The Gmaw Arc Acoustic Parameters Of The Model And Pattern Recognition

As concomitant of the welding process, the arc sound signal in the GMAW contains plenty of information relevant to arc behavior, melting metal transition mode, welding parameters, arc stability, which sensing and data acquisition are simple and easy. The arc sound signal is the important information resource for studying stability of welding process and monitoring and controlling of welding quality in the GMAW. Purposed on welding state of the short circuit GMAW, the relativity between characteristic of arc sound signal and welding state is analysised. Producing and formative mechanism of acoustic signal is approached. LPC forecast model was constructed. According to the theory above, the concept of tone channel and its equivalent mathematical model were advanced, and by which characteristic of arc sound signal is picked up. RBF Network and SVM model are used to set up the image model of arc sound signal and welding state in order to realize the pattern recognition on-line of the welding conditions.A synchronous signal collection system was developed with AC6115. The graphical user interface based on VB is designed, which is friendly and simple and stable. At the same time, the welding signals in CO2 gas shield arc welding are continuously collected under high sample rate, and signal waveform is display.The analysis methods of signal are used to analyze characteristic of arc sound signal in time-domain and frequency-domain. Synchronization, correlation of three kinds of signal of current, voltage and arc sound is studied. The research indicates that, the arc sound presents a series of ringing which mainly occurs at the end of short circuit transfer or the moment of arc re-ignition. The sound signal is some similar to the variation of arc power, in which replaced by pulse. The discrepancy of arc sound signal and power difference is indicated by analysis of frequency-domain. Consequently, it is proved that the variation of arc power can not be used to absolutely described the arc sound signal.By analysis based on time-domain and frequency-domain, the producing and formative mechanism of acoustic signal is approached, and the tone channel is put forward. The research indicates that variation of arc power is the exciting source, andtone channel is made up of the shielded gas, arc column, magnetic field and temperature field during the welding process. They are combined to generate the arc sound. For thoroughly studying characteristic of arc sound, Linear Prediction Coding (LPC) forecast model was constructed to describe the system of tone channel in welding process which is described with a all-poles time dependent coefficients digital filter, which basically conform the assumption of LPC model. Therefore, the LPC model of sound can be factually considered a parametric estimation of the tone channel. The RBF neural networks and SVM model were applied for pattern recognition of the flux of the shield gas and wire extension in welding process, in which the input vectors were constructed by the LPC parameters and reflectance of sound signal.