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.
Finite element analysis (FEA) was conducted to investigate the cutting process of a single-layer PET film during rotary die cutting. In a roll-to-roll system, cutting blades formed on rollers were modeled as rigid bodies, while the PET film was modeled as an elastoplastic material using a two-dimensional approach. Stress-strain behavior of the film was measured through experimental tensile testing and used as input data for FEA. Force-displacement data from vertical cutting experiments of PET film were collected to validate the FE model and compared with simulation results. Stress distribution of the film and cutting force per unit thickness during the rotary cutting process were analyzed. The cutting force and range of effective cutting angles were proportional to tip angle of the blade within a range of 25 to 60 degrees, showing a noticeable change in proportionality slope at a tip angle of 40 degrees. As the film tension increased, the cutting force in thickness direction decreased, while that in longitudinal direction remained almost constant. Errors in film feed velocity significantly affected the cutting force. When the film moved slightly slower than the reference velocity, the cutting force was minimized due to reduced contact between the film and blade surface.
This study investigated the natural frequency of a self-excited vibrating workpiece and cutting tool using a hammer impact test to acquire vibration data. Time-domain cutting vibration data were converted to the frequency domain using FFT. The workpiece signal exhibited a high amplitude, peaking at 392 Hz, while the cutting tool signal presented a peak at 930 Hz. Stability Lobe Diagrams were constructed to assess dynamic stability. Cutting experiments revealed an obvious relationship between spindle speed and signal amplitude, with higher speeds leading to larger amplitudes. Frequency analysis revealed a peak near the cutting tool's 900 Hz natural frequency. Smoother surface finishes were observed at 0.15 mm cutting depth, while 0.2 mm resulted in a wavy surface, indicating chatter. To investigate chatter frequency and reduce noise, a multiple-denoising method combined Bior 3.7 and DB10 wavelets to reduce amplitude and improve signal representation, especially for non-smooth features. The proposed method aimed to reduce the 900 Hz cutting tool’s natural frequency. Results showed a clear chatter frequency at 450-480 Hz for 0.2 mm depth cuts at spindle speeds of 500, 1,000, and 1,400 rpm. The proposed method exhibited high efficiency, achieving the higher signal-to-noise ratio and lower mean-square error than Bior 3.7 and DB10 wavelet denoising techniques.
Citations
Citations to this article as recorded by
A Review of Intelligent Machining Process in CNC Machine Tool Systems Joo Sung Yoon, Il-ha Park, Dong Yoon Lee International Journal of Precision Engineering and Manufacturing.2025; 26(9): 2243. CrossRef
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.
Chemically strengthened glass has recently gained attention for use in mobile device display covers due to its enhanced mechanical properties. However, cutting chemically strengthened glass poses challenges because of its high surface compressive stress, derived from the ion exchange between Na+ and K+ during the strengthening process. To address this, we propose an efficient method for cutting chemically strengthened glass by integrating electrochemical discharge (ECD) and grinding processes. The ECD process helps alleviate surface compressive stress through reverse ion exchange, while the grinding process helps mitigate compressive stress on the bottom surface without flipping the glass. Chemical composition analysis of the cross-section of glass cut along the line treated by the ECD process revealed that this method can induce reverse ion exchange on both the upper and bottom surfaces of chemically strengthened glass. Furthermore, nano-indentation hardness tests conducted on the cross-section demonstrated that the subsurface hardness could be reduced by the ECD process, indicating a relaxation of the surface compressive layers. It has also been proven that chemically strengthened glass can be successfully cut using this method, suggesting it offers a viable solution for efficient glass cutting.
