LI Optical Waste Separator, NIR Scanning

Sorting Principle:

After pre-sorting (manual picking and/or screening), waste is fed via a belt conveyor into a hopper and then onto a vibrating plate, which transfers the material into the feeding chutes.

The material (waste) flows freely down the chutes and is scanned by sensors from both sides. The signals from the sensors are sent to a processor. If the processor detects a "target image," it triggers the corresponding ejector. The ejector removes impurities from the product stream using a focused jet of compressed air.

The "Deep Learning + NIR" sorting technology combines deep machine learning with near-infrared (NIR) sensors for highly accurate identification of raw materials by material type, color, and appearance. It can also identify different shapes of the same material.

Deep learning is a subset of machine learning that essentially functions as a neural network for the sorting camera. These neural networks attempt to mimic the behavior of the human brain (though far from matching its full capabilities), allowing the system to "learn" from large volumes of data.

Deep learning makes the optical sorter more akin to an Artificial Intelligence (AI), operating and performing its analytical tasks without human intervention. This technology enables the optical sorter to perform not only color sorting but also analysis of an object's shape, size, and structure. This system allows our optical sorter to handle more complex sorting tasks.