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

As the main working part of the combined harvester, the cleaning device affects the cleaning performance of the machine. The simulation of flow field in cleaning chamber has become an important mean of the design. Now post-processing analysis of the flow field simulation still relies on the researchers’ experience, so it is difficult to obtain information from the post-processing automatically. The experience of researchers is difficult to express and spread. This paper studied an intelligent method to analyse the simulation result data, which was based on the object detection algorithm and the reasoning mechanism. YOLOv8, one of the deep learning object detection algorithm, was selected to identify key point data from flow field in the cleaning chamber. First the training data set was constructed by scatter plot drawing, data enhancement, random screening and other technologies. Then the flow field in the cleaning chamber was divided into 6 key areas by identifying the key points of the flow field. And the analysis of the reasonable wind velocity in the areas and the cleaning results of grain were completed by reasoning mechanism based on rules and examples. Finally a system based on the above method was established by Python software. With the help of the method and the system in this paper, the flow field characteristic in the cleaning chamber and the effects of wind upon cleaning effect could be obtained automatically if the physical property of the crop, geometric parameters of the cleaning chamber, working parameters of the machine were given.