GRAS (Grain Analytic System) development: digital and automated equipment for grain grading in soybeans without the need of grain cut

• Grant number: 23/09721-4
• Support Opportunities: Scholarships in Brazil - Support Program for Fixating Young Doctors
• Start date until: September 01, 2023
• End date until: August 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Physics
• Agreement: CNPq
• Principal Investigator: Débora Marcondes Bastos Pereira
• Grantee: Anielle Coelho Ranulfi
• Host Institution: Embrapa Instrumentação Agropecuária. Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA). Ministério da Agricultura, Pecuária e Abastecimento (Brasil). São Carlos , SP, Brazil
• Associated research grant: 23/01505-0 - GRAS (Grain Analytic System) development: digital and automated equipment for grain grading in soybeans without the need of grain cut, AP.R

Abstract

Brasil Agritest, in partnership with Embrapa Instrumentação, aims to add value to the Brazilian and global agribusiness through the challenge of innovation in grain quality control, whose important step involves the grain defects grading. This is a procedure that must be carried out at each point in the logistics chain where cargoes loading responsibility changes, and which is of great importance when selling the product as the load value is determined by the grain grading.Despite the relevance of soybeans, everywhere in the world, the method used for grain grading is still based today on a visual inspection carried out by the few existing classification professionals through a manual process which considers grain colors and shapes, and that still needs cutting the grain for internal verification. All this makes the process being a subjective and standardless method, resulting in errors, divergences, conflicts, and great damage to the sector. In addition, speediness wise, it is an execution costly process, resulting in analysis criteria loss to the detriment of the necessary speed. To solve this problem, Brasil Agritest proposes to offer simple-to-operate equipment that can carry out the analysis per soybean grain without the need to cut it, by using computer vision, artificial intelligence tools, and the application of photonic techniques that allow the analysis of physicochemical grain information for their classification. Until today, visual inspection is the only effective method for classifying soybeans, and there is no similar equipment on the market. Implementing this new technology should transform the sector's reality, bringing speed and dynamism to the logistics chain, low cost, and great rigor in the delivery, standardization, transparency, and process impartiality.