Automated System for Hass Avocado Grading System

Cruz-Mendez J.M.; Katherine Melo-Susanibar L.; Renojo-De La Cruz C.V.; Antonio Vilchez-Baca H. · Proceedings - 2023 International Conference on Intelligent Computing and Control, IC and C 2023 (2023) · DOI: 10.1109/ic-c57619.2023.00011

Resumen

According to the National Institute of Statistics and Informatics in the period of 2021, avocado production was 62 thousand 744 tons, in which Peru has a share of 8.6% of world avocado production. This work develops an automated system for Hass avocado grading. For the simulation of the classification of ripe, unripe and overripe avocados, the bottleneck was determined by direct observation and then the neural network was programmed using roboflow software and the recognition of Hass avocados was trained in YOLO V5, to then obtain the simulation in Factory IO and TIA PORTAL with connection to PLC S7-1200 1214 DC/DC/DC and a HMI TP700. Finally the proposal of classification was implemented in which a 100% recognition of the avocados was obtained by means of the interactive screen of HMI, being able to classify it in an automatic way and to count them, which has a graphical environment so that the operator to manipulate, eliminating the bottleneck and increasing productivity in the sorting process.

Instituciones: Universidad Continental