• 산업경영시스템학회지
• /
• 제45권4호
• /
• pp.157-166
• /
• 2022

In the case of a die-casting process, defects that are difficult to confirm by visual inspection, such as shrinkage bubbles, may occur due to an error in maintaining a vacuum state. Since these casting defects are discovered during post-processing operations such as heat treatment or finishing work, they cannot be taken in advance at the casting time, which can cause a large number of defects. In this study, we propose an approach that can predict the occurrence of casting defects by defect type using machine learning technology based on casting parameter data collected from equipment in the die casting process in real time. Die-casting parameter data can basically be collected through the casting equipment controller. In order to perform classification analysis for predicting defects by defect type, labeling of casting parameters must be performed. In this study, first, the defective data set is separated by performing the primary clustering based on the total defect rate obtained during the post-processing. Second, the secondary cluster analysis is performed using the defect rate by type for the separated defect data set, and the labeling task is performed by defect type using the cluster analysis result. Finally, a classification learning model is created by collecting the entire labeled data set, and a real-time monitoring system for defect prediction using LabView and Python was implemented. When a defect is predicted, notification is performed so that the operator can cope with it, such as displaying on the monitoring screen and alarm notification.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2009년도 춘계학술대회 논문집
• /
• pp.94-97
• /
• 2009

Cast defect in large steel ingots are estimated in quality and compared each other cast conditions on simulation results by now. The cast defects, micro-crack, shrinkage, pin hole which are predictable in simulation with a reasonable accuracy. In this study, 15 ton steel ingot casting was simulated for solidification model and cast defect prediction. And the real cast was carried out in a foundry for the compeer to the simulation results, the cast defect prediction. Also, the quantity of predicted defect was tried to measuring with the defect mach counting for the various simulated cast conditions. The defect quantity work was used to find the optimized cast condition in DOE(design of experiment) procedure.

• 한국주조공학회지
• /
• 제41권6호
• /
• pp.521-527
• /
• 2021

본 연구는 고압 다이캐스팅 공정에서 제품 결함을 사전에 예측하기 위한 기계 학습 기반의 공정 관리 모델 개발에 관한 연구이다. 모델은 이전 사이클에서의 온도를 입력받고, 사이클에 걸쳐서 나타나는 특징을 인식하여 다음 사이클의 결함 발생 여부를 예측한다. 기어 박스 형상에 대하여 제안된 알고리즘을 적용하여, 3 사이클의 정보를 통해서 98 .9%의 정확도와 96.8 %의 재현율로 제품 수축 결함을 사전에 예측하였다.

• 대한기계학회논문집A
• /
• 제35권10호
• /
• pp.1243-1248
• /
• 2011

내부결함은 주조제품의 강도 및 피로 수명에 있어 상당한 영향을 미치기 때문에 주조공정에서 주요 관심사 이다. 일반적으로 내부결함은 응력집중을 발생시키며 균열의 시작점이 되므로 피로 수명과 같은 기계적 거동에 있어 수축공과 같은 결함을 이해하는 것이 중요하다. 본 논문에서는 내부결함을 고려한 인장시편에 대해 피로시험을 수행하고 주조결함을 고려할 때의 특정하중피로노치 계수를 산정하였다. 실제 내부결함은 산업용 CT 장비를 통해서 확인하였으며 확인된 결함은 형상단순화법에 의해 타원체로 단순화 하고 응력해석과 피로해석을 수행하였다. 그 결과 우리가 제안한 방법이 기계적 거동에 있어 내부결함의 영향을 조사하고 피로수명 등을 예측함에 있어 유용함을 확인할 수 있었다.

• 소성∙가공
• /
• 제14권3호
• /
• pp.224-232
• /
• 2005

The high-pressure die-casting is one of the most effective methods to produce a large amount of products in short cycle time. This process, however, has a problem that the gas porosity defect appears easily. The generation of gas porosity is known mainly due to the air entrapment during the injection stage. Most of numerical simulations for the molten metal flow pattern observations have done in the treating of one phase fluid flow but the gas-liquid interface is essentially multi- phase phenomenon. In this paper, the two-phase fluid flow numerical simulation methods have been adapted to predict the gas porosity generations in the molten metal. The accuracy and the usefulness of the new simulation module have been emphasized and verified through some comparison experiments.

• 한국주조공학회지
• /
• 제42권1호
• /
• pp.61-66
• /
• 2022

Hydraulic units are important components of agricultural and construction machinery, and thus require high-quality castings. However, gas defects occurring inside the sand cores of the castings due to the resin used is a problem. This study therefore aimed to develop a casting simulation method that can clarify the gas defect positions. Gas defects are thought to be caused by gas generated after the molten metal fills up the mold cavity. The gas constant is the most effective factor for simulating this gas generated from sand cores. It is calculated by gas generating temperature and analysis of composition in the inert gas atmosphere modified according to the mold filling conditions of molten metal. It is assumed that gases generated from the inside of castings remain if the following formula is established. [Time of occurrence of gas generation] + [Time of occurrence of gas floating] > [Time of occurrence of casting surface solidification] The possibility of gas defects is evaluated by the time of occurrence of gas generation and gas floating calculated using the gas constant. The residual position of generated gases is decided by the closed loops indicating the final solidification location in the casting simulation. The above procedure enables us to suggest suitable casting designs with zero gas defects, without the need to repeat casting tests.

• 한국주조공학회지
• /
• 제42권4호
• /
• pp.209-217
• /
• 2022

본 연구에서는 전통 유기 주조 시 발생하는 미충전 결함을 방지하기 위하여, 주조 공정 조건 선택 방안을 제시하고자 한다. 공정 조건에 따라 발생하는 결함 유무를 학습하여 어떠한 공정 조건이 주어질 때, 결함 발생 여부를 예측하는 인공지능 모델을 개발하고 검증하였다. 이를 응용하여 적합한 공정 조건을 결정하였고, 추가적인 시뮬레이션의 결과를 상호 비교하여 결정된 조건을 검증하였다. 이를 통해 원하는 사형 모델에서 결함을 방지할 수 있는 주조 공정 조건을 결정할 수 있다. 이와 같은 기계학습 및 전통기술 표준화를 통해 향후 전통 유기의 스마트 공방화에 기여할 수 있을 것으로 판단된다.

• 한국주조공학회지
• /
• 제39권1호
• /
• pp.1-6
• /
• 2019

During the casting process, it is possible to minimize shrinkage and blowholes by modifying the casting design. However, it is impossible to eliminate these factors completely. Therefore, mechanical design engineers apply a sufficient safety factor owing to the possibility of insufficient performances of the cast products. In this paper, prediction method of the fatigue life of cast products containing shrinkage is conducted by using CT (computed tomography) and the SSM (shape simplification method), and additional fatigue analyses are carried out. The analysis results are then compared to results from actual experiments on samples with shrinkage defects. It is found to be that the considering actual shrinkage in cast products by means of stress and fatigue analyses is more accurate and effective. It is also considered that the proposed hot spot method provides us a good tool to predict the fatigue lifes of cast product.