http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
타이타늄 압연재의 기계학습 기반 극저온/상온 변형거동 예측
천세호,유진영,이성호,이민수,전태성,이태경 한국소성∙가공학회 2023 소성가공 : 한국소성가공학회지 Vol.32 No.2
A deformation behavior of commercially pure titanium (CP-Ti) is highly dependent on material and processing parameters, such as deformation temperature, deformation direction, and strain rate. This study aims to predict the multivariable and nonlinear tensile behavior of CP-Ti using machine learning based on three algorithms: artificial neural network (ANN), light gradient boosting machine (LGBM), and long short-term memory (LSTM). The predictivity for tensile behaviors at the cryogenic temperature was lower than those in the room temperature due to the larger data scattering in the train dataset used in the machine learning. Although LGBM showed the lowest value of root mean squared error, it was not the best strategy owing to the overfitting and step-function morphology different from the actual data. LSTM performed the best as it effectively learned the continuous characteristics of a flow curve as well as it spent the reduced time for machine learning, even without sufficient database and hyperparameter tuning.
XGB 및 LGBM을 활용한 Ti-6Al-4V 적층재의 변형 거동 예측
천세호,유진영,김정기,오정석,남태현,이태경 한국소성∙가공학회 2022 소성가공 : 한국소성가공학회지 Vol.31 No.4
The present study employed two different machine-learning approaches, the extreme gradient boosting (XGB) and light gradient boosting machine (LGBM), to predict a compressive deformation behavior of additively manufactured Ti-6Al-4V. Such approaches have rarely been verified in the field of metallurgy in contrast to artificial neural network and its variants. XGB and LGBM provided a good prediction for elongation to failure under an extrapolated condition of processing parameters. The predicting accuracy of these methods was better than that of response surface method. Furthermore, XGB and LGBM with optimum hyperparameters well predicted a deformation behavior of Ti-6Al-4V additively manufactured under the extrapolated condition. Although the predicting capability of two methods was comparable, LGBM was superior to XGB in light of six-fold higher rate of machine learning. It is also noted this work has verified the LGBM approach in solving the metallurgical problem for the first time.
Study on the Response Surface Model of Machining Error in Internal Lathe Boring
천세호,고태조 한국정밀공학회 2011 International Journal of Precision Engineering and Vol. No.
To achieve high quality and precision of machining products, the machining error must be examined. The machining error,defined as the difference between designed surface and the actual tool, is generally caused by tool deflection and wear, thermal effects and machine tool errors. Among these error sources, tool deflection is usually known as the most significant factor. The tool deflection problem is analyzed using the instantaneous cutting forces on the cutting edge. This study presents a model of the machining error caused by tool deflection in the internal boring process. The machining error prediction model was described by the surface response method using overhang, feed per revolution and depth of cut as the factors for the analysis. The least square method revealed that overhang and depth of cut were significant factors within 90% confidence intervals. Analysis of variance (ANOVA) and residual analysis show that the second-order model is adequate.
엔드밀을 활용한 홀 가공 시 표면거칠기 예측에 관한 연구
천세호 한국기계가공학회 2019 한국기계가공학회지 Vol.18 No.10
Helical machining is an efficient method for machining holes using an endmill. In this study, a surface roughness prediction model was constructed for improving the productivity of hole machining. Experiments were conducted to form holes by the helical machining of AL6061-T4 aluminum sheets and correlation analysis was performed to examine the relationships between the variables based on the measured results. Meanwhile, a regression analysis technique was used to construct and evaluate the prediction model. Through these analyses, the parameter which has the greatest influence on the surface roughness when the hole is formed by the helical machining is the feed, followed by the number of revolutions of the endmill. Moreover, for the axial feed of the endmill, it was concluded that the influence of the surface roughness is small compared to the other two parameters but it is a factor worth considering to improve the accuracy when constructing the predictive model.
