• Journal of the Korean Data and Information Science Society
• /
• 제19권2호
• /
• pp.609-620
• /
• 2008

There may be several parallel equipments having the same function in a multi-stage manufacturing process, which affect the product quality differently and have significant differences in defect rate. The product quality may depend on what equipments it has been processed as well as what process variable values it has. Applying one model ignoring the presence of different equipments may distort the prediction of defect rate and the identification of important quality variables affecting the defect rate. We propose a procedure for data segmentation when constructing models for predicting the defect rate or for identifying major process variables influencing product quality. The proposed procedure is based on the principal component analysis and the analysis of variance, which demonstrates a better performance in predicting defect rate through a case study with a PDP manufacturing process.

• 한국기계가공학회지
• /
• 제7권4호
• /
• pp.155-160
• /
• 2008

End part of the brake tube formed with the shape of snake head is important for the braking of automobile in safety because it has to prevent crack, fracture and defects occurred during the forming process. Especially, the shape of tube end has influence on the ability of brake. Based on the procedure of process design, in this paper, the forming operation is done by finite element method and the design variables are analyzed by Taguchi method. Design variables such as the outer angle of tube end with the shape of snake head(A), the inner angle to make a hole at tube end with the shape of snake head(B) and the forming distance at tube end(C) are used. Optimization of design variables is performed to minimize the damage factor of the tube end occurred during the forming process. The value of damage factor of 0.327 was obtained under the optimal condition like $A=114^{\circ},\;B=80^{\circ}$ and C=5.3mm, respectively.

• 한국시뮬레이션학회논문지
• /
• 제7권2호
• /
• pp.137-152
• /
• 1998

One of the components that constitute the simulation models is the state variables whose values are determined by the time related simulation process. Embedding rule-based expert systems into the simulation models should provide a systematic way of handling these time-dependent variables without distracting the essential problem solving capabilities of the expert systems which are well suited for expressing the decision making function of complex cases. The expert system, however, is inefficient in dealing with the time elapsing characteristics of target system compare to the simulation models. To solve the problem, this paper provides an interruptible inference engine whose inferencing process can be interrupted when the variables' value, which are used as the parameters of the rules, are not yet determined due to the time dependent nature of the state variables. The process is resumed when the variables are ready. The elapse of time is calculated by time-advance function of the simulation model to which the expert system has been embedded. The example modeling shown exploits the embedded interruptible inferencing capability for the controlling and monitoring of metal grating process.

• 산업경영시스템학회지
• /
• 제44권4호
• /
• pp.12-22
• /
• 2021

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F₁-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

• 한국생산제조학회지
• /
• 제24권4호
• /
• pp.407-413
• /
• 2015

Research for renewable energy is being performed since it has the merits of little pollution of the environment and sustainable energy resources. Microalgae is attractive as a renewable energy resource. Biomass of the microalgae can be produced by mass culturing, and bulk harvest technology of is needed to produce biomass continuously. Recently, ultrasonic waves were used to harvest the cultivated microalgae continuously. In this study, the separation process using ultrasonic waves was performed to effectively harvest the microalgae. An ultrasonic wave separation resonator was designed and manufactured based on the acoustic field analysis. Separation experiments using design of experiment were carried out, and the influence of experimental variables from the ultrasonic wave separation process was investigated. Mixing conditions of variables were estimated to obtain high separation efficiency and a large microalgae harvest. Experimental results for suitable mixing conditions were compared with simulation results calculated from the state equation.

• 산업경영시스템학회지
• /
• 제30권2호
• /
• pp.99-105
• /
• 2007

According to the automated manufacturing processes followed by the development of computer manufacturing technologies, products or quality characteristics produced on the processes have measured and recorded automatically. Much amount of data daily produced on the processes may not be efficiently analyzed by current statistical methodologies (i.e., statistical quality control and statistical process control methodologies) because of the dimensionality associated with many input and response variables. Although a number of statistical methods to handle this situation, there is room for improvement. In order to overcome this limitation, we integrated data mining and robust design approach in this research. We find efficiently the significant input variables that connected with the interesting response variables by using the data mining technique. And we find the optimum operating condition of process by using RSM and robust design approach.

