Skip to main content

Soo Yeon Kim

Seoul National University · 工学

研究室紹介

Professor Soo Yeon Kim's research lab specializes in advanced control systems for complex engineering processes, with a strong focus on reinforcement learning (RL)-based optimal and safe control of nonlinear dynamical systems. The lab develops novel algorithms that integrate control Lyapunov functions (CLFs) and barrier functions into RL frameworks to ensure stability and constraint satisfaction, particularly in chemical processes and aftertreatment systems for emissions control. A key research direction involves model predictive control (MPC) and state estimation techniques, such as nonlinear MPC (NMPC) and Moving Horizon Estimation (MHE), enhanced with machine learning and optimization strategies to improve computational efficiency and real-time applicability. The lab also applies these methods to real-world challenges, including water network monitoring and diesel exhaust aftertreatment systems like LNT-pSCR.

reinforcement learningnonlinear model predictive controlcontrol Lyapunov functionbarrier functionssafe control

Research Overview

Papers
133
Total Citations
938
Papers (5y)
30
Primary Field
工学

Research Output Trend

Figures are computed from collected data and may differ slightly.

Publications per year (5y)
30total
2022
2023
2024
2025
2026
Citations per year (5y)
150total
20222023202420252026

Selected Papers

15
1
Article|48 citations·2016
Robust leak detection and its localization using interval estimation for water distribution network
Yeonsoo Kim, Shin Je Lee, Taekyoon Park, Gibaek Lee, Jung Chul Suh, Jong Min Lee
SJR Q1Computers & Chemical Engineering
Civil and Structural EngineeringEngineering
2
Article|25 citations·2022
Safe model‐based reinforcement learning for nonlinear optimal control with state and input constraints
Yeonsoo Kim, Jong Woo Kim
SJR Q1AIChE Journal

Abstract Safety is a critical factor in reinforcement learning (RL) in chemical processes. In our previous work, we had proposed a new stability‐guaranteed RL for unconstrained nonlinear control‐affine systems. In the approximate policy iteration algorithm, a Lyapunov neural network (LNN) was updated while being restricted to the control Lyapunov function, and a policy was updated using a variation of Sontag's formula. In this study, we additionally consider state and input constraints by introd

Computational Theory and MathematicsComputer Science
3
Article|24 citations·2022
An improved thermal single particle model and parameter estimation for high-capacity battery cell
Changbeom Hong, Hyeonwoo Cho, Dae-Ki Hong, Se-Kyu Oh, Yeonsoo Kim
SJR Q1Electrochimica Acta
Automotive EngineeringEngineering
4
Article|22 citations·2018
Backstepping control integrated with Lyapunov-based model predictive control
Yeonsoo Kim, Tae Hoon Oh, Taekyoon Park, Jong Min Lee
SJR Q1Journal of Process Control
Control and Systems EngineeringEngineering
5
Article|21 citations·2020
Model‐based reinforcement learning for nonlinear optimal control with practical asymptotic stability guarantees
Yeonsoo Kim, Jong Min Lee
SJR Q1AIChE Journal

Abstract We propose a new reinforcement learning approach for nonlinear optimal control where the value function is updated as restricted to control Lyapunov function (CLF) and the policy is improved using a variation of Sontag's formula. The practical asymptotic stability of the closed‐loop system is guaranteed during the training and at the end of training without requiring an additional actor network and its update rule. For a single‐layer neural network (NN) with exact basis functions, the a

Computational Theory and MathematicsComputer Science
6
Article|18 citations·2018
Hybrid Nonlinear Model Predictive Control of LNT and Urealess SCR Aftertreatment System
Yeonsoo Kim, Taekyoon Park, Changho Jung, Chang Hwan Kim, Yong Wha Kim, Jong Min Lee
SJR Q1IEEE Transactions on Control Systems Technology

In recent years, more stringent regulatory standards (EURO 6 emission standards) with a real driving test have been adopted for diesel vehicles. To meet the new regulations, a lean NOx trap (LNT) followed by a urealess selective catalytic reduction [passive SCR (pSCR)], i.e., LNT-pSCR, has been proposed as one of the promising aftertreatment systems for light-duty vehicles. In this brief, we propose hybrid nonlinear model predictive control (NMPC) that determines the optimal timing of rich mode

