Cuong (Henry) Nguyen

I have practical vibration experience with the PT500 machinery diagnostics rig at ITD Lab. I selected and installed the experimental setup, then carried out vibration measurements on the rig to collect data for fault diagnosis research.

My Role

I chose the rig configuration, assembled and mounted the components and sensors, and ran the vibration measurements.

Highlights

• Selected and installed the experimental setup on the PT500 rig.
• Mounted sensors and connected the data acquisition system.
• Carried out vibration measurements and recorded data for analysis.

ITD Lab and the VICEM Institute of Cement Technology ran a 5-day intensive course (code VCN.VC.2026.13) for 18 engineers from 7 VICEM member units, going from vibration theory to AI methods for diagnostics and predictive maintenance.

My Role

Instructor

Highlights

• Vibration monitoring foundations, maintenance strategies, the ISO 20816 standard, and an introduction to PHM and AI.
• Gear and rolling-bearing fault diagnosis (GMF, BPFO/BPFI/BSF/FTF, envelope spectrum) and vertical roller mill (VRM) diagnosis.
• Machine learning for bearing fault diagnosis (SVM, Random Forest, SHAP) and a RAG-based smart maintenance assistant.
• Dynamic unbalance identification and field balancing practice.

Stack

• Python
• Google Colab
• scikit-learn
• SHAP

I built this website to give ITD Lab a clear place to share its research, members, publications, and activities. It is available in Vietnamese and English, helping students and research partners quickly understand what the lab does and how to get in touch.

My Role

I handled the project from design and development to organizing the content and deploying the finished website.

Highlights

• Publications are updated from BibTeX and automatically organized by year, making new papers quick to add.
• News, events, member profiles, and admissions information each have a clear place and are easy to update.
• The site works well on phones, supports Vietnamese and English, and is prepared for search engines.

Stack

• Next.js 16
• TypeScript
• Tailwind v4
• GSAP
• next-intl
• Vercel

A Vietnamese-language interface for asking business-data questions without writing SQL. The system parses the question, generates the query, runs it on ClickHouse, and returns the result. Three modes: single questions, follow-ups, and switching context between topics.

My Role

Backend Engineer. I own the Memory subsystem (Redis + Postgres + Graphiti/Neo4j) and the FastAPI service that wires the pipeline together.

Highlights

• Built and own the full Memory stack: Redis for short-term context, Postgres for long-term storage, Graphiti/Neo4j for the knowledge graph.

Stack

• Python
• FastAPI
• LangGraph
• Redis
• PostgreSQL
• Neo4j
• Qdrant
• ClickHouse
• Docker
• LangFuse