In machining operations, dynamometers are typically used to directly measure the forces acting on cutting tools. However, their high cost and complex setup restrict their use to laboratory environments, making them unsuitable for real-time monitoring in general production settings. To overcome this limitation, this study proposes an autoencoder-based learning model for estimating cutting forces using only spindle vibration signals acquired during milling. The model features a deep neural network (DNN) that takes processed spindle vibration signals as input and predicts latent features derived from cutting force signals through an autoencoder. These predicted latent features are then fed into a pretrained decoder to reconstruct the corresponding cutting force signals. To enhance the model's accuracy and robustness, the raw vibration signals sampled at 20 kHz were filtered with a bandpass filter that spans the effective frequency range of 20–2500 Hz, effectively removing irrelevant noise. For validation, an accelerometer was mounted on the spindle head of a milling machine, and vibration data were collected during cutting. The estimated cutting forces were compared to ground truth measurements obtained from a dynamometer. The model achieved a Pearson correlation coefficient of 0.943, demonstrating that reliable cutting force estimation is achievable using only low-cost vibration sensors.

The importance of cutting forces in machining has been emphasized for monitoring and optimizing cutting conditions, leading to various method to detecting cutting forces researched. Cutting forces can be directly measured using dynamometer or indirectly estimated using AE sensors and accelerometers, etc. However, these external sensors demand high costs and have accuracy limitations due to environment issues. To compensate for these drawbacks, utilizing internal signals of machine tool has been developed. Among these, using internal electrical signals of machine tool is representative. In commercial machine tools, cutting forces are often estimated through current measurements. However, due to the characteristics of the spindle motor, electrical properties such as slip, power factor, and efficiency vary with the load, resulting in relatively lower accuracy. This study introduces current-based method considering characteristics of motor and power-based method for estimating cutting forces and compare accuracy of those methods with the measurements from dynamometer respectively.

Drill processing is essential in various industries, such as automobiles and aviation. Carbide is mainly used for drilling, but cermet is also one of the most used materials. Since cermet has low reactivity with iron and low reactivity at high temperatures, excellent surface roughness can be obtained. However, experimental research comparing the performance of carbide and cermet drills is lacking. The purpose of this study was to investigate the difference in the cutting characteristics of cermet and carbide tools. The experimental conditions were feed rates of 150, 200, 250, and 300 ㎜/min and 1,000, 1,500, and 2,000 revolutions per minute. S45C was used as the workpieces. In this study, surface roughness, inner diameter, and spindle load were derived as experimental results and used as indicators to evaluate the performance of carbide and cermet drills. The results showed that the performance of the cermet drill was superior to that of the carbide drill.

In the existing machine tool field, the focus was on the displacement of the feed system from the viewpoint of the motion of the machine tool. The displacement of the tool or spindle of a machine tool is useful for developing various functions. In this study, using the acceleration data of the spindle, we proposed an algorithm that tracked the displacement of the spindle with respect to the pseudo-step waveform motion. In order to solve the bandwidth problem of the pseudo-step waveform, the displacement data measured by the motor encoder of the feed system was used. In addition, in order to solve the drift problem due to double integration, a new drift removal filter was proposed and a displacement estimation algorithm was implemented. In order to examine the performance and possibility of the proposed spindle displacement estimation algorithm, it was applied to a gantry-type engraver and its excellent performance was confirmed compared to other algorithms.

This paper presents the effects of bearing locations on the mechanical characteristics of a multi-stepped spindle system related to bearing fatigue life, natural frequency, and static stiffness. The multi-stepped spindle is supported by a pair of tapered roller bearings (TRBs) and subjected to radial loading. To solve the equilibrium equation of the spindle system which is inherently statically-indeterminate, this study adopts an integrated shaft-bearing model, where the spindle is modelled by the finite shaft elements and the supporting TRBs are modelled by the five degrees-of-freedom TRB model developed by the authors. An iterative computational method is used to estimate the spindle deflection coupled with bearing deflections, and afterwards the bearing stiffness and internal contact loads of rolling elements are computed. The bearing fatigue life based on the ISO standard and the first natural frequency of the spindle system are evaluated with the spindle-bearing model. The influences of bearing locations on the static stiffness and natural frequency of the spindle, and the fatigue life of TRBs are rigorously investigated. The numerical results show the noticeable effects of bearing locations on the spindle system characteristics. The presented results provide a comprehensive assessment to aid for design optimization of spindle-TRB system.

Bearings having a small clearance during normal operation are selected. In some cases, bearings having a negative clearance when mounted are selected, to generate internal stress which enables achieving various effects. This so-called preload can be applied only to rolling bearings and not sliding ones. The performance of bearings is greatly affected by the applied preload. Application of a heavy preload to enhance the stiffness at the spindle undermines the high-speed rotation performance. In contrast, when a light preload is applied for high speed rotation, the stiffness is undermined. Therefore, a variable preload method is required. This study aims to develop a variable preload device using a linear actuator of the ball screw type, and to perform the performance evaluation of the developed device. Our studies verified that the proposed device worked satisfactorily.