Based on the drive signals of a milling center, process forces can be reconstructed. Therefore, a novel approach is presented to reconstruct the process forces with a long short-term memory neural network (LSTM) using drive signals as an input. The LSTM is evaluated and compared to a model-based approach. The latter compensates nonlinearities and disturbances such as friction and inertia. For training of the LSTM, multiple milling processes are considered to enhance the generalizability. Training data is generated by recording drive signals and process forces measured by a dynamometer. The LSTM is then evaluated using a test set, which comprises new process parameters. It is shown that the LSTM has a lower root mean square error (RMSE) in comparison to the model-based approach. Especially, when changing the feed motion direction during milling, the neural network clearly outperforms the model-based approach. Nevertheless, there are processes, where the LSTM induced oscillations, which do not correspond to the measured forces.

Monitoring of grinding wheel wear is a crucial task to ensure adequate quality of the manufactured workpiece. While external sensors, such as acoustic emission sensors, are commonly used for this task, the use of internal control signals has been neglected. Consequently, the extent to which degree these signals can be utilized to monitor the grinding process remains uncertain. Therefore, this work focuses on monitoring grinding wheel wear based on internal control signals in the case of surface grinding of 100Cr6. It is shown, that the novel approach can estimate tool life volume with a R² value of 0.98. The results are compared to models using force measurements of a dynamometer as well as sensor fusion approaches relying on both signal sources. Despite its low resolution in the frequency domain, drive signals can be used for grinding wheel wear monitoring. Nevertheless, dynamometer measurements enable more accurate estimations with a R² value of 0.99. The differences have to be considered when scheduling the grinding wheels redressing based on the estimated tool life volume.