Este artículo es resultado de un trabajo de investigación sobre las aplicaciones de algoritmos bioinspirados e inteligentes en el ámbito de ingeniería en producción, en la Universidad Distrital Francisco José de Caldas, abarcando las temáticas de investigación de operaciones, distribución en planta industrial de manufactura entre otros. Se pretende buscar la optimización a problemas propios de esos campos, aplicando inteligencia artificial de enjambres, a partir de la implementación de un algoritmo de Optimización de Colonias de Hormigas (Ant Colony Optimization - ACO) como herramienta metaheurística de planificación y optimización del problema de distribución en planta, con el objetivo de buscar la mejor asignación espacial de estaciones o celdas de trabajo. Se presentan los conceptos teóricos explorados y los resultados obtenidos. En primer lugar se efectuó la revisión de estado del arte sobre la temática, luego se evaluaron los posibles algoritmos de solución, para identificar la función objetivo a optimizar, para finalmente aplicar el algoritmo ACO, y evaluar los resultados de desempeño del mismo frente a la configuración inicial que tenía la planta.
This paper is the result of the research work on the application of an artificial neural network algorithm applied in decision making in the process of AIO (Automatic Optical Inspection) for quality control from an electronic prototyping company, generating models for the assurance of Quality in the PCB (Printed Circuit Board) product, covering the fields of decision making, quality management, production processes, neural computer systems and artificial vision among others. It is intended to develop an algorithm of artificial neural networks that provides an approach to human recognition and perception when performing a quality inspection of the final product, based on image analysis and recognition. It is presented the theoretical concepts explored and the results obtained. Initially a problem definition was made to model, then the data processing was performed, the artificial neural network model was selected to be applied, then the relevant adjustments made to the model to finally obtain a simulation and validation of the same
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.