Microstructure and Mechanical Properties of Joints Depending on the Process Used.

Today, numerous design solutions require joining thin-walled sheets or profiles as the traditional methods of welding with a consumable electrode in gas shielding, most often used in production processes, do not work well. The reason for this is that a large amount of heat is supplied to the joint, causing numerous welding deformations, defects, and incompatibilities. Moreover, the visual aspect of the connections made more and more often plays an equally crucial role. Therefore, it is important to look for solutions and compare different joining processes in order to achieve production criteria. The paper compares the properties of a 1.5 mm thick steel sheet joined by the manual and robotic MAG 135 and 138 welding process, manual and robotic laser welding, CMT welding with the use of solid or flux-cored wire, and butt welding. The macro- and microstructure, as well as the microhardness distribution of individual regions of the joints, were analyzed depending on the type of joining technology used. Furthermore, the mechanical properties of individual zones of joints were investigated with the use of a digital image correlation system. On the basis of the obtained test results, it was found that the joints made by the processes of manual laser welding and butt welding were characterized by a very regular weld shape, the smallest joint width, and greater grain refinement compared to other analyzed processes. Moreover, this method was characterized by the narrowest zone of hardness increase, only 3 mm, compared to, e.g., a joint made in the process of robotic welding CMT, for which this zone was more than twice as wide. Furthermore, the heat-affected zone for the joints made in this way, in relation to the welds produced by the MAG 135/138 method, was, respectively, 2 and 2.7 times smaller.

Specifications for Modelling of the Phenomenon of Compression of Closed-Cell Aluminium Foams with Neural Networks.

The article presents a novel application of the most up-to-date computational approach, i.e., artificial intelligence, to the problem of the compression of closed-cell aluminium. The objective of the research was to investigate whether the phenomenon can be described by neural networks and to determine the details of the network architecture so that the assumed criteria of accuracy, ability to prognose and repeatability would be complied. The methodology consisted of the following stages: experimental compression of foam specimens, choice of machine learning parameters, implementation of an algorithm for building different structures of artificial neural networks (ANNs), a two-step verification of the quality of built models and finally the choice of the most appropriate ones. The studied ANNs were two-layer feedforward networks with varying neuron numbers in the hidden layer. The following measures of evaluation were assumed: mean square error (MSE), sum of absolute errors (SAE) and mean absolute relative error (MARE). Obtained results show that networks trained with the assumed learning parameters which had 4 to 11 neurons in the hidden layer were appropriate for modelling and prognosing the compression of closed-cell aluminium in the assumed domains; however, they fulfilled accuracy and repeatability conditions differently. The network with six neurons in the hidden layer provided the best accuracy of prognosis at MARE≤2.7% but little robustness. On the other hand, the structure with a complexity of 11 neurons gave a similar high-quality of prognosis at MARE≤3.0% but with a much better robustness indication (80%). The results also allowed the determination of the minimum threshold of the accuracy of prognosis: MARE≥1.66%. In conclusion, the research shows that the phenomenon of the compression of aluminium foam is able to be described by neural networks within the frames of made assumptions and allowed for the determination of detailed specifications of structure and learning parameters for building models with good-quality accuracy and robustness.

Effect of FSW Traverse Speed on Mechanical Properties of Copper Plate Joints.

The paper describes the influence of the friction stir welding travel speed on the mechanical properties of the butt joints of copper plates. The results of static and fatigue tests of the base material (Cu-ETP R220) and welded specimens produced at various travel speeds were compared, considering a loading applied both parallel and perpendicularly to the rolling direction of the plates. The mechanical properties of the FSW joints were evaluated with respect to parameters of plates' material in the delivery state and after recrystallisation annealing. The strength parameters of friction stir welding joints were compared with the data on tungsten inert gas welded joints of copper plates available in the literature. The results of microhardness tests and fractographic analysis of tested joints are also presented. Based on the above test results, it was shown that although in the whole range of considered traverse speeds (from 40 to 80 mm/min), comparable properties were obtained for FSW copper joints in terms of their visual and microstructural evaluation, their static and especially fatigue parameters were different, most apparent in the nine-fold greater observed average fatigue life. The fatigue tests turned out to be more sensitive criteria for evaluation of the FSW joints' qualities.