Unlock instant, AI-driven research and patent intelligence for your innovation.

An Industrial Soft Sensing Method Based on Depth Partial Least Squares Model

A technology of partial least squares and soft measurement, applied in measuring devices, neural learning methods, biological neural network models, etc., can solve the problems that the PLS method cannot be applied, and achieve the effect of expanding the complexity of the model and improving the learning ability

Active Publication Date: 2022-05-03
ZHEJIANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a kind of industrial soft sensor method based on depth partial least squares model to solve the deficiency that the traditional PLS method in the prior art cannot be applied to nonlinear industrial soft sensor modeling

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An Industrial Soft Sensing Method Based on Depth Partial Least Squares Model
  • An Industrial Soft Sensing Method Based on Depth Partial Least Squares Model
  • An Industrial Soft Sensing Method Based on Depth Partial Least Squares Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0080] The effectiveness of the deep partial least squares model proposed by the present invention is illustrated below in conjunction with a specific case of regression prediction of key industrial variables. The industrial regression prediction problem presented here comes from the case of a reformer in the ammonia synthesis process.

[0081] Synthetic ammonia process to produce ammonia gas NH 3 , NH 3 It is then used to produce urea, a chemical fertilizer commonly used in agriculture. In the ammonia synthesis process, hydrogen is produced NH 3 an important raw material. In actual industrial production, hydrogen is usually produced by cracking methane, and the cracking reaction mainly occurs in the primary reformer in the process of ammonia synthesis. According to the reaction mechanism, the temperature has a great influence on the hydrogen content and purity. Therefore, it is crucial to control the reaction temperature in actual production, and the temperature is usual...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention proposes an industrial soft sensor method based on a deep partial least square model. The invention combines nonlinear mapping and PLS hidden variable extraction, and proposes a nonlinear partial least squares modeling algorithm (NPLS). Before performing hidden variable feature extraction, NPLS performs a nonlinear mapping on the independent variables in the training data to map them to the high-dimensional nonlinear feature space, and then establishes the regression relationship between the nonlinear features and the dependent variable in the high-dimensional space. NPLS can effectively solve nonlinear problems. In addition, in order to further expand the model complexity and improve its learning ability, the present invention uses a hierarchical cascade model architecture to convert the shallow NPLS model into a deep deep partial least squares model (DPLS). Compared with the traditional PLS, the DPLS proposed by the present invention can extract deep nonlinear features, and is an effective and powerful industrial soft sensor modeling method.

Description

technical field [0001] The invention belongs to the field of industrial process prediction and soft measurement, in particular to an industrial soft measurement method based on a deep partial least squares model. Background technique [0002] In industrial production, there are many variables that are difficult to measure directly or costly to measure, and these variables are often crucial to production operations. Industrial process soft measurement technology is a method to estimate the true value of the measured variable by establishing a mathematical model between the measured variable and other easy-to-measure variables. In this type of problem, the easy-to-measure variables are usually called process variables, mainly including temperature, pressure, flow and other indicators, and the difficult-to-measure variables to be predicted are usually called quality variables, such as the content or concentration of certain chemical substances. [0003] Industrial soft sensor ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08G01D21/02
CPCG06N3/04G06N3/08G01D21/02G06F18/211G06F18/2414
Inventor 葛志强孔祥印
Owner ZHEJIANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com