Chemical risk monitoring method based on principal component analysis

A principal component analysis, risk monitoring technology, applied in electrical testing/monitoring, testing/monitoring control systems, program control, etc., can solve chemical risks and faults. Accurate and effective diagnosis is very large, and cannot achieve accurate and effective chemical risks and faults. Diagnosis, early warning, difficulty and other problems, to reduce the time for troubleshooting risk failures, improve the ability to assist decision-making, and eliminate noise interference.

Pending Publication Date: 2020-05-15
南京连易智能科技有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is still very difficult to achieve accurate and effective diagnosis of chemical risks and faults under the massive data
The DCS system monitors individual indicators separately, which are numerous and unconnected with each other; in the face of large-scale chemical processes, the single threshold alarm of the DCS system cannot achieve accurate and effective diagnosis and early warning of chemical risks and failures under massive data

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
  • Chemical risk monitoring method based on principal component analysis
  • Chemical risk monitoring method based on principal component analysis
  • Chemical risk monitoring method based on principal component analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Such as figure 1 and figure 2 As shown, a chemical risk monitoring method based on principal component analysis is divided into two steps: offline part and online part, which analyze sample data and real-time data respectively. The offline part establishes a principal component analysis algorithm model based on normal data samples, and the online part uses the established model to conduct online chemical risk analysis on real-time data.

[0021] Step 1: Establish principal component analysis algorithm model (offline part):

[0022] 1-1. Obtain m samples of n sensors by sampling to form an X∈R m×n matrix;

[0023] 1-2. Standardize the data;

[0024] 1-3. Perform eigenvalue decomposition on the covariance matrix of X to obtain eigenvalues ​​of different sizes and corresponding eigenvectors;

[0025] 1-4. Arrange according to the size of the eigenvalues ​​to obtain the load matrix P (composed of eigenvectors) and the score matrix T (principal variable);

[0026] Fin...

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 provides a chemical risk monitoring method based on principal component analysis. The chemical risk monitoring method comprises the steps of offline establishment of an analysis algorithm model and online risk monitoring. In the step of offline establishment of an analysis algorithm model, a plurality of index data of normal operation in the chemical production process are sampled, aPCA (Principle Component Analysis) model is established after data preprocessing; in the step of online risk monitoring, online real-time data of chemical production is analyzed by utilizing the established PCA model, whether abnormality exists in the production process or not is judged, and early warning is carried out in time. According to the invention, the chemical risk early warning problemunder mass data is solved, comprehensive diagnosis analysis is carried out on high-dimensional data, and chemical safety production early warning is effectively realized.

Description

technical field [0001] The invention belongs to the technical field of chemical industry risk monitoring, and in particular relates to a chemical industry risk monitoring method based on principal component analysis. Background technique [0002] With the expansion of the chemical process scale and the complexity of the process, the probability of various chemical accidents is also increasing. At present, the DCS system is generally used to monitor the individual indicators in the chemical production process in real time, and judge the chemical risks by judging whether they exceed the threshold and give an alarm and early warning. However, it is still very difficult to achieve accurate and effective diagnosis of chemical risks and faults under the massive data. The DCS system monitors individual indicators separately, which are numerous and unconnected with each other; in the face of large-scale chemical processes, the single threshold alarm of the DCS system cannot achieve...

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 Applications(China)
IPC IPC(8): G05B23/02
CPCG05B23/0221G05B2219/24065
Inventor 燕妮胡庚松
Owner 南京连易智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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