Grün HPB Series AI-Driven Sorting System

Plastic bottle sorting faces a core challenge: the complexity of mixed waste streams. PET, HDPE, and other polymers are commingled with varying colors, inconsistent labels, and fluctuating contamination levels, which creates obvious efficiency and accuracy bottlenecks for manual sorting or single-sensor sorting systems. For recycling plants running PET whole-bottle recovery lines and MRFs processing municipal solid waste, the ability to efficiently sort by polymer type and target surface features in a single scan directly determines output purity, downstream recycling efficiency, and the commercial value of recovered materials.

The Grün HPB Series is an intelligent machine-vision-based sorting system tailored for this exact scenario. It integrates cutting-edge InGaAs-SWIR imaging with high-resolution RGB (HR-RGB) VIS imaging, paired with proprietary AI deep learning algorithms and high-performance air ejectors, to accurately identify and sort target polymers and surface features from mixed waste streams within milliseconds in a single pass.

Empowered by AI-driven surface feature recognition, the system continuously learns from real production data, steadily improving its detection accuracy. This means the equipment's performance is not static after deployment; instead, it continuously adapts and improves as production data accumulates, delivering stable and reliable sorting performance that helps recycling plants and MRFs significantly boost recovery efficiency and commercial value.

Technical Features

● High-Precision Simultaneous Polymer & Color Detection System

✦ Cutting-edge InGaAs-SWIR Imaging

Analyzes the unique short-wave infrared spectral absorption characteristics of various polymers across two different wavelength bands to efficiently identify polymer types (e.g., PET, HDPE, PP, etc.), achieving reliable polymer differentiation.

✦ High-Stability Halogen Illumination

Provides stable illumination across the full spectrum range; the air-cooled design helps maintain stable light output during operation and extends lamp lifespan.

✦ High-Resolution RGB (HR-RGB) VIS Imaging

Clearly presents material surface colors, ensuring the accuracy and stability of visual recognition.

✦ High-Intensity LED Illumination

Maintains a consistent imaging environment with clear and stable images, unaffected by external light changes, ensuring consistent detection results across different time periods and batches.

● Proprietary AI Deep Learning Algorithms 

✦ Visual Feature Recognition

Automatically classifies bottles, caps, label types, and contaminants (metal, silicone), complementing polymer type identification.

✦ AI Model Optimization

Continuously improves sorting accuracy by training with new production data including challenging bottle forms such as printed-label bottles.

✦ Reliable Handling of Challenging Scenarios

Ensures consistent sorting accuracy under diverse inout conditions, including highly reflective, black, and crushed bottles.

● High-Performance Belt Sorting

✦ Multi-Specification Model Portfolio

Available in three width specifications (1200 mm, 2000 mm, and 2800 mm) with a throughput range of 2–6 tons/hour, meeting diverse capacity requirements.

✦ Precision Pneumatic Ejectors

Offered in three nozzle configurations (88, 160, and 224 nozzles) with a response time of ≤1 ms and an ejection accuracy of ±2 mm, ensuring efficient and reliable material separation at high speeds.

Applications

Typical Application Scenarios

Sorts whole bottles by polymer type (PET/HDPE/PP) and color (clear/blue/green).

● Municipal Solid Waste (MSW) Processing

Separates recyclable plastic bottles from mixed municipal solid waste in MRFs.

● Mixed Plastic Sorting

Categorizes commingled plastic packaging by material type to enhance the purity of downstream pelletizing.

Specifications