• Transactions of Materials Processing
• /
• v.16 no.6
• /
• pp.479-487
• /
• 2007

Die life is generally estimated taking failure life and wear amount into consideration. In this study, the forging die life was investigated considering both of these two factors. The fatigue life prediction for the die was performed using the stress-life method, i.e. Goodman's and Gerber's equations. The Archard's wear model was used in the wear life simulation. These die life prediction techniques were applied to the die used in the forging process of the socket ball joint of a transportation system. A rigid-plastic finite element analysis for the die forging process of the socket ball was carried out and also the elastic stress analysis for the die set was performed in order to get basic data for the die fatigue life prediction. The wear volume of the die was measured using a 3-dimensional measurement apparatus. The simulation results were relatively in good agreement with the experimental measurements.

• Journal of the Korean Society of Safety
• /
• v.11 no.2
• /
• pp.122-127
• /
• 1996

The purpose of this study has been studied and investigated to prediction algorithms of the Kalman Filtering theory which are based on the state-vector description, including system identification, model structure determination, parameter estimation. And the prediction algorithms applied of rainfall-runoff process, has been worked out. The analysis of runoff process and runoff prediction algorithms of the river-basin established, for the verification of prediction algorithms by the Kalman Filtering theory, the observed historical data of the hourly rainfall and streamflows were used for the algorithms. In consisted of the above, Kalman Filtering rainfall-runoff model applied and analysised to Wi-Stream basin in Nak-dong River(Basin area : $472.53km^2$).

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.9
• /
• pp.100-105
• /
• 2019

In wire drawing, aterial deformation is concentrated on the surface of the drawn wire because of surface contact with the drawing die. Therefore, strain varies from the center to the surface of the drawn wire. In this study, based on the upper bound method, an effective strain prediction method from the center to the surface of a drawn wire was proposed. Using the proposed method, the effective strain of the drawn wire was calculated verify the proposed prediction method, the predicted effective strain was compared with the result of finite element analysis.

• The Journal of Korea Robotics Society
• /
• v.16 no.3
• /
• pp.283-290
• /
• 2021

We propose a task and motion planning algorithm for clearing obstacles and wiping surfaces, which is essential for surface disinfection during the pathogen disinfection process. The proposed task and motion planning algorithm determines task parameters such as grasping pose and placement location during the planning process without using pre-specified or discretized values. Furthermore, to quickly inspect many unit motions, we propose a motion feasibility prediction algorithm consisting of collision checking and an SVM model for inverse mechanics and self-collision prediction. Planning time analysis shows that the feasibility prediction algorithm can significantly increase the planning speed and success rates in situations with multiple obstacles. Finally, we implemented a hierarchical control scheme to enable wiping motion while following a planner-generated joint trajectory. We verified our planning and control framework by conducted an obstacle-clearing and surface wiping experiment in a simulated disinfection environment.

• Korean Chemical Engineering Research
• /
• v.54 no.5
• /
• pp.606-611
• /
• 2016

Carbon dioxide injection is a widely known method of enhanced oil recovery (EOR). It is critical for the $CO_2$ EOR that the injected $CO_2$ to reach a condition fully miscible with oil. To reach the miscible point, a certain level of pressure is required, which is known as minimum miscibility pressure (MMP). In this study, a MMP prediction method using a process simulator is proposed. To validate the results of the simulation, those are compared to a slim tube experiment and several empirical correlations of previous literatures. Aspen HYSYS is utilized as the process simulator to create a model of $CO_2$/crude oil encounter. The results of the study show that the process simulator model is capable of predicting MMP and comparable to other published methods.

• Journal of Computational Design and Engineering
• /
• v.3 no.1
• /
• pp.63-70
• /
• 2016

Deep drawing is a forming process in which a blank of sheet metal is radially drawn into a forming die by the mechanical action of a punch and converted to required shape. Deep drawing involves complex material flow conditions and force distributions. Radial drawing stresses and tangential compressive stresses are induced in flange region due to the material retention property. These compressive stresses result in wrinkling phenomenon in flange region. Normally blank holder is applied for restricting wrinkles. Tensile stresses in radial direction initiate thinning in the wall region of cup. The thinning results into cracking or fracture. The finite element method is widely applied worldwide to simulate the deep drawing process. For real-life simulations of deep drawing process an accurate numerical model, as well as an accurate description of material behavior and contact conditions, is necessary. The finite element method is a powerful tool to predict material thinning deformations before prototypes are made. The proposed innovative methodology combines two techniques for prediction and optimization of thinning in automotive sealing cover. Taguchi design of experiments and analysis of variance has been applied to analyze the influencing process parameters on Thinning. Mathematical relations have been developed to correlate input process parameters and Thinning. Optimization problem has been formulated for thinning and Genetic Algorithm has been applied for optimization. Experimental validation of results proves the applicability of newly proposed approach. The optimized component when manufactured is observed to be safe, no thinning or fracture is observed.

