This study proposes a deep learning-based image anomaly detection system to identify irregular defects in metallic DC fuses. In the manufacturing industry, product quality control is directly linked to productivity, and appearance-related defects, such as surface imperfections, impact competitiveness and reliability. However, conventional visual inspection and simple image-processing methods have limitations in inspection speed and precision, often struggling to accurately detect complex and diverse irregular defects. To address these challenges, this study employs Dinomaly, an unsupervised reconstructionbased Transformer model that can be trained using only normal images. The proposed method takes images of DC fuses as input, automatically detects anomalous regions, and visualizes the location and morphology of irregular defects through an anomaly map, facilitating intuitive interpretation. Additionally, various data preprocessing techniques, including adjustments for diverse illumination conditions and brightness, are applied to augment the dataset, reflecting real-world environmental variations and ensuring robust performance. Experimental results demonstrate that the proposed approach effectively detects irregular defects in DC fuse data. This study is expected to contribute to the automation of DC fuse quality inspection processes, enhance the reliability of automotive electronic components, and advance quality management in smart manufacturing.

With rapid growth of the global electric vehicle market, interest in the development of secondary batteries such as lithium batteries is also increasing. Core functional parts of secondary batteries are known to determine the performance of these batteries. Micro cracks, scratches, and markings that may occur during the manufacturing process must be checked in advance. As part of developing an automated inspection system based on machine vision, this study optimized the design of a linear feeder exposed to an environment with a specific operating frequency continuously to transfer parts at a constant supply speed. Resonance can occur when the natural frequency and the operating frequency of the linear feeder are within a similar range. It can negatively affect stable supply and the process of finding good or defective products during subsequent vision tests. In this study, vibration characteristics of the linear feeder were analyzed using mode analysis, frequency response analysis, and finite element analysis. An optimal design plan was derived based on this. After evaluating effects on vibration characteristics for structures in which vibrations or periodic loads such as mass and rails were continuously applied, the shape of the optimal linear feeder was presented using RSM.

Metal stamping is widely used in the mass-production process of the automobile. During the stamping process, air may be trapped between the draw die and the panel and/or between the punch and the panel. Air pocket rapidly not only increases forming load in the final stage, but also deforms the product just formed by compressive air inside the air pocket in knockout process. To prevent these problems air bent holes are drilled in the die to exhaust the trapped air but all processes associated with air bent holes are performed by empirical know-how of workers in the field due to lack of researches. Therefore this study developed an automated design system for predicting the shape and position, and volume of air pocket on the draw die by using the AutoLISP language under AutoCAD circumstance. The system is able to display the shape of air pocket occurred in the draw die and to calculate automatically its volume by strokes. So it makes a stepping stone to calculate theoretical size of an air bent hole and numbers according to it by predicting and analyzing the position and volume of air pocket. Results obtained from the system enable the designers or manufacturers of the stamping die to be more efficient in this field.

This paper presents the experimental results to analyze the atomization characteristics and environmental impact of cutting fluid in grinding process. Grinding is a major machining process to improve surface quality with different machining mechanism which is compared with turning or milling process. The environmental impact due to aerosol generation via grinding process is a major concern associated with environmental consciousness. Experimental results show that the generated fine aerosol which particle size less than 10 micron appears near working zone under given operational conditions. The aerosol concentration is much higher enough to affect human health risk with its generated aerosol quantities. This study can be provided a basic knowledge for further research of environmental consciousness machining development.