AI Engineering
| Type of study | Bachelor |
|---|---|
| Language of instruction | Czech |
| Code | 450-2110/01 |
| Abbreviation | AIINZ |
| Course title | AI Engineering |
| Credits | 4 |
| Coordinating department | Department of Cybernetics and Biomedical Engineering |
| Course coordinator | prof. Ing. Radek Martinek, Ph.D. |
Subject syllabus
Lectures:
1. AI Fundamentals for Engineers: Basic AI principles. Traditional ML vs. LLM. Prompt engineering: clear requirements, iterative dialog, role-based prompting. Context engineering for technical tasks. Industrial applications.
2. AI Tools Ecosystem for Development: Types of AI assistants – conversational, IDE-integrated (GitHub Copilot, Cursor, Codex, Claude), local solutions (Ollama). Installation and configuration.
3. Version Control and Collaboration with Git: Git fundamentals, team workflow. GitHub/GitLab: pull requests, code review, issue tracking. AI assistants for git: commit message generation, explaining changes, conflict resolution.
4. Linux, Bash, and Python for Industrial Applications: Linux in industry: embedded systems, edge devices, industrial servers. Bash scripting: automation, file operations, process management. Python ecosystem, virtual environments, and core libraries. AI-assisted coding in Python. Jupyter notebooks. Scripting for industrial task automation.
5. Industrial Data Analysis: Exploratory data analysis (EDA). Cleaning and preprocessing sensor and PLC data. Time series analysis. Industrial data visualization. Pandas library and visualization creation.
6. Machine Learning in Industry: ML basics: supervised learning, unsupervised learning. Typical industrial applications: predictive maintenance, anomaly detection, quality control. Feature engineering. Model selection and evaluation. Practical use of scikit-learn, TensorFlow libraries.
7. PLC Programming and AI Assistants: Introduction to PLC: hardware, programming languages. Industrial communication protocols: Modbus, OPC UA, MQTT. AI assistants for PLC code: logic generation, testing, debugging, documentation.
8. Robotics and AI: Industrial robotics fundamentals: kinematics, path planning, coordinate systems. Robot Operating System (ROS). AI for robotic applications. Robotic system simulation.
9. Cloud Engineering and Linux for Industry: Linux in cloud and edge: systemd services, process management, networking. Cloud platforms: AWS, Azure, Google Cloud – core services. Containerization: Docker, docker-compose. Infrastructure as Code. Edge computing vs. cloud processing. IoT platforms for industrial data. Remote access and SSH.
10. API Integration and Industrial Systems: REST API: GET, POST, PUT, DELETE. API authentication and security. Industrial system integration via API. Websockets for real-time data. AI assistants for API work: request generation, response parsing.
11. Prompt and Context Engineering for Technical Tasks: Advanced prompt engineering techniques for engineering tasks. Context design and management for complex projects. System instructions for technical domains. Building agent systems for intelligent industrial assistants.
12. Vibe-coding and Rapid Prototyping: Vibe-coding concept: rapid functional prototype creation with AI. Micro-applications: dashboards, visualization tools, automation scripts. From prototype to production solution. Best practices and anti-patterns.
13. Code Review, Debugging, and Optimization with AI: AI for systematic bug and security issue detection. Debugging workflow: error log analysis, stack traces, hypothesis generation. Industrial application performance optimization. Legacy code refactoring. Static analysis tools. AI ethics in Industrial applications. Future trends.
Laboratories:
1. Development Environment Setup: Linux basics: terminal navigation, basic commands. Installing VS Code, Python, git on Linux/WSL. Configuring AI assistants. GitHub account setup. Clone repository, first commit.
2, Git Fundamentals: Repository creation, basic git workflow. Branches, merge, conflict resolution. GitHub pull requests and code review. AI-assisted commit messages. Collaborative team exercises.
3. Bash and Python Scripting for Industry: Bash scripts for automation. File processing, log parsing. Cron jobs for periodic tasks. Python scripting: reading CSV/Excel data. Basic Pandas operations. Sensor data processing automation. AI-assisted script creation. Error handling and logging.
