Continuous Quality Guard (CQG) System

The Continuous Quality Guard (CQG) is a real-time monitoring and intervention system designed for flow regime monitoring in industrial fluid systems. It provides continuous quality assessment, risk detection, and automated supervisory control to maintain optimal system performance.

• Real-time Data Ingestion: High-throughput streaming data processing from sensors and IoT devices
• Feature Factory: Advanced feature engineering with temporal and statistical transformations
• Regime Detection: ML-powered flow regime classification with confidence scoring
• Quality & Risk Assessment: Multi-dimensional quality scoring and risk prediction
• Supervisory Policy Engine: Rule-based and adaptive control strategies
• Action Gateway: Safe, coordinated execution of control actions
• TimescaleDB Integration: Time-series optimized data storage and retrieval
• Kubernetes-Ready: Production-grade deployment with horizontal scaling

# Clone the repository
git clone <repository-url>
cd "Flow Regime Monitoring"
# Set up environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
# Configure environment
cp .env.example .env
# Edit .env with your settings
# Start services with Docker Compose
docker-compose up -d
# Run initialization
python scripts/init_database.py
python scripts/load_baseline_models.py
# Start the CQG system
python src/main.py

The CQG system consists of six core components:

1. Ingestion Service: Receives and validates sensor data in real-time
2. Feature Factory: Transforms raw data into engineered features
3. Regime Detection: Classifies flow regimes using ML models
4. Quality & Risk Engine: Evaluates system health and predicts risks
5. Supervisory Policy: Determines optimal control actions
6. Action Gateway: Executes approved control commands

See CQG_SYSTEM_ARCHITECTURE.md for detailed architecture.

• Master Index - Complete file and component index
• Implementation Quickstart - Step-by-step setup guide
• System Architecture - Technical architecture details
• API Reference - REST and gRPC API documentation
• Configuration Guide - Configuration options
• Deployment Guide - Production deployment
• Contributing - Development guidelines

• Python 3.10+
• PostgreSQL 14+ with TimescaleDB 2.8+
• 4 GB RAM
• 2 CPU cores

• Python 3.11+
• PostgreSQL 15+ with TimescaleDB 2.11+
• 16 GB RAM
• 8 CPU cores
• SSD storage

# Install dependencies
pip install -r requirements.txt
pip install -r requirements-dev.txt
# Set up pre-commit hooks
pre-commit install
# Run tests
pytest tests/

See Deployment Guide for:

• Docker deployment
• Kubernetes deployment
• Cloud provider setup (AWS, Azure, GCP)
• High availability configuration
• Monitoring and alerting

Primary configuration file: config/cqg_config.yaml

Key configuration sections:

• Database connection settings
• Feature engineering parameters
• Model hyperparameters
• Risk thresholds
• Control policies
• Logging and monitoring

See Configuration Guide for details.

# Run all tests
pytest tests/
# Run specific test suites
pytest tests/unit/
pytest tests/integration/
pytest tests/acceptance/
pytest tests/performance/
# Run with coverage
pytest --cov=src --cov-report=html tests/

The CQG system includes built-in monitoring:

• Prometheus metrics export
• Grafana dashboards
• Health check endpoints
• Performance profiling
• Audit logging

Expected performance characteristics:

• Data ingestion: 10,000+ samples/second
• Feature computation: <10ms per sample
• Regime detection: <50ms per classification
• End-to-end latency: <100ms (p95)
• Throughput: 5,000+ decisions/second

• API authentication via JWT tokens
• Role-based access control (RBAC)
• Encrypted data at rest and in transit
• Audit logging for all control actions
• Configurable action approval workflows

MIT License - See LICENSE for details

We welcome contributions! Please see CONTRIBUTING.md for:

• Code style guidelines
• Testing requirements
• Pull request process
• Development workflow

• Documentation: docs/
• Issues: GitHub Issues
• Discussions: GitHub Discussions

See CHANGELOG.md for version history and release notes.

Built with:

• Python 3.11
• FastAPI
• TimescaleDB
• scikit-learn
• pandas
• NumPy
• Kubernetes

Version: 1.0.0
Status: Production Ready
Last Updated: February 2026