Share this page

GAIN Intelligence

Deep learning add-on solution for unrivaled sorting accuracy


GAIN is an optional software-based technology that analyzes images and data to enable AUTOSORT machines to perform tasks more effectively over time. The data-driven innovation continually learns to differentiate recyclable vs non-recyclable materials that are difficult to sort using conventional technology and excels in removing contaminants with similar properties.

Specially programmed by TOMRA software engineers, GAIN uses a neural network that holds thousands of images to make a pool of valuable object information. The network is trained to recognize complex patterns and properties as objects pass along the sensors on the high-speed conveyor belt and connects the information pool to the applicable sorting task.

NEW: GAIN for wood chips
GAIN is now available for wood recycling applications. It delivers clean recycled wood chip fractions by differentiating between non-processed wood (wood A) and processed wood (wood B).

GAIN purifies wood chips by removing impurities such as:
• MDF (medium density fiberboard)
• HDF (high density fiberboard)
• WPC (wood polymer composites)
• OSB (oriented strand board)
• Chipboard
• Plywood

GAIN for silicone cartridges
GAIN purifies post-consumer polyethylene (PE) streams by removing PE-silicone cartridges and non-PE objects. Even if the silicon cartridges are bundled, damaged or deformed, GAIN detects and separates the objects from clean PE fractions, giving plastic recyclers a significant competitive advantage.

Your benefits:
• Unrivaled post-consumer PE purity levels
• Great adaptability
• Supports maximum belt speed