Accurate prediction of cutting forces in milling is crucial for intelligent machining. However, traditional methods of collecting discrete data are often time-consuming and can lead to overfitting due to data sparsity. This study introduces a continuously variable data collection strategy designed to efficiently gather training data for machine learning models. By linearly varying the feed rate and radial depth of cut along a single tool path, we obtained continuous data that reflect the variations in machining conditions. Additionally, we applied trigonometric feature transformation to the tool rotation angle to maintain its periodic characteristics. The collected data were used to train Artificial Neural Network (ANN), Support Vector Regression (SVR), and Gaussian Process Regression (GPR) models. The results demonstrate that models trained with continuous data exhibit improved generalization performance under unseen conditions compared to those trained with discrete data. Furthermore, comparable predictive accuracy was achieved using a subset of the continuous dataset. These findings suggest that the proposed approach enhances data efficiency in model training and has the potential to reduce the experimental effort required in developing machining monitoring systems.

Work coordinate setup is a time-consuming and difficult task in ultraprecision machining. The setup process determines the precision and tolerance of the machined parts. In ultraprecision machining, the table can be moved in the nanometer range, but the accuracy of the measuring device has not reached the nanometer accuracy range. Although several measurement methods have been proposed, the attained precision is still insufficient. Some methods also lose the precision when the sensor is changed with the tool after the work coordinate setup is completed. A work coordinate setup method proposed in this study could improve the precision and the measurement process using electron tunneling. Since the method can use the tool as a sensor probe, the changing process does not degrade the measurement precision. In addition, the proposed method can theoretically detect the distance between the tool and the workpiece in sub-nanometers like a scanning tunneling microscope. The simple system requires a precision current amplifier capable of measuring electron tunneling current in the picoampere to nanoampere range and a power supply. The method, installed on an ultra-precision machine tool, was tested on WC and aluminum material. The accuracy of the method was evaluated for applied voltage.