TOMRA unveils deep learning technology for sorting wood
TOMRA has announced that it will be implementing deep learning technology in its wood recycling operations in order to distinguish between different types of material.
The recycling company claims that the use of artificial intelligence will ‘boost yield and purity’ across its activity, with the GAIN add-on being applied to the business’ established AUTOSORT technology in order to sort Wood A – non-processed wood – from Wood B – processed wood, including medium-density fiberboard (MDF); high-density fiberboard (HDF); oriented strand board (OSB); and chipboard.
Investment into the technology comes after calls from ‘an increasing number of customers’ who sought after recycled wood that was high in purity. This requires not only the removal of inert material and metals in the infeed stream, which TOMRA’s existing X-TRACT units already successfully executed, but also the removal of other impurities, including engineered wood composites and polymers. Such materials are not able to be distinguished with x-ray technology, which led to the development of the company’s deep-learning machinery.
Philipp Knopp, Product Manager at TOMRA Recycling, commented: “Wood recycling is a fast-evolving market, with increasingly stringent legislation being introduced in a number of regions globally to move towards a more circular economy model. Our AUTOSORT with GAIN solution uses deep learning technology to create a robust and flexible solution which we are confident will be welcomed by wood good producers across the globe.
“It will also enable our customers to future-proof their operations as they will be better equipped to adapt and react to any future changes in the global wood recycling market such as new legislation. We are delighted to be the first in the market to offer this artificial intelligence-based solution.”