Sungbum Jun

Prof. Dr. Sungbum Jun

Department of Industrial and Systems Engineering, Dongguk University, Seoul, Korea

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
1 September 2020 in Processes
Verified
Journal Article
Open access
PDF file
JJJi-Hye Jun
Ji-Hye Jun
TCTai-Woo Chang
Tai-Woo Chang
Sungbum JunSungbum Jun
Sungbum Jun
Quality management is important for maximizing yield in continuous-flow manufacturing. However, it is more difficult to manage quality in continuous-flow manufacturing than in discrete manufacturing because partial defects can significantly affect the quality of an entire lot of final product. In this paper, a comprehensive framework that consists of three steps is proposed to predict defects and improve yield by using semi-supervised learning, time-series analysis, and classification model. In Step 1, semi-supervised learning using both labeled and unlabeled data is applied to generate quality values. In addition, feature values are predicted in time-series analysis in Step 2. Finally, in Step 3, we predict quality values based on the data obtained in Step 1 and Step 2 and calculate yield values with the use of the predicted value. Compared to a conventional production plan, the suggested plan increases yield by up to 8.7%. The production plan proposed in this study is expected to contribute to not only the continuous manufacturing process but the discrete manufacturing process. In addition, it can be used in early diagnosis of equipment failure.

30 April 2022 in International Journal of Production Research
Verified
Journal Article
Closed access
Sungbum JunSungbum Jun
Sungbum Jun
CCChul Hun Choi
Chul Hun Choi
SLSeokcheon Lee
Seokcheon Lee
As autonomous robot and sensor technologies have advanced, utilisation of autonomous mobile robots (AMRs) in material handling has grown quickly, owing especially to their scalability and versatility compared with automated guided vehicles (AGVs). In order to take full advantage of AMRs, in this paper, we address an AMR scheduling and routing problem by dividing the entire problem into three sub-problems: path finding, vehicle routing, and conflict resolution. We first discuss the previous literature on characteristics of each sub-problem. We then present a comprehensive framework for minimising total tardiness of transportation requests with consideration of conflicts between routes. First, the shortest paths between all locations are calculated with A*. Based on the shortest paths, for vehicle routing, we propose a new local search algorithm called COntextual-Bandit-based Adaptive Local search with Tree-based regression (COBALT), which utilises the contextual bandit to select the best operator in consideration of contexts. After routing of AMRs, an agent-based model with states and protocols resolves collisions and deadlocks in a decentralised way. The results indicate that the proposed framework can improve the performance of AMR scheduling for conflict-free routes and that, especially for vehicle routing, COBALT outperforms the other algorithms in terms of average total tardiness.

18 April 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Sungbum JunSungbum Jun
Sungbum Jun
Due to the recent advance in the industrial Internet of Things (IoT) in manufacturing, the vast amount of data from sensors has triggered the need for leveraging such big data for fault detection. In particular, interpretable machine learning techniques, such as tree-based algorithms, have drawn attention to the need to implement reliable manufacturing systems, and identify the root causes of faults. However, despite the high interpretability of decision trees, tree-based models make a trade-off between accuracy and interpretability. In order to improve the tree’s performance while maintaining its interpretability, an evolutionary algorithm for discretization of multiple attributes, called Decision tree Improved by Multiple sPLits with Evolutionary algorithm for Discretization (DIMPLED), is proposed. The experimental results with two real-world datasets from sensors showed that the decision tree improved by DIMPLED outperformed the performances of single-decision-tree models (C4.5 and CART) that are widely used in practice, and it proved competitive compared to the ensemble methods, which have multiple decision trees. Even though the ensemble methods could produce slightly better performances, the proposed DIMPLED has a more interpretable structure, while maintaining an appropriate performance level.

22 February 2024 in Systems
Verified
Journal Article
Open access
PDF file
BSByung Duk Song
Byung Duk Song
Sungbum JunSungbum Jun
Sungbum Jun
SLSeokcheon Lee
Seokcheon Lee
Disaster management requires efficient allocation of essential facilities with consideration of various objectives. During the response and recovery phase of disaster management (RRDM), various types of missions occur in multiple periods, and each of them needs different support from facilities. In this study, a bi-objective mathematical model was derived to support multi-period RRDM by optimal allocation of required facilities such as drone stations, shelters, emergency medical facilities, and warehouses according to the mission life cycle. Connectivity between facilities was considered to ensure inter-facility complementarity. For efficient derivation of Pareto solutions, a modified epsilon-constraint algorithm for bi-objective optimization was developed. The algorithm was tested with a realistic disaster simulation scenario using HAZUS 4.0 as a demonstration of the benefits of the proposed approach. With the simulation experiments, the proposed approach was expected to provide efficient operational plans and guidelines to decision makers for the bi-objective optimization problem in RRDM systems. In addition, the consideration of inter-facility connectivity can play an important role in the RRDM, especially for robustness and readiness.

15 April 2024 in IEEE Transactions on Evolutionary Computation
Verified
Journal Article
Closed access
CLChan Gyu Lee
Chan Gyu Lee
Sungbum JunSungbum Jun
Sungbum Jun
For fault detection (FD) in manufacturing, various machine learning (ML) models have been widely applied to minimise human intervention and improve detection performance. Even though ML models such as neural networks (NN) have been shown to identify faults effectively, root cause identification (RCI) is becoming more difficult due to their black-box structures and the trade-off between accuracy and interpretability. In order to improve performance while maintaining interpretability, we propose a new framework named FERMAT (Feature Extraction for finding Root causes for Manufacturing Applications with Tree-based algorithms), which enhances the performance of height-limited decision trees (C4.5) through dimensionally-aware genetic programming for feature extraction. Especially in FERMAT, only interpretable features are extracted to prevent decision trees from delivering uninterpretable expressions to practitioners. In the present study, FERMAT’s applicability to RCI was verified with both manufacturing and non-manufacturing datasets with different imbalance ratios. The experimental results showed that FERMAT outperformed the other single-tree-based models by extracting good features and delivered performance comparable to the black-box models.

11 April 2026 in International Journal of Production Research
Verified
Journal Article
Closed access
BKBonwoo Koo
Bonwoo Koo
YKYonggab Kim
Yonggab Kim
JCJaekoung Choi
Jaekoung Choi
Sungbum JunSungbum Jun
Sungbum Jun
YSYoungchul Shin
Youngchul Shin
1. Recently, the demand for semiconductors has continued to rise steadily, driven by the rapid growth of advanced technology sectors such as smartphones, automobiles, artificial intelligence, the I...