Quoc-Nguyen Banh

This study presents a machine learning-driven framework for the constrained multi-criteria optimization of family-mold processes, where the simultaneous production of geometrically dissimilar parts creates complex flow imbalances. Dimensional deformation (warpage) and shear stress are identified as critical quality characteristics affecting the functional performance and structural integrity of molded products, while product weight is treated as a practical manufacturing constraint to ensure material efficiency. Preliminary experimental trials are conducted to verify process feasibility and to determine realistic operating ranges for key injection molding parameters. Based on these ranges, a face-centered central composite design (FCCCD) is constructed, and high-fidelity computational fluid dynamics (CFD) data are generated using Moldex3D analysis. A Kriging-based surrogate model is then developed to represent the complex and nonlinear relationships between process parameters and quality responses. The surrogate model is integrated with the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to perform constrained multi-criteria optimization, where warpage and shear stress are simultaneously minimized under a prescribed weight constraint. The optimization process yields Pareto-optimal process parameter combinations that effectively balance dimensional accuracy and stress reduction while satisfying material usage requirements. Selected Pareto-optimal solutions are validated through detailed CFD simulations, yielding average relative errors of 1.56 % and 3.58 % for warpage and shear stress, respectively, demonstrating the predictive accuracy and robustness of the proposed framework. Overall, this study establishes an effective data-driven optimization strategy for quality-oriented design and decision support in intelligent family-mold processes.

The global trend of replacing plastic straws with environmentally friendly alternatives has significantly increased the demand for biodegradable straws such as those made from Lepironia grass. However, the current production process still heavily relies on manual labor, particularly in the stage of cleaning the inner velvet layer of the grass stem—an essential step for ensuring product quality. This study focuses on the mechanical design and development of a core removal and inner-cleaning system capable of processing 100 straws per minute. The proposed system consists of three main units: the cleaning unit, positioning unit, and clamping unit, supported by auxiliary mechanisms including a feeding system and product discharge module. A spatial cam mechanism is employed to generate both translational and rotational motion for the cleaning probe, enabling efficient removal of the inner velvet layer while allowing flexible adaptation to different straw diameters. In addition, the system utilizes an elastic belt-based positioning mechanism and a synchronized rotary structure to ensure smooth operation, minimize error, and prevent straw breakage. This modular mechanical design not only enhances productivity and precision but also contributes significantly to the mechanization of the Lepironia straw production process. It promotes sustainable development by reducing labor dependency, improving product consistency, and supporting the local raw material industry. The study represents a crucial step toward automation and localization of straw production equipment, addressing the need for cost-effective and environmentally responsible manufacturing while leveraging the native Lepironia grass resource found abundantly in the Mekong Delta region of Vietnam.

The combination of V-bending and V-grooving has proven to be highly effective in forming aesthetically refined sheet metal products, especially in high-end interior applications. This technique enables the creation of sharp, clean bend angles and enhances the geometric accuracy of final products, delivering a modern and seamless appearance. However, one of the key challenges in the V-bending process is the spring back phenomenon, which significantly affects the accuracy of the final bending angle. This paper presents an experimental study on the influence of three primary technological parameters—groove depth, bending height, and end hold time—on the spring back behavior in the V-bending process with pre-cut V-grooves. A Taguchi L9 orthogonal array is employed to efficiently design the experiments, minimizing the number of trials while ensuring statistical reliability. The Signal-to-Noise (S/N) ratio is used as the evaluation criterion, with the quality objective of “smaller is better” applied to minimize spring back. The results indicate that bending height has the most significant effect on reducing spring back, followed by groove depth, whereas end hold time shows negligible influence and may be treated as a noise factor in further optimization. The optimal set of process parameters identified from the study includes a bending height of 0.6 mm, groove depth of 0.3 mm, and end hold time of 3 seconds. These findings provide valuable insights for improving the forming accuracy of V-bent sheet metal parts, especially in applications requiring precise and visually appealing features.The study contributes to the scientific basis for optimizing metal bending processes and supports the development of more efficient manufacturing techniques for high-quality decorative metal components.

The V-bending process, widely used across various everyday products, has experienced a growing demand for tighter quality control measures. Traditional methods often rely on visual inspection or manual angle gauges, which can be time-consuming and prone to human error. This journal explores the application of image processing techniques for automated angle measurement of V-bending workpieces. The proposed method places a camera to capture an image of the workpiece. Subsequently, the Canny edge detection algorithm is employed to identify the edges within the image. These edges are then utilized by the Hough transform, a technique capable of extracting lines from the detected edges. Through analysis of the extracted lines, the angle of the V-bending is calculated. This approach offers a promising alternative to traditional quality control methods, potentially leading to increased accuracy and efficiency. While the result shows high reliability with a minimal error, further development can focus on refining the system's factors like camera placement and specimen variations. Ultimately, this method paves the way for a more automated and reliable approach to V-bending quality control besides existing high-precision techniques like Coordinate Measuring Machines (CMM).