In recent years, the demand for lightweight parts has been gradually increasing, particularly in the E-mobility industry. Among lightweight materials, aluminum alloys are highly beneficial for improving the fuel efficiency of automobile engines due to their lighter weight compared to iron-based materials. As electric vehicles become more prevalent, aluminum alloys are also extensively used in components such as battery housings and EV platform frames. To enhance productivity, aluminum parts processing companies require Polycrystalline Diamond (PCD) cutting tools for high-speed and ultraprecision processing. PCD cutting tools are known for their excellent cutting performance and wear resistance in highspeed aluminum machining, and they are anticipated to have significant growth potential in the global cutting tool market. In this study, we manufactured three types of PCD cutting tools (Drill, Endmill, and Reamer) using a self-developed brazing device and analyzed the machining surface quality through experiments. The results showed that the brazing joint quality of the PCD cutting tools was high, and the differences in surface roughness values under various machining conditions were minimal, confirming no issues with machining performance. Future research will focus on evaluating machining precision and tool life through comparative experiments with advanced PCD cutting tools from overseas.
Digital twin technology offers the advantage of monitoring the status of equipment, systems, and more in a virtual environment, allowing validation through simulation. This technology has found numerous applications in the industrial robotics field, driven by recent advancements in the manufacturing industry. Consequently, predicting machining quality using digital twin technology is imperative for ensuring high-quality processed goods. In this study, we developed a digital twin program based on a cutting-force physical model and created a performance enhancement module that allows the visualization of material removal for user convenience. The predicted cutting forces from both conventional CNC and the physical model demonstrate a high accuracy of within 2%. Within the digital twin environment, the error rate for the robotic drilling process is 13.5%. Building upon this, we developed and validated a module for material removal visualization, aiming to increase convenience for on-site operators.
Citations
Citations to this article as recorded by
A Review of Intelligent Machining Process in CNC Machine Tool Systems Joo Sung Yoon, Il-ha Park, Dong Yoon Lee International Journal of Precision Engineering and Manufacturing.2025; 26(9): 2243. CrossRef
Zinc sulfide (ZnS) is a widely used material in far-infrared and near-infrared imaging systems due to its exceptional optical transmittance properties. Through a hot isostatic compression process, during manufacturing, ZnS undergoes crystal structure modifications, resulting in increased transmittance across the visible and infrared spectra. However, ZnS exhibits low fracture toughness and irregular crystal orientations, making it prone to brittle fracture during the conventional cutting processes. Such brittleness often leads to surface defects that scatter light, diminishing optical transmittance. Therefore, understanding the conditions conducive to ductile processing is critical and necessitates a thorough brittle fracture analysis. This study introduces a novel quantitative analysis method to determine the occurrence of ductile processing and brittle fracture in ZnS materials after the turning process. To validate the efficacy of this approach, experimental machining was conducted through diamond turning and magnetorheological fluid polishing processes. Subsequently, a comprehensive quantitative assessment of brittle fracture was performed. Additionally, the relationship between brittle fracture and optical transmittance was explored using the proposed analysis method.
In this paper, the relationship between various physical and chemical dynamics included in a gas cutting process was analyzed and a mathematical model was presented. To express the gas cutting process in a formula that could reflect the physics and chemical reaction dynamics, the entire process was classified into three stages: flame spurt, metal oxidation, and metal oxide melting. Flame spurt is caused by combustion of fuel gas and oxygen. It was modeled through fluid dynamics, chemical species transport, and reaction kinetics. Metal oxidation was modeled as a chemical reaction of surface oxidation and oxide growth based on temperature and concentration of species of the metal surface obtained through flame and cutting oxygen spurt results. Finally, the melting of metal oxide was expressed as a rate equation based on melting conditions, heat flux obtained in the previous two stages, and changed properties of the metal. The presented mathematical model could analyze dynamic relationships for each stage of a gas cutting process and connect them into one process. Results of this study can be used as basic data for future finite element analysis and simulations.
