Monitoring gas metal arc welding in real-time: a fuzzy logic approach

This paper proposes a new approach for real-time weld quality monitoring based on the combination of optical sensors with fuzzy logic classification algorithms. The sensing hardware encompasses photodiodes measuring the relations emitted by the plasma surrounding the welding arc and A/D converters. The measured data is then filtered and processed to determine in real-time indices of local quality of the welding process. These indices are then fed to a fuzzy system, which provides an index of the overall quality of the weld, classifying type and position of specific events (e.g. anomalies in the current, voltage or speed of the arc, the contamination with other materials, holes). In an expensive experimental comparison, the fuzzy system outperforms the former version of the detection algorithm based on a statistical approach.