• 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.

• Design & Manufacturing
• /
• v.17 no.4
• /
• pp.72-78
• /
• 2023

Injection molding is a process widely used in various industries because of its high production speed and ease of mass production during the plastic manufacturing process, and the product is molded by injecting molten plastic into the mold at high speed and pressure. Since process conditions such as resin and mold temperature mutually affect the process and the quality of the molded product, it is difficult to accurately predict quality through mathematical or statistical methods. Recently, studies to predict the quality of injection molded products by applying artificial neural networks, which are known to be very useful for analyzing nonlinear types of problems, are actively underway. In this study, structural optimization of neural networks was conducted by applying multi-task learning techniques according to the characteristics of the input and output parameters of the artificial neural network. A structure reflecting the characteristics of each process step was applied to the input parameters, and a structure reflecting the quality characteristics of the injection molded part was applied to the output parameters using multi-tasking learning. Building an artificial neural network to predict the three qualities (mass, diameter, height) of injection-molded product under six process conditions (melt temperature, mold temperature, injection speed, packing pressure, pacing time, cooling time) and comparing its performance with the existing neural network, we observed enhancements in prediction accuracy for mass, diameter, and height by approximately 69.38%, 24.87%, and 39.87%, respectively.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.13 no.3
• /
• pp.131-137
• /
• 2005

Ultra high pressure injection equipment was developed to estimate and analyze the spray characteristics in ultra high pressure injection. Spray patterns were visualized by schlieren method and analyzed in ultra high pressure. Spray tip penetration, spray thickness, spray volume, and entrained air mass increased with the increase of the injection pressure. But over 2,800 bars of the injection pressure region, it was shown that the rate of improvement was not increased remarkably ,and the spray characteristics such as spray penetration, volume, and entrained air mass were reversed and got worse at 4,140 bars.

• International Journal of Automotive Technology
• /
• v.6 no.6
• /
• pp.571-577
• /
• 2005

Combustion of turbulent sprays in a direct injection diesel engine is modeled by the conditional moment closure (CMC) model. The CMC routines are combined with the KIVA code to provide conditional flame structures to determine mean state variables, instead of mean reaction rates. An independent transport equation is solved for each flame group with equal mass of sequentially evaporating fuel vapor. CMC calculation begins as the fuel mass for each flame group begins to evaporate with corresponding initialization conditions. Comparison is made with measured pressure traces for four operating conditions at different rpm's and injection conditions. Results show that the CMC model with multiple flame histories can successfully be applied to ignition and mixing-controlled combustion phases of a diesel engine.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.752-755
• /
• 2003

Injection molding is the one of the most important processes for mass production of plastic parts. Usually Injection molds for mass production are constituted to multi-cavity runner system to manufacture the more parts at a time. To uniformly fill to each cavity, multi-cavity molds are designed to geometrically balanced runner system. However. in practice this is not the case. The previous studies by Beaumount at.[2] reported that filling imbalance occurred by thermal unbalance on the mold and viscosity variation of resins and so on. In this study, we conducted experiments in order to know the causes or filling imbalance for 3 plate type mold with 8 cavities. We presented a new so called 4BF mold(4plate Type Balanced Filling Mold) to improve filling balance. We conducted a experimental injection molding to verify a efficiency of the 4BF mold. In the results of the experiment, We could confirmed the possibility of the 4BF mold.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.85-88
• /
• 1995

Recently, the micro mold maching techining technology is developed by means of the mechanical and high energy beam process. It is possible to make the micro structure mold with high aspect ratio by the LIGA technology. This mode is used for mass production of plastic parts by the micro injection molding method. In this study, we intend to research on the basic technology of micro injection molding. As the result, we developed the injection molding technology for small column plastic parts which diameter is 500 .mu. m and 200 .mu. m respectively with wbout aspect ratio 20.

• 한국전산유체공학회:학술대회논문집
• /
• 1997.10a
• /
• pp.113-119
• /
• 1997

This paper addresses to the injection pressure effect on the diesel spray. The injection pressure is varied from 10MPa, in general system, upto 200MPa, in high pressured system in order to understand the effect. The gas phase is modelled in terms of the Eulerian continuum conservation equations of mass, momentum, energy and fuel vapour fraction. The liquid phase is modelled following the discrete droplet model approach in Lagrangian form. The droplet distributions, vapor fractions and gas flows are analyzed in various injection pressure cases.

• Nuclear Engineering and Technology
• /
• v.42 no.3
• /
• pp.297-304
• /
• 2010

In the design of advanced light water reactors (ALWRs) and in the safety assessment of currently operating nuclear power plants, it is necessary to evaluate the possibility of experiencing a degraded core accident and to develop innovative safety technologies in order to assure long-term debris cooling. The objective of this experimental study is to investigate the enhancement factors of dryout heat flux in debris beds by coolant injection from below. The experimental facility consists mainly of an induction heater, a double-wall quartz-tube test section containing a steel-particle bed and coolant injection and recovery condensing loop. A fairly uniform heating of the particle bed was achieved in the radial direction and the axial variation was within 20%. This paper reports the experimental data for 3.2 mm and 4.8 mm particle beds with a 300 mm bed height. The dryout heat density data were obtained for both the top-flooding and the forced coolant injection from below with an injection mass flux of up to $1.5\;kg/m^2s$. The dryout heat density increased as the rate of coolant injection increased. At a coolant injection mass flux of $1.0\;kg/m^2s$, the dryout heat density was ${\sim}6.5\;MW/m^3$ for the 4.8 mm particle bed and ${\sim}5.6\;MW/m^3$ for the 3.2 mm particle bed. The enhancement factors of the dryout heat density were 1.6-1.8.

• Aerospace Engineering and Technology
• /
• v.5 no.2
• /
• pp.134-142
• /
• 2006

Sub-cooling of cryogenic propellant by helium injection is one of the most effective methods for suppressing bulk boiling and keeping sub-cooled liquid oxygen before rocket launch. In order to design the cooling system, understanding of the limitations of heat and mass transfer is required. In this paper, an analytical model for the helium injection system is presented. This model's main feature is the representation of bubbling system using finite-rate heat transfer and instantaneous mass transfer concept. With this simplified approach, the effect of helium injection to liquid oxygen system under several circumstances is examined. Experimental results along with simulations of single bubble rising in liquid oxygen and bubbling system are presented with various helium injection flow rates, and with change of oxygen chamber pressure.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.4
• /
• pp.456-466
• /
• 2004

An experimental study has been conducted to investigate the flow and heat/mass transfer characteristics within a rectangular film cooling hole of normal injection angle for various blowing ratios and Reynolds numbers. The results are compared with those for the square hole. The experiments have been performed using a naphthalene sublimation method and the flow field has been analyzed by numerical calculation using a commercial code (FLUENT). The heat/mass transfer around the hole entrance region is enhanced considerably due to the reattachment of separated flow and the vortices generated within the hole. At the hole exit region, the heat/mass transfer increases because the main flow induces a secondary vortex. It is observed that the overall heat/mass transfer characteristics are similar to those for the square hole. However, the different heat/mass transfer patterns come out due to increased aspect ratio. Unlike the square hole, the heat/mass transfer on the trailing edge side of hole entrance region has two peak regions due to split flow reattachment, and heat/mass transfer on the hole exit region is less sensitive to the blowing ratios than the square hole.