GitHub
Prognostics & Health Management
Fault diagnosis, anomaly detection, and predictive maintenance for rotating machines and thermal power plants.
Personal Homepage
Hyeongmin Kim
Hi, I am Hyeongmin. I am currently a Staff Engineer at Samsung Research, and this is my small home for work, research notes, and the things I have been building around engineering AI.
I started from mechanical engineering, spent my graduate and postdoctoral years studying PHM and domain-informed AI at Seoul National University, and now work on practical AI systems that use knowledge graphs, LLMs, and RAG.
NEON VOID Browser space shooter — play now v1.0.3About
A quick intro.
I work where mechanical systems meet AI — turning messy engineering knowledge into systems that are easier to reason with, search through, and actually use. My work spans prognostics & health management, domain-informed neural networks, design optimization, and LLM-based engineering workflows.
Skills
Toolbox
Domains
PHM
Fault Diagnosis
Motors / PMSM
Rotating Machinery
Thermal Power Plants
Engineering Design
Methods
Deep Learning
Signal Processing
Domain-informed NN (DINN)
Anomaly Detection
Domain Adaptation
Self-/Semi-supervised
Reinforcement Learning
Inverse Modeling
Uncertainty Estimation
AI Systems
LLM / RAG
Knowledge Graphs
LLM Agents
Multi-modal LLM
Tools
Python
PyTorch
Research
What I Work On
A recurring theme in my work: engineering AI shouldn’t stop at a single number. It should expose useful structure — which signals matter, which physical constraints hold, and how an engineer can act on the result.
Domain Knowledge Informed Neural Networks
Networks guided by physics, signal analysis, and expert priors — for generalization, physical consistency, and interpretability.
- DINN review — survey of domain-informed PHM methodsin progress
- Physically-consistent models (PINN-style losses)theme
- Interpretable inputs (2D time–frequency maps)theme
AI-driven Design
Generative design, performance prediction, and parameter / topology optimization via inverse modeling and reinforcement learning.
- Inverse modeling of springback in metal bipolar-plate stampingFraunhofer IPT
- Design evaluation with PINNs & explainable AItheme
- RL-based design-parameter optimizationtheme
LLM Applications in Engineering
Domain-specialized LLMs, knowledge graphs, and RAG workflows for engineering design and signal analysis.
- LLM-based engineering design frameworkin development
- KG-RAG-LLM for PHM — graph-grounded, continuously validatedresearch
- Multi-modal LLM for CAD / simulation / sensor dataresearch
Experience
Career & Education
Work
-
Staff EngineerSamsung Research
Now
-
Postdoctoral ResearcherHAI Lab, Seoul National University
2024
-
Part-time InternOnepredict Inc.
2023
-
Visiting ResearcherFraunhofer IPT, Aachen
2022
-
Undergraduate InternBiorobotics Lab, SNU
2017
Education
-
Ph.D., Mechanical EngineeringSeoul National University · Adviser: B. D. Youn
2019–24
-
B.S., Mechanical & Aerospace Eng.Seoul National University
2015–19
Certification
-
Professional ML EngineerGoogle Cloud
2026–28
Research Output
Publications, Patents & Awards
211 citations · h-index 7 · i10-index 7 (Google Scholar, June 2026)
27
Publications
12 journal articles and 15 peer-reviewed conference papers in PHM, fault diagnosis, and domain-informed AI.
View publications → 8Patents
Registered and filed Korean patents on motor fault diagnosis, boiler-tube leakage detection, and anomaly detection.
View patents → 10Awards
Best-paper, doctoral dissertation, and competition awards from KSME, PHMAP, and IEEE PHM.
View awards →Activities
Talks & Presentations
-
May 2024
Window Size and Sampling Rate Selection for Cost-optimal Deep Learning-based Fault Diagnosis
ACSMO 2024 · Zhengzhou, China
-
Aug 2023
Convolutional Auto-Encoder-Based Boiler Tube Leakage Detection in a Thermal Power Plant
ASME IDETC-CIE 2023 · Boston, USA
-
Aug 2022
A Multi-scale Residual Network with Attention Mechanism for Fault Diagnosis of Rotating Machines
ASME IDETC-CIE 2022 · St. Louis, USA
-
Aug 2022
Reinforcement Learning-based Optimal Parameter Estimation of Ultra Precision Machine
ICEAS 2022 · Ansan, South Korea
-
Sep 2021
Anomaly Detection of Multichannel Complex Industrial Systems Using Physically Grouped Convolutional Autoencoder
PHMAP 2021 · Jeju, South Korea
Side Project
Built for fun
Browser Game · WebGL
NEON VOID v1.0.3
A neon roguelite space shooter I built with Three.js — weave through bullet-hell waves, grab power-ups, chain combos, and fight a boss every five stages. Plays right in the browser, with a global leaderboard. Keyboard + mouse on desktop, dual-stick on mobile.
Extra
Older notes and study logs.
I keep older lecture notes and study materials in a separate archive so this homepage can stay focused while the earlier material remains available.
Open extra archiveContact
Get in touch.
HyperAutomation AI Lab · Rm 324-2, Bldg 313
Seoul National University, Seoul 08826