基于数字孪生和聚类算法的采煤机数据异常识别研究
Research on Coal Mining Machine Data Anomaly Identification Based on Digital Twin and Clustering Algorithm

本文针对煤矿采煤机数字孪生模型构建中数据采集的精确性问题，提出了一种基于数字孪生和改进的R-DBSCAN聚类算法的采煤机数据异常识别方法。该方法首先建立了采煤机的数字孪生模型，通过采用改进的R-DBSCAN算法进行异常数据识别。改进算法通过K-dist图自适应地确定了DBSCAN算法的参数，从而提高了对异常数据的识别效果。实验结果表明，该算法相比其他聚类算法，能更准确地识别采煤机异常数据，进而使采煤机数字孪生模型构建的准确性和有效性得到提高。
In this paper, a coal mining machine data anomaly identification method based on digital twin and improved R-DBSCAN clustering algorithm is proposed for the accuracy of data collection in the construction of digital twin model of coal mining machine. The method first establishes the digital twin model of coal mining machine and carries out abnormal data identification by using the improved R-DBSCAN algorithm. The improved algorithm adaptively determines the parameters of the DBSCAN algorithm through K-dist graph, thereby improving the recognition effect of abnormal data. Empirical tests have revealed that the suggested algorithm can more accurately recognize the abnormal data of coal mining machine compared with other clustering algorithms, which in turn leads to the improvement of the accuracy and effectiveness of the construction of a digital twin model of coal mining machine.