• Transactions of Materials Processing
• /
• v.29 no.4
• /
• pp.218-228
• /
• 2020

The prediction of final mass and optimized process conditions of injection molded products using Artificial Neural Network (ANN) were demonstrated. The ANN was modeled with 10 input parameters and one output parameter (mass). The input parameters, i.e.; melt temperature, mold temperature, injection speed, packing pressure, packing time, cooling time, back pressure, plastification speed, V/P switchover, and suck back were selected. To generate training data for the ANN model, 77 experiments based on the combination of orthogonal sampling and random sampling were performed. The collected training data were normalized to eliminate scale differences between factors to improve the prediction performance of the ANN model. Grid search and random search method were used to find the optimized hyper-parameter of the ANN model. After the training of ANN model, optimized process conditions that satisfied the target mass of 41.14 g were predicted. The predicted process conditions were verified through actual injection molding experiments. Through the verification, it was found that the average deviation in the optimized conditions was 0.15±0.07 g. This value confirms that our proposed procedure can successfully predict the optimized process conditions for the target mass of injection molded products.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.9
• /
• pp.90-96
• /
• 2021

As real-time data of factories can be collected using various sensors, the adaptation of intelligent unmanned processing systems is spreading via the establishment of smart factories. In intelligent unmanned processing systems, data are collected in real time using sensors. The equipment is controlled by predicting future situations using the collected data. Particularly, a technology for the prediction of tool wear and for determining the exact timing of tool replacement is needed to prevent defected or unprocessed products due to tool breakage or tool wear. Directly measuring the tool wear in real time is difficult during the cutting process in milling. Therefore, tool wear should be predicted indirectly by analyzing the cutting load of the main spindle, current, vibration, noise, etc. In this study, data from the current and acceleration sensors; displacement data along the X, Y, and Z axes; tool wear value, and shape change data observed using Newroview were collected from the high-speed, two-edge, flat-end mill machining process of SKD11 steel. The support vector machine technique (machine learning technique) was applied to predict the amount of tool wear using the aforementioned data. Additionally, the prediction accuracies of all kernels were compared.

• Design & Manufacturing
• /
• v.16 no.3
• /
• pp.1-8
• /
• 2022

In this study, an artificial neural network(ANN) was constructed to establish the relationship between process condition prameters and the qualities of the injection-molded product in the injection molding process. Six process parmeters were set as input parameter for ANN: melt temperature, mold temperature, injection speed, packing pressure, packing time, and cooling time. As output parameters, the mass, nominal diameter, and height of the injection-molded product were set. Two learning structures were applied to the ANN. The single-task learning, in which all output parameters are learned in correlation with each other, and the multi-task learning structure in which each output parameters is individually learned according to the characteristics, were constructed. As a result of constructing an artificial neural network with two learning structures and evaluating the prediction performance, it was confirmed that the predicted value of the ANN to which the multi-task learning structure was applied had a low RMSE compared with the single-task learning structure. In addition, when comparing the quality specifications of injection molded products with the prediction values of the ANN, it was confirmed that the ANN of the multi-task learning structure satisfies the quality specifications for all of the mass, diameter, and height.

• Journal of KIISE:Software and Applications
• /
• v.30 no.10
• /
• pp.983-991
• /
• 2003

The Web-based instruction on the internet provides lots of learners with the related information and knowledge beyond time and space. But in the Web-based instruction, there is a problem that the teaming process statuses for learners can be known only through an exam. This paper introduces a web monitoring method to check whether the learner has some problems in learning process and to be able to find out the students with the problems. In the method this paper proposes a learning time prediction model for predicting the proper next study time intervals based on the learner`s learning times and grades on Previous learning units. This method provides the educator with the learning Process statuses for learners. The Loaming prediction model for web-based monitoring can be used to stimulate learners to take the good teaming processes by sending automatically alerting messages if their real teaming times exceeds on his predicted learning time interval. The results of the estimation through case study on the web-based monitoring to use the teaming time prediction model show that most of on-line learners with Poor teaming process statuses get poor grades. In addition, the results show that learner`s poor habits keep going on without change.