This work aims at a novel approach to estimate the root-pass penetration towards its feedback control, in which the real penetration is measured by the backside bead width. The major challenge is that it happens under the workpiece and likely cannot be directly observable. The dynamic evolution of the weld pool surface has been analysed to design an active vision method monitoring the pool surface, yet fundamentally correlated to the unobservable penetration. The designed convolutional neural network model is trained, validated, and tested for recognising the weld penetration with satisfactory accuracy.

Direct aluminium–stainless steel joints are difficult to create by the vaporized foil actuator welding (VFAW) method because brittle intermetallic compounds (IMCs) tend to form along the interface. The use of an interlayer as a transition layer between the two materials with vast difference in hardness and ductility was proposed as a solution to reduce the formation of the IMCs. In this work, VFAW was used to successfully weld sheet aluminium alloy 5A06 to stainless steel 321 with a 3003 aluminium alloy interlayer. Input energy levels of 6 kJ, 8 kJ, 10 kJ, and 12 kJ were used and as a trend, higher energy inputs resulted in higher impact velocities, larger weld area, and better mechanical properties. In lap-shear and peel testing, all samples failed at the interface of the interlayer and target. At 10 kJ energy input, flyer velocities up to 935 m/s, lap-shear peak load of 44 kN, and peel load of 2.15 kN were achieved. Microstructure characterization and element distribution were performed, and the results show a wavy pattern created between the flyer and interlayer which have similar properties, and the interface between the interlayer and target was dominated by element diffusion and IMCs identified mainly as FeAl₃ and FeAl. The results demonstrate VFAW is a suitable joining method for dissimilar metals such as aluminium alloy and stainless steel, which has a broad and significant application prospect in aerospace and chemical industry.

Expulsion identification is of significance for welding quality assessment and control in resistance spot welding. In order to improve the identification accuracy, a novel wavelet decomposition and Back Propagation (BP) neural networks with the peak-to-peak amplitude and the kurtosis index were proposed to identify the expulsion from electrode force sensing signals. The rapid step impulse and resultant damping vibration of electrode force was determined as a robust indication of expulsion, and this feature was extracted from the electrode force waveform by seven-layer wavelet decomposition with Daubechies5 wavelets. Then, the energy distribution proportion of the decomposed detail signals were calculated, and the highest-energy one was selected as the target signal. Two statistical indexes were introduced in this paper to measure the target signal in overall situation and volatility. The bigger the peak-to-peak amplitude is, the more violent the fluctuation is. Moreover, the higher the kurtosis index is, the stronger the impact is, and the lower the dispersion degree of the data is. Experimental analysis showed that neither the peak-to-peak amplitude nor the kurtosis index could accurately judge the expulsion defect individually, because of the early signal fluctuation, likely affected by the work-piece clamping, work-piece clearance, or the oxide film thickness. Therefore, the BP neural networks were introduced to identify the expulsion defects, which is a mature and stable non-linear pattern recognition method. Testing experiments presented good results with the trained networks and improved the evaluable accuracy effectively in the quality assessment of the resistance spot welding.

While penetration occurs underneath the workpiece, the raw information used to detect it during welding must be measurable to a sensor attached to the torch. Challenges are apparent because it is difficult to find such measurable raw information that fundamentally correlates with the phenomena occurring underneath. Additional challenges arise because the welding process is extremely complex such that analytically correlating any raw information to the underneath phenomena is practically impossible; therefore, handcrafted methods to propose features from raw information are human dependent and labor extensive. In this paper, the profile of the weld pool surface was proposed as the raw information. An innovative method was proposed to acquire it by projecting a single laser stripe on the weld pool surface transversely and intercepting its reflection from the mirror-like weld pool surface. To minimize human intervention, which can affect success, a deep-learning-based method was proposed to automatically recognize features from the single-stripe active vision images by fitting a convolutional neural network (CNN). To train the CNN, spot gas tungsten arc welding experiments were designed and conducted to collect the active vision images in pairs with their actual penetration states measured by a camera that views the backside surface of the workpiece. The CNN architecture was optimized by trying different hyperparameters, including kernel number, kernel size, and node number. The accuracy of the optimized model is about 98% and the cycle time in the personal computer is ~ 0.1 s, which fully meets the required engineering application.