AL6061-T4의 보링가공 시 절삭조건에 따른 직경 변화에 관한 연구
천세호(Se-Ho Chun) 한국기계가공학회 2020 한국기계가공학회지 Vol.19 No.6
The purpose of this study is to investigate the effects of the change in the spindle speed and the feed rate on the diameter change of a hole using a boring cutter for the internal boring process of AL6061-T4 alloys. The experimental results are quantitatively analyzed by applying the factor analysis and the response surface analysis of the experimental design method. The tendency of the diameter change according to the change in the spindle speed and feed level is also evaluated. During the internal boring process of AL6061-T4 alloys, the main factor affecting the diameter change is the spindle speed in which the diameter decreases as the number of revolutions increases. In addition, the diameter tends to increase as the feed is increased; however, as the number of spindle revolutions increases, the influence of the feed decreases.
AL7075-T6의 슬롯가공 시 표면거칠기와 진동의 상관관계에 관한 연구
천세호(Se-Ho Chun) 한국기계가공학회 2022 한국기계가공학회지 Vol.21 No.5
This study investigated the characteristics and relationship between surface roughness and vibration according to the cutting conditions in the slot milling of AL7075-T6. The spindle speed, feed, and depth of cut were selected as independent variables and the amplitude of acceleration and surface roughness as dependent variables. Feed affected the surface roughness. As the spindle speed increased, the amplitude of vibration increased in the direction perpendicular to the feed direction. In addition, the amplitude of vibration and surface roughness showed a negative correlation. Under a given feed, the surface roughness improved as the vibration increased.
AL6061-T4의 측면 엔드밀 가공에서 표면거칠기 예측을 위한 인공신경망 적용에 관한 연구
천세호(Se-Ho Chun) 한국기계가공학회 2021 한국기계가공학회지 Vol.20 No.5
We applied an artificial neural network (ANN) and evaluated surface roughness prediction in lateral milling using an endmill. The selected workpiece was AL6061-T4 to obtain data of surface roughness measurement based on the spindle speed, feed, and depth of cut. The Bayesian optimization algorithm was applied to the number of nodes and the learning rate of each hidden layer to optimize the neural network. Experimental results show that the neural network applied to optimize using the Expected Improvement(EI) algorithm showed the best performance. Additionally, the predicted values do not exactly match during the neural network evaluation; however, the predicted tendency does march. Moreover, it is found that the neural network can be used to predict the surface roughness in the milling of aluminum alloy.
보링커터의 세장비에 따른 구멍 정밀도 변화에 관한 연구
천세호(Se-Ho Chun) 한국기계가공학회 2017 한국기계가공학회지 Vol.16 No.5
It is assumed that the buckling and cutting conditions depending on the slenderness ratio will affect the machining quality of the rotary boring tool mounted on a milling machine. In this study, the boring cutter was designed and fabricated to precisely create the Ø30 hole. Through the performance evaluation, the accuracy of the hole according to the slenderness ratio and cutting conditions was analyzed, and the following conclusions were obtained. The higher the RPM, the smaller the change in the working diameter, and the smaller the hole. Next, the smaller the slenderness ratio, the smaller the change in straightness due to the change in cutting conditions. Finally, the slenderness ratio also affects the tendency for changes in the concentricity. The larger the slenderness ratio, the more sensitive the concentricity to changes in cutting conditions.
알루미늄 합금의 스파이럴 상향가공 시 절삭조건이 표면거칠기에 미치는 영향
천세호(Se-Ho Chun) 한국기계가공학회 2014 한국기계가공학회지 Vol.13 No.4
The spiral up milling of an aluminum alloy was performed in this study. In accordance with the cutting condition, the surface roughness behavior and significance of the research with regard to specific factors were analyzed. The cutting speed, feed, and depth of the cut were found to be statistically significant. A higher cutting speed improved the surface roughness. On the other hand, as the feed and depth of the cut increase, the surface roughness decreases. An interaction effect between the feed and depth of the cut was detected. According to the surface roughness in relation to the cutting conditions, the model showed non-linear behavior.