In this paper, to improve the optical quality of aspherical plastic lenses for mobile use, the optimal molding conditions that can minimize the phase difference are derived using injection molding simulation, design of experiments, and machine learning. First, factors affecting the phase difference were derived using the design of the experiment method, and a data set was created using the derived factors, followed by the machine learning process. After predicting the model trained using the generated training data as test data and verifying it with the performance evaluation index, the model with the best predictive performance was the random forest model. Therefore, to derive the optimal molding conditions, random forests were used to predict 10,000 random pieces of data. As a result of applying the derived optimal molding conditions to the injection molding simulation, the phase difference of the lens could be reduced by 8.2%.

In this study, we used a numerical analysis program to study the molding conditions that affect the flow rate at the time of injection, using a spiral mold, which is mainly used for the evaluation of the flow rate of plastic resin. The mold temperature, melt temperature, and flow rate are composed of experimental factors. The three plastic forming factors were divided into five to six levels each. Since then, changes in the flow rate temperature were analyzed as the level of each forming factor increased. Experiments showed that all three forming factors increased the filling length of the spiral mold and the temperature of the flow front by a total of 34.53°C, melt temperatures increased the temperature of the flow front by a total of 34.53°C, the temperature increased by the flow rate was 23.5°C, and the temperature increased by the mold temperature was 1.99°C. It was shown that the melt temperature was the largest, followed by the flow rate and mold temperature. It was also possible to check the effect of plastic forming factors on the speed of the flow front.

Warpage of injection molded product is caused by non-uniform shrinkage and residual stress. A method of removing uneven molding shrinkage and residual stress is to remove the defective factor to Uniform cooling of products. Warpages for part designs have been investigated in this study according to the injection molding conditions for amorphous ABS and crystalline PP by the rapid cooling and heating system. Experimental results showed that the crystalline resin was more warped than amorphous resin, Warpages have been observed in the regions of the part, near gate region and flow direction region.

High speed steels (HSS) were used as cutting tools and wear parts, because of high strength, wear resistance, and hardness together with an appreciable toughness and fatigue resistance. Conventional manufacturing process for production of components with HSS was used by casting. The powder metallurgy techniques were currently developed due to second phase segregation of conventional process. The powder injection molding method (PIM) was received attention owing to shape without additional processes. The experimental specimens were manufactured with T42 HSS powders (59 vol%) and polymer (41 vol%). The metal powders were prealloyed water-atomised T42 HSS. The green parts were solvent debinded in normal n-Hexane at for 24 hours and thermal debinded at mixed gas atmosphere for 14 hours. Specimens were sintered in , gas atmosphere and vacuum condition between 1200 and . In result, polymer degradation temperatures about optimum conditions were found at and . After sintering at gas atmosphere, maximum hardness of 310Hv was observed at . Fine and well dispersed carbide were observed at this condition. But relative density was under 90%. When sintering at gas atmosphere, relative density was observed to 94.5% at . However, the low hardness was obtained due to decarbonization by hydrogen. In case of sintering at the vacuum of torr at temperature of , full density and 550Hv hardness were obtained without precipitation of MC and in grain boundary.

Defining the relationship between the quality of injection molded parts and the process condition is very complicate because of lots of factor are involved and each factor has a non-linearity. With the development of CAE(Computer Aided Engineering) technology, the estimation of volumetric shrinkage of injection mold parts is possible by computer simulation even though restricted application. In this research, the Taguchi method and Neural Network applied for finding optimal processing condition. The percent of volumetric shrinkage compared on each case and show neural network can be successfully applied.

A study to analyze and solve problems of plastic injection molding experiment has presented in this paper. We have taken Taguchi's parameter design approach, specifically orthogonal array, and determined the optimal levels of the selected variables through analysis of the experimental results using S/N ratio.