¶ RZ/V2L Factory Automation
¶ ℹ️ Introduction to the Board
The Renesas RZ/V2L processor-based development kit is the ideal development platform for a variety of different vision-AI and edge AI applications, solving modern design problems for ease-of-use and fast prototyping.The innovative RZ/V2L processor is equipped with a 1.2GHz Dual-Core Arm Cortex-A55, a 200MHz Cortex-M33 core for real-time applications, and a 3D Graphics and Video Codec Engine.This processor SoC further differentiates itself with an on-chip DRP-AI accelerator, making it ideal for implementing cost-and power efficient embedded-vision applications.This vision-AI accelerated development board is ideal for embedded vision, healthcare, home and building automation, industrial Internet of Things, security and surveillance application designs
Onboard memory includes 2GB DDR4, 32GB eMMC and 16MB QSPI flash memory, plus microSD slot for removable media
¶ 💡 Board Features
- RZV2L Board is engineered in a compact Raspberry Pi form-factor with a versatile set of expansion interfaces, including Gigabit Ethernet, 801.11ac Wifi and Bluetooth 5, two USB 2.0 hosts and a USB 2.0 OTG interface, MIPI DSI and CSI camera interfaces, CAN FD interface, Pi-HAT compatible 40-pin expansion header and Click Shuttle expansion header
- DRP-AI consists of “DRP core” and “MAC circuit”. It realizes high speed processing, and low power consumption
- Software enablement includes CIP Kernel based Linux BSP (maintained for 10 years+) plus reference designs that highlight efficient vision AI implementations using the DRP-AI core
- Onboard 10-pin JTAG/SWD miniheader and 4-pin UART header enable the use of an external debugger and USB-serial interface.
¶ 💡 Key Specifications
- The Lab setup emulates an industrial manufacturing unit where Renesas Vision-AI is used to autonomously identify the faulty items (anomalies) & assure quality of the production line.
- The demo system has two significant parts. 1) The RZboard for hosting AI application 2) Lego conveyor for emulating the production line.
- The Avnet RZ/V2L board is connected to the network using ethernet cable.
- It operates in 2 modes Simple mode (single click operation) & Advanced mode (user defined Detection Threshold, Conveyor Speed & Direction control).
- The output of the system will be displayed on the screen with cross (X) marks enveloped in square
¶ 📝 Steps to Evaluate the Design
¶ 📑 Frequently Ask Questions
1. What are the key features of the Avnet RZBoard V2L?
The RZBoard V2L boasts a 1.2GHz dual-core Arm® Cortex®-A55 CPU, a 200MHz Cortex-M33 core for real-time processing, an Arm Mali-G31 3D GPU, and an Image Scaling Unit. It includes an on-chip DRP-AI accelerator and supports H.264 video encoding/decoding at 1920 x 1080 resolution. The board adopts a Raspberry Pi form factor, facilitating compatibility with various expansion interfaces.
**2. How does the RZBoard V2L contribute to factory automation? **
In factory settings, the RZBoard V2L enables real-time anomaly detection on production lines. By processing visual data, it can autonomously identify defective items, ensuring quality control and reducing the need for manual inspections.
3. What role does the DRP-AI accelerator play in the RZBoard V2L?
The DRP-AI (Dynamically Reconfigurable Processor for AI) accelerator enhances the board's ability to perform AI inference tasks efficiently. It allows for real-time processing of complex algorithms like TinyYoloV2, enabling high-speed image recognition with low power consumption.
4. Can you explain the significance of the TinyYoloV2 algorithm in this setup?
TinyYoloV2 is a lightweight version of the You Only Look Once (YOLO) object detection algorithm. Optimized for real-time processing, it enables the RZBoard V2L to detect anomalies at speeds up to 20 frames per second, facilitating immediate identification of defects on production lines.
5. What are the power consumption characteristics of the RZBoard V2L
Designed for energy efficiency, the RZBoard V2L operates with a power consumption of less than 5 watts. This low power requirement supports its use in environments where energy efficiency is critical.
6. How does the lab setup emulate an industrial manufacturing unit?
The lab setup includes a LEGO conveyor equipped with an IR sensor to detect objects and control motion. A camera feed provides real-time visual data to the RZBoard V2L, which processes the information to detect anomalies. Additionally, voltage and current sensors monitor power consumption, offering insights into the system's energy usage.
7. What operational modes are available in the lab setup?
The system supports both automatic and manual operation modes. In automatic mode, the RZBoard V2L autonomously detects anomalies and controls the conveyor accordingly. In manual mode, users can adjust the speed and direction of the conveyor, allowing for customized testing and observation.
8. How is anomaly detection threshold configured?
Users can manually set the anomaly detection threshold, defining the sensitivity of the system to defects. This configurability allows for adaptation to various quality control standards and specific application requirements.
9. What types of anomalies can the system detect?
Leveraging the TinyYoloV2 algorithm, the system can identify a range of visual anomalies, such as dents, scratches, or misalignments on products. The detection capabilities can be tailored by training the AI model on specific defect types relevant to the manufacturing process.
10. Is the RZBoard V2L suitable for deployment in harsh industrial environments?
While the RZBoard V2L features a fanless, compact design conducive to various settings, its suitability for harsh industrial environments depends on factors like exposure to dust, moisture, and extreme temperatures. Protective enclosures and environmental controls may be necessary to ensure reliable operation in such conditions.
11. How does the RZBoard V2L interface with other factory automation systems?
The board's versatile expansion interfaces allow for integration with various sensors, actuators, and communication modules. This flexibility enables seamless connectivity with existing factory automation systems, facilitating data exchange and coordinated control.
12. What development resources are available for the RZBoard V2L?
Developers have access to comprehensive documentation, user guides, and software libraries provided by Avnet and Renesas. These resources support the development and deployment of custom applications tailored to specific industrial automation needs.
¶ 🔗 Reference Links
Product page: Click Here
Discussion Forum: Click Here
Renesas DRP-AI: Click Here
Renesas DRP-AI: Click Here
DRP-AI Tutorial:: Click Here
Github DRP-AI: Click Here
RZ_V series introduction(JP): Click Here
Visual Inspection Solution demo page: Click Here
RZ_V series introduction(EN): Click Here
Lego Setup: Click Here