Analysis of Aluminum Alloy Double-Pulse MIG Welding Arc Signal Characteristics Based on Broadband Mode Decomposition

Welding voltage and current in arc signals are directly related to arc stability and welding quality.Process experiments with different parameters were organized according to the orthogonal experimental design method by constructing an aluminum alloy double-pulse metal inert gas(MIG)welding arc electric signal test platform.The data acquisition system of the aluminum alloy MIG welding process was established to obtain real-time arc signal information reflecting the welding process.The aluminum alloy’s collected double-pulse arc current signals are decomposed adaptively by broadband mode decomposition(BMD).The direct current(DC)signal,pulse signal,distortion signal,ripple signal,and noise signal are separated and extracted,and the composite multiscale fuzzy entropy(CMFE)is calculated for the component set of the electrical signal.The experimental results show that the current waveform obtained by the double-pulse MIG welding current signal is consistent with the corresponding weld forming diagram.Simultaneously,the composite multiscale fuzzy entropy is calculated for the arc characteristic parameters.The rationality of matching process parameters and arc stability of aluminum alloy’s double-pulse MIG welding were evaluated.

Characteristics analyzing and parametric modeling of the arc sound in CO_2 GMAW for on-line quality monitoring

For on-line monitoring of welding quality, the characteristics of the arc sound signals in short circuit CO2 GMAW were analyzed in the time and frequency domains. The arc sound presents a series of ringing-like oscillations that occur at the end of short circuit i. e. the moment of arc re-ignition, and distributes mainly in the frequency band below 10 kHz. A concept of the arc tone channel and its equivalent electrical model were suggested, which is considered a time-dependent distributed parametric system of which the transmission properties depend upon the geometric and physical characteristics of the arc and surroundings, and is excited by the sound source results from the change of arc energy so that results in arc sound. The linear prediction coding （ LPC ） model is an estimation of the tone channel. The radial basis function （ RBF ） neural networks were built for on-line pattern recognition of the gas-lack in welding, in which the input vectors were formed with the LPC coefficients. The test results proved that the LPC model of arc sound and the RBF networks are feasible in on-line quality monitoring.

Development of Welding Multi-Information Remote Wireless Monitoring System Based on STM32

A single sensor is used to obtain welding information in welding monitoring process, but this method has some shortcomings. In order to obtain more comprehensive and reliable welding information, this paper designed and built a welding multi-information wireless monitoring system with STM32-F407ZET6 as the control core and ALK8266 as the wireless transmission module. Real-time acquisition, transmission and display of electric arc signal and welding image information are realized in the monitoring system. This paper mainly introduces the hardware and software core of the monitoring system. At the same time, the signal collected by the monitoring system is compared with the original signal, and the accuracy of the remote monitoring system is tested. The monitoring system is used in welding test. The test results show that the accuracy of the monitoring system meets the requirements, and the on-line monitoring of electric arc signal and welding image can be realized in the welding process.

Feature Extraction and Modeling of Welding Quality Monitoring in Pulsed Gas Touch Argon Welding Based on Arc Voltage Signal

Arc sensing plays a significant role in the control and monitoring of welding quality for aluminum alloy pulsed gas touch argon welding(GTAW). A method for online quality monitoring based on adaptive boosting algorithm is proposed through the analysis of acquired arc voltage signal. Two feature extraction algorithms were developed in time domain and frequency domain respectively to extract six statistic characteristic parameters before removing the pulse interference using the wavelet packet transform(WPT), based on which the Adaboost classification model is successfully established to evaluate and classify the welding quality into two classes and the classified accuracy of the model is as high as 98.81%. The Adaboost algorithm has been verified to be feasible in the online evaluation of welding quality.