{"slug": "show-hn-ev-qa-framework-ml-powered-qa-for-electric-vehicle-battery-systems", "title": "Show HN: EV-QA-Framework – ML-powered QA for electric vehicle battery systems", "summary": "EV-QA-Framework, an open-source machine learning tool for electric vehicle battery quality assurance, has been released on GitHub. The framework combines rule-based validation with Isolation Forest anomaly detection and LSTM-based State of Health prediction, and includes a CAN bus emulator for testing without physical hardware. The tool aims to help QA engineers and battery researchers catch anomalies, predict degradation, and validate battery performance without expensive test rigs.", "body_md": "Electric vehicle battery systems produce a lot of telemetry data - thousands of readings per minute. EV-QA-Framework helps QA engineers and battery researchers catch anomalies, predict degradation, and validate battery performance without needing expensive test rigs.\n\nThe framework combines rule-based validation with machine learning (Isolation Forest for anomaly detection, LSTM for State of Health prediction), plus a CAN bus emulator so you can test without physical hardware.\n\n- ML anomaly detection via Isolation Forest with adjustable sensitivity\n- State of Health prediction using an LSTM neural network\n- CAN bus emulation (CAN 2.0B and J1939 protocols)\n- Interactive real-time dashboard (FastAPI + WebSocket + Chart.js)\n- Configurable safety thresholds per vehicle profile\n- Save/load trained models as JSON or joblib\n- 100+ pytest tests with ML validation edge cases\n\n```\npip install -r requirements.txt\n\n# Run analysis on sample data\npython -m ev_qa_framework.cli analyze examples/tesla_model_s_defective.csv\n\n# Launch dashboard\npython -m ev_qa_framework.cli dashboard\n\n# Generate synthetic CAN data\npython -m ev_qa_framework.cli emulate --duration 60\n```\n\nWith Docker:\n\n```\ndocker compose -f docker-compose.prod.yml up -d\n# then open http://localhost:8080\n```\n\nThe framework has four main components:\n\n**Core QA Engine**- Pydantic-based validation with configurable safety thresholds** ML Analyzer**- Isolation Forest for anomaly detection, LSTM for SOH prediction** CAN Emulator**- Generates CAN 2.0B and J1939 data streams for offline testing** Dashboard**- FastAPI server with WebSocket-powered real-time charts\n\nData flows: CSV/API input -> Pydantic validation -> ML analysis -> dashboard visualization.\n\n```\npython -m ev_qa_framework.cli analyze examples/tesla_model_s_defective.csv\n\npython -m ev_qa_framework.cli dashboard\n\npython -m ev_qa_framework.cli emulate --duration 120 --protocol j1939\n\npython -m ev_qa_framework.cli analyze examples/tesla_model_s_defective.csv \\\n  --config config/tesla_config.json \\\n  --output report.json \\\n  --save-model\ndocker compose -f docker-compose.prod.yml up -d\n\n# With custom configuration\ncp .env.example .env\ndocker compose -f docker-compose.prod.yml --env-file .env up -d\n```\n\nImages are published to GitHub Container Registry:\n`ghcr.io/remontsuri/ev-qa-framework:latest`\n\n```\npip install -r requirements-dev.txt\npytest -v --cov=ev_qa_framework\n\n# Specific test suites\npytest tests/test_ml_analysis.py -v\npytest tests/test_integration.py -v\nEV-QA-Framework/\n  ev_qa_framework/         # Core package\n    analysis.py            # ML anomaly detection\n    cli.py                 # CLI entry point\n    config.py              # Thresholds and logging setup\n    framework.py           # Main QA engine\n    models.py              # Pydantic validation models\n    soh_predictor.py       # LSTM SOH predictor\n    can_bus.py             # CAN bus simulator\n  dashboard/               # Web dashboard\n    app.py                 # FastAPI + WebSocket server\n    templates/             # Jinja2 frontend\n  api/                     # REST API\n    routes.py              # API endpoints\n  config/                  # Configuration profiles\n  examples/                # Usage examples\n  tests/                   # Test suite\n```\n\n- Core QA engine\n- ML anomaly detection\n- SOH prediction\n- CAN bus emulation\n- Interactive dashboard\n- Docker deployment\n- PyPI package\n- Automated release pipeline\n- Cell imbalance detection\n- Thermal runaway prediction\n- Grafana datasource plugin\n\nBug reports, feature requests, and pull requests are welcome. See CONTRIBUTING.md for the workflow.\n\nMIT. See LICENSE for details.", "url": "https://wpnews.pro/news/show-hn-ev-qa-framework-ml-powered-qa-for-electric-vehicle-battery-systems", "canonical_source": "https://github.com/remontsuri/EV-QA-Framework", "published_at": "2026-05-29 08:35:24+00:00", "updated_at": "2026-05-29 08:48:12.981568+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "ai-products", "ai-tools", "mlops"], "entities": ["EV-QA-Framework", "Isolation Forest", "LSTM", "CAN bus", "FastAPI", "WebSocket", "Chart.js", "Docker"], "alternates": {"html": "https://wpnews.pro/news/show-hn-ev-qa-framework-ml-powered-qa-for-electric-vehicle-battery-systems", "markdown": "https://wpnews.pro/news/show-hn-ev-qa-framework-ml-powered-qa-for-electric-vehicle-battery-systems.md", "text": "https://wpnews.pro/news/show-hn-ev-qa-framework-ml-powered-qa-for-electric-vehicle-battery-systems.txt", "jsonld": "https://wpnews.pro/news/show-hn-ev-qa-framework-ml-powered-qa-for-electric-vehicle-battery-systems.jsonld"}}