Near-infrared model online update method based on local weighted Lasso
A local weighting and update method technology, which is applied to computer components, character and pattern recognition, and measuring devices, can solve problems such as model performance deterioration, increased computing costs, and noise redundancy, and achieve improved model accuracy and prediction capabilities. The effect of enhancing generalization performance and reducing the amount of calculation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0034] Example: such as figure 1 As shown, an online update method of near-infrared model based on locally weighted Lasso.
[0035] Step 1: Use the MATRIX-F Fourier near-infrared spectrometer produced by Bruker, Germany to collect the spectrum of the desalted crude oil output process. A total of 262 samples were collected (the spectral wavelength measurement range is 1000-2200nm, and the resolution is selected as 2cm -1 ), and determine the moisture content in the sample according to the standard method. The collected spectra and moisture content values form a historical database as a sample calibration set.
[0036] The collected spectrum is preprocessed by first-order differential, and the outliers are eliminated according to the 3σ criterion for the samples of the calibration set.
[0037] Step 2: and They are the spectral matrix and physical parameter matrix, N is the number of samples, and M is the number of spectral variables. For new incoming query samples x q...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap