本发明提供一种基于孤立森林机器学习的机器人实时异常监测方法及系统，包括以下步骤：数据采集：采集机器人良好运行下的历史数据以及机器人监测过程中的实时数据；建模：利用历史数据基于孤立森林机器学习建立异常检测模型；检测：所述实时数据输入异常监测模型进行异常检测，并输出检测结果。与现有技术相比，基于孤立森林机器学习所建立的一侧监测模型可针对多维度数据综合分析，提高检测的准确度。

The invention provides a method and system for real-time abnormality monitoring of robots based on isolated forest machine learning, comprising the following steps: data collection: collecting historical data under good operation of the robot and real-time data in the monitoring process of the robot; modeling: using historical data to base on The isolated forest machine learning establishes an anomaly detection model; detection: the real-time data is input into the anomaly monitoring model for anomaly detection, and the detection result is output. Compared with the prior art, the one-side monitoring model established based on the isolated forest machine learning can comprehensively analyze multi-dimensional data and improve the detection accuracy.