Analysis of SMAW Parameters Using Self Organizing Maps and Probability Density Distributions

Abstract

Shielded Metal Arc Welding (SMAW) is one of the most important welding process used in the industry for joining ferrous and nonferrous metals. In an arc welding process random variations in current and voltage takes place. Reliable acquisition of these variations during actual welding process and its subsequent analysis can be very useful to various parameters of the arc welding process. Now a day, the welding power sources have a provision of advance arc control to suitably adjust the welding parameters with minimum time delay and to set the right welding parameters during actual process. Hence, to study the exact behaviour of these modern power sources used for welding it is essential to acquire all the possible minute variations taking place while welding is in progress. In the present study, the effect of varying input current and welding power sources on SMAW process is studied. To evaluate the effect of current variations in a SMAW process data were acquired at different current values (from 70 to 120 A). Similarly, to study the behaviour of welding power sources data acquisition was done for six different welding power sources. In both the cases data were acquired at a sampling rate of 100,000 samples/s for duration of 20 s using a general purpose DSO while welding is in progress. These welds were prepared using same type of welding electrode by the same welder employing the identical parameters. The data thus obtained was filtered using the Fast Fourier Transform (FFT) low pass filter and subjected to statistical and neural network analyses. From the Probability Density Distributions (PDDs) and Self Organized Maps (SOM) generated using the data acquired, it is possible to differentiate various weld geometry. Further using these analyses, it is also possible to evaluate the performances of the different welding power sources. Grading of the power sources based on SOM technique matched well with grading arrived at based on the appearance of the weld bead. Results clearly indicate that the procedure presented here can be effectively used to assess the various parameters of welding power sources.