Citations
Citations to this article as recorded by
A Comprehensive Review on Flame Scarfing of Steel Slabs: Fundamentals, Challenges, Evolution, and Future Jin Gao, Fengsheng Qi, Zhongqiu Liu, Sherman C. P. Cheung, Baokuan Li, Deqiang Li steel research international.2025;[Epub] CrossRef
With the advent of the 4th industrial revolution, advanced digital manufacturing technologies are actively developed to strengthen manufacturing competitiveness. Smart factories require a real-time digital twin including a Cyber-Physical System (CPS) of machines and processes and intelligent technologies based on the CPS. To predict machining quality and optimize machines and processes, it is necessary to analyze the cutting force during machining. Therefore, for real-time digital twin, a fast cutting force simulation model that receives information such as the positions of the feed axes in short time intervals from the CNC and calculates the cutting force until the next information is input is required. This paper proposes a voxel-based fast cutting force simulation in NC milling for real-time digital twin. The proposed simulation model quickly calculates the cutting force by using only information of voxel elements removed by each tool edge without complicated Cutter-Workpiece Engagement (CWE) and chip thickness calculations in previous studies. To verify the performance of the developed simulation, experimental machining was performed and the measured cutting force and simulated cutting force were compared. It was demonstrated that the proposed model can successfully predict the cutting force 3.5 times faster than the actual process.
Citations
Citations to this article as recorded by
Autonomous Mobile Machining and Inspection System Technology for Large-Scale Structures Seung-Kook Ro, Chang-Ju Kim, Dae-Hyun Kim, Sungcheul Lee, Byung-Sub Kim, Jeongnam Kim, Jeong Seok Oh, Gyungho Khim, Seungman Kim, Seongheum Han, Quoc Khanh Nguyen, Jongyoup Shim, Segon Heo International Journal of Precision Engineering and Manufacturing.2025; 26(9): 2345. CrossRef
Among the monitoring technologies in the metal-cutting process, tool wear is the most critical monitoring factor in real machining sites. Extensive studies have been conducted to monitor equipment breakdown in real-time. For example, tool wear prediction studies using cutting force signals and deducting force coefficient values from the cutting process. However, due to many limitations, those wearable monitoring technologies have not been directly adopted in the field. This paper proposes a novel tool wear predictor using the cutting force coefficient with various cutting tools, and its validity evaluates through cutting tests. Tool wear prediction from the cutting force coefficient should conduct in real-time for adoption in real machining sites. Therefore, a real-time calculation algorithm of the cutting force coefficient and a tool wear estimation method proposes, and they compare with actual tool wear in cutting experiments for validation. Validation cutting tests are conducted with carbon steel and titanium, the most commonly used materials in real cutting sites. In future work, validation will be conducted with different materials and cutting tools, considering the application in real machining sites.
Citations
Citations to this article as recorded by
A Review of Intelligent Machining Process in CNC Machine Tool Systems Joo Sung Yoon, Il-ha Park, Dong Yoon Lee International Journal of Precision Engineering and Manufacturing.2025; 26(9): 2243. CrossRef
In this paper, we developed a virtual model predicting the tool deflection induced surface error and investigated the sensitivity and direction of the maximum surface error in various tool geometries and cutting conditions. The characteristics of the error were classified into the axial sensitive, radial sensitive, robust, overcut, and overlap zones according to the depth of cut. The maximum surface error was sensitive to the uncertainty of the radial depth of cut and robust to axial depth variation at the finishing process using a small radial depth of cut. The radial sensitivity was reduced by a large helix angle of tool. The sensitivity was decreased by increasing the depth of cut and it arrived at zero in the robust zone where the maximum surface error was not changed by both radial and axial depths of cut. An overcut occurred if axial and radial depths were deep and the overcut zone was enlarged by the helix angle and the number of teeth.
