A multi-strand composite welding wire was applied to join high nitrogen austenitic stainless steel, and microstructures and mechanical properties were investigated. The electrical signals demonstrate that the welding process using a multi-strand composite welding wire is highly stable. The welded joints are composed of columnar austenite and dendritic ferrite and welded joints obtained under high heat input and cooling rate have a noticeable coarse-grained heat-affected zone and larger columnar austenite in weld seam. Compared with welded joints obtained under the high heat input and cooling rate, welded joints have the higher fractions of deformed grains, high angle grain boundaries, Schmid factor, and lower dislocation density under the low heat input and cooling rate, which indicate a lower tensile strength and higher yield strength. The rotated Goss (G_RD) ({110}〈1 $\overline{1}$ 0〉) orientation of a thin plate and the cube (C) ({001}〈100〉) orientation of a thick plate are obvious after welding, but the S ({123}〈63 $\overline{4}$ 〉) orientation at 65° sections of Euler’s space is weak. The δ-ferrite was studied based on the primary ferrite solidification mode. It was observed that low heat input and a high cooling rate results in an increase of δ-ferrite, and a high dislocation density was obtained in grain boundaries of δ-ferrite. M₂₃C₆ precipitates due to a low cooling rate and heat input in the weld seam and deteriorates the elongation of welded joints. The engineering Stress–strain curves also show the low elongation and tensile strength of welded joints under low heat input and cooling rate, which is mainly caused by the high fraction of δ-ferrite and the precipitation of M₂₃C₆.

The accurate online detection of laser welding penetration depth has been a critical problem to which the industry has paid the most attention. Aiming at the laser welding process of TC4 titanium alloy, a multi-sensor monitoring system that obtained the keyhole/molten pool images and laser-induced plasma spectrum was built. The influences of laser power on the keyhole/molten pool morphologies and plasma thermo-mechanical characteristics were investigated. The results showed that there were significant correlations among the variations of the keyhole–molten pool, plasma spectrum, and penetration depth. The image features and spectral features were extracted by image processing and dimension-reduction methods, respectively. Moreover, several penetration depth prediction models based on single-sensor features and multi-sensor features were established. The mean square error of the neural network model built by multi-sensor features was 0.0162, which was smaller than that of the model built by single-sensor features. The established high-precision model provided a theoretical basis for real-time feedback control of the penetration depth in the laser welding process.