Jongsun Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jongsun Kim has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Junhan Lee
Molding & Metal Forming R & D Department, Korea Institute of Industrial Technology, Bucheon 14442, Republic of Korea
3 shared publications - Dongcheol Yang
Department of Mechanical Engineering, Dankook University, Yongin 16890, Korea
2 shared publications - Jongsu Kim
Molding & Metal Forming R&D Department, Korea Institute of Industrial Technology, Bucheon 14441, Korea
2 shared publications - Kyunghwan Yoon
Department of Mechanical Engineering, Dankook University, Yongin 16890, Korea
2 shared publications - Chul Jin Hwang
Korea Institute of Industrial Technology (KITECH), Gyeonggi‐Do 420‐734, Korea
1 shared publication - Gu Young Cho
Department of Mechanical Engineering, Dankook University
1 shared publication
Latest Publications
- Open Access
- 20 March 2026
- Published by Oxford University Press (OUP) in Journal of Computational Design and Engineering
- Vol. 13 (4) , 67-81
Analysis of geometric feature importance for enhancing performance of injection-moulding simulation surrogate model
Injection-moulding computer-aided engineering simulation is a numerical analysis process with high computational costs, presenting limitations for direct application to real-time simulation-based digital twin technology. To overcome these limitations, this study proposes an accelerated surrogate model that ensures generalisation performance for unseen geometries and process conditions within the same product family, and conducts a feature importance analysis for model interpretability. The model was trained using simulation data generated by randomly sampled combinations of six injection-moulding process conditions across various toothbrush geometries. In addition, seven geometric features based on distance, area, volume, thickness, and curvature were utilised as input features to effectively represent the characteristics of the product geometry. The surrogate model was constructed using a graph attention network that integrates an attention mechanism with a message-passing structure. The proposed model was applied to predict unseen product geometries and process conditions that were not included in the training dataset. The model achieved normalised root mean square errors (NRMSE) of 0.0125, 0.0451, 0.0712, and 0.0373 for fill time, the temperature at the end of filling, the pressure at the velocity-to-pressure switchover point, and the average of the three directional deflection components, respectively, averaged over 400 unseen process-condition combinations. In terms of the average acceleration performance across the four toothbrush geometries, the unseen product geometry preprocessing accounted for approximately 20.68% of the computation time of the conventional simulation, whereas prediction time for unseen process conditions required on average only approximately 0.14%. In addition, the importance of the geometric features for the prediction accuracy of each physical quantity was analysed using permutation feature importance. Based on this analysis, key geometric features were identified, and an ablation study was conducted to further examine their influence on the prediction of injection-moulding physical quantities. These results provide useful insights into geometric feature selection for injection-moulding surrogate models.
- 20 March 2026
- Published by Oxford University Press (OUP) in Journal of Computational Design and Engineering
- Vol. 13 (4) , 67-81
Open AccessAnalysis of geometric feature importance for enhancing performance of injection-moulding simulation surrogate model
Injection-moulding computer-aided engineering simulation is a numerical analysis process with high computational costs, presenting limitations for direct application to real-time simulation-based digital twin technology. To overcome these limitations, this study proposes an accelerated surrogate model that ensures generalisation performance for unseen geometries and process conditions within the same product family, and conducts a feature importance analysis for model interpretability. The model was trained using simulation data generated by randomly sampled combinations of six injection-moulding process conditions across various toothbrush geometries. In addition, seven geometric features based on distance, area, volume, thickness, and curvature were utilised as input features to effectively represent the characteristics of the product geometry. The surrogate model was constructed using a graph attention network that integrates an attention mechanism with a message-passing structure. The proposed model was applied to predict unseen product geometries and process conditions that were not included in the training dataset. The model achieved normalised root mean square errors (NRMSE) of 0.0125, 0.0451, 0.0712, and 0.0373 for fill time, the temperature at the end of filling, the pressure at the velocity-to-pressure switchover point, and the average of the three directional deflection components, respectively, averaged over 400 unseen process-condition combinations. In terms of the average acceleration performance across the four toothbrush geometries, the unseen product geometry preprocessing accounted for approximately 20.68% of the computation time of the conventional simulation, whereas prediction time for unseen process conditions required on average only approximately 0.14%. In addition, the importance of the geometric features for the prediction accuracy of each physical quantity was analysed using permutation feature importance. Based on this analysis, key geometric features were identified, and an ablation study was conducted to further examine their influence on the prediction of injection-moulding physical quantities. These results provide useful insights into geometric feature selection for injection-moulding surrogate models.
