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
Introduction to Edge AI in Industrial Environments
- The significance of edge computing in modern manufacturing.
- A comparative analysis of edge AI versus cloud-based AI.
- Practical applications in computer vision, predictive maintenance, and process control.
Hardware Platforms and Device-Level Limitations
- An overview of standard edge hardware, including Raspberry Pi, NVIDIA Jetson, and Intel NUC.
- Key considerations regarding processing power, memory, and energy consumption.
- Choosing the optimal platform based on the specific application requirements.
Model Development and Optimization for Edge
- Techniques for model compression, pruning, and quantization.
- Deploying models to embedded systems using TensorFlow Lite and ONNX.
- Achieving the right balance between accuracy and speed in resource-constrained environments.
Computer Vision and Sensor Fusion at the Edge
- Implementing visual inspection and monitoring capabilities at the edge.
- Aggregating data from diverse sensor sources, such as vibration, temperature, and cameras.
- Performing real-time anomaly detection using Edge Impulse.
Communication and Data Exchange
- Utilizing MQTT for efficient industrial messaging.
- Interfacing with SCADA, OPC-UA, and PLC systems.
- Ensuring security and robustness in edge communication layers.
Deployment and Field Testing
- Packaging and releasing models onto edge devices.
- Tracking performance metrics and managing software updates.
- Case study: Establishing a real-time decision loop with local actuation.
Scaling and Maintenance of Edge AI Systems
- Strategies for managing fleets of edge devices.
- Handling remote updates and continuous model retraining cycles.
- Addressing lifecycle requirements for industrial-grade deployments.
Summary and Next Steps
Requirements
- Solid knowledge of embedded systems or IoT architectures.
- Proficiency in Python or C/C++ programming.
- Working experience with machine learning model development.
Target Audience
- Embedded systems developers.
- Industrial IoT engineering teams.
21 Hours
Testimonials (1)
That we can cover advance topic and work with real-life example
