A method and device for online identification of plastic materials
A technology of materials and plastics, applied in measuring devices, analyzing materials, and analyzing materials through optical means, can solve the problems of unrecognizable, large data volume, poor adaptability of waste materials, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0059] figure 1 It is a flowchart of a method for online plastic material identification provided by Embodiment 1 of the present invention. Such as figure 1 As shown, the method mainly includes the following steps:
[0060] Step 11, establish recognition model; figure 2 As shown, it mainly includes:
[0061] Step A, sampling, collecting spectral data and preprocessing spectral data.
[0062] Select one or more samples from plastic products of various materials contained in waste plastic raw materials, and classify the samples into type a and non-a according to the plastic material a to be detected; perform spectrum measurement on each sample, and analyze the obtained spectrum The measurement result data is preprocessed; in actual work, samples can also be classified after preprocessing.
[0063] In the embodiment of the present invention, performing spectral measurement on each sample and preprocessing the obtained spectral measurement result data include: performing spe...
example 1
[0086] In this example, the identification and sorting of PVC plastics in waste plastic raw materials containing PVC and ABS are taken as an example (that is, the PVC material is designated as the aforementioned plastic material a). The implementation process includes the following steps:
[0087] 1) Collect 26 samples from waste plastic raw materials, use a standard spectrometer, measure the reflection spectrum curves of each sample with a spectral resolution of 3nm, and a wavelength range of 1100nm to 2000nm, and then perform 5-point smoothing and standard normalization with spectral processing software After chemical treatment, the spectral curve of each sample is obtained, and the samples are classified according to PVC and non-PVC materials, such as Figure 4 As shown, the curve marked with circles is the spectrum of PVC samples, and the curve marked with squares is the spectrum of ABS samples.
[0088] 2) After resampling the spectral data of the collected samples at 2nm...
example 2
[0098] In this example, PVC raw materials are identified and sorted from waste plastic raw materials composed of various plastic materials, including PVC, ABS, PA, PE, PET, PP, and PS. The implementation process includes the following steps:
[0099] A total of 70 samples were selected from waste plastic raw materials, and the spectral data were measured and classified. The spectral measurement and processing parameters were consistent with the previous example, and will not be repeated here.
[0100] Based on the sample spectral data, select the threshold T = 0.25 to calculate the overall identification matrix P 0 (m,n) and statistical matrix Q 0 (m,n). In this example the overall identification matrix P 0 (m,n) is an all-zero matrix, based on the statistical matrix Q 0 (m,n) selects the first pair of measurement wavelengths. For the numerical distribution of the statistical matrix and the index wavelength of the maximum element, see Figure 6 , according to which the fi...
PUM
Property | Measurement | Unit |
---|---|---|
diameter | aaaaa | aaaaa |
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com