As a direct reflection of the interaction between the stirring tool and the base metal in the friction stir welding process, the force signal is an important means to characterize welding quality. In this paper, the variation mechanism of three-dimensional force and its relation with welding quality were explored. The acquired signals were subject to interference from high-frequency noise, so mean filtering and variational mode decomposition were applied to obtain the real signals. The denoised signals were analyzed and the results showed that the traverse force was ahead of the lateral force by a ratio of π /4, while the phase difference between the axial force and the other two forces changed with the process parameters. Through application of the least square method and polynomial fitting, the empirical formulas of three-dimensional force were obtained, and these were applicable regardless of tunnel defects. The minimum value of the lateral force increased several times more than that of traverse force when the welding speed increased from 80 mm/min to 240 mm/min. When the pole radiuses of most data points had a value greater than 4, tunnel defects were highly likely to generate. In order to predict welding quality more accurately, a prediction model based on long short-term memory was constructed. The model recognized the various modes of good welds and tunnel defects with 100% accuracy. The identification ability for large and small defects was relatively poor, and the average accuracy of classifying the three categories of welding quality was 84.67%.

The softening of aluminum–lithium alloy welded joints generally leads to a reduction in mechanical properties. In this study, a piece of 2A97-T3 aluminum–lithium alloy with a thickness of 2.8 mm was selected as the test material, and the tool and process used for wire-filled stationary shoulder friction stir welding (SSFSW) were developed. By increasing the bearing area of the softening zone, an equal-strength T-joint was manufactured. Good weld formation was obtained when the rotation speed was set to 2000 rpm and the welding speed ranged from 100 to 120 mm/min. The thickness of the softening zone was controlled by adjusting the reserved gap between the shoulder and the workpiece. The softening mechanism of the weld joint was revealed. The softening was attributed to the coarsening of the main precipitated phases (T1 and θ′ phases) in the heat-affected zone (HAZ) and the dissolution of precipitated phases in the thermo-mechanically affected zone (TMAZ). Grain refinement in the nugget zone (NZ) led to a certain fine-grained strengthening effect, although the precipitated phase was almost completely dissolved. Due to the thermal effect of second-pass welding, the hardness value of the NZ and HAZ in the center of the skin further decreased, and the minimum hardness was approximately 70% that of the base material. Tensile testing results indicated that the softening effect was largely offset by the increased bearing area of the softening zone, resulting in the successful welding of high-strength Al-Li alloy T-joints with equal strength. The strength coefficient was found to be 0.977.