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
Fundamentals of Edge AI in Industrial Contexts
- The significance of edge computing in the manufacturing sector
- Contrasting edge AI with cloud-based alternatives
- Practical applications in visual inspection, predictive maintenance, and process control
Hardware Architectures and Device-Level Limitations
- Survey of prevalent edge hardware, including Raspberry Pi, NVIDIA Jetson, and Intel NUC
- Key factors in processing power, memory allocation, and energy consumption
- Criteria for selecting appropriate platforms based on specific application requirements
Model Engineering and Optimization for Edge Deployment
- Techniques for model compression, pruning, and quantization
- Leveraging TensorFlow Lite and ONNX for embedded environments
- Achieving an optimal balance between model accuracy and inference speed under constraints
Edge-Based Computer Vision and Sensor Fusion
- Edge-driven visual inspection and continuous monitoring solutions
- Aggregating and correlating data from diverse sensors, such as vibration, temperature, and cameras
- Implementing real-time anomaly detection using Edge Impulse
Data Communication and Exchange Mechanisms
- Utilizing MQTT for efficient industrial messaging
- Seamless integration with SCADA, OPC-UA, and PLC ecosystems
- Ensuring security and robustness in edge network communications
Deployment Strategies and Field Validation
- Packaging and deploying AI models onto edge hardware
- Monitoring operational performance and managing software updates
- Case study: Implementing real-time decision loops with local actuation
Scaling and Maintaining Edge AI Ecosystems
- Strategies for managing fleets of edge devices
- Executing remote updates and establishing model retraining cycles
- Long-term lifecycle planning for industrial-grade deployments
Recap and Future Directions
Requirements
- Foundational knowledge of embedded systems or IoT architectures
- Practical experience in Python or C/C++ programming
- Working familiarity with machine learning model development lifecycles
Target Audience
- Embedded system developers
- Industrial IoT engineering teams
21 Hours
Testimonials (1)
That we can cover advance topic and work with real-life example
