Bumsoo Park

Bumsoo Park

Auto-generated profile, based on publicly available information

Bumsoo Park

Department of Manufacturing Systems and Design Engineering (MSDE), Seoul National University of Science and Technology, Seoul, Republic of Korea

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
15 April 2024 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
BPBumsoo Park
Bumsoo Park
ACAlvin Chen
Alvin Chen
SMSandipan Mishra
Sandipan Mishra
This paper presents a real-time geometry-informed control strategy to homogenize melt pool measurements in laser powder bed fusion (L-PBF) using reinforcement learning. The learning control strategy incorporates geometric information of the scan path as well as in-situ melt pool measurements to compute the laser power signal for reducing in-process melt pool inhomogeneities. First, we design and validate a data-driven model to train the reinforcement learning agent in simulation, with the goal of reducing the amount of experimental data needed for training. Using this simulation-based training approach has the added benefit of avoiding unsafe or infeasible experiments, an issue that is often encountered in training the reinforcement learning agent. After training, the learned control strategy attenuates the 1-norm error by $\mathbf{37\%}$ and standard deviation by $\mathbf{39\%}$ in simulation. We then deploy this learned control strategy in an experimental test bed for a new scan geometry. In this test scenario, the policy achieves a $\mathbf{30\%}$ reduction in error, and a $\mathbf{36\%}$ reduction in melt pool signal variation, thereby illustrating the potential of reinforcement learning in real-time geometry-agnostic control for L-PBF. Finally, we demonstrate that the reinforcement learning agent delivers the same level of performance as a model-based feedforward controller with PID feedback, with 20 $\times$ less computational time for a single geometry. Note to Practitioners —This work was motivated by the need to develop a practical control algorithm for L-PBF systems. Because L-PBF systems manufacture customized on-demand geometries, it is critical that the control strategy is extendable to and easily optimized for each geometry. Specifically, this effort develops an efficient and robust reinforcement learning control algorithm that can be used across novel part geometries, once trained. The control strategy is designed using a simulation-to-real approach, which is key for avoiding extensive training effort and avoids unsafe training experiments.

16 June 2023 in Applied Energy
Verified
Journal Article
Closed access
BPBumsoo Park
Bumsoo Park
ARAlexandra Rempel
Alexandra Rempel
SMSandipan Mishra
Sandipan Mishra


14 January 2026 in Measurement
Verified
Journal Article
Closed access
BPBumsoo Park
Bumsoo Park
JMJulius Mauch
Julius Mauch
HKHyeokjin Kweon
Hyeokjin Kweon
JKJochen Kriegseis
Jochen Kriegseis
SLSeungchul Lee
Seungchul Lee
HKHyoungsoo Kim
Hyoungsoo Kim

3 March 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
IJIljoo Jeong
Iljoo Jeong
BPBumsoo Park
Bumsoo Park
KPKeonhyeok Park
Keonhyeok Park
ALAnna Lee
Anna Lee
IJIn-Jee Jung
In-Jee Jung
SLSeungchul Lee
Seungchul Lee
Determining the precise direction of arrival (DOA) presents a substantial inverse problem in the field of sound source localization (SSL). Intensimetry, a method known for SSL, provides accurate sound direction estimation at low Helmholtz numbers (kd), which facilitates miniaturization and scalability of microphone array modules. However, its performance in accurately estimating DOA at high kd values is limited, which restricts its practical application. This limitation arises from an inverse problem in which the measured intensity becomes biased due to uneven directivity in sound intensity measurement, depending on the direction of the sound source. The issue of sound intensity bias errors becomes more pronounced in systems with a limited number of microphones and is exacerbated at higher Helmholtz numbers. This study introduces the Dual-port conditional invertible neural network (Dual-port CINN), a deep learning approach designed to address intensity bias errors inherent in SSL. Integral to our model is the normalizing flow (NF), a foundational component of the invertible neural network framework, which enables the dual-port CINN to effectively estimate complex distributions for accurate DOA compensation. The model employs an invertible neural network architecture, equipped with two specialized conditional ports: a global condition port for referencing the Helmholtz number and an observance condition port for refining biased DOA corrections. This design makes the model exceptionally effective for conditional regression tasks that require the estimation of complex distributions. Consequently, it provides a solution to the challenging inverse problem of DOA estimation based on intensity, which is complicated by spatially non-uniform directivity. The proposed model was trained and validated across a kd range of 0 to π in a simulation environment using a tetrahedral array composed of four microphones. Furthermore, an experiment was conducted in an anechoic chamber with a cutoff frequency of 80 Hz using various microphone array sizes, including arrays with microphone distances of d = 0.14 m and a smaller array with d = 0.01 m. This research addresses a critical barrier in intensity-based SSL and presents a robust solution for practical SSL applications with a compact microphone array system.

4 June 2026 in Nature Communications
Verified
Journal Article
Open access
YSYounghan Song
Younghan Song
BPBumsoo Park
Bumsoo Park
SJSeungbae Jeon
Seungbae Jeon
HKHyeokjin Kweon
Hyeokjin Kweon
SLSeungchul Lee
Seungchul Lee
JNJongbeom Na
Jongbeom Na
The development of high-performance resins for vat photopolymerization-based three-dimensional printing is constrained by coupled trade-offs among viscosity, curing kinetics, and mechanical properties. Material discovery is often limited because conventional printing-based screening cannot evaluate formulations that are highly viscous or slow-curing. This study introduces a data-efficient workflow linking small-volume formulation screening, machine-learning optimization, and functional validation for constraint-aware design. By using a systematic library of formulations spanning printable and non-printable regimes, small-volume mold curing decouples material characterization from printing limitations to expand the training domain. Regression models trained on viscosity, curing time, elongation at break and tensile modulus identify an optimized formulation with suitable processability and high stretchability. Thermomechanical analyses reveal a homogeneous network and improved stability, while printed components exhibit robust durability. In this work, we show that a generalizable blueprint for rapid photopolymer formulation enables the constraint-aware design of functional materials for soft robotics and programmable three-dimensional devices.