To prevent undesirable effects during milling processes, online predictions of upcoming events can be used. Process simulations enable the capability to retrieve additional knowledge about the process, since their application allows the generation of data about characteristics, which cannot be measured during the process and can be incorporated as pre-calculated features into the analysis. Furthermore, sensor technologies were used as reasonable data sources for analyzing different monitoring scopes of milling processes. Machine learning-based models utilize data, acquired by various available data sources, to generate predictions of upcoming events in real-time. In this paper, we propose a novel approach for combining simulation data with sensor data to generate online predictions of process forces, which are influenced by tool wear, using an ensemble-based machine learning method. In addition, a methodology was developed in order to synchronize pre-calculated simulation data and streaming sensor measurements in real time. Milling experiments using ball-end milling tools with varying cutting speeds and tooth feeds showed the robustness of the approach in enhancing the prediction accuracy compared to only using one of each data source.

为了防止在铣削过程中产生不良影响，可以使用即将发生的事件的在线预测。流程模拟可以检索有关流程的其他知识，因为它们的应用程序允许生成有关特性的数据，这些特性在流程中无法测量，可以作为预先计算的特征并入分析中。此外，传感器技术被用作合理的数据源，用于分析铣削过程的不同监控范围。基于机器学习的模型利用各种可用数据源获取的数据来实时生成即将发生的事件的预测。在本文中，我们提出了一种将仿真数据与传感器数据相结合以生成过程力在线预测的新颖方法，该过程力受刀具磨损的影响，使用基于整体的机器学习方法。另外，开发了一种方法以实时同步预先计算的仿真数据和流式传感器测量结果。与仅使用每个数据源之一相比，使用具有可变切削速度和齿进给的球头铣刀进行的铣削实验表明，该方法在增强预测精度方面具有鲁棒性。