Memory, fire risk prediction model construction method, system and device

A technology of risk prediction and construction method, applied in prediction, instrument, character and pattern recognition, etc., can solve the problems of neglecting the nonlinear relationship of fire risk, low accuracy of prediction model, obvious collinearity and independence between independent variables, etc. Achieve effective development trend, collinearity and obvious effect of independence
CN113553754APending Publication Date: 2021-10-26CHINA PETROLEUM & CHEM CORP +1
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
CHINA PETROLEUM & CHEM CORP
Publication Date
2021-10-26

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a memory, a fire risk prediction model construction method, system and device. The fire risk prediction model construction method comprises the following steps: forming a variable data set according to variable items related to fire occurrence of a target area and generating an independent variable data set; taking the fire density of the target area as a dependent variable item and generating a dependent variable data set; screening variable items in the variable data set through feature selection to obtain optimized variable items, and generating an importance degree sequence of the optimized variable items; determining a final variable item from the optimal variable items according to the importance degree sequence; forming a sample data set according to the final independent variable item and the dependent variable item; and randomly dividing a preset number of data subsets according to the sample data set, determining a training set and an internal test set from the data subsets, and generating a plurality of sub-models through training to construct a fire risk prediction model. According to the method, more accurate model reference can be provided for predicting the fire risk of the industrial park and developing more effective fire response prevention measures.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of process industry safety, in particular to a memory and a method, system and device for constructing a fire risk prediction model. Background technique

[0002] The relatively dense buildings, crowds, and rich vegetation resources in the surrounding area have significantly increased the frequency and hazards of fires in this area. The occurrence of fire is closely related to factors such as terrain, climate and human activities.

[0003] Existing technologies mainly use multiple linear regression models and correlation analysis to analyze the relationship between industrial park fire risk and impact factors; the inventors have found through research that multiple linear regression models and correlation analysis in the prior art are used to analyze industrial park fire risks and impacts The relationship between factors has at least the following defects:

[0004] It only reflects the linear relationship between va...

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