Check patentability & draft patents in minutes with Patsnap Eureka AI!

An online alarm analysis method based on the fusion of pls model and pca contribution

A technology of alarm analysis and contribution, which is applied to alarms, character and pattern recognition, instruments, etc., can solve problems such as flooding of alarms, difficult analysis, single alarm information, etc., to reduce noise interference, accurate process information, and improve online analysis effect of ability

Active Publication Date: 2021-10-01
BEIJING UNIV OF CHEM TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, when the system generates potential safety hazards, too many variables alarm at the same time, resulting in flooding of alarms, single alarm information and difficult analysis have become the disadvantages of single-variable threshold alarms
The problem of alarm flooding is solved from the perspective of alarm threshold optimization, which effectively improves the performance of the alarm system, but fails to solve the problem fundamentally.

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 online alarm analysis method based on the fusion of pls model and pca contribution
  • An online alarm analysis method based on the fusion of pls model and pca contribution
  • An online alarm analysis method based on the fusion of pls model and pca contribution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] With the development of the era of big data, the acquisition of a large amount of data in complex industries, the improvement of computer data processing capabilities has promoted the rapid development of multivariate analysis methods, methods based on multivariate statistics, such as Principal Component Analysis (Principal Component Analysis, PCA), Partial Least Squares (PLS) and canonical variate analysis (CVA) are also widely used in alarm systems. Due to the complexity of the chemical process and too many variables, the multivariate analysis method has not been able to provide interpretable analysis results for the actual industry, and there are still many problems for the alarm system.

[0067] The traditional PCA method performs dimensionality reduction in the direction of maximizing the variance, extracts device features for process monitoring, and performs effective fault detection. Since the PCA method does not pay attention to the relationship between the inpu...

Embodiment 2

[0116] Fault 10 is a random fault of the TE process, and its main fault problem is caused by the feed flow of C material. Due to the heavy randomness of the fault, a large amount of noise is generated, which seriously affects the analysis results of the multivariate statistical method. Figure 8 The diagram of PCA and MCB-PLS detection results for TE process fault 10 provided for Embodiment 2 of the present invention. Figure 8 (a) is the detection result of fault 10 by the traditional method. It can be found that at time 160, PCA detected the occurrence of the fault. Phenomenon. According to the simulation results, the false alarm rate and false alarm rate of PCA method for fault 10 are 19.63% and 25.62%, respectively. In contrast to the MCB-PLS method proposed in this embodiment, Figure 8 (b) to Figure 8 (e) are the detection results of the four sub-modules respectively. It can be seen that the detection of faults by subset 3 is more accurate. Figure 8 (f) is the ove...

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 discloses an online alarm analysis method based on the fusion of PLS ​​model and PCA contribution degree, which includes: obtaining industrial data, performing block processing on the overall system according to the industrial process, and performing sub-modules respectively according to the partial least square method of multi-associated modules Modeling analysis, according to the principal component analysis method to obtain the real-time contribution of each sub-module to the overall system, according to the real-time contribution ratio of the sub-module to the overall system to obtain the contribution of variables in each process to the overall system, according to the key variable extraction method Screen the variables to obtain variables with preset contribution, obtain the real-time importance of process variables according to the online root cause analysis strategy, and manage industrial alarms according to the real-time importance of process variables. The technical solution provided by the invention realizes the goals of reducing noise interference between multiple variables, providing more accurate process information, and improving the online analysis ability of alarm data in the process of chemical process monitoring and alarm management.

Description

technical field [0001] The invention relates to the technical field of industrial alarms, in particular to an online alarm analysis method based on the fusion of PLS ​​model and PCA contribution degree. Background technique [0002] The alarm system is an important part of process industry monitoring. The alarm system can make the operator grasp the operation status of the equipment in real time and detect abnormal operating conditions in time. Through the alarm management system, the authenticity and reliability of the alarm system can be improved. An alarm management system covers a complete life cycle: conception, identification, rationalization, design, implementation, operation, etc. [0003] The alarm system is an important guarantee for the safety of the chemical process. Accurate alarm information and fast response are the two most important indicators of the alarm system. In traditional industries, univariate threshold alarm methods such as filtering, dead zone, a...

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): G06Q10/04G06Q10/06G06K9/62G08B25/00
CPCG06Q10/04G06Q10/0639G08B25/007G06F18/2135
Inventor 朱群雄林崇阳骆意徐圆贺彦林
Owner BEIJING UNIV OF CHEM TECH
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