This study explores the application of a machine vision system integrated with convolutional neural network (CNN) for detecting and classifying welding defects. By leveraging the power of deep learning approaches, the proposed approach aims to enhance the efficiency and reliability of defect classification. This method not only reduces human dependency, but also establishes a framework for automated welding quality control systems. A CNN-based machine vision system has been developed to classify welding defects in radiographic images. Particularly, two transfer learning algorithms, mainly, ResNet-18 and ResNet-50, have been applied and evaluated in order to determine the most effective method in detecting and classifying weld defects. The dataset covered three classes of weld defects: cracks, lack of penetration, and porosity. The performance of each ResNet-based CNN model was assessed using performance evaluation metrics and visualization techniques. ResNet-50 emerged as the best performing model and had a strongest response in the weld defects regions, achieving an average accuracy of 96.061%. This model proved effective in detecting and classifying defects, demonstrating its potential to significantly enhance the reliability and automation of detection and recognition.

The machining of polymers has become widely common in several components of industry 4.0 technology, i.e., mechanical and structural components and chemical and medical instruments, due to their unique characteristics such as: being strong and light-weight with high stiffness, chemical resistance, and heat and electricity insolation. Along with their properties, there is a need to attain a higher quality surface finish of machined parts. Therefore, this research concerns an experimental and analytical study dealing with the effect of process parameters on process performance during the turning two different types of polymers: high-density polyethylene (HDPE) and unreinforced polyamide (PA6). Firstly, the machining output responses (surface roughness (Ra), material removal rate (MRR), and chip formation (λc)) are experimentally investigated by varying cutting speed (v_c), feed rate (f), and depth of cut (d) using the full factorial design of experiments (FFD). The second step concerns the statistical analysis of the input parameters’ effect on the output responses based on the analysis of variance and 3D response surface plots. The last step is the application of the RSM desirability function, genetic algorithm (GA), and hybrid FFD-GA techniques to determine the optimum cutting conditions of each output response. The lowest surface roughness for HDPE was obtained at v_c = 50 m/min, f = 0.01 mm/rev, and d = 1.47 mm and for PA6 it was obtained at v_c = 50 m/min, f = 0.01 mm/rev, and d = 1 mm. The highest material removal rate was obtained at v_c = 150 m/min, f = 0.01 mm/rev, and d = 1.5 mm for both materials. At f = 0.01 mm/rev, d = 1.5 mm, and v_c = 100 for HDPE, and v_c = 77 m/min for PA6, the largest chip thickness ratios were obtained. Finally, the multi-objective genetic algorithm (MOGA) methodology was used and compared.

This work investigates the efficacy of high-pressure torsion (HPT), as a severe plastic deformation mechanism for processing plain and silicon-carbide-reinforced AA6061, with the broader objective of using the technique for improving the properties of lightweight materials for a range of objectives. The interactions between input variables, such as the pressure and equivalent strain (ε_eq) applied during HPT processing, and the presence of SiCp and response variables, like the relative density, grain refinement, homogeneity of the structure, and the mechanical properties of the AA6061 aluminum matrix, were investigated. Hot compaction (HC) of the mixed powders followed by HPT were employed to produce AA6061 discs with and without 15% SiCp. The experimental findings were then analyzed statistically using the response surface methodology (RSM) and a machine learning (ML) approach to predict the output variables and to optimize the input parameters. The optimum combination of HPT process parameters was confirmed by the genetic algorithm (GA) and ML approaches. Furthermore, the constructed ML and RSM models were validated experimentally by HPT processing the same material under new conditions not fed into the models and comparing the experimental results to those predicted by the model. From the ML and RSM models, it was found that processing the AA6061/SiCp composite HPT via four revolutions at 3 GPa produced the highest mechanical properties coupled with significant grain refinement compared to the HC condition. ML analysis revealed that the equivalent strain induced by the number of revolutions was the most effective parameter for grain refinement, whereas the presence of SiCp played the highest role in improving both the hardness values and the compressive strength of the AA6061 matrices.

This work investigates the efficacy of Friction Stir Surface Treatment (FSST), as an innovative surface modification technique, in enhancing the surface mechanical properties of AA1050 aluminum alloy. A comprehensive experimental study was employed to systematically evaluate the influence of key FSST processing parameters: rotational spindle speed (N), feed rate (f), tool design (pinless vs. single pin), and number of passes. Taguchi L16 orthogonal array was utilized for the determination of the most important parameters affecting FSST process. The improvement in the surface characteristics was evaluated specifically focusing on surface microhardness and mechanical wear resistance compared with the base material. Results revealed that rotational spindle speed and tool design emerged as the most dominant factors influencing both properties. Notably, FSST conditions leading to higher microhardness consistently resulted in reduced material weight loss. Optimization of the FSST parameters identified that a pinless tool with a single pass, processed at a rotational speed of 280 rpm and a feed rate of 100 mm/min. Under these conditions, microhardness was maximized to ≈ 128 HRV, while weight loss was minimized to ≈ 0.0011 g, demonstrating significant enhancement compared to the base material. This research provides valuable insights for tailoring FSST parameters to achieve superior surface characteristics in AA1050 for various industrial applications.