Entrance

One of the most important steps in all kinds of manufacturing is inspection and error detection. Machine vision controllers and applications known as Automatic Optical Inspection or AOI for short can be performed in the manufacture of printed circuit boards (PCBs). However, due to the increasing complexity, the use of compact components and cards makes it even more difficult for machine vision systems to keep up.

In reality, machine vision is often thought of as a simple kind of AI when it is not actually intelligent and is defined as a structure that requires that every step and condition, known ashard-code intelligence, be programmed into the system. As PCBs become more complex, programs can also become more complex and cumbersome, causing errors. With visual inspection, it becomes almost impossible in practice to try to program every way that the PCB may have a defect or malfunction.

A company is creating an AI solution to power AOI to eliminate this situation. With artificial intelligence, it began to work to identify errors and flaws in a self-evolving environment, and AAEON supported this company to help build and develop hardware to power AOI application AI's.

Challenges

AOI is an intensive and difficult application. It requires not only high-performance software but an equally powerful and high-performance hardware system. This creates several challenges to improve the system.

High Processing Demand

To process images and signals quickly and accurately, AOI requires a system with high computing power and processor performance.

Visual and AI Processing

To fully meet the needs of AOI, the system needs to support expansion cards such as graphics/GPU cards or neural accelerator modules to process images and power the AI system.

Cameras and Sensors

Different machines have different configurations and components, from the number of cameras and sensors to the type. To meet the full potential of the AI-powered AOI solution, the system needs to support a range of I/O connections.

Solution

AAEON worked closely with the developer and provided the best solution for the task through our manufacturer services. The BOXER-6841M with AI Core XP8was selected as the best solution for AOI powered by AI.

Intel Processors

The BOXER-6841M supports 6th and 7th Generation Intel Core processors, as well as Intel Xeon server-class processors. Paired with up to 32GB of memory, the BOXER-6841M offers the high-performance processing required for the most demanding applications.

Extensibility

The BOXER-6841M offers a number of expansion bay configurations, such as PCIe [x16], PCIe [x8] , and PCIe [x1]. This allows users to add expansion cards to help Edge computing applications, such as the AI Core XP8 module with eight Intel Movidius Myriad X VPU.

Impressive I/O

The BOXER-6841M is designed for embedded industrial applications and comes with an impressive array of I/O ports to easily integrate into any project. With five LAN ports and four USB 3.0 ports, it can be connected to a wide range of cameras and sensors for use in AOI and other applications.

Real Impact…

With the powerful BOXER-6841M, the developer can push its applications to their full potential and create an AOI system that can review multiple product lines, quickly train for new products, or detect previously unknown flaws without the need for restructuring. The system will help PCB manufacturers save costs and increase productivity with greater accuracy and fewer errors than traditional machine vision-based AOI. This means happier customers for manufacturers.

Product

AAEON's BOXER-6841M system is a powerful embedded Industrial PC designed for the most demanding machine vision and AI Edge applications. Supporting 7th generation Intel Core and Intel Xeon Server Class processors, the BOXER-6841M delivers up to 32GB of memory. The BOXER-6841M series offers a combination of expansion options including PCIe [x16], PCIe [x8] and PCIe [x1]. This can be extended with frame-capture cards for machine vision applications, or allows for further acceleration with cards such as the NVIDIA GeForce GTX 1080 or AI Core XP8 from AAEON.

The AI Core XP8 is a PCIe [x4] expansion card with eight Intel Movidius Myriad X modules. This innovative module delivers speeds of up to 840 fps (typical 560 typical) to power the most demanding AI applications. By installing AI inference on AI Core XP8, it allows the system processor to perform other concurrent tasks and improves overall system performance. The AI Core XP8 is also compatible with AI frameworks such as the Intel OpenVINO toolkit and TensorFlow.