Artificial neural network modeling of weld joint strength prediction of a pulsed metal inert gas welding process using arc signals

Wire arc additive manufacturing (WAAM) is an important metal 3D printing method, which has many advantages, such as rapid deposition rate, low cost, and suitability for large complex metal components manufacturing, and it has received extensive attention. This paper summarizes the research developments of WAAM in recent years, including the WAAM-suitable metal materials and processing technology, deposition strategy optimization including slicing and path planning algorithm, multi-sensor monitoring and intelligent control, and the large complex metal components manufacturing technology. The promising development directions of WAAM are prospected, including the research of new materials and new technology, composite manufacturing, multi-sensor and real-time monitoring, algorithmic optimization of metal filling strategy, and the application of artificial intelligence technology in WAAM, etc.

Wire and arc additive manufacturing of metal components: a review of recent research developments

Technical innovations in robotic welding and greater availability of sensor-based control features have enabled manual welding processes in harsh work environments with excessive heat and fumes to be replaced with robotic welding The use of industrial robots or mechanized equipment for high-volume productivity has become increasingly common, with robotized gas metal arc welding (GMAW) generally being used More widespread use of robotic welding has necessitated greater capability to control welding parameters and robotic motion and improved fault detection and fault correction Semi-autonomous robotic welding (ie, highly automated systems requiring only minor operator intervention) faces a number of problems, the most common of which are the need to compensate for inaccuracies in fixtures for the workpiece, variations in workpiece dimensions, imperfect edge preparation, and in-process thermal distortions Major challenges are joint edge detection, joint seam tracking, weld penetration control, and measurement of the width or profile of a joint Such problems can be most effectively solved with the use of sensory feedback signals from the weld joint Thus, sensors play an important role in robotic arc welding systems with adaptive and intelligent control system features that can track the joint, monitor in-process quality of the weld, and account for variation in joint location and geometry This work describes various aspects of robotic welding, programming of robotic welding systems, and problems associated with the technique It further discusses commercially available seam-tracking and seam-finding sensors and presents a practical case application of sensors for semi-autonomous robotic welding This study increases familiarity with robotic welding and the role of sensors in robotic welding and their associated problems

/pdf/robotic-arc-welding-sensors-and-programming-in-industrial-235321pos9.pdf

Robotic arc welding sensors and programming in industrial applications

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 was proposed based on the analysis of acquired arc voltage signal, through which two algorithms of feature extraction were developed in time and frequency domain, respectively. In time domain,the wavelet packet transform was carried out to eliminate the pulse interference of the feature parameter curve. In frequency domain, the other new algorithm was proposed based on the voltage power spectrum density (PSD) which was calculated by using the improved Welch algorithm and divided into five frequency bands before the statistic parameters were extracted. The correlation between the feature parameters in different frequency bands and welding defects were carefully analyzed to select a more sensitive one as the monitoring parameters. The proposed algorithms on this paper were verified to be capable of detecting lack of penetration, burn through, and the defect caused by lack of gas.

Online welding quality monitoring based on feature extraction of arc voltage signal

A model is developed to predict variations in welding parameters due to surface tension and electromagnetic force.

Simulation of dynamic behavior in a GMAW system

A method for detecting flaws in automatic, constant-voltage gas metal arc welding using the process current and voltage signals was developed. Seven algorithms process the current and voltage signals to give quality parameters. A defect-detection algorithm processes the quality parameters and flags welds that are different from a baseline. The baseline is constructed from the recorded quality parameters of previously made, defect-free welds. Two series of tests were conducted to test the sensitivity of the algorithms for defects and to test the entire sensor system in production. In the first series, on a 3-mm lap joint, the algorithms detected a lack of shielding gas, oily parts and melt-through from inadequate part cross section, but could not detect off-joint welding. The algorithms showed a mixed sensitivity to melt-through from large root openings. In production tests, 520 welds were monitored. The defect detection algorithm was tuned on data from the first 82 welds. The sensot flagged five of the six defects monitored and did not flag any defect-free welds The defect not detected was a small pore, < 3 mm diameter.

E. G. Blachowiak

Papers

Arc sensing for defects in constant-voltage gas metal arc welding

Weld defect decisions using through-the-arc sensor data