Garnet Subclass Recognition Method Based on Thermal Infrared Spectral Features and BP Neural Network Model
A BP neural network, garnet technology, applied in the field of garnet subclass classification, to achieve the effect of good technical inspiration
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0043] Embodiment 1 BP Neural Network Model Construction Method for Identifying Garnet Subtypes Based on Thermal Infrared Spectrum Features
[0044] The method of constructing BP neural network model based on thermal infrared spectral features and garnet subtypes is as follows: figure 1 As shown, the specific steps are as follows:
[0045] 1. Acquisition of thermal infrared spectral characteristic data of garnet samples of known subtypes
[0046]The thermal infrared spectral characteristic data of 85 garnet samples were extracted from the thermal infrared spectral library (Table 1), including 18 almandine, 15 andandrite, 25 andandroid, 18 The wavelength data of the reflection peaks of pyrope, 6 spessartines, and 3 garnets in the 9-13μm spectrum, that is, the wavelength of reflection peak 1, the wavelength of reflection peak 2, and the wavelength of reflection peak 3, and reflection peak wavelength difference information, reflection peak 3 wavelength minus reflection peak 2 w...
Embodiment 2
[0070] Embodiment 2 Based on the thermal infrared spectrum characteristics and the BP neural network model constructed in Embodiment 1, the method for identifying the garnet subtype of the sample to be tested
[0071] Obtain the thermal infrared spectrum characteristic data of the garnet sample to be tested, that is, the first reflection peak wavelength, the second reflection peak wavelength, the third reflection peak wavelength, and the third reflection peak and The wavelength difference of the second reflection peak, wherein the third reflection peak wavelength is greater than the second reflection peak wavelength and greater than the first reflection peak wavelength;
[0072] By inputting the feature data into the BP neural network model constructed as described in Example 1, the subtype of the garnet sample to be tested can be identified.
[0073] It can be seen from the identification results obtained by verifying the sample in Example 1 that the present invention obtains...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


