Development of an Automated Machine for Green Coffee Beans Classification by Size and Defects
Development of an Automated Machine for Green Coffee Beans Classification by Size and Defects
复制标题
开发根据尺寸和缺陷对生咖啡豆进行分类的自动化机器
DOI：
10.18178/joaat.8.1.17-24
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Dante Arroyo
中科院分区：
文献类型：
--
作者：
Grover Susanibar;J. Ramírez;Jennifer Sánchez;R. Ramirez;Dante Arroyo
- 本文介绍了一个原型的设计和实现自动化机器的绿色咖啡豆分类的小型农业工业。这项工作响应的需要，同时自动化的大小排序和分级的物理缺陷的绿色咖啡豆的目的是优化时间和提高最终产品的质量。首先，机器通过机械分选系统将谷物分为三个尺寸范围。其次，它具有真实的时间工作的计算机视觉算法，以区分好的和有缺陷的谷物。然后，它有一个嵌入式系统，用于控制沿着与一组传感器和执行器和控制面板，使选择的质量绿色咖啡豆。结果表明，按尺寸分类的准确率为96%，按物理缺陷分级的准确率为80%。出口处的咖啡豆流量约为每小时5公斤。最后，一组结论和未来的工作。
— This paper presents the design and implementation of a prototype automated machine for green coffee beans classification for small agro-industries. This work responds to the need to simultaneously automate the processes of sorting by size and grading by physical defects of green coffee beans with the aim of optimizing the time and increasing the quality of the final product. Firstly, the machine classifies grains into three size ranges through a mechanical sorting system. Secondly, it has computer vision algorithms working in real time to differentiate good and defective grains. Then it has an embedded system for control along with a set of sensors and actuators and a control panel that make possible a selection of quality of green coffee beans. The results show an accuracy of 96% for sorting by size and an accuracy of 80% for grading by physical defects. The flow of coffee beans at the outlet is approximately 5 kilograms per hour. Finally, a set of conclusions and future works are presented.