Performance Analysis of Deep Learning Models for Classification of Surface-Mount Device (SMD) Components

Accurate classification of Surface-Mount Device (SMD) components is important for a range of electronics manufacturing and assembly applications. Impressive results have been achieved using recent deep learning models when applied to image-classification problems. This study provides a comprehensive examination of the categorization of Surface-Mounted Device (SMD) components using advanced learning models. Four cutting-edge Deep Learning (DL) models–ResNet50, VGG16, AlexNet, and MobileNet–were utilized to categorize SMD components into eight classes: capacitors, diodes, Electrolytic Capacitors (EC), Integrated Circuits (IC), LED, resistors, supercapacitors, and Zener diodes. Our approach encompasses the training of these models on a dataset containing SMD component images and the assessment of their performance in terms of accuracy, precision, recall, and F1-score. The findings indicate that MobileNet achieved the highest classification accuracy, reaching up to 98%, surpassing the other models. Through a comprehensive comparative analysis, we discern the strengths and limitations of each model in this categorization task. Our results suggest that MobileNet is the most effective deep-learning framework for SMD component classification, underscoring its potential applications in automated electronic assembly and quality control processes. This study contributes to the progress of automated electronic component classification and guides future research in selecting suitable deep learning models for similar tasks.