4. Time Series Data Analysis: Loading industrial data from PLC/SCADA systems. Exploratory analysis. Anomaly detection in time series. Trend visualization. AI-assisted data cleaning.
5. Visualization and Dashboards: Interactive visualization and dashboards in Python. AI for visualization generation.
6. Machine Learning: Dataset preparation for ML. Feature engineering. Training simple ML models. Model evaluation. Result interpretation for industrial practice.
7. PLC Programming Basics: PLC environment simulator. Creating simple Ladder Logic programs. AI assistants for PLC code. Debugging PLC logic.
8. Industrial Communication and Protocols: Modbus communication – reading registers. MQTT pub/sub for IoT. OPC UA client-server communication. Python libraries for industrial protocols. AI for communication code generation.
9. Linux, Docker, and Containerization: Linux process management: ps, top, htop, systemctl. Networking: ifconfig, netstat, curl, wget. Docker basics: images, containers, volumes. Dockerfile creation for Python applications. Industrial application deployment in containers. AI-assisted Docker configuration and Bash scripts.
10. Cloud Integration and SSH: SSH fundamentals: remote access, key-based authentication, SCP, SFTP. Cloud platform registration (AWS/Azure free tier). Connecting to Linux VM via SSH. Storage services: storing industrial data in cloud. Compute services: running analysis in cloud. AI for Infrastructure as Code and Bash scripts on remote server.
11. REST API and System Integration: Creating REST API with FastAPI. CRUD operations for industrial data. API documentation with OpenAPI. Calling external APIs. AI for API development.
12. Robotics – Simulation and Programming: Robotic arm simulation (ROS/Gazebo or simpler tool). Robot kinematics basics. Path planning tasks. Computer vision for robotic applications – object detection. AI assistants for robotics code.
13. Vibe-coding Project – Micro-application: Rapid prototyping: micro-application design and implementation (e.g., monitoring dashboard, data analyzer, automation tool). Iterative development with AI. Cloud deployment. Results presentation. Docummentation with AI assistance. Code review in groups.
1. AI Fundamentals for Engineers: Basic AI principles. Traditional ML vs. LLM. Prompt engineering: clear requirements, iterative dialog, role-based prompting. Context engineering for technical tasks. Industrial applications.
2. AI Tools Ecosystem for Development: Types of AI assistants – conversational, IDE-integrated (GitHub Copilot, Cursor, Codex, Claude), local solutions (Ollama). Installation and configuration.
3. Version Control and Collaboration with Git: Git fundamentals, team workflow. GitHub/GitLab: pull requests, code review, issue tracking. AI assistants for git: commit message generation, explaining changes, conflict resolution.
4. Linux, Bash, and Python for Industrial Applications: Linux in industry: embedded systems, edge devices, industrial servers. Bash scripting: automation, file operations, process management. Python ecosystem, virtual environments, and core libraries. AI-assisted coding in Python. Jupyter notebooks. Scripting for industrial task automation.
5. Industrial Data Analysis: Exploratory data analysis (EDA). Cleaning and preprocessing sensor and PLC data. Time series analysis. Industrial data visualization. Pandas library and visualization creation.
6. Machine Learning in Industry: ML basics: supervised learning, unsupervised learning. Typical industrial applications: predictive maintenance, anomaly detection, quality control. Feature engineering. Model selection and evaluation. Practical use of scikit-learn, TensorFlow libraries.
7. PLC Programming and AI Assistants: Introduction to PLC: hardware, programming languages. Industrial communication protocols: Modbus, OPC UA, MQTT. AI assistants for PLC code: logic generation, testing, debugging, documentation.
8. Robotics and AI: Industrial robotics fundamentals: kinematics, path planning, coordinate systems. Robot Operating System (ROS). AI for robotic applications. Robotic system simulation.
9. Cloud Engineering and Linux for Industry: Linux in cloud and edge: systemd services, process management, networking. Cloud platforms: AWS, Azure, Google Cloud – core services. Containerization: Docker, docker-compose. Infrastructure as Code. Edge computing vs. cloud processing. IoT platforms for industrial data. Remote access and SSH.