- 10 December 2025
- Published by Springer Nature in International Journal of Precision Engineering and Manufacturing
- Vol. 27 (3) , 993-1004
Gradient-Based ANN for Fine-Mesh Fill Time and Temperature Prediction From Coarse-Mesh in AI-Accelerated CAE Analysis of Injection Molding
- 10 December 2025
- Published by Springer Nature in International Journal of Precision Engineering and Manufacturing
- Vol. 27 (3) , 993-1004
Gradient-Based ANN for Fine-Mesh Fill Time and Temperature Prediction From Coarse-Mesh in AI-Accelerated CAE Analysis of Injection Molding
- Open Access
- 30 November 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (23) , 12876
The Effect of Grouping Output Parameters by Quality Characteristics on the Predictive Performance of Artificial Neural Networks in Injection Molding Process
In this study, a multi-input, multi-output-based artificial neural network (ANN) was constructed by classifying output parameters into different groups, considering the physical meanings and characteristics of product quality factors in the injection molding process. Injection molding experiments were conducted for bowl products, and a dataset was established. Based on this dataset, an ANN model was developed to predict the quality of molded products. The input parameters included melt temperature, mold temperature, packing pressure, packing time, and cooling time. The output parameters included mass, diameter, and height of the molded product. The output parameters were divided into two cases. In one case, diameter, and height, representing length, were grouped together, while mass was organized into a separate group. In the other case, mass, diameter and height were separated individually and applied to the ANN. A multi-task learning method was used to group the output parameters. The performance of the two constructed multi-task learning-based ANNs was compared with that of the conventional ANN where the output parameters were not separated and applied to a single layer. The comparative results showed that the multi-task learning architecture, which grouped the output parameters considering the physical meaning and characteristics of the quality of molded products, exhibited an improved prediction performance of about 32.8% based on the RMSE values.
- 30 November 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (23) , 12876
Open AccessThe Effect of Grouping Output Parameters by Quality Characteristics on the Predictive Performance of Artificial Neural Networks in Injection Molding Process
In this study, a multi-input, multi-output-based artificial neural network (ANN) was constructed by classifying output parameters into different groups, considering the physical meanings and characteristics of product quality factors in the injection molding process. Injection molding experiments were conducted for bowl products, and a dataset was established. Based on this dataset, an ANN model was developed to predict the quality of molded products. The input parameters included melt temperature, mold temperature, packing pressure, packing time, and cooling time. The output parameters included mass, diameter, and height of the molded product. The output parameters were divided into two cases. In one case, diameter, and height, representing length, were grouped together, while mass was organized into a separate group. In the other case, mass, diameter and height were separated individually and applied to the ANN. A multi-task learning method was used to group the output parameters. The performance of the two constructed multi-task learning-based ANNs was compared with that of the conventional ANN where the output parameters were not separated and applied to a single layer. The comparative results showed that the multi-task learning architecture, which grouped the output parameters considering the physical meaning and characteristics of the quality of molded products, exhibited an improved prediction performance of about 32.8% based on the RMSE values.
- Open Access
A Study on the Architecture of Artificial Neural Network Considering Injection-Molding Process Steps
In this study, an artificial neural network (ANN) was established to predict product properties (mass, diameter, height) using six process conditions of the injection-molding process (melt temperature, mold temperature, injection speed, packing pressure, packing time, and cooling time) as input parameters. The injection-molding process consists of continuous sequential stages, including the injection stage, packing stage, and cooling stage. However, the related research tends to have an insufficient incorporation of structural characteristics based on these basic process stages. Therefore, in order to incorporate these process stages and characteristics into the ANN, a process-based multi-task learning technique was applied to the connection between the input parameters and the front-end of the hidden layer. This resulted in the construction of two network structures, and their performance was evaluated by comparing them with the typical network structure. The results showed that a multi-task learning architecture that incorporated process-level specific structures in the connections between the input parameters and the front end of the hidden layer yielded relatively better root mean square errors (RMSEs) values than a conventional neural network architecture, by as much as two orders of magnitude. Based on these results, this study has provided guidance for the construction of artificial neural networks for injection-molding processes that incorporates process-stage specific features and structures in the architecture.
