Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Foundational Concepts of Edge AI in Industrial Contexts
- The significance of edge computing in production settings
- Application scenarios in visual inspection, predictive upkeep, and process control
Hardware Ecosystems and Device-Level Limitations
- Review of standard edge hardware (Raspberry Pi, NVIDIA Jetson, Intel NUC)
- Factors regarding processing power, memory capacity, and energy consumption
- Choosing the optimal platform based on specific application needs
Crafting and Tuning Models for Edge Deployment
- Utilizing TensorFlow Lite and ONNX for embedded implementation
- Striking a balance between accuracy and speed in resource-limited environments
Edge-Based Computer Vision and Multi-Sensor Fusion
- Implementing visual quality checks and monitoring at the edge
- Aggregating inputs from diverse sensors (vibration, thermal, optical)
- Detecting irregularities in real-time using Edge Impulse
Data Transmission and Inter-Device Exchange
- Applying MQTT for industrial message brokering
- Connecting with SCADA, OPC-UA, and PLC infrastructures
- Ensuring security and robustness in edge data channels
Rollout Strategies and On-Site Validation
- Tracking performance metrics and handling version updates
- Practical example: executing a real-time decision cycle with local actuation
Expanding and Sustaining Edge AI Infrastructures
- Strategies for overseeing distributed edge devices
Recap and Future Directions
Requirements
- Proficiency in embedded systems or IoT architectures
- Practical experience with Python or C/C++ programming
- Working knowledge of machine learning model creation
Target Participants
- Embedded software engineers
- Industrial IoT specialists
21 Hours
Testimonials (1)
That we can cover advance topic and work with real-life example
