Two different cases regarding the zinc coating at the lap joint faying surface are selected for studying the influence of zinc vapor on the keyhole dynamics of the weld pool and the final welding quality. One case has the zinc coating fully removed at the faying surface; while the other case retains the zinc coating on the faying surface. It is found that removal of the zinc coating at the faying surface produces a significantly better weld quality as exemplified by a lack of spatters whereas intense spatters are present when the zinc coating is present at the faying surface. Spectroscopy is used to detect the optical spectra emitted from a laser generated plasma plume during the laser welding of galvanized high strength DP980 steel in a lap-joint configuration. A correlation between the electron temperature and defects within the weld bead is identified by using the Boltzmann plot method. The laser weld pool keyhole dynamic behavior affected by a high-pressure zinc vapor generated at the faying surface of galvanized steel lap-joint is monitored in real-time by a high speed charge-coupled device (CCD) camera assisted with a green laser as an illumination source.

Real-time monitoring of laser welding of galvanized high strength steel in lap joint configuration

The validity of a processing technique, based on feature selection and artificial neural networks, when applied to arc-welding on-line quality monitoring is analyzed. An optical fiber embedded within the welding torch captures the plasma radiation, which is delivered to a CCD spectrometer. In the proposed solution the spectral analysis is performed in two stages: dimensionality reduction is accomplished using a feature selection algorithm and, after that, an artificial neural network carries out the spectral identification task. The validity of the technique has been successfully demonstrated by means of several experimental welding tests.

Spectral processing technique based on feature selection and artificial neural networks for arc-welding quality monitoring

A new technique is presented in this paper for the analysis of welding process emission spectra to accurately estimate in real-time the plasma electronic temperature. The estimation of the electronic temperature of the plasma, through the analysis of the emission lines from multiple atomic species, may be used to monitor possible perturbations during the welding process. Unlike traditional techniques, which usually involve peak fitting to Voigt functions using the Levenberg-Marquardt recursive method, sub-pixel algorithms are used to more accurately estimate the central wavelength of the peaks. Three different sub-pixel algorithms will be analysed and compared, and it will be shown that the LPO (linear phase operator) sub-pixel algorithm is a better solution within the proposed system. Experimental tests during TIG-welding using a fibre optic to capture the arc light, together with a low cost CCD-based spectrometer, show that some typical defects associated with perturbations in the electron temperature can be easily detected and identified with this technique. A typical processing time for multiple peak analysis is less than 20 ms running on a conventional PC.

Fast algorithm for spectral processing with application to on-line welding quality assurance

When plasma optical spectroscopy is applied to on-line welding quality monitoring, the plasma electronic temperature is commonly selected as the spectroscopic parameter to determine. However, several processing stages have to be considered in this case, including plasma emission line identification, which is significantly costly in terms of computational performance. In this paper, the wavelength associated with the maximum intensity of the plasma background emission is proposed as the new monitoring signal, as it will be demonstrated that there is a clear correlation between this parameter and the welding quality. The resulting processing scheme is clearly simpler, and experimental and field tests will prove the feasibility of the proposed technique.

Spectroscopic analysis of the plasma continuum radiation for on-line arc-welding defect detection

Diverse welding processes have been utilized in manufacturing industry for years. But up to date, welding quality still cannot be guaranteed, due to the lack of an efficient and on-line welding defects monitoring method, and this leads to increased manufacturing costs. In this paper, a method based on feature extraction and machine learning algorithm for on-line quality monitoring and defects classification was presented. Plasma radiation was captured by an optical fiber probe, and delivered by an optical fiber to the spectrometer. The captured spectral signal was processed by selecting sensitive emission lines and extracting features of spectral data's evolution, which realized spectral data compression with low computational cost. After selecting the proper training data set, the designed ANN and SVM allows automatic detection and classification of welding defects. The validity of proposed method was successfully approved by test data set in welding experiments. Welding experiments on galvanized steel sheets showed the corresponding relationship between the output of classifiers and welding defects. Finally, the two classifiers were compared. Experiments indicated the performance of ANN is slightly better than that of SVM, while both of them have its own advantages.

A spectroscopic method based on support vector machine and artificial neural network for fiber laser welding defects detection and classification

Non-intrusive and real-time monitoring techniques are increasingly required by manufacturing industry in order to detect flaws in arc welding processes. In this work the development of an optical inspection system, for monitoring the manual gas tungsten arc welding (GTAW) process of steel pipes, is described. The arc plasma visible emission produced during the process was acquired and spectroscopically analysed. Measuring the intensities of selected argon emission lines allowed real time calculation and recording of the axial electron temperature of the plasma. Experimental results showed that the temperature signal varies greatly in the case of instabilities of the weld pool that cause weld defects. A suitable algorithm, based on a statistical analysis of the signal, was developed in order to real time flag defective joints. It is shown that several weld defects such as porosity, dropout, lack of fusion, solid inclusions and craters were successfully detected in a production environment. The performances of the optical sensor were compared with the results of state-of-the-art post-weld controls such as x-rays and penetrating dyes, showing good agreement and thus demonstrating the validity of this quality monitoring system.

http://iopscience.iop.org/article/10.1088/0957-0233/15/12/010/pdf

Fabio Ottonelli

Papers

A sensing torch for on-line monitoring of the gas tungsten arc welding process of steel pipes

Experimental detection and theoretical prediction of laser welding plasma oscillations