Skip to content

Repository files navigation

🏭 IntelliPlant β€” AI-Powered Industrial Knowledge Intelligence Platform

Transform unstructured industrial documents into actionable, AI-driven intelligence β€” in real-time.


πŸ“Œ Problem Statement

Industrial plants generate enormous volumes of unstructured data β€” equipment manuals, P&IDs (Piping & Instrumentation Diagrams), SCADA telemetry logs, maintenance records, compliance reports, and safety SOPs. Plant engineers currently spend 60%+ of their time manually searching through scattered documents to find answers during critical operations.

IntelliPlant solves this by creating a unified AI-powered knowledge layer that ingests all facility documentation, builds an intelligent vector index, and provides instant, citation-backed answers through a natural language AI Copilot β€” while simultaneously powering a Digital Twin visualization, predictive analytics, and compliance tracking.


🌟 Key Features

🧠 AI Copilot (Retrieval-Augmented Generation)

  • Upload any industrial document (PDF, DOCX, XLSX, TXT) and chat with it instantly
  • AI provides precise, grounded answers with verifiable source citations (document name, section, page)
  • Powered by LLaMA 3.3 70B via Groq with LangChain RAG pipeline
  • Intelligent fallback engine ensures zero downtime β€” always returns answers even during API failures
  • Futuristic Neural Scanner Loading Animation with real-time pipeline stage indicators

🏭 Interactive Digital Twin

  • Drag-and-drop asset positioning on a 2D plant map with real-time health indicators
  • Dynamic asset management β€” Add, connect, reposition, and delete equipment directly from the UI
  • Animated process flow lines showing connections between assets with pulsing health-based colors
  • No hardcoded data β€” every position, connection, and asset is stored in the database
  • Any new client/factory can start from a blank canvas and build their plant layout visually

πŸ“Š Intelligent Analytics Dashboard

  • Auto-extracts physical assets (Pumps, Compressors, Valves, Motors) from uploaded documents using Named Entity Recognition (NER)
  • Real-time KPI cards: Total Assets, Health Score, Open Incidents, Compliance Rate
  • Failure pattern detection with AI-generated maintenance recommendations
  • Severity distribution charts and incident trend analysis

πŸ“ Smart Document Management

  • Upload industrial documents with automatic AI processing (summarization + entity extraction)
  • FAISS vector indexing for lightning-fast semantic search across all documents
  • Documents are automatically linked to physical equipment tags (e.g., P-101, C-401)

βœ… Compliance Tracker

  • Track regulatory requirements (ISO 55000, OSHA, API 653) against asset compliance status
  • Visual risk-level indicators: Compliant, Non-Compliant, Overdue
  • Gap analysis with automated audit readiness scoring

πŸ“ˆ Predictive Insights

  • AI-powered failure pattern recognition across the asset fleet
  • Thermal anomaly detection, vibration analysis, and seal degradation tracking
  • Maintenance recommendations ranked by severity and recurrence count

🌐 Premium Landing Page

  • Responsive, dark/light mode landing page with Three.js bioluminescent particle background
  • Asymmetric Bento Grid showcasing platform capabilities
  • Interactive AI Copilot preview with live step-by-step demonstration
  • Footer pages: Privacy Policy, Terms of Service, Enterprise Security, System Status

πŸ—οΈ System Architecture

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                        FRONTEND (React 19 + Vite 8)            β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚
β”‚  β”‚Dashboard β”‚ β”‚AI Copilotβ”‚ β”‚Documents β”‚ β”‚   Digital Twin     β”‚ β”‚
β”‚  β”‚(KPIs)    β”‚ β”‚(RAG Chat)β”‚ β”‚(Upload)  β”‚ β”‚   (Plant Map)      β”‚ β”‚
β”‚  β””β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚
β”‚       β”‚             β”‚            β”‚                β”‚             β”‚
β”‚  β”Œβ”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚
β”‚  β”‚                  Axios API Service Layer                   β”‚  β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                β”‚ REST API (HTTP)
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                        BACKEND (FastAPI)                        β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚
β”‚  β”‚                   API Router Layer                         β”‚  β”‚
β”‚  β”‚  /api/chat  /api/assets  /api/documents  /api/analytics   β”‚  β”‚
β”‚  β””β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚
β”‚       β”‚              β”‚              β”‚              β”‚             β”‚
β”‚  β”Œβ”€β”€β”€β”€β”΄β”€β”€β”€β”€β”   β”Œβ”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”      β”‚
β”‚  β”‚LLM      β”‚   β”‚Entity    β”‚  β”‚Document   β”‚  β”‚Analytics β”‚      β”‚
β”‚  β”‚Service  β”‚   β”‚Extractor β”‚  β”‚Processor  β”‚  β”‚Engine    β”‚      β”‚
β”‚  β”‚(Groq/   β”‚   β”‚(NER)     β”‚  β”‚(PDF/DOCX) β”‚  β”‚(Patterns)β”‚      β”‚
β”‚  β”‚ Gemini) β”‚   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜      β”‚
β”‚  β””β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”˜                                                    β”‚
β”‚       β”‚                                                         β”‚
β”‚  β”Œβ”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚
β”‚  β”‚              FAISS Vector Store (CPU)                      β”‚  β”‚
β”‚  β”‚        Sentence-Transformers (all-MiniLM-L6-v2)           β”‚  β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚
β”‚                                                                 β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚
β”‚  β”‚                   SQLite Database                          β”‚  β”‚
β”‚  β”‚  Assets β”‚ Incidents β”‚ Documents β”‚ Compliance β”‚ Entities   β”‚  β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

