Course Outline

Introduction to Edge AI in Industrial Settings

  • The significance of edge computing in manufacturing environments
  • A comparative analysis of edge computing versus cloud-based AI solutions
  • Practical applications in visual inspection, predictive maintenance, and real-time control

Hardware Platforms and Device-Level Constraints

  • An overview of common edge hardware platforms (Raspberry Pi, NVIDIA Jetson, Intel NUC)
  • Considerations for processing power, memory, and energy efficiency
  • Selecting the appropriate platform based on specific application requirements

Model Development and Optimization for Edge Deployment

  • Techniques for model compression, pruning, and quantization to enhance performance
  • Utilizing TensorFlow Lite and ONNX for efficient embedded deployment
  • Balancing accuracy with speed in resource-constrained environments

Computer Vision and Sensor Fusion at the Edge

  • Implementing edge-based visual inspection and monitoring systems
  • Integrating data from various sensors (vibration, temperature, cameras) for comprehensive insights
  • Real-time anomaly detection using tools like Edge Impulse

Communication and Data Exchange in Industrial Settings

  • Utilizing MQTT for robust industrial messaging
  • Integrating with SCADA, OPC-UA, and PLC systems to ensure seamless data flow
  • Enhancing security and resilience in edge communication networks

Deployment and Field Testing of Edge AI Solutions

  • Packaging and deploying models on edge devices for government applications
  • Monitoring system performance and managing software updates
  • Case study: Implementing a real-time decision loop with local actuation

Scaling and Maintenance of Edge AI Systems

  • Strategies for effective edge device management
  • Procedures for remote updates and model retraining cycles
  • Long-term lifecycle considerations for industrial-grade deployment

Summary and Next Steps

Requirements

  • A comprehensive understanding of embedded systems or Internet of Things (IoT) architectures
  • Practical experience with Python or C/C++ programming languages
  • Knowledge of machine learning model development processes

Audience for Government

  • Embedded systems developers
  • Industrial IoT teams within public sector organizations
 21 Hours

Number of participants


Price per participant

Upcoming Courses

Related Categories