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

Method for intelligently identifying and predicting underground safety accident based on CO monitoring data

A technology of monitoring data and intelligent identification, which is applied in neural learning methods, earthwork drilling, mining equipment, etc., can solve the problem of which accident causes are not reflected in the early warning of gas classification, and achieve reduced labor costs, high prediction accuracy, and fast The effect of using

Active Publication Date: 2022-02-15
SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN +1
View PDF19 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the existing technology can provide graded early warning for gas hazards, it does not reflect the cause of the accident that the gas graded early warning corresponds to.

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
  • Method for intelligently identifying and predicting underground safety accident based on CO monitoring data
  • Method for intelligently identifying and predicting underground safety accident based on CO monitoring data
  • Method for intelligently identifying and predicting underground safety accident based on CO monitoring data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0097] An intelligent identification method based on CO monitoring data, comprising:

[0098] 1) Preprocessing the collected carbon monoxide data that caused the alarm:

[0099] The carbon monoxide data is divided into a training set and a test set, and the training set and the test set include multiple groups of data respectively: each group of carbon monoxide data is x={x 1 ,x 2 ,Λ,x n}, the cause of each group of alarms is o={o 1 ,o 2 ,Λ,o p}, in the implementation of the present invention, the data when selecting 200 groups of carbon monoxide sensors to report to the police is analyzed, and the first 180 groups of data are used as training sets, and the back 20 groups of data are used as test sets;

[0100] Use Min-Max standardization to map all carbon monoxide data to [0,1]:

[0101]

[0102] This technical feature is used to eliminate the dimensional influence between data and conduct comprehensive comparison and evaluation, so that the operating efficiency and ...

Embodiment 2

[0144] A method for intelligently predicting underground safety accidents based on CO monitoring data, comprising:

[0145] 7) Data preparation: input the data value of the carbon monoxide sensor to be predicted, and extract the data value of the carbon monoxide sensor monitored per second within one minute as the training data, denoted as x={x 1 , x 2,...,x 60}; The design and training process of the network will not change due to the number of training samples, but the network trained with large-capacity samples will have smaller prediction errors and stronger extrapolation capabilities;

[0146] 8) Normalize the training data:

[0147]

[0148] 9) Denormalization calculation formula:

[0149]

[0150] Among them, z i is the normalized data;

[0151] 10) Group the normalized data into groups, 10 data as a group, here z n ~z n+9 is a group, n ∈ [1, 2...51], and is divided into 51 groups of data; the first 45 groups of samples are used as training sets, and the la...

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 a method for intelligently identifying and predicting underground safety accidents based on CO monitoring data. According to the method, the carbon monoxide detection data in the coal mine are effectively identified based on the neural network model, and the carbon monoxide detection data are input into the trained neural network model, so that the accident cause behind the detection data can be obtained in real time. In the prior art, objective statistics of accident reasons after the carbon monoxide data exceeds the standard can be realized without manual statistics or data entry by technicians, so that the intelligent identification efficiency is greatly improved, and workers only need to partially modify data even if errors exist.

Description

technical field [0001] The invention discloses a method for intelligently identifying and predicting downhole safety accidents based on CO monitoring data, and belongs to the technical field of downhole intelligence. Background technique [0002] Coal mine production is generally a multi-link and multi-process process of mining underground. The geological and mining conditions are complex, and there are many uneasy factors. They are often threatened by gas, water, fire, carbon monoxide, ventilation, temperature, and roof. Therefore only putting coal mine safety in the first place of work can ensure the safety of underground staff and the normal progress of coal mine production work. Today, prediction of the cause of an alarm is a top priority in coal production. Moreover, many coal mining industries are still in the stage of manually recording the cause of the alarm. Most of them rely on the staff to manually record in the mine and then enter the system for storage. And th...

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): E21F17/18G06N3/04G06N3/08
CPCE21F17/18G06N3/08G06N3/048
Inventor 郝慧娟袁慧苗张让勇张梦白金强郝凤琦唐勇伟程广河李娟
Owner SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
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