πŸ› οΈ Tech Stack

Layer Technology Purpose
Frontend React 19, Vite 8, React Router 7 SPA with component-based architecture
UI Framework Custom CSS (Glassmorphism), Lucide Icons Premium dark-mode industrial control room UI
3D Effects Three.js Bioluminescent particle background on landing page
Backend FastAPI 0.115, Python 3.12+ Async REST API with auto-generated Swagger docs
Database SQLite + SQLAlchemy 2.0 Zero-config relational storage with ORM
Vector DB FAISS-CPU 1.14 Facebook AI Similarity Search for document embeddings
Embeddings Sentence-Transformers (all-MiniLM-L6-v2) Lightweight, high-quality text embeddings
LLM Groq (LLaMA 3.3 70B Versatile) Ultra-fast inference for RAG answers
RAG Framework LangChain 0.3 Orchestrates retrieval, context assembly, and generation
Doc Processing PyPDF2, python-docx, openpyxl Multi-format document text extraction

πŸš€ Quick Start

Prerequisites

1. Clone the Repository

git clone https://github.com/Husam26/IntelliPlant.git
cd IntelliPlant

2. Setup Backend

cd backend
python -m venv venv

# Windows
venv\Scripts\activate

# macOS / Linux
source venv/bin/activate

pip install -r requirements.txt

3. Configure Environment

Create a .env file in the project root:

GROQ_API_KEY=your_groq_api_key_here

4. Seed Demo Data (Recommended)

cd backend
python seed_demo_data.py

This populates the database with 7 industrial assets, 4 incidents, and 4 compliance records for a realistic demonstration.

5. Start Backend Server

uvicorn app.main:app --reload

Backend runs at http://localhost:8000 | Swagger Docs at http://localhost:8000/docs

