论文部分内容阅读
农业机械在田间作业过程中,时间和空间维度上产生大量的作业数据,对农业机械作业轨迹数据进行聚类分析在农机作业状态分析和效率研究中具有重要意义。为此,应用DBSCAN(Density-Based Spatial Clustering of Applications with Noise)算法对模拟农业机械作业轨迹进行分析,设计了基于密度聚类的农机作业状态分类算法。对模拟数据的聚类结果表明:该方法正确分类农机作业班次内的有效作业轨迹、空行转移轨迹和停歇轨迹的精度达到98.33%、70%和100%。聚类作业轨迹反映的农机利用率为95.35%,为农机田间作业轨迹研究提供了依据。
Agricultural machinery in the process of field operations, the time and space dimensions produce a large number of operating data, the clustering analysis of agricultural machinery trajectory data is of great significance in agricultural operation status analysis and efficiency study. Therefore, the application of DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to simulate the trajectory of agricultural machinery operation, design based on the density clustering of agricultural machinery state classification algorithm. The clustering results of simulation data show that this method can effectively classify the effective work path within agricultural work shift, and the accuracy of empty line transfer path and stop path reaches 98.33%, 70% and 100%. The utilization ratio of agricultural machinery reflected by the cluster trajectories is 95.35%, which provides the basis for the research on the track of farm machinery field operation.