Ultrasonic cutting is used not only for cutting various materials such as metals and non-metals, but also for bone cutting of the human body or for various surgical operations. In recent, ultrasonic cutting technology is being applied for cutting various food products such as cakes, pizza, and cheese. It is shown that ultrasonic vibrations for cutting food products enables high-precision and high-quality cutting, and the quality of the cutting surface is affected by the shape of food products and cutting conditions. However, most of the studies have been on industrial cutting horns that can be used in large-scale grocery factories, but these cutting horns are very different from the shape of knives used in the households. Accordingly, research or technology development for ultrasonic cutting knives that can be used in household has not been studied. Therefore, this study developed a knife that can cut or process food by applying ultrasonic vibration while having a shape similar to the existing knife as possible so that it can be used in general. To develop such a knife, a modal analysis was performed using the finite element method for knife models of various shapes, and a suitable model for a kitchen knife was proposed.
Citations
Citations to this article as recorded by
Development and Performance Verification of an Ultrasonic Food Cutter Byung-Soo Yang, Ji-Chan Suk, Jeong-Suk Seo, Dong-Sam Park Journal of the Korean Society of Manufacturing Process Engineers.2023; 22(5): 54. CrossRef
Social interest in the 4th industry, intelligent factories, and smart manufacturing is continually growing along with the core technologies like big data and artificial intelligence, which can generate meaningful information by collecting and accumulating sensor data. Demand for industrial automation equipment is increasing worldwide due to the efforts needed to modernize manufacturing facilities, reduce automation and cycle time, and improve quality. Currently, the majority of research is focused on the development of automation facilities and improving productivity. The research on the contents of real-time data considering the characteristics of the cutting machine plasma machine is insufficient. In this study, based on the current data measured according to cutting current and cutting speed, a reference value for cutting quality is presented and the optimal process parameter has been selected. A model for predicting cutting quality by introducing the Mahalanobis Distance Method is presented. An attempt has been made to derive selection and optimal cutting process variables. Based on the predictive model, threshold values were specified and used in real-time data to consider the correlations between multivariate variables and evaluate the degree of scattering around the average of specific values of each variable. Also, process parameters suitable for surface roughness were calculated.
Citations
Citations to this article as recorded by
A quantitative diagnostic method of feature coordination for machine learning model with massive data from rotary machine Yoonjae Lee, Byeonghui Park, Minho Jo, Jongsu Lee, Changwoo Lee Expert Systems with Applications.2023; 214: 119117. CrossRef
Silicon nanoparticles: fabrication, characterization, application and perspectives Taeyeong Kim, Jungchul Lee Micro and Nano Systems Letters.2023;[Epub] CrossRef
Feature selection algorithm based on density and distance for fault diagnosis applied to a roll-to-roll manufacturing system Hyogeun Oh, Yoonjae Lee, Jongsu Lee, Changbeom Joo, Changwoo Lee Journal of Computational Design and Engineering.2022; 9(2): 805. CrossRef
Impact of Sensor Data Characterization with Directional Nature of Fault and Statistical Feature Combination for Defect Detection on Roll-to-Roll Printed Electronics Yoonjae Lee, Minho Jo, Gyoujin Cho, Changbeom Joo, Changwoo Lee Sensors.2021; 21(24): 8454. CrossRef
With the progress of flexible devices, numerous researchers aim to manufacture the flexible battery with freefrom at various scales. Laser cutting is considered as one of the essential processes to achieve on-demand manufacturing but continuous wave or long-pulse laser beam may cause large heat affect zone (HAZ) in cutting edge and may even result in failure of battery function. Herein, it was demonstrated that the sophisticated cutting process using ultra-short pulse laser is applicable for tailoring of flexible battery with multilayered structure. Based on the comparison of cutting results using nanosecond laser and femtosecond laser, we confirmed that laser cutting by femtosecond laser induces much less thermal damage on thin foil electrodes, separator, and electrolyte. Furthermore, we investigated the interaction of femtosecond laser with the materials composed of a flexible battery and implemented a process for cutting each material without causing any critical damage. To prevent a short circuit between the anode and cathode, which usually occurs during laser cutting of the actual battery, the double-side cutting process was done by adjusting the focal points of the laser beam. We assume that the proposed approach can be applied in a roll-to-roll based cutting process for the mass-production of flexible devices.
First
Prev
