Accurate characterization of mixed plastic waste using machine learning and fast infrared spectroscopy

Stas Zinchik et al., ACS Sustainable Chemistry & Engineering 9, pp. 14143-14151 (2021)
Accurate Characterization of Mixed Plastic Waste Using Machine Learning and Fast Infrared Spectroscopy using NLIR technology as in ASC Sustainable Chemistry & Engineering, 2021

Accurate Plastic Characterization with MIDWAVE Spectrometer

We present a combination of convolutional neural network (CNN) framework and fast MIR (mid-infrared spectroscopy) for classifying different types of dark plastic materials that are commonly found in mixed plastic waste (MPW) streams. Dark plastic materials present challenges in fast identification because of the low signal-to-noise ratio. The proposed CNN architecture (which we call PlasticNet) can reach an overall classification accuracy of 100% and can identify the constituent materials in a multiplastic blend with 100% accuracy. The fast MIR system can collect spectral data at a rate up to 400 Hz, and the CNN model can reach prediction speeds of 8200 Hz. Therefore, this method provides an avenue to be able to characterize MPW in a real-time high-throughput manner.

Explore Spectroscopy news with NLIR

Would you like to learn more?

Are you interested in characterizing mixed plastic with mid-infrared spectroscopy? Discover how NLIR’s mid-infrared spectrometers can enable your research as well as industrial application – giving sharp insights and enabling more efficient differentiation of plastics, including black plastics, that are often missed with NIR characterization.

Related News

Characterization of the NEP of Mid-Infrared Upconversion Detectors using NLIR technology as in IEEE Photonics Technology Letters, 2019

Characterization of the NEP of mid-infrared upconversion detectors

Rasmus. L. Pedersen et al., IEEE Photonics Technology Letters 31, pp. 681 – 684 (2019)
More information
Spatially and temporally resolved IR-DFWM measurement of HCN released from gasification of biomass pellets using NLIR technology as featured in Proceedings of the Combustion Institute, 2019

Spatially and temporally resolved IR-DFWM measurement of HCN released from gasification of biomass pellets

Dina Hot et al., Proceedings of the Combustion Institute 37, pp. 1337 – 1344 (2019)
More information
Room-Temperature, High-SNR Upconversion Spectrometer in the 6–12 µm Region using Nlir technology as in Laser & Photonics Review, 2021 - Copy

Room‐temperature, high‐SNR upconversion spectrometer in the 6–12 µm region

Peter John Rodrigo et al., Laser & Photonics Reviews 15, 2000443 (2021)
More information

Related Scientific Research

Stay up-to-date

Sign up to our newsletter to stay up to date with the latest NLIR news!

RD engineer interested in the latest mid-infrared spectrometer news