Grün HPB Series AI SWIR Sorting System

Plastic bottles present a sorting challenge defined by the complexity of mixed waste streams — PET, HDPE, and other polymers arrive commingled with varying colors, labels, and contamination levels, making manual or single-sensor sorting both inefficient and unreliable. For recycling plants operating PET bottle lines and waste sorting centers processing municipal solid waste, the ability to accurately separate materials by both polymer type and color in a single pass directly determines the purity of output streams, the efficiency of downstream recycling, and the commercial value of recovered material. Intelligent multi-spectral sorting is the key to transforming mixed waste into pure, market-ready material streams — efficiently, reliably, and at scale.

The Grün HPB Series is an intelligent multi-spectral sorting system custom-designed for recycling plants (PET bottle lines) and waste sorting centers (MSW processing facilities). Leveraging the fusion of cutting-edge InGaAs-SWIR and high-resolution RGB (HR-RGB) imaging technology powered by proprietary AI algorithms, the system performs simultaneous color and polymer identification across mixed waste streams — automatically classifying PET, HDPE, and other plastics with exceptional accuracy in a single pass.

AI-driven surface defect recognition algorithms — trained on real-world production data using deep learning, with sorting precision refined continuously — ensure consistently high sorting accuracy across diverse waste compositions and contamination conditions — helping processors maximize material recovery, deliver high-purity output streams, and meet the exacting standards of modern recycling operations with unmatched confidence.

Technical Features

● Simultaneous Dual-Sensor  Detection

✦ Cutting-edge InGaAs-SWIR Camera System identifies polymer types (PET/HDPE/PP, etc.) by analyzing their unique near-infrared spectral signatures.

✦ High-Resolution RGB Camera System classifies bottles by color variation (clear/blue/green/contaminated) with precise chromatic discrimination.

● Proprietary AI Deep Learning Algorithms 

✦ Automatically classifies bottles, caps, labels, and contaminants (metal, silicone) by leveraging visual feature recognition to complement sensor-based material identification.

✦ Continuously enhances sorting performance through deep learning, adapting to new materials and complex patterns such as printed-label bottles.

✦ Reliably handles challenging scenarios, including reflective, black, and crushed bottles, ensuring consistent accuracy across diverse feed conditions.

● High-Performance Belt Sorting

✦ The modular belt system offers 1200 to 2800 mm width options (1200/2000/2800) and 2 to 6 tons/hour throughput for maximum flexibility. Modular belt system available in three width options — 1200 / 2000 / 2800 mm — paired with a throughput range of 2–6 tons/hour, providing flexible configuration to match varying capacity requirements.

✦ Three nozzle configurations available — 88 / 160 / 224 precision nozzles — with a response time of ≤1 ms and an ejection accuracy of ±2 mm, ensuring precise and reliable material separation at high speed.

Applications

Benefits

✦ SWIR polymer identification with RGB color classification delivers cleaner material streams, reducing cross-contamination between PET, HDPE, PP, and color fractions.

✦ Precise detection of bottles, caps, labels, and contaminants maximizes recoverable material yield while minimizing good product loss.

✦ Automated classification of challenging items (reflective, black, crushed, and printed-label bottles) lowers labor costs and improves consistency.

✦ Cleaner, well-sorted fractions reduce reprocessing steps, lower equipment wear, and support higher-quality recycled material output.

Specifications