인공신경망 구조에 따른 사출 성형폼 품질의 예측성능 차이에 대한 비교 연구
A study on the comparison of the predicting performance of quality of injection molded product according to the structure of artificial neural network
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The quality of products produced by injection molding process is greatly influenced by the process variables set on the injection molding machine during manufacturing. It is very difficult to predict the quality of injection molded product considering the stochastic nature of manufacturing process, because the process variables complexly affect the quality of the injection molded product. In the present study we predicted the quality of injection molded product using Artificial Neural Network (ANN) method specifically from Multiple Input Single Output (MISO) and Multiple Input Multiple Output (MIMO) perspectives. In order to train the ANN model a systematic plan was prepared based on a combination of orthogonal sampling and random sampling methods to represent various and robust patterns with small number of experiments. According to the plan the injection molding experiments were conducted to generate data that was separated into training, validation and test data groups to optimize the parameters of the ANN model and evaluate predicting performance of 4 structures (MISO1-2, MIMO1-2). Based on the predicting performance test, it was confirmed that as the number of output variables were decreased, the predicting performance was improved. The results indicated that it is effective to use single output model when we need to predict the quality of injection molded product with high accuracy.
Abstract
The quality of products produced by injection molding process is greatly influenced by the process variables set on the injection molding machine during manufacturing. It is very difficult to predict the quality of injection molded product considering the stochastic nature of manufacturing process, because the process variables complexly affect the quality of the injection molded product. In the present study we predicted the quality of injection molded product using Artificial Neural Network (ANN) method specifically from Multiple Input Single Output (MISO) and Multiple Input Multiple Output (MIMO) perspectives. In order to train the ANN model a systematic plan was prepared based on a combination of orthogonal sampling and random sampling methods to represent various and robust patterns with small number of experiments. According to the plan the injection molding experiments were conducted to generate data that was separated into training, validation and test data groups to optimize the parameters of the ANN model and evaluate predicting performance of 4 structures (MISO1-2, MIMO1-2). Based on the predicting performance test, it was confirmed that as the number of output variables were decreased, the predicting performance was improved. The results indicated that it is effective to use single output model when we need to predict the quality of injection molded product with high accuracy.
참고문헌 (17)
- Xuehong, L., "A Statictical Experiment Study of the Injection Molding of Optical Lenses", J. Mater. Process. Technol., 113(1-3), pp.189~195 (2001)
- Gevrey, M., "Review and Comparison of Methods to Study the Contribution of Variables in Artificial Neural Network Models", Ecol. Modell., 160(3), pp.249~264 (2003)
- Choi, G. H., "Optimization of Process Parameters of Injection Molding with Neural Network Application in a Process Simulation Environment", Ann. CIRP, 43(1), pp.449~452 (1994)
- Yarlagadda, P. K., "Development of Hybrid Neural Network System for Prediction of Process Parameters in Injection Moulding", J. Mater. Process. Technol, 118(1), pp.109~115 (2001)
- Kenig, S., "Control of Properties in Injection Molding by Neural Networks", Eng. Appl. Artif. Intell., 14(6), pp.819~823 (2001)
- Lau, H. C. W., "Neural Networks for the Dimensional Control of Molded Parts based on Reverse Process Model", J. Mater. Process. Technol., 117(1), pp.89~96 (2001)
- Manjunath, P. G., "Prediction and Optimization of Dimensional Shrinkage Variations in Injection Molded Parts using Forward and Reverse Mapping of Artificial Neural Networks", Adv. Mater. Res., 463, pp.674~678 (2012)
- Liao, S. J., "Shrinkage and Warpage Prediction of Injection Molded Thin Wall Parts using Artificial Neural Networks", Polym. Eng. Sci., 44(11), pp.2029~2040 (2004)
- Chang, F. J., "Multi-step-ahead Neural Networks for Flood Forecasting", Hydrol. Sci. J., 52(1), pp.114~130 (2007)
- Petlenkov, E., "Neural Networks based Identification and Control of Nonlinear Systems : ANARX Model Based Approach", Tallinn University of Technology, Estonia, pp.67~69 (2007)
- Shen, C., "Optimization of Injection Molding Proces Parameters Using Combination of Artifcial Neural Network and Genetic Algorithm Method", J. Mater. Proces. Technol., 183(2-3), pp.412~418 (2007)
- Altan, M., "Reducing Shrinkage in Injection Moldings via the Taguchi, ANOVA and Neural Network Methods", Mater. Des., 31(1), pp.59~604 (2010)
- Solvason, C. C, "Efficient Visual Mixture Design of Experiments Using Property Clustering Techniques", Ind. Eng. Chem. Res., 48(4), pp.245~256 (2009)
- Leaman, R., "Disease Name Normalization with Pairwise Learning to Rank", Bioinf, 29(22), pp.2909~2917 (2013)
- Goldberg, Y., "Neural Network Methods for Natural Language Processing", Synth. Lect. Hum. Lang. Technol., 10(1), pp.1~309 (2017)
- Selvaraj, R, "Neural networks for the identification of MSF desalination plants", Desalin, 101(2), pp.185~193 (1995)
- Li, L, "Hyperband : A Novel Bandit-Based Approach to Hyperparameter Optimization", J. Mach. Learn. Res., 18(1), pp.1~52 (2018)