• Transactions of Materials Processing
• /
• v.28 no.2
• /
• pp.83-88
• /
• 2019

This paper introduces a new concept - on-line FE model, as applied to metal rolling. The new technology allows for completion of process simulation within a tiny fraction of a second without loss of high-level prediction accuracy inherent to FEM. The three steps of an on-line FE model design namely, process metamorphosis, mesh design, and process variable design, are described in detail. The procedure is demonstrated step by step through designing actual on-line models for the prediction of the dog-bone profile in edge rolling. The validity and prediction accuracy of the on-line FE models are analyzed and discussed.

• Transactions of Materials Processing
• /
• v.32 no.6
• /
• pp.352-359
• /
• 2023

Recently, independent suspension systems have been applied not only to passenger cars but also to large commercial vehicles. Therefore, the need for research to domestically produce such independent suspensions for large commercial vehicles is gradually increasing. In this paper, we conducted research on the manufacturing technology of the relay lever, which are integral components of independent suspension systems for large commercial vehicles. Our goal was to reduce the flash volume generated during the forging process. The shape variables of the initial billet were adjusted to find proper forming conditions that could minimize flash volume while performing product forming smoothly. Shape variables were set as input variables and the flash volume was set as an output variable, and simulations were carried out to analytically predict the volume of the flash area for each variable condition. Based on the data obtained through numerical simulations, a regression model and an artificial neural network model were used to develop a prediction model that can easily predict the flash volume for variable conditions. For the corresponding prediction model, a goodness of-fit test was performed to confirm a high level of fit. By comparing and analyzing the two prediction models, the high level of fit of the ANN model was confirmed.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.8 no.1
• /
• pp.31-40
• /
• 1983

An uncertain dynamic evolving process has been a continuing challenge to decision problems. The dynamic random variable (drv) changes which characterize such a process are very important for the decision-maker in selecting a course of action in a world that is perceived as uncertain, complex, and dynamic. Using this subjective point prediction algorithm based on a modified recursive filter, the decision-maker becomes to have periodically changing plausible points with the passage of time.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.344-349
• /
• 1990

Under the assumption that process input/output data are sufficiently rich to allow reasonable plant identification, a long-range predictive control method for SISO bilinear plant is derived. In order to ensure offset-free behaviour of the control method, a new bilinear CARIMA model with variable dead-time is introduced. Furthermore, to extend the maximum output prediction horizon, the future predicted outputs in the bilinear term are assumed to be equal to the known future set-points. With a classical recursive adaptation algorithm, the proposed control scheme is capable of stable control of bilinear plants with variable parameters, with variable dead-time, and with a model order which changes instantaneously. Several simulation results demonstrate the characteristics of the proposed bilinear model predictive control method.

• Journal of Korean Society for Quality Management
• /
• v.52 no.2
• /
• pp.185-199
• /
• 2024

Purpose: The improvement of yield and quality in product manufacturing is crucial from the perspective of process management. Controlling key variables within the process is essential for enhancing the quality of the produced items. In this study, we aim to identify key variables influencing product defects and facilitate quality enhancement in CNC machining process using SHAP(SHapley Additive exPlanations) Methods: Firstly, we conduct model training using boosting algorithm-based models such as AdaBoost, GBM, XGBoost, LightGBM, and CatBoost. The CNC machining process data is divided into training data and test data at a ratio 9:1 for model training and test experiments. Subsequently, we select a model with excellent Accuracy and F1-score performance and apply SHAP to extract variables influencing defects in the CNC machining process. Results: By comparing the performances of different models, the selected CatBoost model demonstrated an Accuracy of 97% and an F1-score of 95%. Using Shapley Value, we extract key variables that positively of negatively impact the dependent variable(good/defective product). We identify variables with relatively low importance, suggesting variables that should be prioritized for management. Conclusion: The extraction of key variables using SHAP provides explanatory power distinct from traditional machine learning techniques. This study holds significance in identifying key variables that should be prioritized for management in CNC machining process. It is expected to contribute to enhancing the production quality of the CNC machining process.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2004.08a
• /
• pp.359-367
• /
• 2004

In this research on-line model for the prediction of the effective strain distribution in strip on finishing mill process is presented. To describe the effective strain distribution in strip, three guide points and a distribution fitting variable are used. On-line models to get these points and fitting variable non-dimensionalization method and least square method were used with FEM simulation results. The model is developed using strip only FEM simulation as reference sets and compared with roll coupled FEM simulation results as perturbed sets. The on-line model to describe effective strain distribution shows good agreement with coupled FEM analysis results.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1343-1346
• /
• 2005

In the cold rolling mill, coil breakage that generated in rolling process makes the various types of troubles such as the degradation of productivity and the damage of equipment. Recent researches were done by the mechanical analysis such as the analysis of roll chattering or strip inclining and the prevention of breakage that detects the crack of coil. But they could cover some kind of breakages. The prediction of Coil breakage was very complicated and occurred rarely. We propose to build effective prediction modes for coil breakage in rolling process, based on data mining model. We proposed three prediction models for coil breakage: (1) decision tree based model, (2) regression based model and (3) neural network based model. To reduce model parameters, we selected important variables related to the occurrence of coil breakage from the attributes of coil setup by using the methods such as decision tree, variable selection and the choice of domain experts. We developed these prediction models and chose the best model among them using SEMMA process that proposed in SAS E-miner environment. We estimated model accuracy by scoring the prediction model with the posterior probability. We also have developed a software tool to analyze the data and generate the proposed prediction models either automatically and in a user-driven manner. It also has an effective visualization feature that is based on PCA (Principle Component Analysis).

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.4
• /
• pp.1007-1018
• /
• 2008

The purpose of this case study is to demonstrate database-marketing management. First, we explore original variables for insurance customer's data, modify them if necessary, and go through variable selection process before analysis. Then, we develop churn prediction models using logistic regression, neural network and SVM analysis. We also compare these three data mining models in terms of misclassification rate.

• Proceedings of the Korean Reliability Society Conference
• /
• 2000.04a
• /
• pp.213-222
• /
• 2000

In present study, a stochastic model is developed for the low cycle fatigue life prediction and reliability assessment of 316L stainless steel under variable multiaxial loading. In the proposed model, fatigue phenomenon is considered as a Markov process, and damage vector and reliability are defined on every plane. Any low cycle fatigue damage evaluating method can be included in the proposed model. The model enables calculation of statistical reliability and crack initiation direction under variable multiaxial loading, which are generally not available. In present study, a critical plane method proposed by Kandil et al., maximum tensile strain range, and von Mises equivalent strain range are used to calculate fatigue damage. When the critical plane method is chosen, the effect of multiple critical planes is also included in the proposed model. Maximum tensile strain and von Mises strain methods are used for the demonstration of the generality of the proposed model. The material properties and the stochastic model parameters are obtained from uniaxial tests only. The stochastic model made of the parameters obtained from the uniaxial tests is applied to the life prediction and reliability assessment of 316L stainless steel under variable multiaxial loading. The predicted results show good accordance with experimental results.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.7 no.9
• /
• pp.48-55
• /
• 1999

In this paper, a zero-dimensional two zone model is developed to investigate the effects of variable valve timing on combustion process in SI engine. The simulation results show that the predicted data has good agreement with experimental ones. The useful information of combustion process such like residual gas fraction cylinder pressure, cylinder temperature and NO concentration can be obtained and the effects of engine variables on combustion processes and performances can be evaluated.