• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.3
• /
• pp.117-124
• /
• 2021

The development of IOT technology and artificial intelligence technology is promoting the smartization of manufacturing system. In this study, data extracted from acceleration sensor and current sensor were obtained through experiments in the cutting process of SKD11, which is widely used as a material for special mold steel, and the amount of tool wear and product surface roughness were measured. SVR (Support Vector Regression) is applied to predict the roughness of the product surface in real time using the obtained data. SVR, a machine learning technique, is widely used for linear and non-linear prediction using the concept of kernel. In particular, by applying GSVQR (Generalized Support Vector Quantile Regression), overestimation, underestimation, and neutral estimation of product surface roughness are performed and compared. Furthermore, surface roughness is predicted using the linear kernel and the RBF kernel. In terms of accuracy, the results of the RBF kernel are better than those of the linear kernel. Since it is difficult to predict the amount of tool wear in real time, the product surface roughness is predicted with acceleration and current data excluding the amount of tool wear. In terms of accuracy, the results of excluding the amount of tool wear were not significantly different from those including the amount of tool wear.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.392-392
• /
• 2000

This study performs optimization of paper mill scheduling using MINLP(Mixed-Integer Non-Linear Programming) method and 2-step decomposing strategy. Paper mill process is normally composed of five units: paper machine, coater, rewinder, sheet cutter and roll wrapper/ream wrapper. Various kinds of papers are produced through these units. The bottleneck of this process is how to cut product papers efficiently from raw paper reel and this is called trim loss problem or cutting stock problem. As the trim must be burned or recycled through energy consumption, minimizing quantity of the trim is important. To minimize it, the trim loss problem is mathematically formulated in MINLP form of minimizing cutting patterns and trim as well as satisfying customer's elder. The MINLP form of the problem includes bilinearity causing non-linearity and non-convexity. Bilinearity is eliminated by parameterization of one variable and the MINLP form is decomposed to MILP(Mixed-Integer Linear programming) form. And the MILP problem is optimized by means of the optimization package. Thus trim loss problem is efficiently minimized by this 2-step optimization method.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.16 no.2
• /
• pp.237-248
• /
• 2014

Linear cutting test is known to be very effective to determine machine parameters (i.e. thrust force and torque) and to estimate penetration rate of TBM and other operation conditions. Although the linear cutting test has significant advantages, the test is expensive and time-consuming because it requires large size specimen and high load capacity of the testing machine. Therefore, a few empirical prediction models (e.g. CSM, NTNU and QTBM) alternatively adopt laboratory index tests to estimate design parameters of TBM. This study discusses the estimation method of TBM machine parameters and disc cutter consumption using punch penetration test and Cerchar abrasion test of which the researches are rare. The cutter forces and cutter consumption can be estimated by the empirical models derived from the relationship between laboratory test result with field data and linear cutting test data. In addition, the estimation process was programmed through which the design parameters of TBM (e.g. thrust, torque, penetration rate, and cutter consumption) are automatically estimated using laboratory test results.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.12 no.2
• /
• pp.1-8
• /
• 2003

Conventionally used linear or circular interpolator is undesirable for the precision machining of 3D free-form surface as the following reason: the transmission errors due to the huge number of data, discontinuity of segmentation, unsmooth motion speed. To this regard, modern CNC machine tools are designed with the function of machining arbitrary parametric curves. However, these systems don't consider the adaptive federate, which dominates the quality of the machining process. This paper proposes a NURBS interpolator for the constant material removal rate. That is accomplished by the variable federate using curvature of curve. The curvature-compensated feederate system has important Potential applications in ensuring part accuracy and protecting cutting tool. The simulated result show it can be applicable to the real machining.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.4
• /
• pp.101-107
• /
• 2007

The objective of this research work is to investigate into effects of an auto tracking of the focal distance on the quality of the cut part in the cutting of a low carbon sheet using a high-power CW Nd:YAG laser. An auto-tracking system with a capacitance based distance control loop has been employed to perform a real control of the focal distance. In order to examine the influence of the auto-tracking of a focal distance on the optimum focal distance, the kerfwidth, surface roughness and the formation of the cut section, several linear cutting tests have been carried out using the auto-tracking system. The results of experiments have been shown that the optimum focal distance is 0.9mm. In addition, it has been shown that the variation of kerfwidth and the surface roughness of the cut part with control of the focal distance are reduced 40-80% and 30-55% in comparison with those of the cut part without tracking of the focal distance. From the results of the experiments, it has been found that the real time tracking of the focal distance can improve the part quality.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.04a
• /
• pp.466-471
• /
• 2003

In order to analyze linear motor driven feed system, preliminary studies have been conducted focusing on the performance evaluation of the system based on the various combination of control gain along with acceleration. Tentative simulation revealed that due to the complexity of control system reduced number of control condition is recommended. Actual machining process with conventional feed system using endmill tool was employed as a preliminary study. Several sensing methods including AE, acceleration sensors and tool dynamometer were used. Results revealed the consistency in AE and cutting resistance. There were inconsistent empirical results in accelerometer probably due to the insensitivity of the sensor signal with respect to the experimental system

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.374-378
• /
• 2003

From linear motor feed system model, two axis control rules have been applied. As an application process, a flexible disk grinding system process has been also introduced that utilized varying disk orientation with respect to workpiece along with the applied feed speed. A known process model methodologies has been used to fomulate processed surface profiles. Various process conditions including cutting speed, maximum feed speed and orientation angles could applied to observe process results sensitivities. Even though continuous and constant feed speed has been applied to the process, the results from the trapezoidal input velocity profiles would be observed and compared.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.100-105
• /
• 2003

With the recent development of machining technology, high speed machining process is widely used for-the mold and difficult-to -cut-materials machining since it allows achieving high productivity and surface quality. However, during the high speed machining process, high cutting speed and feed rate can cause abrupt tool life decrease due to rapid rising of the cutting tool temperature. Such situation may cause increase of machining cost. Thus, in this study, developed optimization algorithm is applied to determine optimal machining variables for multiple high speed machining. The R-T characteristic curve for machining economics problems with a linear-lorarithmic tool life model is determined by applying sensitivity analysis. finally, a series of high speed machining experiments are performed to determine the desired optimal machining variables, and the results are analyzed.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.10 no.1
• /
• pp.81-90
• /
• 2008

It is of great importance to determine the optimum cutter spacing in TBM. In order to determine the optimum cutter spacing, a series of cutting tests by linear cutting machine (LCM) are performed with changing cutter space. This study showed that a numerical method for estimating the optimum cutter spacing could be developed by AUTODYN-3D in order to overcome the limitation of LCM test. By using this method, the optimum cutter spacing of Hwangdeung granite was estimated.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.11
• /
• pp.93-101
• /
• 1997

Ever since the nonlinearity of machine tool dynamics was established, researchers attempted to make use of this fact to devise better monitoring, diagnostics and control system, which were hitherto based on linear models. Theory of chaos which explains many nonlinear phenomena comes handy for furthering the analysis using nonlinear model. In this study, measuring system will be constructed using multi-sensor (Tool Dynamometer, Acoustic Emission) in end milling process. Then, it will be verified that cutting force is low-dimensional chaos by calculating Lyapunov exponents. Fractal dimension, embedding dimension. And it will be investigated that the relation between characteristic parameter calculated from sensor signal and tool wear.