Open AccessA Study on the Architecture of Artificial Neural Network Considering Injection-Molding Process Steps
In this study, an artificial neural network (ANN) was established to predict product properties (mass, diameter, height) using six process conditions of the injection-molding process (melt temperature, mold temperature, injection speed, packing pressure, packing time, and cooling time) as input parameters. The injection-molding process consists of continuous sequential stages, including the injection stage, packing stage, and cooling stage. However, the related research tends to have an insufficient incorporation of structural characteristics based on these basic process stages. Therefore, in order to incorporate these process stages and characteristics into the ANN, a process-based multi-task learning technique was applied to the connection between the input parameters and the front-end of the hidden layer. This resulted in the construction of two network structures, and their performance was evaluated by comparing them with the typical network structure. The results showed that a multi-task learning architecture that incorporated process-level specific structures in the connections between the input parameters and the front end of the hidden layer yielded relatively better root mean square errors (RMSEs) values than a conventional neural network architecture, by as much as two orders of magnitude. Based on these results, this study has provided guidance for the construction of artificial neural networks for injection-molding processes that incorporates process-stage specific features and structures in the architecture.
- Open Access
Effects of Input Parameter Range on the Accuracy of Artificial Neural Network Prediction for the Injection Molding Process
Artificial neural network (ANN) is a representative technique for identifying relationships that contain complex nonlinearities. However, few studies have analyzed the ANN’s ability to represent nonlinear or linear relationships between input and output parameters in injection molding. The melt temperature, mold temperature, injection speed, packing pressure, packing time, and cooling time were chosen as input parameters, and the mass, diameter, and height of the injection molded product as output parameters to construct an ANN model and its prediction performance was compared with those of linear regression and second-order polynomial regression. Following the preliminary experiment results, the learning data sets were divided into two groups, i.e., one showed linear relation between the mass of the final product and the range of packing time (linear relation group), and the other showed clear nonlinear relation (nonlinear relation group). The predicted results of ANN were relatively better than those of linear regression and second-order polynomial for both linear and nonlinear relation groups in our specific data sets of the present study.
Open AccessEffects of Input Parameter Range on the Accuracy of Artificial Neural Network Prediction for the Injection Molding Process
Artificial neural network (ANN) is a representative technique for identifying relationships that contain complex nonlinearities. However, few studies have analyzed the ANN’s ability to represent nonlinear or linear relationships between input and output parameters in injection molding. The melt temperature, mold temperature, injection speed, packing pressure, packing time, and cooling time were chosen as input parameters, and the mass, diameter, and height of the injection molded product as output parameters to construct an ANN model and its prediction performance was compared with those of linear regression and second-order polynomial regression. Following the preliminary experiment results, the learning data sets were divided into two groups, i.e., one showed linear relation between the mass of the final product and the range of packing time (linear relation group), and the other showed clear nonlinear relation (nonlinear relation group). The predicted results of ANN were relatively better than those of linear regression and second-order polynomial for both linear and nonlinear relation groups in our specific data sets of the present study.
- 17 March 2022
- Published by Springer Nature in Korea-Australia Rheology Journal
- Vol. 34 (2) , 147-157
A study on the practical application of the integrated ANN system for manufacturing the target quality of the injection molded product
- 17 March 2022
- Published by Springer Nature in Korea-Australia Rheology Journal
- Vol. 34 (2) , 147-157
A study on the practical application of the integrated ANN system for manufacturing the target quality of the injection molded product
- 8 August 2019
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 33 (8) , 3803-3812
Injection mold design of reverse engineering using injection molding analysis and machine learning
- 8 August 2019
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 33 (8) , 3803-3812
Injection mold design of reverse engineering using injection molding analysis and machine learning
- 1 April 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 387-388
Fabrication of Partition Wall for Solar Cell by Hot Embossing
Hot embossing technology, one of nanoimprint lithography (NIL) techniques, has been getting attention as an alternative candidate of next generation micro-patterning technologies by the advantages of simplicity and low cost compared to conventional photo-lithographies. For this study of fabrication of partition wall for polymer solar cell, The manufacturing process is made up of three stages as in the following: (i) the stage of lithography process, (ii) the stage of electro-plating process for mold, and (iii) the stage of hot embossing process. As a result, we made 6 inch Ni-mold and hot embossed partition wall for polymer solar cell.
- 1 April 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 387-388
Fabrication of Partition Wall for Solar Cell by Hot Embossing
Hot embossing technology, one of nanoimprint lithography (NIL) techniques, has been getting attention as an alternative candidate of next generation micro-patterning technologies by the advantages of simplicity and low cost compared to conventional photo-lithographies. For this study of fabrication of partition wall for polymer solar cell, The manufacturing process is made up of three stages as in the following: (i) the stage of lithography process, (ii) the stage of electro-plating process for mold, and (iii) the stage of hot embossing process. As a result, we made 6 inch Ni-mold and hot embossed partition wall for polymer solar cell.