Junhee Lee

Junhee Lee

Auto-generated profile, based on publicly available information

Junhee Lee


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 February 2025 in Sensors
Verified
Journal Article
Open access
PDF file
JLJunhee Lee
Junhee Lee
JJJaeseok Jang
Jaeseok Jang
QTQing Tang
Qing Tang
HJHail Jung
Hail Jung
The advent of Industry 4.0 has significantly transformed the manufacturing sector, bringing advancements in quality control efficiency, environmental sustainability, and production development. These changes have led to the development of intelligent technologies such as artificial intelligence (AI). However, implementing AI solutions in manufacturing processes still presents challenges in many aspects, particularly in handling irregular datasets influenced by diverse manufacturing settings. In the field of injection molding, quality inspection often occurs at the batch level rather than at the individual level, providing only the overall defect ratio of batch production instead of labeling each individual product. These issues limit the general application of AI and data-driven decision-making. To address these limitations and enhance product efficiency, this study proposes a novel anomaly detection framework for a specific manufacturing process. In Recipe-Based Learning, we first apply K-Means clustering to account for the flexible manufacturing process, which relies on diverse settings. The injection molding data are classified into setting-specific recipes to ensure data normality and uniqueness. The Kruskal-Wallis test is conducted to provide statistical evidence of differences in data based on varying settings, further justifying the necessity of Recipe-Based Learning. Then, Autoencoders for anomaly detection are trained with normal data from each recipe. With this data-driven AI approach, 61 defective products are predicted, compared to the existing 41 defects. Meanwhile, the integrated model, which does not consider variations in settings, only predicted 2 defects, indicating poor and distorted quality inspection. For Adaptable Learning, which focuses on new inputs with unseen settings, we apply KL-Divergence to identify the closest trained recipe data and its corresponding model. This approach outperformed both the integrated and additionally trained models in predictive power. As a result, continuous prediction is achieved without the need for further training, successfully enhancing process optimization. In the context of smart factories in the injection molding industry, such improvements in process management can significantly enhance overall productivity and decision-making, primarily through a data-driven AI approach.

13 January 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
JLJunhee Lee
Junhee Lee
JJJaeseok Jang
Jaeseok Jang
QTQing Tang
Qing Tang
HJHail Jung
Hail Jung
The advent of Industry 4.0 has significantly transformed the manufacturing sector, bringing advancements in quality control efficiency, environmental sustainability, and production development etc. These changes have led to the development of intelligent technologies such as artificial intelligence(AI). However, implementing AI solutions in manufacturing processes still faces challenges in many aspects, particularly in handling irregular datasets influenced by diverse manufacturing settings. Especially in the field of injection molding, quality inspection often occurs in a batch level rather than singular data, providing only the overall defective ratio of the batch production instead of each individual labeling result. These issues limit the general application of AI and data-driven decision making. To address these limitations and promote product efficiency, this study proposes a novel anomaly detection framework for a specific manufacturing process. For Recipe-Based Learning, we first apply K-Means to take the flexible manufacturing process relying on diverse settings into account. The injection molding data are classified into specific-setting based recipes to secure data normality and uniqueness. Then, autoencoders for anomaly detection are trained with normal data from each recipe. With this data-driven AI approach, 61 defective products are predicted compared to the existing 41 defects. Meanwhile, the integrated model without considering the change of settings only predicted 2 defects which imply a poor and distorted quality inspection. For Adaptable Learning focused on new inputs with unseen settings, we apply KL-Divergence to find the closest trained recipe data and its model. In this case, it also exceeded the predictivity compared to the integrated and additionally trained models. This leads to continuous prediction without further training, which also successfully implies the enhancement of process optimization. In the aspect of smart factory in the injection molding field, such improvement of process management can first improve the overall productivity and decision making mainly with data-driven AI approach. Furthermore, it is expected to enhance energy efficiency such as reduction of environmental waste and computational cost, ensuring sustainable manufacturing.

6 August 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
JLJunhee Lee
Junhee Lee
SASAJID ALI
SAJID ALI
HJHail Jung
Hail Jung
The rise of Industry 4.0 has made robust forecasting and process control central to achieving sustainable smart manufacturing. While deep learning improves prediction accuracy, most models lack uncertainty quantification and process control—both critical for minimizing waste and optimizing energy use. Generative models are promising but underused in real-world manufacturing due to data and integration challenges. To address this, we propose a unified two-stage deep learning framework for real-time simulation and adaptive process control in dynamic manufacturing environments. The first stage leverages DeepAR and Monte Carlo Dropout to produce both accurate point predictions and calibrated uncertainty intervals. The second stage introduces a novel LSTM-based Conditional Variational Autoencoder (LSTM-CVAE) that reconstructs temporally coherent multivariate input sequences conditioned on target specifications. Then a two-stage filtering mechanism ensures the plausibility of generated inputs and their predictive alignment with operational goals. Experiments on two real-time industrial datasets (sugar and bioprocessing) and a public benchmark demonstrate average improvements of up to 35.7%, 21.0%, 24.6% in Balanced MAE, and 21.3%, 9.8%, 25.2% in Comprehensive Uncertainty Score metrics. The framework remains robust under batch-wise shuffling, supporting real-world deployment. Overall, it enables interpretable, forecast-aware, target-driven process control that improves resource efficiency and product cost—advancing sustainable manufacturing.