Method for quickly discriminating ice blast type for cigarette
A technology of explosive beads for cigarettes, which is applied in the direction of measuring devices, material analysis through optical means, instruments, etc., can solve problems such as methods or methods that have no good effects in the evaluation of explosive beads for cigarettes, and achieve the elimination of noise and interference , Fast analysis speed and strong penetrating ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment example 1
[0094] The near-infrared spectra of the three types of popping beads were collected and tested on different days. A batch of samples was tested 3 times. Wave number setting range 10000cm -1 ~4520cm -1 , the data is prioritized regardless of preprocessing. The results corresponding to the sample numbers of different calibration sets selected by K-S are shown in Table 5 below. It can be found that by selecting different calibration set samples through K-S, when the number of selected samples reaches 60 or 70, the prediction accuracy rate for the validation set samples is 100%, indicating that the model has the ability to use value. However, when the number of samples is 50, the accuracy rate drops, indicating that there are interference factors in the spectral data during modeling.
[0095] Table 5 The relationship between the number of samples in the calibration set without preprocessing and the accuracy rate
[0096]
Embodiment example 2
[0098] The near-infrared spectra of the three types of popping beads were collected and tested on different days. A batch of samples was tested 3 times. Wave number setting range 10000cm -1 ~4520cm -1 . Due to the instrument and other reasons, the spectral data generally has noise or interference components in the data. The results are shown in Table 6 below. The data can be preprocessed to improve the robustness of the model. The preprocessing method chosen in this example is the Savitzky-Golay first derivative (9-point method). When the number of samples is selected as 30, the accuracy reaches 100%, indicating that the noise of the spectral data is effectively deducted and the robustness of the calibration model is improved.
[0099] Table 6 The relationship between the number of samples in the preprocessed calibration set and the accuracy rate
[0100]
PUM
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