A Study on On-line Mathematical Model to Control of Bead Width for Arc Welding Process

Son, Joon-Sik; Lee, Jong-Pyo; Park, Min‐Ho; Jin, Byeong-Ju; Yun, Tae-Jong; Kim, Ill-Soo

doi:10.1016/j.proeng.2017.01.146

Cited by 6 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Backpropagation Fig. 6 Comparison between the developed BP and the developed LM neural network models 62) network model with optimal architecture of neural network using genetic algorithm is proposed to be applicable for the real-time prediction of bead geometry 68) . The on-line learning neural network has been carried out a learning each time data acquired so that on-line learning neural network has a good adaptability more than off-line learning neural network on the other welding circumstances.…”

Section: Levenbergmarquardtmentioning

confidence: 99%

A Review on Optimizations of Welding Parameters in GMA Welding Process

Kim

Park

2018

Journal of Welding and Joining

Self Cite

View full text Add to dashboard Cite

With the increase of automatic welding system employed in the manufacturing industries, the selection of optimal welding parameters must be more specific to ensure that quality is obtained. Furthermore, it is necessary to have a suitable model that establishes the interrelationship between welding parameters and bead geometry to get the desired weld ability as quality since it is a complicated process, which involves interactions of thermal, mechanical, electrical and metallurgical phenomenon. Many researchers have reported theoretical, numerical, empirical and AI models to give the optimal welding conditions for GMA(Gas Metal Arc) welding process. In addition, controlling the welding parameters plays an important role in ensuring the quality of the weld. However, there is a need to comprehensively review the GMA welding process in terms of different independent and dependent welding parameters for the purpose of modeling and optimization of GMA process. In this paper, several experimental design and optimization methodologies are reviewed and discussed with current literature on experimental design, multiple regressions analysis, the neural network, fuzzy logic, and genetic algorithm to improve the quality of weldments. This review underlines the need of development of appropriate nature inspired algorithm for the optimization of such advanced manufacturing process.

show abstract

Section: Levenbergmarquardtmentioning

confidence: 99%

A Review on Optimizations of Welding Parameters in GMA Welding Process

Kim

Park

2018

Journal of Welding and Joining

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [6], regression analysis models were researched for predicting the quality of the weld. The quality of the weld was determined depending on the welding speed, welding current and arc voltage.…”

mentioning

confidence: 99%

“…The study also took into account the surface temperatures of the welded product. The authors of [6] argue that empirical models can predict optimal welding parameters to achieve the required welding criteria. Models can be applied in automatic control systems and in an expert system to solve the problem of welding process optimization.…”

mentioning

confidence: 99%

Research on the possibilities of using linear observation models in welding processes

Shamkhee¹,

Fedorovich²,

Ivanovich³

et al. 2019

PEN

View full text Add to dashboard Cite

The usage relevance of linear observation models of welding processes is substantiated. A brief analytical review of scientific papers on using linear observation models for researching the processes of arc welding is introduced. An example of studies utilizing a linear observation model based on the results of experiments with alloying of a weld metal is given. The type of linear observation modelfractional replicationis determined. An experiment planning matrix and test results are given. After performing tests and processing the experimental data, mathematical models in the form of dependencies of the transfer of alloying elements into the weld metal were obtained. According to the results of the experiments, empirical models in the form of dependencies evaluating the percentages of manganese, silicon and carbon, transfer coefficients from the "wire-to-product" distance, the diameter of the welding nozzle and the filling wire feed rate were obtained. Since the degree of uncertainty of parameters during welding is high enough, the necessity of further modification of linear observation models using expert knowledge is justified. The mathematical specification of the linear observation model with parameters in the form of fuzzy intervals is given. An algorithm for identifying the parameters of a linear observation model in the form of fuzzy intervals has been developed.

show abstract