Defect Detection in Arc-Welding Processes by Means of the Line-to-Continuum Method and Feature Selection

Abstract

Plasma optical spectroscopy is widely employed in on-line welding diagnostics. The determination of the plasma electron temperature, which is typically selected as the output monitoring parameter, implies the identification of the atomic emission lines. As a consequence, additional processing stages are required with a direct impact on the real time performance of the technique. The line-to-continuum method is a feasible alternative spectroscopic approach and it is particularly interesting in terms of its computational efficiency. However, the monitoring signal highly depends on the chosen emission line. In this paper, a feature selection methodology is proposed to solve the uncertainty regarding the selection of the optimum spectral band, which allows the employment of the line-to-continuum method for on-line welding diagnostics. Field test results have been conducted to demonstrate the feasibility of the solution.

Optical Methods for On-line Quality Assurance of Welding Processes in Nuclear Steam Generators

“…However, it has been demonstrated that no all emission lines are good candidates to infer information about the welding process . For that reason, a previous process of line selection using the Sequential Floating Forward Selection (SFFS) algorithm is proposed (García-Allende et al, 2009). This algorithm is widely applied to reduce the dimensionality, i.e., the number of wavelengths, of spectral data prior to their interpretation (Ferry et al, 1994).…”

Welding diagnostics based on feature selection and optimization algorithms

“…In a previous paper [5] SFFS was used to select the best spectral bans in terms of discrimination between correct seams and different weld defects for a GTAW (Gas Tungsten Arc Welding) process. The chosen spectral bands, that can be associated with plasma emission lines or continuum radiation, were then used to generate the required output monitoring profiles by using the line-to-continuum method.…”

“…5. Proceed to change velocity and position of each particle within the swarm according to the following expression: (5) 6. If the stopping condition is met then exit with the best result so far; otherwise repeat from point 2.…”

“…Within this framework we have studied some new methods trying to improve the solutions, especially the processing times involved, which can be relevant if welding speeds are fast. One of this contributions has been designed using a feature selection algorithm (SFFS) to identify the most discriminant plasma emission lines in terms of defect detection [5]. In doing so, the use of the line-to-continuum method allows to obtain profiles that can be directly correlated to the quality of the seams.…”

Use of the plasma RMS signal for on-line welding quality monitoring

“…Other solutions are more related to the conventional approach mentioned above, for example the selection of the wavelength associated with the maximum intensity of the plasma continuum [3], or the employment of the line-to-continuum method as an alternative to obtain the plasma temperature [4].…”