Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent monitoring method for monitoring abnormal conditions of fire-fighting engineering

An abnormal state and intelligent monitoring technology, applied in data processing applications, instruments, complex mathematical operations, etc., can solve the problems of reducing the risk prediction accuracy of process abnormal state, model convergence speed, increasing model computing resource occupation, etc., to improve dynamic abnormality The effect of identifying, improving training speed, and simplifying the solution process

Inactive Publication Date: 2020-04-24
SHENZHEN UNIV +2
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These problems will reduce the accuracy of process abnormal state risk prediction, model convergence speed, increase the resource consumption of model calculation, etc.

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
  • Intelligent monitoring method for monitoring abnormal conditions of fire-fighting engineering
  • Intelligent monitoring method for monitoring abnormal conditions of fire-fighting engineering
  • Intelligent monitoring method for monitoring abnormal conditions of fire-fighting engineering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, the present embodiment provides an intelligent monitoring method for fire engineering abnormal state monitoring, which includes the following steps:

[0041] 1. Acquisition of dynamic data streams;

[0042] 2. Use the principal component analysis method PCA to perform cluster analysis on the existing historical experience data, and establish a multi-classifier model;

[0043] 3. Perform the least squares support vector machine algorithm LSSVM on the principal metadata factors to obtain the optimal decision function equation;

[0044] 4. Use different decision function equations of different principal metadata factors to process the collected dynamic data flow, and realize abnormal mode state recognition in the process.

[0045] In step 2, first analyze and extract the data distribution of different basic state modes, and use the principal component analysis method to convert the sample data with similar principal component characteristics in...

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 relates to the technical field of intelligent fire protection, in particular to an intelligent monitoring method for monitoring the abnormal conditions of fire fighting engineering, which comprises the following steps of: 1, acquiring a dynamic data stream; 2, performing clustering analysis on existing historical empirical data by utilizing a principal component analysis (PCA) method, and establishing a multi-classifier model; 3, performing least square support vector machine algorithm LSSVM processing on the principal element data factor to obtain an optimal decision function equation; and 4, processing the acquired dynamic data streams by using different decision function equations of different principal element data factors to realize abnormal mode state identification inthe process. According to the method, the solving process of the model is greatly simplified, the training speed of the model is increased, and great help is provided for improving dynamic anomaly recognition in a fire-fighting project.

Description

technical field [0001] The invention relates to the technical field of intelligent fire protection, in particular to an intelligent monitoring method for abnormal state monitoring of fire protection engineering. Background technique [0002] Due to the characteristics of one-time, large-scale, and complex processes, there are many uncertain factors in the process, and it is generally carried out in harsh environments. Traditional supervision uses manual inspections or fixed camera monitoring. Difficult to fully grasp. The standard support vector machine (SVM) is used to identify and monitor the possible abnormal fluctuations in the observed data during the construction process based on the historical data. [0003] SVM has many advantages and can solve the problem of risk factor prediction and classification, but it still has some disadvantages. The main performance is the limitation of the loss function of the model and the optimization combination of the penalty factor 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 Applications(China)
IPC IPC(8): G06Q50/26G06K9/62G06F17/12
CPCG06Q50/26G06F17/12G06F18/2135G06F18/2411
Inventor 李政道贾春林柯程炜陈哲
Owner SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com