10. API Integration and Industrial Systems: REST API: GET, POST, PUT, DELETE. API authentication and security. Industrial system integration via API. Websockets for real-time data. AI assistants for API work: request generation, response parsing.
11. Prompt and Context Engineering for Technical Tasks: Advanced prompt engineering techniques for engineering tasks. Context design and management for complex projects. System instructions for technical domains. Building agent systems for intelligent industrial assistants.
12. Vibe-coding and Rapid Prototyping: Vibe-coding concept: rapid functional prototype creation with AI. Micro-applications: dashboards, visualization tools, automation scripts. From prototype to production solution. Best practices and anti-patterns.
13. Code Review, Debugging, and Optimization with AI: AI for systematic bug and security issue detection. Debugging workflow: error log analysis, stack traces, hypothesis generation. Industrial application performance optimization. Legacy code refactoring. Static analysis tools. AI ethics in Industrial applications. Future trends.
Laboratories:
1. Development Environment Setup: Linux basics: terminal navigation, basic commands. Installing VS Code, Python, git on Linux/WSL. Configuring AI assistants. GitHub account setup. Clone repository, first commit.
2, Git Fundamentals: Repository creation, basic git workflow. Branches, merge, conflict resolution. GitHub pull requests and code review. AI-assisted commit messages. Collaborative team exercises.
3. Bash and Python Scripting for Industry: Bash scripts for automation. File processing, log parsing. Cron jobs for periodic tasks. Python scripting: reading CSV/Excel data. Basic Pandas operations. Sensor data processing automation. AI-assisted script creation. Error handling and logging.
4. Time Series Data Analysis: Loading industrial data from PLC/SCADA systems. Exploratory analysis. Anomaly detection in time series. Trend visualization. AI-assisted data cleaning.
5. Visualization and Dashboards: Interactive visualization and dashboards in Python. AI for visualization generation.
6. Machine Learning: Dataset preparation for ML. Feature engineering. Training simple ML models. Model evaluation. Result interpretation for industrial practice.
7. PLC Programming Basics: PLC environment simulator. Creating simple Ladder Logic programs. AI assistants for PLC code. Debugging PLC logic.
8. Industrial Communication and Protocols: Modbus communication – reading registers. MQTT pub/sub for IoT. OPC UA client-server communication. Python libraries for industrial protocols. AI for communication code generation.
9. Linux, Docker, and Containerization: Linux process management: ps, top, htop, systemctl. Networking: ifconfig, netstat, curl, wget. Docker basics: images, containers, volumes. Dockerfile creation for Python applications. Industrial application deployment in containers. AI-assisted Docker configuration and Bash scripts.
10. Cloud Integration and SSH: SSH fundamentals: remote access, key-based authentication, SCP, SFTP. Cloud platform registration (AWS/Azure free tier). Connecting to Linux VM via SSH. Storage services: storing industrial data in cloud. Compute services: running analysis in cloud. AI for Infrastructure as Code and Bash scripts on remote server.
11. REST API and System Integration: Creating REST API with FastAPI. CRUD operations for industrial data. API documentation with OpenAPI. Calling external APIs. AI for API development.
12. Robotics – Simulation and Programming: Robotic arm simulation (ROS/Gazebo or simpler tool). Robot kinematics basics. Path planning tasks. Computer vision for robotic applications – object detection. AI assistants for robotics code.
13. Vibe-coding Project – Micro-application: Rapid prototyping: micro-application design and implementation (e.g., monitoring dashboard, data analyzer, automation tool). Iterative development with AI. Cloud deployment. Results presentation. Docummentation with AI assistance. Code review in groups.
E-learning
Supporting materials are available at LMS https://lms.vsb.cz/
Literature
[1] MAŘÍK, Vladimír a KEIL, Robert. Průmysl 4.0: základ ekonomické transformace ČR. V Praze: Management Press, 2024. ISBN 978-80-7261-604-6.