Materials ChemistryMaterials Science
7
Article|13 citations·2015
Robust Leakage Detection and Interval Estimation of Location in Water Distribution Network
Yeonsoo Kim, Shin Je Lee, Taekyoon Park, Gibaek Lee, Jung Chul Suh, Jong Min Lee
IFAC-PapersOnLineOA

The water supply network has a complex structure especially in cities with high population density. A damage to the water pipe can occur in the form of a leakage or a burst and the technique for early detection of the occurrence and for the exact determination of the location is required. In this paper, we propose a novel method that can detect the leakage of the water supply network using the pressure data. After the noise is eliminated using the Kalman Filter, the mean of normal state pressure

Civil and Structural EngineeringEngineering
8
Article|13 citations·2023
Feature construction for on-board early prediction of electric vehicle battery cycle life
Jun‐Seop Shin, Yeonsoo Kim, Jong Min Lee
SJR Q2Korean Journal of Chemical Engineering
Automotive EngineeringEngineering
9
Article|12 citations·2021
Design of switching multilinear model predictive control using gap metric
Byung Jun Park, Yeonsoo Kim, Jong Min Lee
SJR Q1Computers & Chemical Engineering
Control and Systems EngineeringEngineering
10
Article|11 citations·2021
Multirate moving horizon estimation combined with parameter subset selection
Jaehan Bae, Yeonsoo Kim, Jong Min Lee
SJR Q1Computers & Chemical Engineering
Control and Systems EngineeringEngineering
11
Article|8 citations·2023
Exergy destruction improvement of hydrogen liquefaction process considering variations in cooling water temperature
D.H. Lee, Seo Yeon Yu, Seung Yeol Yeom, Jeong Jun Lee, Byeong Chan Kang, Chung Hun Cho, Seok Goo Lee, Yeonsoo Kim
SJR Q2Korean Journal of Chemical Engineering
Energy Engineering and Power TechnologyEnergy
12
Article|8 citations·2022
Advanced-multi-step moving horizon estimation for large-scale nonlinear systems
Yeonsoo Kim, Kuan‐Han Lin, David M. Thierry, Lorenz T. Biegler
SJR Q1Journal of Process ControlOA

Nonlinear Model Predictive Control (NMPC) is an optimization-based control strategy that directly incorporates nonlinear dynamic models and has desirable stability and robustness properties. State estimation is an essential counterpart to NMPC and Moving Horizon Estimation (MHE) is also an optimization-based strategy that directly incorporates the nonlinear dynamics and constraints. However, NMPC and MHE are challenged by the computational expense of solving NLPs at each time step. For NMPC, thi

Control and Systems EngineeringEngineering
13
Article|7 citations·2020
Serial advanced-multi-step nonlinear model predictive control using an extended sensitivity method
Yeonsoo Kim, David M. Thierry, Lorenz T. Biegler
SJR Q1Journal of Process Control
Control and Systems EngineeringEngineering
14
Article|7 citations·2000
Preparation of Y1−x Yb x Ba2Cu3O7−y superconducting films by chemical vapor deposition
Yeonsoo Kim, Hyeoung-Ho Park, Young Soon Kim, Hyung–Shik Shin
SJR Q2Korean Journal of Chemical Engineering
Condensed Matter PhysicsPhysics and Astronomy
15
Article|6 citations·2023
Neural network models for atmospheric residue desulfurization using real plant data with novel training strategies
Yungun Jung, Hyungjun Kim, Gyeonggwan Jeon, Yeonsoo Kim, Yeonsoo Kim
SJR Q1Computers & Chemical Engineering
Mechanical EngineeringEngineering

Research Areas

Materials ChemistryControl and Systems EngineeringAutomotive EngineeringMechanical EngineeringCivil and Structural EngineeringComputational Theory and Mathematics

Soo Yeon Kimの研究をNubintでさらに深く

この研究室の論文をアプリで開き、AIと共に読み、要約し、引用しましょう。