Deep Learning Based Inversion of Locally Anisotropic Weld Properties from Ultrasonic Array Data

The ability to reliably detect and characterise defects embedded in austenitic steel welds depends on prior knowledge of microstructural descriptors, such as the orientations of the weld’s locally anisotropic grain structure. These orientations are usually unknown but it has been shown recently that they can be estimated from ultrasonic scattered wave data. However, conventional algorithms used for solving this inverse problem incur a significant computational cost. In this paper, we propose a framework which uses deep neural networks (DNNs) to reconstruct crystallographic orientations in a welded material from ultrasonic travel time data, in real-time. Acquiring the large amount of training data required for DNNs experimentally is practically infeasible for this problem, therefore a model based training approach is investigated instead, where a simple and efficient analytical method for modelling ultrasonic wave travel times through given weld geometries is implemented. The proposed method is validated by testing the trained networks on data arising from sophisticated finite element simulations of wave propagation through weld microstructures. The trained deep neural network predicts grain orientations to within 3° and in near real-time (0.04 s), presenting a significant step towards realising real-time, accurate characterisation of weld microstructures from ultrasonic non-destructive measurements. The subsequent improvement in defect imaging is then demonstrated via use of the DNN predicted crystallographic orientations to correct the delay laws on which the total focusing method imaging algorithm is based. An improvement of up to 5.3 dB in the signal-to-noise ratio is achieved.

Microstructural, Thermal and Corrosion Characterization of Friction Stir Welded Magnesium Alloys

The requirement for structural materials with demanding properties is always a major concern among automotive researchers. Magnesium alloys possess the required properties. In this work magnesium alloys, AZ31B and AZ91B were joined by friction stir welding. The influence of process parameters on the weld properties has been studied. The process parameters were tool rotational speed, welding speed, tilt angle. Three different combinations AZ31B-AZ91B, AZ31B-AZ31B and AZ91B-AZ91B were friction stir welded. Non-destructive tests have been performed on the welded joints as the primary analysis. After mechanical testing, optical microscopic examination comprising of macrostructure analysis, microstructure analysis and SEM analysis were carried out on selected specimens and the results are formulated. The corrosion behavior of Mg alloys has been tested using a salt spray test. The thermal behavior was studied using thermogravimetric and differential thermal analysis. The joints were friction stir welded with maximum efficiency where grain refinement was observed in the weld microstructure of dissimilar alloys and the elongated grains was recrystallized. This paper primarily focuses on the microstructural aspects, corrosion performances and TG/DTA analysis.

Evaluating Temperature Control in Friction Stir Welding for Industrial Applications

Reports in the literature indicate that temperature control in Friction Stir Welding (FSW) enables better weld properties and easier weld process development. However, although methods of temperature control have existed for almost two decades, industry adoption remains limited. This work examines single-loop Proportional-Integral-Derivative (PID) control on spindle speed as a comparatively simple and cost-effective method of adding temperature control to existing FSW machines. Implementation of PID-based temperature control compared to uncontrolled FSW in AA6111 at linear weld speeds of 1–2 m per minute showed improved mechanical properties and greater consistency in properties along the length of the weld under temperature control. Additionally, results indicate that a minimum spindle rpm may exist, above which tensile specimens do not fracture within the weld centerline, regardless of temperature. This work demonstrates that a straightforward, PID-based implementation of temperature control at high weld rates can produce high quality welds.

Microstructural Characterization of Laser Weld of Hot-Stamped Al-Si Coated 22MnB5 and Modification of Weld Properties by Hybrid Welding

The presence of Al-Si coating on 22MnB5 leads to the formation of large ferritic bands in the dominantly martensitic microstructure of butt laser welds. Rapid cooling of laser weld metal is responsible for insufficient diffusion of coating elements into the steel and incomplete homogenization of weld fusion zone. The Al-rich regions promote the formation of ferritic solid solution. Soft ferritic bands cause weld joint weakening. Laser welds reached only 64% of base metal's ultimate tensile strength, and they always fractured in the fusion zone during the tensile tests. We implemented hybrid laser-TIG welding technology to reduce weld cooling rate by the addition of heat of the arc. The effect of arc current on weld microstructure and mechanical properties was investigated. Thanks to the slower cooling, the large ferritic bands were eliminated. The hybrid welds reached greater ultimate tensile strength compared to laser welds. The location of the fracture moved from the fusion zone to a tempered heat-affected zone characterized by a drop in microhardness. The minimum of microhardness was independent of heat input in this region.

Comparative Analysis of Polyurethane Drive Belts with Different Cross-Section Using Thermomechanical Tests for Modeling the Hot Plate Welding Process

The paper presents a comparative analysis of the circular and flat cross-section belts using measurements of a set of thermomechanical parameters, contributing to research about hot plate welding of drive belts. On the basis of thermogravimetric and spectrophotometric tests, information about the same chemical composition of the two belts was obtained. Dynamic thermomechanical analysis and scanning differential calorimetry provided information about a small difference between belts, which disappeared when the material was placed in a state of increased temperature and mechanical stress. On the basis of the analysis of the specific heat, thermal diffusion, density, and hardness, the values of the selected thermal properties of the belt were obtained, and a large similarity between the belts was identified. On the basis of the novel performed test cycle, it has been hypothesized that circular and flat belts made from thermoplastic polyurethane elastomer could be used interchangeably for butt-welding testing. It has also been proven that cyclic thermomechanical loads unify the properties of both materials so that multiple mechanical and thermal loads do not result in any change in the material properties of the two belts. As a consequence, changes in the weld properties after welding, compared to a solid belt, are not expected.