Papers by Keyword: Quality Control

Abstract: This paper explores advanced methods and techniques for defect detection, focusing on their effectiveness, challenges, and implications for industrial applications. We explore the combination of CNNs with deflectometry and dark-field polarization imaging for surface defect detection in refrigerator manufacturing and optical components inspection, respectively. We highlight the importance of automated inspection systems in detecting surface defects and discuss the challenges associated with real-time defect detection and limited datasets. This study contributes to advancing defect detection methodologies and provides valuable insights for industrial quality control processes.

Abstract: This paper presents an overview of advanced deep learning techniques and machine vision technologies aimed at automating defect recognition tasks with unparalleled accuracy and efficiency. Various methodologies, including deep random chains combined with adaptive Faster R-CNN, Gradient-weighted Flaw Detecting using Convolutional Neural Networks (CNNs), and established architectures like Faster R-CNN and YOLOv5, are discussed. These methods leverage CNNs’ robustness in image classification tasks and feature extraction capabilities to improve defect detection accuracy on machined components. Furthermore, the integration of machine vision with optical inspection platforms enables rapid defect recognition, classification, and localization, significantly enhancing the overall quality control process in manufacturing environments. Visualizations of defect recognition scores and improvements in accuracy demonstrate the effectiveness of these methodologies, highlighting their potential to drive efficiency and competitiveness in the manufacturing industry. Overall, the continuous evolution and integration of these technologies offer immense potential for transforming quality control practices and driving excellence in defect detection in machined parts.

Abstract: Numerous quality issues can be found in the apparel sector in a number of disciplines, including fabric spreading, cutting, sewing, printing, embroidery, ironing, and packing. In the garment business, the boundaries of acceptable product quality have retreated, penalizing every flaw with one point. In the garment business, total quality management, or TQM, is essential for increasing output, enhancing product quality, and cutting production costs by minimizing scraping and rework. Data on quality flaws has been gathered from Supply Chain Management (SCM) clothing using AQL standard of 7.0point Traffic light system (Green, Yellow, Red). To perform this study to use the TQM tools such as bar chart and pie chart, easy to compare the before implementation and after implementation product quality were analyzed. Additionally, data is collected in order to find flaws and fix them. Rework operations are initially found and fixed in order to lower the defect ratio. We will put our thoughts into practice and contribute to this project in order to control quality.

Abstract: Bakpia is made from green beans and sugar wrapped in flour. Bakpia Latief Kediri is a bakpia industry in the City of Kediri. The company needs help in the production process activities. There are still products that need to be fixed. The types of it defects in the company are burnt and cracked. This study aimed to determine the performance of its quality control, determine the most dominant types of defects in its products, and provide suggestions for improving its production process. The research method uses the Statistical Quality Control method. Data is taken in the form of primary data and secondary data. Primary data was collected by interview and observation. Interviews were conducted using in-depth interviews. Observations were made for 30 days. Data analysis uses statistical tools, which include check sheets, histograms, fishbone diagrams, Pareto diagrams, and control charts p. Bakpia quality control at Bakpia Latief is under control because the p chart control chart shows that only one point is out of the control limits. The most dominant defect in its products is burnt, with an average percentage of 0.617%. Corrective actions to reduce the existence of defective products, namely repairing and maintaining production machines, improving the stages of the production process, developing human resources, and repairing production facilities. Keywords: Product Defects, Quality Control, Statistical Quality Control

Abstract: Fiber-reinforced plastics (FRP) are a type of composite material consisting of a reinforcing structure and a plastic matrix. When compared to traditional construction materials, FRP has higher strength and stiffness due to the high mechanical properties of reinforcing fibers such as carbon or glass. However, the properties of FRP are dependent on the alignment of fibers within the composite, with deviations leading to reduced strength and stiffness. Eddy current testing is a non-destructive technique used to visualize carbon fibers in the composite and assess the impact of local fiber orientation on the structural properties of FRP. This study aims to understand the influence of local fiber orientation on tensile strength and elastic modulus by producing composites with defined fiber orientations, analyzing them with eddy current testing, and assessing their mechanical properties through tensile tests. The measured fiber orientations are then used to validate a finite element model, in which the actual, measured fiber orientation is applied to the simulation and correlated with the mechanical properties. In contrast to previous published studies measured fiber orientation is used, which as shown in this work, differs from the theoretically implemented fiber orientation.

