SORTATION | TECHNOLOGY


and identify in heterogeneous material flows. Impu- rities or differentiating good or bad material based on shape, colour and texture can be detected using a multivariant method, efficiently sorted out by blow nozzles, according to Andreas Hanus, Development Engineer and Product Owner Plastics Recycling at Sesotec. Also new is NIR-Ai, which can differentiate between optically similar plastic products, for example such as monolayer PET and multilayer PET. The ability of NIR-Ai to differentiate between closely similar or vastly different polymers using spectral analysis leads to increased accuracy and adaptability of the sorting process, and improved sorting performance, especially for mixed plastics and plastics with additives, Sesotec said. The NIR-Ai solution is available for all Varisort+ family models and can be retrofitted onto existing units. Object-Ai is available currently for the Varisort+ Film, Flex and Unity models, as these systems are supplied with AI capable hardware as standard.


Pre-sorting


Sesotec also developed a mobile multi-sensor pre-sorting system for plastic regrind. Its Pre-Sort VCM model incorporates a colour, metal and NIR sensor to reliably detect and separate plastic types, colours and metals from regrind of various quali- ties. The fully automated, compact system com- bines several standard Sesotec technologies into a single unit on a mobile platform. This includes use of the Varisort Compact multi-sensor system, featuring state-of-the-art signal evaluation tech- nologies that, with the sensors, guarantees high detection accuracy and an evaluation of up to 500,000 parts/sec. Other features include a counterflow classifier system that separates dust and fine particles from the ground material, and a standard central vacuum conveying system that ensures smooth material transport through the dedusting system to the Varisort Compact unit. A central control unit connects the conveyor technology, deduster and sorting unit. It has an integrated start and stop function to ensure optimal operating convenience. The components of the Pre-Sort unit are factory installed onto a structural platform designed for rapid commissioning, the company said. Pre-Sort VCM works with Class 1 materials that have a low level of impurities and up to 10% foreign matter, Class 2 materials with medium to high contamination levels and up to 35% foreign matter, and Class 3 materials that have a colour mixture of materials that require a pre-sorting stage to sort out several material fractions. The unit


www.plasticsrecyclingworld.com


delivers throughput up to 600 kg/hr.and handles grain sizes from 2-10 mm. The addition of AI-powered capability is the most


recent sorting development from US optical plastics sorting equipment supplier MSS Optical, the optical recycling division of CP Group. It is launch- ing Vivid AI, a complementary technology to its Cirrus family of optical sorters for recycling plastics containers, flexible packaging, and flake materials. The addition of the AI component builds on the


identification technologies that its models with NIR technology do not have, the company said, allowing for the detection and sorting of more classes of material. The incorporation of AI technol- ogy will allow for enhanced plastics material sorting, such as differentiating PET bottles from PET thermoformed products.


Vision-based AI The core of MSS’ new Vivid AI solutions is the incorporation of intelligence technology devel- oped by London-based technology company Recycleye that provides deeper levels of data and analysis for finer classifications of individual product and material categories. The company’s Recycleye AI sensor captures images of the items on the conveyor belt which it sends to Recycleye Vision, the company’s AI central processing software which contains millions of product images of materials, packaging and container types, and a custom-build data neural network from which the captured images from actual MRFs and recycling centres are compared for identification. The immediate identification of objects by the


Recycleye technology allows sorting machines to make a yes/no sorting decision in real-time. The neural network’s data collection is continuously growing to accommodate new types of material and expand the characterisation of known materials. MSS offers its Vivid AI in two versions. Vivid Air


September 2024 | PLASTICS RECYCLING WORLD 17


Above: The PlasticMax unit from MSS Optical can operate at a capacity of 2-12 tonnes/hr


IMAGE: MSS OPTICAL


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44