal of Photogrammetry and Remote Sensing , 2022 .

[24]  Mun-Jin Kang,et al.  Optimisation of the wire feed rate during pulse MIG welding of Al sheets , 2008 .

[25]  Yunqian Ma,et al.  Practical selection of SVM parameters and noise estimation for SVM regression , 2004, Neural Networks.

[26]  John J. Lowke,et al.  Predictions of metal droplet formation in arc welding , 1996, Proceeding of Progress in Plasma Processing of Materials 1997.

[27]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[28]  Hai-Lung Tsai,et al.  Determination of equilibrium wire-feed-speeds for stable gas metal arc welding , 2012 .

[29]  Tan Yue-jin.  Heuristic Algorithm for Tuning Hyperparameters in Support Vector Regression , 2007 .

[30]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[31]  electronic resource.  Encyclopedia of statistical science , 2013 .

[32]  F. Tay,et al.  Application of support vector machines in financial time series forecasting , 2001 .