Abstract: Additive manufacturing (AM) is a new technology for fabricating products straight from a 3D digital model, which can lower costs, minimize waste, and increase building speed while maintaining acceptable quality. However, it still suffers from low dimensional accuracy and a lack of geometrical quality standards. Moreover, there is a need for a robust AM configuration to perform in-situ inspections during the fabrication. This work established a 3D printing-scanning setup to collect 3D point cloud data of printed parts and then compare them with nominal 3D point cloud data to quantify the deviation in all X, Y, and Z directions. Specifically, this work aims at predicting the anticipated deviation along the Z direction by applying a deep learning-based prediction model. An experiment with regard to a human “Knee” prototype fabricated by Fused Deposition Modeling (FDM) is conducted to show the effectiveness of the proposed methods.

Abstract: Microstructure of ingot and industrial blanks made of copper M2 was examined for quality control. Microstructure was examined by means of traditional metallographic analysis methods. Exogenous nonmetal inclusions and pores in microstructure were found. The transition from exogenous inclusions and pores, which were not removed in initial processing stage, to the crack, which leads to billet destruction on one of last processing stages, is shown. Without quality control of copper blanks by a metallographic method, it is impossible to provide guarantee of reliable operation of machines and responsible purpose constructions. A comparative study of the temperature dependences of the viscosity of the melts of charge materials and finished ingots for copper M2 was carried out. The study of the viscosity of copper melts M2 was carried out with the aim of quality control in the chain of "charge-melt-ingot" at the foundry stage.

Abstract: Model-based quality control has the potential to reduce the reject rate in the production of fiber-reinforced plastics (FRP) components. After all the cross-market establishment of FRP, undesirable quality deviations often occur with new materials or component shapes. The quality control uses the component quality (e.g. component angle, crystallinity, fiber orientation, pore content) as the control variable. As a key component of the control, a process model is developed to link the process parameters (press pressure, press duration and tool temperature) with the quality parameters. Knowledge of the process-determining cause-effect relationships is necessary to ensure that different quality parameters are in the target value at the same time. Based on experimental tests, these interrelationships are determined using methods of statistical test planning and serve as the basis for model-based quality control. As a result, it has been shown that the targeted control of the component angle is possible in a range of about ±1° by using the control parameters, tool temperature and pressure, which have a significant influence on the quality. In the next step, further quality characteristics are included in the control system in order to demonstrate the ability to control the quality of complex component specifications. Model-based quality control is particularly promising for the reduction of the process run-in phase and thus for the reduction of the reject rate.

Abstract: Laser surface hardening, is a process in which a shaped laser beam is scanned across the surface to produce a hard and wear-resistant surface on components. Compared with the conventional surface hardening process, the laser heat treatment offers a number of attractive characteristics such as minimal part distortion, self-quenching and the need for less finishing work. The challenge of laser hardening is the uneven surfaces found in molds such as those with sharp edges or holes. In these cases, due to the differences in the surrounding volume of the material, overheating problems often appear leading to unacceptable treatment results. The purpose of this paper is to present the new technology, “raio” developed by Talens System for laser hardening process. This technology is able to adapt to geometrical singularities of the components to be treated, ensuring the dimensions of the hardened area and hardness values are compliant with the requirements. The main features of the technology for laser hardening are validated on a set of samples of 1.2738 steel with representative discontinuities of molds. Mechanical and microstructural characterizations of the hardened cross sections confirm the advantages of the raio technology in regard to the quality compliance of the laser hardening process. Furthermore, raio offers the same advantages for other laser processes, like softening of critical area or laser cladding for repairing of damaged components.

Abstract: One of the main aspects of small and medium-sized enterprises is the quality of the products, in a production system several parameters and non-temporal variables must respect very strict variation intervals such as weight measurements, in the chemical industry. This parameter also takes a fundamental part in the quality of the product. The correct production process is based on a given percentage of each material. We chose a food production system where the quality requirements are very high. In this article, we propose a production system modeling by interval constraint Petri net. And we controlled these intervals with a fuzzy type-2 controller for decision making.