•  
  •  
 

Abstract

The presence of polyethylene (PE) in recycled polypropylene (rPP) is a critical quality concern, as the two polymers are inherently incompatible and PE contamination can degrade rPP mechanical performance. Building on our previous development of an AI-assisted partial least squares (PLS) predictive model using laboratory-prepared mixtures, the present study evaluates the model’s performance on real-world materials. Commercial rPP feedstock and finished product samples were obtained from a local plastic recycler, and their Raman spectra were collected and preprocessed through despiking, smoothing, baseline correction, and normalization. When applied to these spectra, the PLS model successfully predicted PE contamination levels in the commercial samples. The finished rPP products were estimated to contain approximately 7-8% PE; meanwhile, one PE piece might be detected in the tested feedstock (Sample# 12). These results demonstrate the model’s practical utility for rapid, non-destructive monitoring of PE contamination in industrial recycling streams.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.