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.

A Transformer model to predict the remaining useful life of a fuel cell, which has demonstrated superior performance in analyzing time series data. The dataset was created from long-term performance evaluation experiments conducted in rated power mode, with measurements taken every 10 hours. We preprocessed the raw data using a moving average, allocating 70% for training and 30% for evaluation. The model's performance, evaluated through MAE, MSE, and MAPE, was excellent. The fuel cell's critical voltage, defined as 94.5% of its initial voltage, was measured at 0.719 V. During the experimental run, the actual critical time was 106.6 hours, while the model predicted 106.8 hours, resulting in a 0.19% error. Since the predictions were based on data collected up to 93 hours, the estimated remaining life was 13.8 hours.