Flight Log Analyzer

A professional drone flight data analysis platform with AI-powered insights. Upload your ArduPilot or PX4 flight logs for comprehensive diagnostics, anomaly detection, and actionable recommendations.

Features

Core Functionality

• Multi-Format Support: Parse ArduPilot Dataflash (.BIN) and PX4 ULog (.ulg) flight logs
• Comprehensive Telemetry Extraction: Battery voltage/current, vibration (X/Y/Z), GPS, altitude, attitude data
• Statistical Analysis: Min, max, average, and sample count for all telemetry parameters
• Anomaly Detection: Z-score based spike detection for vibrations, battery alerts, GPS accuracy warnings
• AI-Powered Insights: GPT-3.5 integration for expert flight diagnostics and recommendations
• Export Options: Download analysis results as CSV or JSON

Detected Anomalies

• Critical battery voltage drops (< 10.5V for 3S LiPo)
• Low battery warnings (< 11.0V)
• Vibration spikes using statistical Z-score analysis (> 3σ)
• GPS HDOP degradation warnings
• Current draw anomalies and motor performance issues

Technology Stack

Frontend

• React 18 with TypeScript
• Tailwind CSS for styling
• Shadcn/UI component library
• Lucide React for icons
• React Query for state management

Backend

• Flask (Python) REST API
• OpenAI GPT-3.5 for AI analysis
• pymavlink for ArduPilot log parsing
• pyulog for PX4 log parsing

Getting Started

Prerequisites

• Node.js 18+ and npm
• Python 3.8+
• OpenAI API key

Frontend Setup

# Install dependencies
npm install

# Start development server
npm run dev

The frontend will be available at http://localhost:8080

Backend Setup

# Navigate to backend directory
cd backend

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Set environment variable
export OPENAI_API_KEY=your_api_key_here  # On Windows: set OPENAI_API_KEY=your_api_key

# Start server
python app.py

The API will be available at http://localhost:5000

API Endpoints

Method	Endpoint	Description
POST	/api/upload	Upload and analyze flight log file
GET	/health	Server health check
GET	/api/debug	Debug information and supported formats

Upload Request

curl -X POST http://localhost:5000/api/upload \
  -F "[email protected]"

Response Structure

{
  "status": "SUCCESS",
  "log_type": "ardupilot",
  "stats": {
    "battery_voltage": { "min": 11.2, "max": 12.6, "avg": 11.89, "count": 1247 },
    "vibration_x": { "min": 0.01, "max": 0.08, "avg": 0.03, "count": 892 }
  },
  "anomalies": [
    {
      "type": "warning",
      "category": "Battery Voltage",
      "message": "LOW: Battery voltage at 11.2V",
      "detail": "Consider landing soon to avoid critical discharge.",
      "confidence": "HIGH"
    }
  ],
  "ai_insights": "Overall flight health: FAIR...",
  "timestamp": "2024-01-15T10:30:00Z"
}

Project Structure

flight-log-analyzer/
├── src/
│   ├── components/
│   │   └── flight-analyzer/
│   │       ├── FileUpload.tsx       # Drag & drop file upload
│   │       ├── ProcessingSteps.tsx  # Analysis progress indicator
│   │       ├── StatsGrid.tsx        # Telemetry statistics display
│   │       ├── AnomaliesList.tsx    # Anomaly detection results
│   │       ├── AIInsights.tsx       # GPT analysis display
│   │       ├── DownloadButtons.tsx  # CSV/JSON export
│   │       ├── Header.tsx           # Page header
│   │       └── ResultsSection.tsx   # Full results layout
│   ├── pages/
│   │   └── Index.tsx                # Main application page
│   └── index.css                    # Design system tokens
├── backend/
│   ├── app.py                       # Flask API server
│   └── requirements.txt             # Python dependencies
└── README.md

Configuration

Environment Variables

Variable	Description	Required
OPENAI_API_KEY	OpenAI API key for GPT insights	Yes
FLASK_PORT	Backend server port (default: 5000)	No
FLASK_DEBUG	Enable debug mode (default: true)	No

Supported Log Formats

Format	Extension	Detection
ArduPilot Dataflash	.bin	Magic bytes: 0xA3 0x95
PX4 ULog	.ulg	Header: ULog

Anomaly Detection Thresholds

Parameter	Warning	Critical
Battery Voltage (3S)	< 11.0V	< 10.5V
Vibration Z-score	> 2.0	> 3.0
GPS HDOP	> 2.5	> 5.0
Current Draw	> 60A	> 100A

Security Notes

⚠️ Important: Never commit API keys to version control

• Store OPENAI_API_KEY in environment variables
• Use .env files for local development (add to .gitignore)
• Rotate API keys if accidentally exposed

Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/new-feature)
3. Commit changes (git commit -m 'Add new feature')
4. Push to branch (git push origin feature/new-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• ArduPilot for Dataflash log format documentation
• PX4 for ULog format specification
• OpenAI for GPT API
• pymavlink for MAVLink parsing utilities