• 산업경영시스템학회지
• /
• 제32권2호
• /
• pp.132-139
• /
• 2009

Yield is a very important measure that can expresses simply for productivity and performance of company. So, yield is used widely in many industries nowadays. With the development of the information technology and online based real-time process monitoring technology, many industries operate the production lines that are developed into automation system. In these production lines, the product structures are very complexity and variety. So, there are many multi-variate processes that need to be monitored with many quality characteristics and associated process variables at the same time. These situations have made it possible to obtain super-large manufacturing process data sets. However, there are many difficulties with finding the cause of process variation or useful information in the high capacity database. In order to solve this problem, neural networks technique is a favorite technique that predicts the yield of process for process control. This paper uses a neural networks technique for improvement and maintenance of yield in manufacturing process. The purpose of this paper is to model the prediction of a sub process that has much effect to improve yields in total manufacturing process and the prediction of adjustment values of this sub process. These informations feedback into the process and the process is adjusted. Also, we show that the proposed model is useful to the manufacturing process through the case study.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1998년도 추계학술대회 논문집
• /
• pp.118-121
• /
• 1998

We present an early result of a research for formalization of the characteristics and effectiveness of manufacturing performance measurement systems (PMS). Recently manufacturing PMS has been a focus of broad research efforts due to its practical role playing in managers' decision making process. There have been so many suggestive researches that explain the troubles with old cost accounting-based PMS and describe the desirable properties of PMS in strategic management of manufacturing operations. The lack of empirical investigation in this area, however, has left us unsure about what are the real characteristics that distinguish one PMS from another. In this paper, we propose a conceptual framework that can be used to describe the environment, in which a specific PMS works, the characteristic and the utilization variables of a PMS. Then we report the result of a field survey, where we found three distinctive characteristics of a PMS, contents, vertical integration, and horizontal integration. Further, we discuss the relationships of the variables with the utilization of PMS, manufacturing strategy, manufacturing improvement programs, and business performance.

• 한국기계가공학회지
• /
• 제18권8호
• /
• pp.51-59
• /
• 2019

Flow forming is an eco-friendly and high-efficiency plastic deformation process with fewer chips during a process which is specifically used to manufacture seamless tubular products like tire wheels, rocket motor cases etc. On the development of mortar barrel using Inconel718 tube, some flow formed products had dimensional errors on their thickness. In this study, our purpose is to optimize the process conditions with the smallest dimensional error. In order to find an optimum process condition, 2D axisymmetric FEM simulation analyses with Taguchi method were conducted. Geometric variables (attack angle, flatting angle, roller nose radius) and operating parameters (depth of forming, feed rate) are considered as control factors. Forward flow forming with single roller was first analyzed to determine the effective factors using AFDEX software and attack angle of the roller was identified as the most influential factor. Also, the nose radius of the rollers was confirmed as a significant factor in multi-rollers flow forming system. The effect of rollers offset values are also studied and finally, we proposed optimal conditions to improve the accuracy of flow forming process with Inconel718 tube for mortar barrel manufacturing.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2004년도 품질경영모델을 통한 가치 창출
• /
• pp.513-516
• /
• 2004

Evolutionary operation is useful to improve on-line full-scale manufacturing processes by systematically changing the levels of the process variables while meeting production schedule. Evolutionary operation was developed using two or three process variables for process operators who are not good at statistics. Recently, when a product is developed, it is very important for the engineers to make the production line stable as soon as possible. And there are many causes which have influences to the product performance. This paper presents an evolutionary operation procedure with many process variables using saturated two level fractional factorial designs including Plackett-Burman design.