Sensor sorting specialist TOMRA Recycling has further strengthened its offering for the global wood recycling industry by becoming the first in the world to use deep learning, a subset of artificial intelligence, in applications wood recycling.
The company has combined its industry-leading AUTOSORT® technology with its deep learning-based sorting add-on, GAIN, to create a solution that can distinguish and sort different types of wood-based materials, significantly improving customers’ sorting and manufacturing processes. .
The main application of TOMRA Recycling’s new solution is sorting Wood A – unprocessed wood – from Wood B – processed wood products such as MDF (medium density fibreboard), HDF (high density fibreboard), oriented strand board (OSB) and particle board.
TOMRA Recycling has been a leader in the global wood recycling industry for over 10 years. The company’s X-TRACT solution quickly caught on with particleboard manufacturers to produce a clean fraction of recycled wood chips by sorting and separating inert materials (glass, stones, ceramics, etc.) and metals. Once the X-TRACT unit has removed these impurities, the recovered wood chips are of a high enough quality to be used in the production of standard particleboard.
Achieve higher levels of purity
In recent years, however, TOMRA Recycling has been approached by an increasing number of customers looking to use recycled wood of a much higher level of purity in their production processes. To achieve these specific purity requirements, in addition to removing inert material and metals in the feed stream, other impurities including engineered wood composites as well as polymers would need to be removed.
As these materials are not distinguishable using X-ray technology, the X-TRACT unit was not suitable for this sorting task. Determined to help these customers and recognizing a potential gap in the market for a solution that would allow companies in the wood recycling industry to optimize their wood sorting processes, the deep learning experts at TOMRA Recycling developed an application that combines TOMRA’s industry-leading AUTOSORT® unit with its deep learning-based sorting add-on, GAIN.
TOMRA’s Wood A vs Wood B app uses deep learning technology to sort and extract impurities that could not be detected before, allowing for the first time to detect, analyze and sort every type of wood different, thereby cleaning the real wood fraction.
TOMRA is the first company in the world to use deep learning technology to detect and separate different types of wood, targeting B-wood (processed wood composites) as impurities to leave a clean A-wood fraction (unprocessed wood) , or, according to customers’, producing individual high-purity engineered wood composite fractions from the feed stream.
Philipp Knopp, Product Manager at TOMRA Recycling, comments: “Wood recycling is a rapidly changing market, with increasingly stringent legislation being introduced in a number of parts of the world to move towards a more cost efficient model. circular. Our AUTOSORT® with GAIN solution uses deep learning technology to create a robust and flexible solution that we are confident will be well received by wood product producers worldwide. This will also allow our customers to use in the future
prove 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 on the market to offer this solution based on artificial intelligence.
About TOMRA Recycling
TOMRA Recycling designs and manufactures sensor-based sorting technologies for the global recycling and waste management industry. Over 7,400 systems have been installed in over 100 countries around the world.
Responsible for developing the world’s first high-capacity near-infrared (NIR) sensor for waste sorting applications, TOMRA Recycling remains an industry pioneer dedicated to extracting high-purity fractions from waste streams that maximize both yield and profit.
TOMRA Recycling is part of TOMRA which also develops sensor-based systems for sorting, peeling and process analysis for the food, mining and other industries.
TOMRA Recycling is owned by the Norwegian company TOMRA Systems ASA, which is listed on the Oslo Stock Exchange. Founded in 1972, TOMRA Systems ASA has sales of around 995 million euros and employs around 4,300 people worldwide.