Bibliographic citations
Juárez, M., De, A. (2024). Diseño de un sistema automático de detección de defectos en cajas de plástico de botellas. [Trabajo de suficiencia profesional, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/683408
Juárez, M., De, A. Diseño de un sistema automático de detección de defectos en cajas de plástico de botellas. [Trabajo de suficiencia profesional]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2024. http://hdl.handle.net/10757/683408
@misc{renati/1039587,
title = "Diseño de un sistema automático de detección de defectos en cajas de plástico de botellas.",
author = "De La Cruz Pihue, Anderson",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2024"
}
This research project proposes the development and implementation of an automatic inspection system for plastic crates using computer vision, aimed at optimizing production processes in the brewing industry. The main objective of this system is to detect physical defects such as cracks and debris inside the crates, which can lead to bottle breakage during packaging and delays in the production line. The system uses a Raspberry Pi and a convolutional neural network (CNN) trained to detect irregularities in the crates. The system classifies the crates based on their condition, allowing for the rapid identification of those that do not meet the required quality standards, preventing them from progressing further in the production process. The control of the crate transportation system is achieved through a variable frequency drive, a photoelectric sensor, and a relay, efficiently integrating crate flow control with real-time image processing. The CNN was trained with a representative dataset, achieving an accuracy of 82% in defect detection. This demonstrates the system’s effectiveness in significantly reducing unplanned downtime and losses during production. Furthermore, the system can identify defects that may not be visible to human operators, ensuring a higher standard of quality control. The results will be evaluated using operational efficiency metrics, such as downtime, error rates, and detection accuracy. This comprehensive approach combines cutting-edge computer vision and automation technologies, aiming to improve both the productivity and quality of the brewing industry’s production line. By minimizing defects and optimizing workflows, this system has the potential to make a meaningful impact on industrial processes, reducing costs and improving production reliability.
This item is licensed under a Creative Commons License