6. Start Frontend

cd frontend
npm install
npm run dev

Frontend runs at http://localhost:5173

7. One-Click Start (Windows)

run_project.bat

πŸ“‚ Project Structure

IntelliPlant/
β”œβ”€β”€ backend/
β”‚   β”œβ”€β”€ app/
β”‚   β”‚   β”œβ”€β”€ main.py              # FastAPI application entry point
β”‚   β”‚   β”œβ”€β”€ config.py            # Environment configuration (Pydantic Settings)
β”‚   β”‚   β”œβ”€β”€ database.py          # SQLAlchemy engine & session management
β”‚   β”‚   β”œβ”€β”€ models/
β”‚   β”‚   β”‚   └── models.py        # ORM models (Asset, Document, Incident, etc.)
β”‚   β”‚   β”œβ”€β”€ schemas/
β”‚   β”‚   β”‚   └── schemas.py       # Pydantic request/response schemas
β”‚   β”‚   β”œβ”€β”€ routers/
β”‚   β”‚   β”‚   β”œβ”€β”€ assets.py        # CRUD endpoints for assets + Digital Twin
β”‚   β”‚   β”‚   β”œβ”€β”€ chat.py          # RAG-powered AI Copilot endpoint
β”‚   β”‚   β”‚   β”œβ”€β”€ documents.py     # Document upload & processing
β”‚   β”‚   β”‚   β”œβ”€β”€ analytics.py     # Dashboard KPIs & pattern detection
β”‚   β”‚   β”‚   └── search.py        # Semantic search endpoint
β”‚   β”‚   β”œβ”€β”€ services/
β”‚   β”‚   β”‚   β”œβ”€β”€ llm_service.py   # LangChain RAG pipeline + Groq integration
β”‚   β”‚   β”‚   β”œβ”€β”€ document_processor.py  # PDF/DOCX/XLSX parsing & FAISS indexing
β”‚   β”‚   β”‚   └── entity_extractor.py    # NER for equipment tag extraction
β”‚   β”‚   └── utils/
β”‚   β”œβ”€β”€ seed_demo_data.py        # Demo data seeder script
β”‚   └── requirements.txt
β”œβ”€β”€ frontend/
β”‚   β”œβ”€β”€ src/
β”‚   β”‚   β”œβ”€β”€ App.jsx              # Root router & layout
β”‚   β”‚   β”œβ”€β”€ pages/
β”‚   β”‚   β”‚   β”œβ”€β”€ Landing.jsx      # Public landing page
β”‚   β”‚   β”‚   β”œβ”€β”€ Dashboard.jsx    # Analytics dashboard
β”‚   β”‚   β”‚   β”œβ”€β”€ Copilot.jsx      # AI chat interface
β”‚   β”‚   β”‚   β”œβ”€β”€ Documents.jsx    # Document management
β”‚   β”‚   β”‚   β”œβ”€β”€ Assets.jsx       # Asset registry
β”‚   β”‚   β”‚   β”œβ”€β”€ Compliance.jsx   # Compliance tracker
β”‚   β”‚   β”‚   β”œβ”€β”€ Insights.jsx     # Predictive insights
β”‚   β”‚   β”‚   β”œβ”€β”€ PlantMap.jsx     # Digital Twin (interactive plant map)
β”‚   β”‚   β”‚   └── InfoPages.jsx    # Privacy, Terms, Security, Status
β”‚   β”‚   β”œβ”€β”€ components/
β”‚   β”‚   β”‚   β”œβ”€β”€ layout/Sidebar.jsx
β”‚   β”‚   β”‚   β”œβ”€β”€ HeroMockup.jsx
β”‚   β”‚   β”‚   └── WhiteboardBioluminescent.jsx
β”‚   β”‚   β”œβ”€β”€ services/
β”‚   β”‚   β”‚   └── api.js           # Axios API service layer
β”‚   β”‚   └── styles/              # CSS modules (Glassmorphism theme)
β”‚   └── package.json
β”œβ”€β”€ data/                        # FAISS index & uploaded documents
β”œβ”€β”€ sample_docs/                 # Sample industrial documents for testing
β”œβ”€β”€ .env                         # Environment variables
β”œβ”€β”€ .gitignore
β”œβ”€β”€ run_project.bat              # One-click Windows launcher
└── README.md

πŸ”Œ API Endpoints

Method Endpoint Description
GET /api/analytics/overview Dashboard KPI summary
GET /api/analytics/patterns AI-detected failure patterns
GET /api/assets List all assets (with filters)
POST /api/assets Create new asset (Digital Twin)
PUT /api/assets/{id}/position Update asset position on map
PUT /api/assets/{id}/connections Update asset flow connections
DELETE /api/assets/{id} Delete an asset
GET /api/assets/{id}/incidents Asset incident history
POST /api/chat Send question to AI Copilot (RAG)
GET /api/chat/history/{session} Retrieve chat history
POST /api/documents/upload Upload & process document
GET /api/documents List all documents
GET /api/search?q=... Semantic search across documents

🎨 Screenshots & UI

Landing Page

  • Responsive dark/light mode with Three.js particle animation
  • Asymmetric Bento Grid with live asset health telemetry widgets
  • Interactive AI Copilot preview section

Dashboard

  • Real-time KPI cards (Total Assets, Health Score, Incidents, Compliance)
  • Glassmorphism-inspired premium dark UI

AI Copilot

  • Natural language chat with industrial document intelligence
  • Verifiable source citations with document name and section
  • Cyber-Emerald Neural Scanner loading animation with live pipeline stages

Digital Twin (Plant Map)

  • Interactive 2D plant layout with draggable asset nodes
  • Real-time health colors (Green/Amber/Red) with pulsing animations
  • Add Asset modal with connection picker for process flow lines
  • Edit connections from the detail panel after creation

πŸ”‘ Innovation & Differentiators

Feature IntelliPlant Traditional Systems
Document Intelligence AI-powered RAG with citations Manual keyword search
Asset Monitoring Dynamic Digital Twin Static P&ID printouts
Knowledge Access Natural language Q&A Browse folder hierarchies
Compliance Automated real-time tracking Manual spreadsheet audits
Setup Time < 5 minutes Weeks of configuration
Infrastructure Local-first (SQLite + FAISS-CPU) Heavy enterprise servers

πŸ‘₯ Team

Team IntelliPlant β€” Built during the ETA Hackathon 2026


πŸ“„ License

This project was built for the ETA Hackathon 2026. All rights reserved.


🏭 IntelliPlant β€” Operate your plant with certainty.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages