Intelligent Analysis of Flow Field in Cleaning Chamber for Combine Harvester Based on YOLOv8 and Reasoning Mechanism

As the main working part of a combine harvester, the cleaning device affects the cleaning performance of the machine. The simulation of flow fields in a cleaning chamber has become an important part of the design. Currently, post-processing analyses of flow field simulation still rely on the researchers’ experience, so it is difficult to obtain information from post-processing automatically. The experience of researchers is difficult to describe and disseminate. This paper studied an intelligent method to analyze simulation result data which is based on the object detection algorithm and the reasoning mechanism. YOLOv8, one of the deep learning object detection algorithms, was selected to identify key-point data from the flow field in a cleaning chamber. First, the training dataset was constructed via scatter plot drawing, data enhancement, random screening, and other technologies. Then, the flow field in the cleaning chamber was divided into six key areas by identifying the key points of the flow field. And, an analysis of the reasonable wind velocity in the areas was conducted, and the cleaning results of the grain were obtained by using the reasoning mechanism based on rules and examples. Finally, a system based on the above method was established in Python 3.10 software. With the help of the method and the system in this paper, the flow field characteristics in a cleaning chamber and the effects of wind on the cleaning effect can be obtained automatically if the physical properties of the crop, the geometric parameters of the cleaning chamber, and the working parameters of the machine are given.